[W socket.cpp:464] [c10d] The server socket cannot be initialized on [::]:29500 (errno: 97 - Address family not supported by protocol). [W socket.cpp:697] [c10d] The client socket cannot be initialized to connect to [::ffff:127.0.0.1]:29500 (errno: 97 - Address family not supported by protocol). [W socket.cpp:697] [c10d] The client socket cannot be initialized to connect to [::ffff:127.0.0.1]:29500 (errno: 97 - Address family not supported by protocol). [W socket.cpp:697] [c10d] The client socket cannot be initialized to connect to [::ffff:127.0.0.1]:29500 (errno: 97 - Address family not supported by protocol). wandb: Currently logged in as: salomon-kisters. Use `wandb login --relogin` to force relogin wandb: WARNING Path ./wandb/wandb/ wasn't writable, using system temp directory. wandb: WARNING Path ./wandb/wandb/ wasn't writable, using system temp directory wandb: Tracking run with wandb version 0.17.1 wandb: Run data is saved locally in /tmp/wandb/run-20240617_155355-q96nvxpq wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run kind-shape-106 wandb: ⭐️ View project at https://wandb.ai/salomon-kisters/distil-whisper wandb: 🚀 View run at https://wandb.ai/salomon-kisters/distil-whisper/runs/q96nvxpq 06/17/2024 15:53:59 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False 06/17/2024 15:53:59 - INFO - __main__ - Training/evaluation parameters DistillationTrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, batch_eval_metrics=False, bf16=False, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=10, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=7200, debug=[], deepspeed=None, disable_tqdm=False, dispatch_batches=None, do_eval=True, do_predict=False, do_train=True, dtype=bfloat16, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_steps=5000.0, eval_strategy=no, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, freeze_decoder=False, freeze_embed_positions=False, freeze_encoder=True, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, generation_config=None, generation_max_length=None, generation_num_beams=None, gradient_accumulation_steps=1, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, greater_is_better=None, group_by_length=False, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, kl_weight=1.0, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0001, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=./runs/Jun17_15-53-54_6296a7809286, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=25, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=linear, max_grad_norm=1.0, max_steps=100000, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=3.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=./, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=8, predict_with_generate=True, prediction_loss_only=False, push_to_hub=True, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=./, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=5000, save_strategy=steps, save_total_limit=5, seed=42, skip_memory_metrics=True, sortish_sampler=False, split_batches=None, temperature=2.0, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, warmup_steps=500, weight_decay=0.0, ) Combining datasets...: 0%| | 0/1 [00:00": 50327, "<|am|>": 50334, "<|ar|>": 50272, "<|as|>": 50350, "<|az|>": 50304, "<|ba|>": 50355, "<|be|>": 50330, "<|bg|>": 50292, "<|bn|>": 50302, "<|bo|>": 50347, "<|br|>": 50309, "<|bs|>": 50315, "<|ca|>": 50270, "<|cs|>": 50283, "<|cy|>": 50297, "<|da|>": 50285, "<|de|>": 50261, "<|el|>": 50281, "<|en|>": 50259, "<|es|>": 50262, "<|et|>": 50307, "<|eu|>": 50310, "<|fa|>": 50300, "<|fi|>": 50277, "<|fo|>": 50338, "<|fr|>": 50265, "<|gl|>": 50319, "<|gu|>": 50333, "<|haw|>": 50352, "<|ha|>": 50354, "<|he|>": 50279, "<|hi|>": 50276, "<|hr|>": 50291, "<|ht|>": 50339, "<|hu|>": 50286, "<|hy|>": 50312, "<|id|>": 50275, "<|is|>": 50311, "<|it|>": 50274, "<|ja|>": 50266, "<|jw|>": 50356, "<|ka|>": 50329, "<|kk|>": 50316, "<|km|>": 50323, "<|kn|>": 50306, "<|ko|>": 50264, "<|la|>": 50294, "<|lb|>": 50345, "<|ln|>": 50353, "<|lo|>": 50336, "<|lt|>": 50293, "<|lv|>": 50301, "<|mg|>": 50349, "<|mi|>": 50295, "<|mk|>": 50308, "<|ml|>": 50296, "<|mn|>": 50314, "<|mr|>": 50320, "<|ms|>": 50282, "<|mt|>": 50343, "<|my|>": 50346, "<|ne|>": 50313, "<|nl|>": 50271, "<|nn|>": 50342, "<|no|>": 50288, "<|oc|>": 50328, "<|pa|>": 50321, "<|pl|>": 50269, "<|ps|>": 50340, "<|pt|>": 50267, "<|ro|>": 50284, "<|ru|>": 50263, "<|sa|>": 50344, "<|sd|>": 50332, "<|si|>": 50322, "<|sk|>": 50298, "<|sl|>": 50305, "<|sn|>": 50324, "<|so|>": 50326, "<|sq|>": 50317, "<|sr|>": 50303, "<|su|>": 50357, "<|sv|>": 50273, "<|sw|>": 50318, "<|ta|>": 50287, "<|te|>": 50299, "<|tg|>": 50331, "<|th|>": 50289, "<|tk|>": 50341, "<|tl|>": 50348, "<|tr|>": 50268, "<|tt|>": 50351, "<|uk|>": 50280, "<|ur|>": 50290, "<|uz|>": 50337, "<|vi|>": 50278, "<|yi|>": 50335, "<|yo|>": 50325, "<|yue|>": 50358, "<|zh|>": 50260 }, "max_initial_timestamp_index": 50, "max_length": 448, "no_timestamps_token_id": 50364, "pad_token_id": 50257, "prev_sot_token_id": 50362, "return_timestamps": false, "suppress_tokens": [ 1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50359, 50360, 50361, 50362, 50363 ], "task_to_id": { "transcribe": 50360, "translate": 50359 } } loading weights file ./distil-large-v3-init/model.safetensors Generate config GenerationConfig { "begin_suppress_tokens": [ 220, 50257 ], "bos_token_id": 50257, "decoder_start_token_id": 50258, "eos_token_id": 50257, "max_length": 448, "pad_token_id": 50256 } All model checkpoint weights were used when initializing WhisperForConditionalGeneration. All the weights of WhisperForConditionalGeneration were initialized from the model checkpoint at ./distil-large-v3-init. If your task is similar to the task the model of the checkpoint was trained on, you can already use WhisperForConditionalGeneration for predictions without further training. loading configuration file ./distil-large-v3-init/generation_config.json Generate config GenerationConfig { "alignment_heads": [ [ 7, 0 ], [ 10, 17 ], [ 12, 18 ], [ 13, 12 ], [ 16, 1 ], [ 17, 14 ], [ 19, 11 ], [ 21, 4 ], [ 24, 1 ], [ 25, 6 ] ], "begin_suppress_tokens": [ 220, 50257 ], "bos_token_id": 50257, "decoder_start_token_id": 50258, "eos_token_id": 50257, "is_multilingual": true, "lang_to_id": { "<|af|>": 50327, "<|am|>": 50334, "<|ar|>": 50272, "<|as|>": 50350, "<|az|>": 50304, "<|ba|>": 50355, "<|be|>": 50330, "<|bg|>": 50292, "<|bn|>": 50302, "<|bo|>": 50347, "<|br|>": 50309, "<|bs|>": 50315, "<|ca|>": 50270, "<|cs|>": 50283, "<|cy|>": 50297, "<|da|>": 50285, "<|de|>": 50261, "<|el|>": 50281, "<|en|>": 50259, "<|es|>": 50262, "<|et|>": 50307, "<|eu|>": 50310, "<|fa|>": 50300, "<|fi|>": 50277, "<|fo|>": 50338, "<|fr|>": 50265, "<|gl|>": 50319, "<|gu|>": 50333, "<|haw|>": 50352, "<|ha|>": 50354, "<|he|>": 50279, "<|hi|>": 50276, "<|hr|>": 50291, "<|ht|>": 50339, "<|hu|>": 50286, "<|hy|>": 50312, "<|id|>": 50275, "<|is|>": 50311, "<|it|>": 50274, "<|ja|>": 50266, "<|jw|>": 50356, "<|ka|>": 50329, "<|kk|>": 50316, "<|km|>": 50323, "<|kn|>": 50306, "<|ko|>": 50264, "<|la|>": 50294, "<|lb|>": 50345, "<|ln|>": 50353, "<|lo|>": 50336, "<|lt|>": 50293, "<|lv|>": 50301, "<|mg|>": 50349, "<|mi|>": 50295, "<|mk|>": 50308, "<|ml|>": 50296, "<|mn|>": 50314, "<|mr|>": 50320, "<|ms|>": 50282, "<|mt|>": 50343, "<|my|>": 50346, "<|ne|>": 50313, "<|nl|>": 50271, "<|nn|>": 50342, "<|no|>": 50288, "<|oc|>": 50328, "<|pa|>": 50321, "<|pl|>": 50269, "<|ps|>": 50340, "<|pt|>": 50267, "<|ro|>": 50284, "<|ru|>": 50263, "<|sa|>": 50344, "<|sd|>": 50332, "<|si|>": 50322, "<|sk|>": 50298, "<|sl|>": 50305, "<|sn|>": 50324, "<|so|>": 50326, "<|sq|>": 50317, "<|sr|>": 50303, "<|su|>": 50357, "<|sv|>": 50273, "<|sw|>": 50318, "<|ta|>": 50287, "<|te|>": 50299, "<|tg|>": 50331, "<|th|>": 50289, "<|tk|>": 50341, "<|tl|>": 50348, "<|tr|>": 50268, "<|tt|>": 50351, "<|uk|>": 50280, "<|ur|>": 50290, "<|uz|>": 50337, "<|vi|>": 50278, "<|yi|>": 50335, "<|yo|>": 50325, "<|yue|>": 50358, "<|zh|>": 50260 }, "max_initial_timestamp_index": 50, "max_length": 448, "no_timestamps_token_id": 50364, "pad_token_id": 50257, "prev_sot_token_id": 50362, "return_timestamps": false, "suppress_tokens": [ 1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50359, 50360, 50361, 50362, 50363 ], "task_to_id": { "transcribe": 50360, "translate": 50359 } } 06/17/2024 15:54:22 - INFO - __main__ - Number of trainable parameters: 1.194e+08 Feature extractor saved in ./preprocessor_config.json tokenizer config file saved in ./tokenizer_config.json Special tokens file saved in ./special_tokens_map.json Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41. Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens': [220, 50257]} Configuration saved in ./config.json Configuration saved in ./generation_config.json loading configuration file ./preprocessor_config.json Feature extractor WhisperFeatureExtractor { "chunk_length": 30, "feature_extractor_type": "WhisperFeatureExtractor", "feature_size": 128, "hop_length": 160, "n_fft": 400, "n_samples": 480000, "nb_max_frames": 3000, "padding_side": "right", "padding_value": 0.0, "processor_class": "WhisperProcessor", "return_attention_mask": false, "sampling_rate": 16000 } loading file vocab.json loading file tokenizer.json loading file merges.txt loading file normalizer.json loading file added_tokens.json loading file special_tokens_map.json loading file tokenizer_config.json Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Processor WhisperProcessor: - feature_extractor: WhisperFeatureExtractor { "chunk_length": 30, "feature_extractor_type": "WhisperFeatureExtractor", "feature_size": 128, "hop_length": 160, "n_fft": 400, "n_samples": 480000, "nb_max_frames": 3000, "padding_side": "right", "padding_value": 0.0, "processor_class": "WhisperProcessor", "return_attention_mask": false, "sampling_rate": 16000 } - tokenizer: WhisperTokenizer(name_or_path='./', vocab_size=50257, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<|endoftext|>', 'eos_token': '<|endoftext|>', 'unk_token': '<|endoftext|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|startoftranscript|>', '<|en|>', '<|zh|>', '<|de|>', '<|es|>', '<|ru|>', '<|ko|>', '<|fr|>', '<|ja|>', '<|pt|>', '<|tr|>', '<|pl|>', '<|ca|>', '<|nl|>', '<|ar|>', '<|sv|>', '<|it|>', '<|id|>', '<|hi|>', '<|fi|>', '<|vi|>', '<|he|>', '<|uk|>', '<|el|>', '<|ms|>', '<|cs|>', '<|ro|>', '<|da|>', '<|hu|>', '<|ta|>', '<|no|>', '<|th|>', '<|ur|>', '<|hr|>', '<|bg|>', '<|lt|>', '<|la|>', '<|mi|>', '<|ml|>', '<|cy|>', '<|sk|>', '<|te|>', '<|fa|>', '<|lv|>', '<|bn|>', '<|sr|>', '<|az|>', '<|sl|>', '<|kn|>', '<|et|>', '<|mk|>', '<|br|>', '<|eu|>', '<|is|>', '<|hy|>', '<|ne|>', '<|mn|>', '<|bs|>', '<|kk|>', '<|sq|>', '<|sw|>', '<|gl|>', '<|mr|>', '<|pa|>', '<|si|>', '<|km|>', '<|sn|>', '<|yo|>', '<|so|>', '<|af|>', '<|oc|>', '<|ka|>', '<|be|>', '<|tg|>', '<|sd|>', '<|gu|>', '<|am|>', '<|yi|>', '<|lo|>', '<|uz|>', '<|fo|>', '<|ht|>', '<|ps|>', '<|tk|>', '<|nn|>', '<|mt|>', '<|sa|>', '<|lb|>', '<|my|>', '<|bo|>', '<|tl|>', '<|mg|>', '<|as|>', '<|tt|>', '<|haw|>', '<|ln|>', '<|ha|>', '<|ba|>', '<|jw|>', '<|su|>', '<|yue|>', '<|translate|>', '<|transcribe|>', '<|startoflm|>', '<|startofprev|>', '<|nospeech|>', '<|notimestamps|>']}, clean_up_tokenization_spaces=True), added_tokens_decoder={ 50257: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50258: AddedToken("<|startoftranscript|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50259: AddedToken("<|en|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50260: AddedToken("<|zh|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50261: AddedToken("<|de|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50262: AddedToken("<|es|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50263: AddedToken("<|ru|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50264: AddedToken("<|ko|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50265: AddedToken("<|fr|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50266: AddedToken("<|ja|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50267: AddedToken("<|pt|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50268: AddedToken("<|tr|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50269: AddedToken("<|pl|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50270: AddedToken("<|ca|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50271: AddedToken("<|nl|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50272: AddedToken("<|ar|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50273: AddedToken("<|sv|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50274: AddedToken("<|it|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50275: AddedToken("<|id|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50276: AddedToken("<|hi|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50277: AddedToken("<|fi|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50278: AddedToken("<|vi|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50279: AddedToken("<|he|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50280: AddedToken("<|uk|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50281: AddedToken("<|el|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50282: AddedToken("<|ms|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50283: AddedToken("<|cs|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50284: AddedToken("<|ro|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50285: AddedToken("<|da|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50286: AddedToken("<|hu|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50287: AddedToken("<|ta|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50288: AddedToken("<|no|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50289: AddedToken("<|th|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50290: AddedToken("<|ur|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50291: AddedToken("<|hr|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50292: AddedToken("<|bg|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50293: AddedToken("<|lt|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50294: AddedToken("<|la|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50295: AddedToken("<|mi|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50296: AddedToken("<|ml|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50297: AddedToken("<|cy|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50298: AddedToken("<|sk|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50299: AddedToken("<|te|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50300: AddedToken("<|fa|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50301: AddedToken("<|lv|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50302: AddedToken("<|bn|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50303: AddedToken("<|sr|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50304: AddedToken("<|az|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50305: AddedToken("<|sl|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50306: AddedToken("<|kn|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50307: AddedToken("<|et|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50308: AddedToken("<|mk|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50309: AddedToken("<|br|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50310: AddedToken("<|eu|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50311: AddedToken("<|is|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50312: AddedToken("<|hy|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50313: AddedToken("<|ne|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50314: AddedToken("<|mn|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50315: AddedToken("<|bs|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50316: AddedToken("<|kk|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50317: AddedToken("<|sq|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50318: AddedToken("<|sw|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50319: AddedToken("<|gl|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50320: AddedToken("<|mr|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50321: AddedToken("<|pa|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50322: AddedToken("<|si|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50323: AddedToken("<|km|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50324: AddedToken("<|sn|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50325: AddedToken("<|yo|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50326: AddedToken("<|so|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50327: AddedToken("<|af|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50328: AddedToken("<|oc|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50329: AddedToken("<|ka|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50330: AddedToken("<|be|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50331: AddedToken("<|tg|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50332: AddedToken("<|sd|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50333: AddedToken("<|gu|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50334: AddedToken("<|am|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50335: AddedToken("<|yi|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50336: AddedToken("<|lo|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50337: AddedToken("<|uz|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50338: AddedToken("<|fo|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50339: AddedToken("<|ht|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50340: AddedToken("<|ps|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50341: AddedToken("<|tk|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50342: AddedToken("<|nn|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50343: AddedToken("<|mt|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50344: AddedToken("<|sa|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50345: AddedToken("<|lb|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50346: AddedToken("<|my|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50347: AddedToken("<|bo|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50348: AddedToken("<|tl|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50349: AddedToken("<|mg|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50350: AddedToken("<|as|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50351: AddedToken("<|tt|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50352: AddedToken("<|haw|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50353: AddedToken("<|ln|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50354: AddedToken("<|ha|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50355: AddedToken("<|ba|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50356: AddedToken("<|jw|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50357: AddedToken("<|su|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50358: AddedToken("<|yue|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50359: AddedToken("<|translate|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50360: AddedToken("<|transcribe|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50361: AddedToken("<|startoflm|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50362: AddedToken("<|startofprev|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50363: AddedToken("<|nospeech|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50364: AddedToken("<|notimestamps|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 50365: AddedToken("<|0.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50366: AddedToken("<|0.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50367: AddedToken("<|0.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50368: AddedToken("<|0.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50369: AddedToken("<|0.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50370: AddedToken("<|0.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50371: AddedToken("<|0.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50372: AddedToken("<|0.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50373: AddedToken("<|0.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50374: AddedToken("<|0.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50375: AddedToken("<|0.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50376: AddedToken("<|0.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50377: AddedToken("<|0.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50378: AddedToken("<|0.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50379: AddedToken("<|0.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50380: AddedToken("<|0.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50381: AddedToken("<|0.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50382: AddedToken("<|0.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50383: AddedToken("<|0.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50384: AddedToken("<|0.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50385: AddedToken("<|0.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50386: AddedToken("<|0.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50387: AddedToken("<|0.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50388: AddedToken("<|0.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50389: AddedToken("<|0.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50390: AddedToken("<|0.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50391: AddedToken("<|0.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50392: AddedToken("<|0.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50393: AddedToken("<|0.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50394: AddedToken("<|0.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50395: AddedToken("<|0.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50396: AddedToken("<|0.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50397: AddedToken("<|0.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50398: AddedToken("<|0.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50399: AddedToken("<|0.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50400: AddedToken("<|0.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50401: AddedToken("<|0.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50402: AddedToken("<|0.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50403: AddedToken("<|0.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50404: AddedToken("<|0.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50405: AddedToken("<|0.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50406: AddedToken("<|0.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50407: AddedToken("<|0.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50408: AddedToken("<|0.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50409: AddedToken("<|0.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50410: AddedToken("<|0.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50411: AddedToken("<|0.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50412: AddedToken("<|0.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50413: AddedToken("<|0.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50414: AddedToken("<|0.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50415: AddedToken("<|1.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50416: AddedToken("<|1.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50417: AddedToken("<|1.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50418: AddedToken("<|1.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50419: AddedToken("<|1.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50420: AddedToken("<|1.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50421: AddedToken("<|1.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50422: AddedToken("<|1.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50423: AddedToken("<|1.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50424: AddedToken("<|1.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50425: AddedToken("<|1.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50426: AddedToken("<|1.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50427: AddedToken("<|1.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50428: AddedToken("<|1.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50429: AddedToken("<|1.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50430: AddedToken("<|1.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50431: AddedToken("<|1.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50432: AddedToken("<|1.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50433: AddedToken("<|1.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50434: AddedToken("<|1.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50435: AddedToken("<|1.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50436: AddedToken("<|1.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50437: AddedToken("<|1.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50438: AddedToken("<|1.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50439: AddedToken("<|1.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50440: AddedToken("<|1.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50441: AddedToken("<|1.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50442: AddedToken("<|1.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50443: AddedToken("<|1.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50444: AddedToken("<|1.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50445: AddedToken("<|1.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50446: AddedToken("<|1.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50447: AddedToken("<|1.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50448: AddedToken("<|1.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50449: AddedToken("<|1.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50450: AddedToken("<|1.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50451: AddedToken("<|1.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50452: AddedToken("<|1.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50453: AddedToken("<|1.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50454: AddedToken("<|1.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50455: AddedToken("<|1.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50456: AddedToken("<|1.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50457: AddedToken("<|1.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50458: AddedToken("<|1.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50459: AddedToken("<|1.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50460: AddedToken("<|1.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50461: AddedToken("<|1.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50462: AddedToken("<|1.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50463: AddedToken("<|1.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50464: AddedToken("<|1.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50465: AddedToken("<|2.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50466: AddedToken("<|2.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50467: AddedToken("<|2.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50468: AddedToken("<|2.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50469: AddedToken("<|2.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50470: AddedToken("<|2.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50471: AddedToken("<|2.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50472: AddedToken("<|2.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50473: AddedToken("<|2.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50474: AddedToken("<|2.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50475: AddedToken("<|2.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50476: AddedToken("<|2.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50477: AddedToken("<|2.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50478: AddedToken("<|2.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50479: AddedToken("<|2.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50480: AddedToken("<|2.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50481: AddedToken("<|2.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50482: AddedToken("<|2.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50483: AddedToken("<|2.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50484: AddedToken("<|2.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50485: AddedToken("<|2.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50486: AddedToken("<|2.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50487: AddedToken("<|2.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50488: AddedToken("<|2.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50489: AddedToken("<|2.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50490: AddedToken("<|2.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50491: AddedToken("<|2.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50492: AddedToken("<|2.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50493: AddedToken("<|2.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50494: AddedToken("<|2.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50495: AddedToken("<|2.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50496: AddedToken("<|2.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50497: AddedToken("<|2.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50498: AddedToken("<|2.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50499: AddedToken("<|2.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50500: AddedToken("<|2.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50501: AddedToken("<|2.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50502: AddedToken("<|2.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50503: AddedToken("<|2.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50504: AddedToken("<|2.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50505: AddedToken("<|2.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50506: AddedToken("<|2.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50507: AddedToken("<|2.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50508: AddedToken("<|2.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50509: AddedToken("<|2.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50510: AddedToken("<|2.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50511: AddedToken("<|2.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50512: AddedToken("<|2.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50513: AddedToken("<|2.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50514: AddedToken("<|2.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50515: AddedToken("<|3.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50516: AddedToken("<|3.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50517: AddedToken("<|3.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50518: AddedToken("<|3.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50519: AddedToken("<|3.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50520: AddedToken("<|3.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50521: AddedToken("<|3.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50522: AddedToken("<|3.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50523: AddedToken("<|3.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50524: AddedToken("<|3.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50525: AddedToken("<|3.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50526: AddedToken("<|3.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50527: AddedToken("<|3.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50528: AddedToken("<|3.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50529: AddedToken("<|3.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50530: AddedToken("<|3.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50531: AddedToken("<|3.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50532: AddedToken("<|3.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50533: AddedToken("<|3.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50534: AddedToken("<|3.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50535: AddedToken("<|3.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50536: AddedToken("<|3.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50537: AddedToken("<|3.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50538: AddedToken("<|3.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50539: AddedToken("<|3.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50540: AddedToken("<|3.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50541: AddedToken("<|3.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50542: AddedToken("<|3.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50543: AddedToken("<|3.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50544: AddedToken("<|3.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50545: AddedToken("<|3.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50546: AddedToken("<|3.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50547: AddedToken("<|3.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50548: AddedToken("<|3.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50549: AddedToken("<|3.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50550: AddedToken("<|3.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50551: AddedToken("<|3.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50552: AddedToken("<|3.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50553: AddedToken("<|3.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50554: AddedToken("<|3.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50555: AddedToken("<|3.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50556: AddedToken("<|3.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50557: AddedToken("<|3.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50558: AddedToken("<|3.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50559: AddedToken("<|3.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50560: AddedToken("<|3.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50561: AddedToken("<|3.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50562: AddedToken("<|3.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50563: AddedToken("<|3.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50564: AddedToken("<|3.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50565: AddedToken("<|4.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50566: AddedToken("<|4.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50567: AddedToken("<|4.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50568: AddedToken("<|4.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50569: AddedToken("<|4.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50570: AddedToken("<|4.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50571: AddedToken("<|4.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50572: AddedToken("<|4.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50573: AddedToken("<|4.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50574: AddedToken("<|4.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50575: AddedToken("<|4.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50576: AddedToken("<|4.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50577: AddedToken("<|4.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50578: AddedToken("<|4.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50579: AddedToken("<|4.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50580: AddedToken("<|4.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50581: AddedToken("<|4.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50582: AddedToken("<|4.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50583: AddedToken("<|4.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50584: AddedToken("<|4.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50585: AddedToken("<|4.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50586: AddedToken("<|4.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50587: AddedToken("<|4.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50588: AddedToken("<|4.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50589: AddedToken("<|4.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50590: AddedToken("<|4.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50591: AddedToken("<|4.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50592: AddedToken("<|4.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50593: AddedToken("<|4.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50594: AddedToken("<|4.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50595: AddedToken("<|4.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50596: AddedToken("<|4.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50597: AddedToken("<|4.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50598: AddedToken("<|4.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50599: AddedToken("<|4.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50600: AddedToken("<|4.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50601: AddedToken("<|4.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50602: AddedToken("<|4.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50603: AddedToken("<|4.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50604: AddedToken("<|4.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50605: AddedToken("<|4.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50606: AddedToken("<|4.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50607: AddedToken("<|4.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50608: AddedToken("<|4.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50609: AddedToken("<|4.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50610: AddedToken("<|4.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50611: AddedToken("<|4.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50612: AddedToken("<|4.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50613: AddedToken("<|4.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50614: AddedToken("<|4.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50615: AddedToken("<|5.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50616: AddedToken("<|5.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50617: AddedToken("<|5.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50618: AddedToken("<|5.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50619: AddedToken("<|5.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50620: AddedToken("<|5.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50621: AddedToken("<|5.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50622: AddedToken("<|5.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50623: AddedToken("<|5.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50624: AddedToken("<|5.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50625: AddedToken("<|5.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50626: AddedToken("<|5.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50627: AddedToken("<|5.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50628: AddedToken("<|5.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50629: AddedToken("<|5.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50630: AddedToken("<|5.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50631: AddedToken("<|5.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50632: AddedToken("<|5.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50633: AddedToken("<|5.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50634: AddedToken("<|5.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50635: AddedToken("<|5.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50636: AddedToken("<|5.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50637: AddedToken("<|5.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50638: AddedToken("<|5.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50639: AddedToken("<|5.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50640: AddedToken("<|5.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50641: AddedToken("<|5.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50642: AddedToken("<|5.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50643: AddedToken("<|5.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50644: AddedToken("<|5.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50645: AddedToken("<|5.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50646: AddedToken("<|5.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50647: AddedToken("<|5.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50648: AddedToken("<|5.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50649: AddedToken("<|5.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50650: AddedToken("<|5.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50651: AddedToken("<|5.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50652: AddedToken("<|5.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50653: AddedToken("<|5.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50654: AddedToken("<|5.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50655: AddedToken("<|5.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50656: AddedToken("<|5.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50657: AddedToken("<|5.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50658: AddedToken("<|5.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50659: AddedToken("<|5.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50660: AddedToken("<|5.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50661: AddedToken("<|5.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50662: AddedToken("<|5.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50663: AddedToken("<|5.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50664: AddedToken("<|5.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50665: AddedToken("<|6.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50666: AddedToken("<|6.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50667: AddedToken("<|6.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50668: AddedToken("<|6.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50669: AddedToken("<|6.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50670: AddedToken("<|6.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50671: AddedToken("<|6.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50672: AddedToken("<|6.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50673: AddedToken("<|6.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50674: AddedToken("<|6.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50675: AddedToken("<|6.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50676: AddedToken("<|6.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50677: AddedToken("<|6.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50678: AddedToken("<|6.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50679: AddedToken("<|6.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50680: AddedToken("<|6.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50681: AddedToken("<|6.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50682: AddedToken("<|6.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50683: AddedToken("<|6.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50684: AddedToken("<|6.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50685: AddedToken("<|6.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50686: AddedToken("<|6.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50687: AddedToken("<|6.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50688: AddedToken("<|6.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50689: AddedToken("<|6.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50690: AddedToken("<|6.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50691: AddedToken("<|6.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50692: AddedToken("<|6.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50693: AddedToken("<|6.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50694: AddedToken("<|6.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50695: AddedToken("<|6.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50696: AddedToken("<|6.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50697: AddedToken("<|6.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50698: AddedToken("<|6.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50699: AddedToken("<|6.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50700: AddedToken("<|6.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50701: AddedToken("<|6.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50702: AddedToken("<|6.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50703: AddedToken("<|6.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50704: AddedToken("<|6.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50705: AddedToken("<|6.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50706: AddedToken("<|6.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50707: AddedToken("<|6.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50708: AddedToken("<|6.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50709: AddedToken("<|6.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50710: AddedToken("<|6.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50711: AddedToken("<|6.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50712: AddedToken("<|6.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50713: AddedToken("<|6.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50714: AddedToken("<|6.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50715: AddedToken("<|7.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50716: AddedToken("<|7.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50717: AddedToken("<|7.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50718: AddedToken("<|7.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50719: AddedToken("<|7.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50720: AddedToken("<|7.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50721: AddedToken("<|7.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50722: AddedToken("<|7.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50723: AddedToken("<|7.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50724: AddedToken("<|7.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50725: AddedToken("<|7.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50726: AddedToken("<|7.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50727: AddedToken("<|7.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50728: AddedToken("<|7.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50729: AddedToken("<|7.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50730: AddedToken("<|7.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50731: AddedToken("<|7.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50732: AddedToken("<|7.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50733: AddedToken("<|7.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50734: AddedToken("<|7.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50735: AddedToken("<|7.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50736: AddedToken("<|7.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50737: AddedToken("<|7.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50738: AddedToken("<|7.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50739: AddedToken("<|7.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50740: AddedToken("<|7.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50741: AddedToken("<|7.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50742: AddedToken("<|7.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50743: AddedToken("<|7.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50744: AddedToken("<|7.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50745: AddedToken("<|7.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50746: AddedToken("<|7.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50747: AddedToken("<|7.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50748: AddedToken("<|7.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50749: AddedToken("<|7.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50750: AddedToken("<|7.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50751: AddedToken("<|7.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50752: AddedToken("<|7.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50753: AddedToken("<|7.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50754: AddedToken("<|7.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50755: AddedToken("<|7.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50756: AddedToken("<|7.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50757: AddedToken("<|7.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50758: AddedToken("<|7.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50759: AddedToken("<|7.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50760: AddedToken("<|7.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50761: AddedToken("<|7.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50762: AddedToken("<|7.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50763: AddedToken("<|7.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50764: AddedToken("<|7.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50765: AddedToken("<|8.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50766: AddedToken("<|8.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50767: AddedToken("<|8.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50768: AddedToken("<|8.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50769: AddedToken("<|8.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50770: AddedToken("<|8.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50771: AddedToken("<|8.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50772: AddedToken("<|8.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50773: AddedToken("<|8.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50774: AddedToken("<|8.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50775: AddedToken("<|8.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50776: AddedToken("<|8.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50777: AddedToken("<|8.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50778: AddedToken("<|8.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50779: AddedToken("<|8.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50780: AddedToken("<|8.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50781: AddedToken("<|8.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50782: AddedToken("<|8.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50783: AddedToken("<|8.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50784: AddedToken("<|8.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50785: AddedToken("<|8.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50786: AddedToken("<|8.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50787: AddedToken("<|8.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50788: AddedToken("<|8.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50789: AddedToken("<|8.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50790: AddedToken("<|8.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50791: AddedToken("<|8.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50792: AddedToken("<|8.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50793: AddedToken("<|8.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50794: AddedToken("<|8.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50795: AddedToken("<|8.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50796: AddedToken("<|8.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50797: AddedToken("<|8.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50798: AddedToken("<|8.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50799: AddedToken("<|8.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50800: AddedToken("<|8.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50801: AddedToken("<|8.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50802: AddedToken("<|8.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50803: AddedToken("<|8.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50804: AddedToken("<|8.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50805: AddedToken("<|8.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50806: AddedToken("<|8.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50807: AddedToken("<|8.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50808: AddedToken("<|8.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50809: AddedToken("<|8.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50810: AddedToken("<|8.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50811: AddedToken("<|8.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50812: AddedToken("<|8.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50813: AddedToken("<|8.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50814: AddedToken("<|8.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50815: AddedToken("<|9.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50816: AddedToken("<|9.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50817: AddedToken("<|9.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50818: AddedToken("<|9.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50819: AddedToken("<|9.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50820: AddedToken("<|9.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50821: AddedToken("<|9.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50822: AddedToken("<|9.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50823: AddedToken("<|9.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50824: AddedToken("<|9.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50825: AddedToken("<|9.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50826: AddedToken("<|9.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50827: AddedToken("<|9.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50828: AddedToken("<|9.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50829: AddedToken("<|9.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50830: AddedToken("<|9.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50831: AddedToken("<|9.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50832: AddedToken("<|9.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50833: AddedToken("<|9.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50834: AddedToken("<|9.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50835: AddedToken("<|9.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50836: AddedToken("<|9.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50837: AddedToken("<|9.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50838: AddedToken("<|9.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50839: AddedToken("<|9.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50840: AddedToken("<|9.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50841: AddedToken("<|9.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50842: AddedToken("<|9.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50843: AddedToken("<|9.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50844: AddedToken("<|9.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50845: AddedToken("<|9.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50846: AddedToken("<|9.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50847: AddedToken("<|9.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50848: AddedToken("<|9.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50849: AddedToken("<|9.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50850: AddedToken("<|9.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50851: AddedToken("<|9.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50852: AddedToken("<|9.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50853: AddedToken("<|9.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50854: AddedToken("<|9.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50855: AddedToken("<|9.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50856: AddedToken("<|9.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50857: AddedToken("<|9.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50858: AddedToken("<|9.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50859: AddedToken("<|9.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50860: AddedToken("<|9.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50861: AddedToken("<|9.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50862: AddedToken("<|9.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50863: AddedToken("<|9.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50864: AddedToken("<|9.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50865: AddedToken("<|10.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50866: AddedToken("<|10.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50867: AddedToken("<|10.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50868: AddedToken("<|10.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50869: AddedToken("<|10.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50870: AddedToken("<|10.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50871: AddedToken("<|10.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50872: AddedToken("<|10.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50873: AddedToken("<|10.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50874: AddedToken("<|10.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50875: AddedToken("<|10.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50876: AddedToken("<|10.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50877: AddedToken("<|10.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50878: AddedToken("<|10.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50879: AddedToken("<|10.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50880: AddedToken("<|10.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50881: AddedToken("<|10.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50882: AddedToken("<|10.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50883: AddedToken("<|10.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50884: AddedToken("<|10.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50885: AddedToken("<|10.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50886: AddedToken("<|10.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50887: AddedToken("<|10.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50888: AddedToken("<|10.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50889: AddedToken("<|10.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50890: AddedToken("<|10.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50891: AddedToken("<|10.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50892: AddedToken("<|10.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50893: AddedToken("<|10.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50894: AddedToken("<|10.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50895: AddedToken("<|10.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50896: AddedToken("<|10.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50897: AddedToken("<|10.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50898: AddedToken("<|10.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50899: AddedToken("<|10.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50900: AddedToken("<|10.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50901: AddedToken("<|10.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50902: AddedToken("<|10.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50903: AddedToken("<|10.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50904: AddedToken("<|10.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50905: AddedToken("<|10.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50906: AddedToken("<|10.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50907: AddedToken("<|10.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50908: AddedToken("<|10.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50909: AddedToken("<|10.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50910: AddedToken("<|10.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50911: AddedToken("<|10.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50912: AddedToken("<|10.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50913: AddedToken("<|10.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50914: AddedToken("<|10.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50915: AddedToken("<|11.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50916: AddedToken("<|11.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50917: AddedToken("<|11.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50918: AddedToken("<|11.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50919: AddedToken("<|11.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50920: AddedToken("<|11.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50921: AddedToken("<|11.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50922: AddedToken("<|11.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50923: AddedToken("<|11.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50924: AddedToken("<|11.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50925: AddedToken("<|11.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50926: AddedToken("<|11.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50927: AddedToken("<|11.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50928: AddedToken("<|11.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50929: AddedToken("<|11.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50930: AddedToken("<|11.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50931: AddedToken("<|11.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50932: AddedToken("<|11.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50933: AddedToken("<|11.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50934: AddedToken("<|11.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50935: AddedToken("<|11.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50936: AddedToken("<|11.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50937: AddedToken("<|11.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50938: AddedToken("<|11.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50939: AddedToken("<|11.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50940: AddedToken("<|11.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50941: AddedToken("<|11.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50942: AddedToken("<|11.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50943: AddedToken("<|11.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50944: AddedToken("<|11.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50945: AddedToken("<|11.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50946: AddedToken("<|11.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50947: AddedToken("<|11.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50948: AddedToken("<|11.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50949: AddedToken("<|11.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50950: AddedToken("<|11.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50951: AddedToken("<|11.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50952: AddedToken("<|11.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50953: AddedToken("<|11.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50954: AddedToken("<|11.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50955: AddedToken("<|11.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50956: AddedToken("<|11.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50957: AddedToken("<|11.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50958: AddedToken("<|11.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50959: AddedToken("<|11.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50960: AddedToken("<|11.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50961: AddedToken("<|11.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50962: AddedToken("<|11.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50963: AddedToken("<|11.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50964: AddedToken("<|11.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50965: AddedToken("<|12.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50966: AddedToken("<|12.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50967: AddedToken("<|12.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50968: AddedToken("<|12.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50969: AddedToken("<|12.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50970: AddedToken("<|12.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50971: AddedToken("<|12.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50972: AddedToken("<|12.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50973: AddedToken("<|12.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50974: AddedToken("<|12.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50975: AddedToken("<|12.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50976: AddedToken("<|12.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50977: AddedToken("<|12.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50978: AddedToken("<|12.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50979: AddedToken("<|12.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50980: AddedToken("<|12.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50981: AddedToken("<|12.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50982: AddedToken("<|12.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50983: AddedToken("<|12.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50984: AddedToken("<|12.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50985: AddedToken("<|12.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50986: AddedToken("<|12.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50987: AddedToken("<|12.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50988: AddedToken("<|12.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50989: AddedToken("<|12.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50990: AddedToken("<|12.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50991: AddedToken("<|12.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50992: AddedToken("<|12.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50993: AddedToken("<|12.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50994: AddedToken("<|12.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50995: AddedToken("<|12.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50996: AddedToken("<|12.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50997: AddedToken("<|12.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50998: AddedToken("<|12.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 50999: AddedToken("<|12.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51000: AddedToken("<|12.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51001: AddedToken("<|12.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51002: AddedToken("<|12.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51003: AddedToken("<|12.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51004: AddedToken("<|12.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51005: AddedToken("<|12.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51006: AddedToken("<|12.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51007: AddedToken("<|12.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51008: AddedToken("<|12.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51009: AddedToken("<|12.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51010: AddedToken("<|12.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51011: AddedToken("<|12.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51012: AddedToken("<|12.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51013: AddedToken("<|12.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51014: AddedToken("<|12.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51015: AddedToken("<|13.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51016: AddedToken("<|13.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51017: AddedToken("<|13.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51018: AddedToken("<|13.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51019: AddedToken("<|13.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51020: AddedToken("<|13.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51021: AddedToken("<|13.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51022: AddedToken("<|13.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51023: AddedToken("<|13.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51024: AddedToken("<|13.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51025: AddedToken("<|13.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51026: AddedToken("<|13.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51027: AddedToken("<|13.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51028: AddedToken("<|13.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51029: AddedToken("<|13.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51030: AddedToken("<|13.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51031: AddedToken("<|13.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51032: AddedToken("<|13.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51033: AddedToken("<|13.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51034: AddedToken("<|13.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51035: AddedToken("<|13.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51036: AddedToken("<|13.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51037: AddedToken("<|13.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51038: AddedToken("<|13.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51039: AddedToken("<|13.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51040: AddedToken("<|13.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51041: AddedToken("<|13.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51042: AddedToken("<|13.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51043: AddedToken("<|13.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51044: AddedToken("<|13.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51045: AddedToken("<|13.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51046: AddedToken("<|13.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51047: AddedToken("<|13.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51048: AddedToken("<|13.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51049: AddedToken("<|13.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51050: AddedToken("<|13.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51051: AddedToken("<|13.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51052: AddedToken("<|13.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51053: AddedToken("<|13.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51054: AddedToken("<|13.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51055: AddedToken("<|13.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51056: AddedToken("<|13.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51057: AddedToken("<|13.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51058: AddedToken("<|13.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51059: AddedToken("<|13.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51060: AddedToken("<|13.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51061: AddedToken("<|13.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51062: AddedToken("<|13.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51063: AddedToken("<|13.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51064: AddedToken("<|13.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51065: AddedToken("<|14.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51066: AddedToken("<|14.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51067: AddedToken("<|14.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51068: AddedToken("<|14.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51069: AddedToken("<|14.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51070: AddedToken("<|14.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51071: AddedToken("<|14.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51072: AddedToken("<|14.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51073: AddedToken("<|14.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51074: AddedToken("<|14.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51075: AddedToken("<|14.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51076: AddedToken("<|14.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51077: AddedToken("<|14.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51078: AddedToken("<|14.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51079: AddedToken("<|14.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51080: AddedToken("<|14.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51081: AddedToken("<|14.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51082: AddedToken("<|14.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51083: AddedToken("<|14.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51084: AddedToken("<|14.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51085: AddedToken("<|14.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51086: AddedToken("<|14.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51087: AddedToken("<|14.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51088: AddedToken("<|14.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51089: AddedToken("<|14.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51090: AddedToken("<|14.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51091: AddedToken("<|14.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51092: AddedToken("<|14.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51093: AddedToken("<|14.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51094: AddedToken("<|14.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51095: AddedToken("<|14.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51096: AddedToken("<|14.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51097: AddedToken("<|14.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51098: AddedToken("<|14.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51099: AddedToken("<|14.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51100: AddedToken("<|14.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51101: AddedToken("<|14.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51102: AddedToken("<|14.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51103: AddedToken("<|14.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51104: AddedToken("<|14.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51105: AddedToken("<|14.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51106: AddedToken("<|14.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51107: AddedToken("<|14.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51108: AddedToken("<|14.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51109: AddedToken("<|14.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51110: AddedToken("<|14.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51111: AddedToken("<|14.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51112: AddedToken("<|14.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51113: AddedToken("<|14.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51114: AddedToken("<|14.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51115: AddedToken("<|15.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51116: AddedToken("<|15.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51117: AddedToken("<|15.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51118: AddedToken("<|15.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51119: AddedToken("<|15.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51120: AddedToken("<|15.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51121: AddedToken("<|15.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51122: AddedToken("<|15.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51123: AddedToken("<|15.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51124: AddedToken("<|15.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51125: AddedToken("<|15.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51126: AddedToken("<|15.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51127: AddedToken("<|15.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51128: AddedToken("<|15.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51129: AddedToken("<|15.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51130: AddedToken("<|15.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51131: AddedToken("<|15.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51132: AddedToken("<|15.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51133: AddedToken("<|15.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51134: AddedToken("<|15.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51135: AddedToken("<|15.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51136: AddedToken("<|15.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51137: AddedToken("<|15.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51138: AddedToken("<|15.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51139: AddedToken("<|15.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51140: AddedToken("<|15.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51141: AddedToken("<|15.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51142: AddedToken("<|15.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51143: AddedToken("<|15.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51144: AddedToken("<|15.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51145: AddedToken("<|15.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51146: AddedToken("<|15.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51147: AddedToken("<|15.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51148: AddedToken("<|15.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51149: AddedToken("<|15.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51150: AddedToken("<|15.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51151: AddedToken("<|15.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51152: AddedToken("<|15.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51153: AddedToken("<|15.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51154: AddedToken("<|15.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51155: AddedToken("<|15.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51156: AddedToken("<|15.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51157: AddedToken("<|15.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51158: AddedToken("<|15.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51159: AddedToken("<|15.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51160: AddedToken("<|15.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51161: AddedToken("<|15.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51162: AddedToken("<|15.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51163: AddedToken("<|15.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51164: AddedToken("<|15.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51165: AddedToken("<|16.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51166: AddedToken("<|16.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51167: AddedToken("<|16.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51168: AddedToken("<|16.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51169: AddedToken("<|16.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51170: AddedToken("<|16.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51171: AddedToken("<|16.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51172: AddedToken("<|16.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51173: AddedToken("<|16.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51174: AddedToken("<|16.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51175: AddedToken("<|16.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51176: AddedToken("<|16.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51177: AddedToken("<|16.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51178: AddedToken("<|16.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51179: AddedToken("<|16.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51180: AddedToken("<|16.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51181: AddedToken("<|16.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51182: AddedToken("<|16.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51183: AddedToken("<|16.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51184: AddedToken("<|16.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51185: AddedToken("<|16.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51186: AddedToken("<|16.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51187: AddedToken("<|16.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51188: AddedToken("<|16.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51189: AddedToken("<|16.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51190: AddedToken("<|16.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51191: AddedToken("<|16.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51192: AddedToken("<|16.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51193: AddedToken("<|16.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51194: AddedToken("<|16.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51195: AddedToken("<|16.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51196: AddedToken("<|16.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51197: AddedToken("<|16.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51198: AddedToken("<|16.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51199: AddedToken("<|16.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51200: AddedToken("<|16.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51201: AddedToken("<|16.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51202: AddedToken("<|16.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51203: AddedToken("<|16.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51204: AddedToken("<|16.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51205: AddedToken("<|16.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51206: AddedToken("<|16.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51207: AddedToken("<|16.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51208: AddedToken("<|16.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51209: AddedToken("<|16.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51210: AddedToken("<|16.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51211: AddedToken("<|16.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51212: AddedToken("<|16.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51213: AddedToken("<|16.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51214: AddedToken("<|16.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51215: AddedToken("<|17.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51216: AddedToken("<|17.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51217: AddedToken("<|17.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51218: AddedToken("<|17.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51219: AddedToken("<|17.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51220: AddedToken("<|17.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51221: AddedToken("<|17.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51222: AddedToken("<|17.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51223: AddedToken("<|17.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51224: AddedToken("<|17.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51225: AddedToken("<|17.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51226: AddedToken("<|17.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51227: AddedToken("<|17.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51228: AddedToken("<|17.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51229: AddedToken("<|17.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51230: AddedToken("<|17.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51231: AddedToken("<|17.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51232: AddedToken("<|17.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51233: AddedToken("<|17.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51234: AddedToken("<|17.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51235: AddedToken("<|17.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51236: AddedToken("<|17.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51237: AddedToken("<|17.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51238: AddedToken("<|17.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51239: AddedToken("<|17.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51240: AddedToken("<|17.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51241: AddedToken("<|17.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51242: AddedToken("<|17.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51243: AddedToken("<|17.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51244: AddedToken("<|17.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51245: AddedToken("<|17.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51246: AddedToken("<|17.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51247: AddedToken("<|17.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51248: AddedToken("<|17.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51249: AddedToken("<|17.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51250: AddedToken("<|17.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51251: AddedToken("<|17.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51252: AddedToken("<|17.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51253: AddedToken("<|17.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51254: AddedToken("<|17.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51255: AddedToken("<|17.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51256: AddedToken("<|17.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51257: AddedToken("<|17.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51258: AddedToken("<|17.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51259: AddedToken("<|17.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51260: AddedToken("<|17.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51261: AddedToken("<|17.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51262: AddedToken("<|17.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51263: AddedToken("<|17.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51264: AddedToken("<|17.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51265: AddedToken("<|18.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51266: AddedToken("<|18.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51267: AddedToken("<|18.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51268: AddedToken("<|18.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51269: AddedToken("<|18.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51270: AddedToken("<|18.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51271: AddedToken("<|18.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51272: AddedToken("<|18.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51273: AddedToken("<|18.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51274: AddedToken("<|18.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51275: AddedToken("<|18.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51276: AddedToken("<|18.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51277: AddedToken("<|18.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51278: AddedToken("<|18.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51279: AddedToken("<|18.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51280: AddedToken("<|18.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51281: AddedToken("<|18.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51282: AddedToken("<|18.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51283: AddedToken("<|18.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51284: AddedToken("<|18.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51285: AddedToken("<|18.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51286: AddedToken("<|18.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51287: AddedToken("<|18.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51288: AddedToken("<|18.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51289: AddedToken("<|18.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51290: AddedToken("<|18.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51291: AddedToken("<|18.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51292: AddedToken("<|18.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51293: AddedToken("<|18.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51294: AddedToken("<|18.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51295: AddedToken("<|18.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51296: AddedToken("<|18.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51297: AddedToken("<|18.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51298: AddedToken("<|18.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51299: AddedToken("<|18.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51300: AddedToken("<|18.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51301: AddedToken("<|18.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51302: AddedToken("<|18.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51303: AddedToken("<|18.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51304: AddedToken("<|18.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51305: AddedToken("<|18.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51306: AddedToken("<|18.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51307: AddedToken("<|18.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51308: AddedToken("<|18.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51309: AddedToken("<|18.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51310: AddedToken("<|18.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51311: AddedToken("<|18.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51312: AddedToken("<|18.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51313: AddedToken("<|18.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51314: AddedToken("<|18.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51315: AddedToken("<|19.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51316: AddedToken("<|19.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51317: AddedToken("<|19.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51318: AddedToken("<|19.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51319: AddedToken("<|19.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51320: AddedToken("<|19.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51321: AddedToken("<|19.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51322: AddedToken("<|19.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51323: AddedToken("<|19.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51324: AddedToken("<|19.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51325: AddedToken("<|19.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51326: AddedToken("<|19.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51327: AddedToken("<|19.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51328: AddedToken("<|19.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51329: AddedToken("<|19.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51330: AddedToken("<|19.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51331: AddedToken("<|19.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51332: AddedToken("<|19.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51333: AddedToken("<|19.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51334: AddedToken("<|19.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51335: AddedToken("<|19.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51336: AddedToken("<|19.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51337: AddedToken("<|19.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51338: AddedToken("<|19.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51339: AddedToken("<|19.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51340: AddedToken("<|19.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51341: AddedToken("<|19.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51342: AddedToken("<|19.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51343: AddedToken("<|19.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51344: AddedToken("<|19.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51345: AddedToken("<|19.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51346: AddedToken("<|19.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51347: AddedToken("<|19.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51348: AddedToken("<|19.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51349: AddedToken("<|19.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51350: AddedToken("<|19.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51351: AddedToken("<|19.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51352: AddedToken("<|19.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51353: AddedToken("<|19.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51354: AddedToken("<|19.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51355: AddedToken("<|19.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51356: AddedToken("<|19.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51357: AddedToken("<|19.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51358: AddedToken("<|19.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51359: AddedToken("<|19.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51360: AddedToken("<|19.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51361: AddedToken("<|19.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51362: AddedToken("<|19.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51363: AddedToken("<|19.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51364: AddedToken("<|19.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51365: AddedToken("<|20.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51366: AddedToken("<|20.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51367: AddedToken("<|20.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51368: AddedToken("<|20.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51369: AddedToken("<|20.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51370: AddedToken("<|20.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51371: AddedToken("<|20.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51372: AddedToken("<|20.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51373: AddedToken("<|20.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51374: AddedToken("<|20.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51375: AddedToken("<|20.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51376: AddedToken("<|20.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51377: AddedToken("<|20.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51378: AddedToken("<|20.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51379: AddedToken("<|20.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51380: AddedToken("<|20.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51381: AddedToken("<|20.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51382: AddedToken("<|20.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51383: AddedToken("<|20.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51384: AddedToken("<|20.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51385: AddedToken("<|20.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51386: AddedToken("<|20.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51387: AddedToken("<|20.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51388: AddedToken("<|20.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51389: AddedToken("<|20.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51390: AddedToken("<|20.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51391: AddedToken("<|20.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51392: AddedToken("<|20.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51393: AddedToken("<|20.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51394: AddedToken("<|20.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51395: AddedToken("<|20.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51396: AddedToken("<|20.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51397: AddedToken("<|20.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51398: AddedToken("<|20.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51399: AddedToken("<|20.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51400: AddedToken("<|20.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51401: AddedToken("<|20.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51402: AddedToken("<|20.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51403: AddedToken("<|20.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51404: AddedToken("<|20.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51405: AddedToken("<|20.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51406: AddedToken("<|20.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51407: AddedToken("<|20.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51408: AddedToken("<|20.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51409: AddedToken("<|20.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51410: AddedToken("<|20.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51411: AddedToken("<|20.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51412: AddedToken("<|20.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51413: AddedToken("<|20.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51414: AddedToken("<|20.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51415: AddedToken("<|21.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51416: AddedToken("<|21.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51417: AddedToken("<|21.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51418: AddedToken("<|21.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51419: AddedToken("<|21.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51420: AddedToken("<|21.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51421: AddedToken("<|21.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51422: AddedToken("<|21.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51423: AddedToken("<|21.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51424: AddedToken("<|21.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51425: AddedToken("<|21.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51426: AddedToken("<|21.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51427: AddedToken("<|21.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51428: AddedToken("<|21.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51429: AddedToken("<|21.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51430: AddedToken("<|21.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51431: AddedToken("<|21.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51432: AddedToken("<|21.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51433: AddedToken("<|21.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51434: AddedToken("<|21.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51435: AddedToken("<|21.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51436: AddedToken("<|21.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51437: AddedToken("<|21.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51438: AddedToken("<|21.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51439: AddedToken("<|21.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51440: AddedToken("<|21.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51441: AddedToken("<|21.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51442: AddedToken("<|21.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51443: AddedToken("<|21.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51444: AddedToken("<|21.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51445: AddedToken("<|21.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51446: AddedToken("<|21.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51447: AddedToken("<|21.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51448: AddedToken("<|21.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51449: AddedToken("<|21.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51450: AddedToken("<|21.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51451: AddedToken("<|21.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51452: AddedToken("<|21.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51453: AddedToken("<|21.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51454: AddedToken("<|21.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51455: AddedToken("<|21.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51456: AddedToken("<|21.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51457: AddedToken("<|21.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51458: AddedToken("<|21.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51459: AddedToken("<|21.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51460: AddedToken("<|21.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51461: AddedToken("<|21.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51462: AddedToken("<|21.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51463: AddedToken("<|21.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51464: AddedToken("<|21.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51465: AddedToken("<|22.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51466: AddedToken("<|22.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51467: AddedToken("<|22.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51468: AddedToken("<|22.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51469: AddedToken("<|22.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51470: AddedToken("<|22.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51471: AddedToken("<|22.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51472: AddedToken("<|22.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51473: AddedToken("<|22.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51474: AddedToken("<|22.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51475: AddedToken("<|22.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51476: AddedToken("<|22.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51477: AddedToken("<|22.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51478: AddedToken("<|22.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51479: AddedToken("<|22.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51480: AddedToken("<|22.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51481: AddedToken("<|22.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51482: AddedToken("<|22.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51483: AddedToken("<|22.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51484: AddedToken("<|22.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51485: AddedToken("<|22.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51486: AddedToken("<|22.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51487: AddedToken("<|22.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51488: AddedToken("<|22.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51489: AddedToken("<|22.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51490: AddedToken("<|22.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51491: AddedToken("<|22.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51492: AddedToken("<|22.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51493: AddedToken("<|22.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51494: AddedToken("<|22.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51495: AddedToken("<|22.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51496: AddedToken("<|22.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51497: AddedToken("<|22.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51498: AddedToken("<|22.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51499: AddedToken("<|22.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51500: AddedToken("<|22.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51501: AddedToken("<|22.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51502: AddedToken("<|22.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51503: AddedToken("<|22.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51504: AddedToken("<|22.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51505: AddedToken("<|22.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51506: AddedToken("<|22.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51507: AddedToken("<|22.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51508: AddedToken("<|22.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51509: AddedToken("<|22.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51510: AddedToken("<|22.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51511: AddedToken("<|22.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51512: AddedToken("<|22.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51513: AddedToken("<|22.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51514: AddedToken("<|22.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51515: AddedToken("<|23.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51516: AddedToken("<|23.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51517: AddedToken("<|23.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51518: AddedToken("<|23.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51519: AddedToken("<|23.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51520: AddedToken("<|23.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51521: AddedToken("<|23.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51522: AddedToken("<|23.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51523: AddedToken("<|23.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51524: AddedToken("<|23.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51525: AddedToken("<|23.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51526: AddedToken("<|23.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51527: AddedToken("<|23.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51528: AddedToken("<|23.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51529: AddedToken("<|23.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51530: AddedToken("<|23.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51531: AddedToken("<|23.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51532: AddedToken("<|23.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51533: AddedToken("<|23.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51534: AddedToken("<|23.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51535: AddedToken("<|23.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51536: AddedToken("<|23.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51537: AddedToken("<|23.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51538: AddedToken("<|23.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51539: AddedToken("<|23.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51540: AddedToken("<|23.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51541: AddedToken("<|23.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51542: AddedToken("<|23.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51543: AddedToken("<|23.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51544: AddedToken("<|23.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51545: AddedToken("<|23.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51546: AddedToken("<|23.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51547: AddedToken("<|23.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51548: AddedToken("<|23.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51549: AddedToken("<|23.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51550: AddedToken("<|23.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51551: AddedToken("<|23.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51552: AddedToken("<|23.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51553: AddedToken("<|23.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51554: AddedToken("<|23.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51555: AddedToken("<|23.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51556: AddedToken("<|23.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51557: AddedToken("<|23.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51558: AddedToken("<|23.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51559: AddedToken("<|23.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51560: AddedToken("<|23.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51561: AddedToken("<|23.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51562: AddedToken("<|23.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51563: AddedToken("<|23.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51564: AddedToken("<|23.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51565: AddedToken("<|24.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51566: AddedToken("<|24.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51567: AddedToken("<|24.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51568: AddedToken("<|24.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51569: AddedToken("<|24.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51570: AddedToken("<|24.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51571: AddedToken("<|24.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51572: AddedToken("<|24.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51573: AddedToken("<|24.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51574: AddedToken("<|24.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51575: AddedToken("<|24.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51576: AddedToken("<|24.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51577: AddedToken("<|24.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51578: AddedToken("<|24.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51579: AddedToken("<|24.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51580: AddedToken("<|24.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51581: AddedToken("<|24.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51582: AddedToken("<|24.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51583: AddedToken("<|24.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51584: AddedToken("<|24.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51585: AddedToken("<|24.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51586: AddedToken("<|24.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51587: AddedToken("<|24.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51588: AddedToken("<|24.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51589: AddedToken("<|24.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51590: AddedToken("<|24.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51591: AddedToken("<|24.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51592: AddedToken("<|24.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51593: AddedToken("<|24.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51594: AddedToken("<|24.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51595: AddedToken("<|24.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51596: AddedToken("<|24.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51597: AddedToken("<|24.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51598: AddedToken("<|24.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51599: AddedToken("<|24.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51600: AddedToken("<|24.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51601: AddedToken("<|24.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51602: AddedToken("<|24.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51603: AddedToken("<|24.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51604: AddedToken("<|24.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51605: AddedToken("<|24.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51606: AddedToken("<|24.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51607: AddedToken("<|24.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51608: AddedToken("<|24.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51609: AddedToken("<|24.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51610: AddedToken("<|24.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51611: AddedToken("<|24.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51612: AddedToken("<|24.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51613: AddedToken("<|24.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51614: AddedToken("<|24.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51615: AddedToken("<|25.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51616: AddedToken("<|25.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51617: AddedToken("<|25.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51618: AddedToken("<|25.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51619: AddedToken("<|25.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51620: AddedToken("<|25.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51621: AddedToken("<|25.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51622: AddedToken("<|25.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51623: AddedToken("<|25.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51624: AddedToken("<|25.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51625: AddedToken("<|25.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51626: AddedToken("<|25.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51627: AddedToken("<|25.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51628: AddedToken("<|25.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51629: AddedToken("<|25.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51630: AddedToken("<|25.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51631: AddedToken("<|25.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51632: AddedToken("<|25.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51633: AddedToken("<|25.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51634: AddedToken("<|25.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51635: AddedToken("<|25.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51636: AddedToken("<|25.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51637: AddedToken("<|25.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51638: AddedToken("<|25.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51639: AddedToken("<|25.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51640: AddedToken("<|25.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51641: AddedToken("<|25.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51642: AddedToken("<|25.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51643: AddedToken("<|25.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51644: AddedToken("<|25.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51645: AddedToken("<|25.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51646: AddedToken("<|25.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51647: AddedToken("<|25.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51648: AddedToken("<|25.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51649: AddedToken("<|25.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51650: AddedToken("<|25.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51651: AddedToken("<|25.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51652: AddedToken("<|25.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51653: AddedToken("<|25.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51654: AddedToken("<|25.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51655: AddedToken("<|25.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51656: AddedToken("<|25.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51657: AddedToken("<|25.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51658: AddedToken("<|25.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51659: AddedToken("<|25.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51660: AddedToken("<|25.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51661: AddedToken("<|25.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51662: AddedToken("<|25.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51663: AddedToken("<|25.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51664: AddedToken("<|25.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51665: AddedToken("<|26.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51666: AddedToken("<|26.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51667: AddedToken("<|26.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51668: AddedToken("<|26.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51669: AddedToken("<|26.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51670: AddedToken("<|26.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51671: AddedToken("<|26.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51672: AddedToken("<|26.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51673: AddedToken("<|26.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51674: AddedToken("<|26.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51675: AddedToken("<|26.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51676: AddedToken("<|26.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51677: AddedToken("<|26.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51678: AddedToken("<|26.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51679: AddedToken("<|26.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51680: AddedToken("<|26.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51681: AddedToken("<|26.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51682: AddedToken("<|26.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51683: AddedToken("<|26.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51684: AddedToken("<|26.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51685: AddedToken("<|26.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51686: AddedToken("<|26.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51687: AddedToken("<|26.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51688: AddedToken("<|26.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51689: AddedToken("<|26.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51690: AddedToken("<|26.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51691: AddedToken("<|26.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51692: AddedToken("<|26.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51693: AddedToken("<|26.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51694: AddedToken("<|26.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51695: AddedToken("<|26.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51696: AddedToken("<|26.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51697: AddedToken("<|26.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51698: AddedToken("<|26.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51699: AddedToken("<|26.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51700: AddedToken("<|26.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51701: AddedToken("<|26.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51702: AddedToken("<|26.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51703: AddedToken("<|26.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51704: AddedToken("<|26.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51705: AddedToken("<|26.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51706: AddedToken("<|26.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51707: AddedToken("<|26.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51708: AddedToken("<|26.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51709: AddedToken("<|26.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51710: AddedToken("<|26.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51711: AddedToken("<|26.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51712: AddedToken("<|26.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51713: AddedToken("<|26.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51714: AddedToken("<|26.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51715: AddedToken("<|27.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51716: AddedToken("<|27.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51717: AddedToken("<|27.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51718: AddedToken("<|27.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51719: AddedToken("<|27.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51720: AddedToken("<|27.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51721: AddedToken("<|27.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51722: AddedToken("<|27.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51723: AddedToken("<|27.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51724: AddedToken("<|27.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51725: AddedToken("<|27.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51726: AddedToken("<|27.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51727: AddedToken("<|27.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51728: AddedToken("<|27.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51729: AddedToken("<|27.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51730: AddedToken("<|27.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51731: AddedToken("<|27.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51732: AddedToken("<|27.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51733: AddedToken("<|27.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51734: AddedToken("<|27.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51735: AddedToken("<|27.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51736: AddedToken("<|27.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51737: AddedToken("<|27.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51738: AddedToken("<|27.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51739: AddedToken("<|27.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51740: AddedToken("<|27.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51741: AddedToken("<|27.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51742: AddedToken("<|27.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51743: AddedToken("<|27.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51744: AddedToken("<|27.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51745: AddedToken("<|27.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51746: AddedToken("<|27.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51747: AddedToken("<|27.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51748: AddedToken("<|27.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51749: AddedToken("<|27.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51750: AddedToken("<|27.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51751: AddedToken("<|27.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51752: AddedToken("<|27.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51753: AddedToken("<|27.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51754: AddedToken("<|27.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51755: AddedToken("<|27.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51756: AddedToken("<|27.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51757: AddedToken("<|27.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51758: AddedToken("<|27.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51759: AddedToken("<|27.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51760: AddedToken("<|27.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51761: AddedToken("<|27.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51762: AddedToken("<|27.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51763: AddedToken("<|27.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51764: AddedToken("<|27.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51765: AddedToken("<|28.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51766: AddedToken("<|28.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51767: AddedToken("<|28.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51768: AddedToken("<|28.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51769: AddedToken("<|28.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51770: AddedToken("<|28.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51771: AddedToken("<|28.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51772: AddedToken("<|28.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51773: AddedToken("<|28.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51774: AddedToken("<|28.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51775: AddedToken("<|28.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51776: AddedToken("<|28.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51777: AddedToken("<|28.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51778: AddedToken("<|28.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51779: AddedToken("<|28.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51780: AddedToken("<|28.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51781: AddedToken("<|28.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51782: AddedToken("<|28.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51783: AddedToken("<|28.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51784: AddedToken("<|28.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51785: AddedToken("<|28.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51786: AddedToken("<|28.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51787: AddedToken("<|28.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51788: AddedToken("<|28.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51789: AddedToken("<|28.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51790: AddedToken("<|28.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51791: AddedToken("<|28.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51792: AddedToken("<|28.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51793: AddedToken("<|28.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51794: AddedToken("<|28.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51795: AddedToken("<|28.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51796: AddedToken("<|28.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51797: AddedToken("<|28.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51798: AddedToken("<|28.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51799: AddedToken("<|28.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51800: AddedToken("<|28.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51801: AddedToken("<|28.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51802: AddedToken("<|28.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51803: AddedToken("<|28.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51804: AddedToken("<|28.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51805: AddedToken("<|28.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51806: AddedToken("<|28.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51807: AddedToken("<|28.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51808: AddedToken("<|28.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51809: AddedToken("<|28.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51810: AddedToken("<|28.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51811: AddedToken("<|28.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51812: AddedToken("<|28.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51813: AddedToken("<|28.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51814: AddedToken("<|28.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51815: AddedToken("<|29.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51816: AddedToken("<|29.02|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51817: AddedToken("<|29.04|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51818: AddedToken("<|29.06|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51819: AddedToken("<|29.08|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51820: AddedToken("<|29.10|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51821: AddedToken("<|29.12|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51822: AddedToken("<|29.14|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51823: AddedToken("<|29.16|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51824: AddedToken("<|29.18|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51825: AddedToken("<|29.20|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51826: AddedToken("<|29.22|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51827: AddedToken("<|29.24|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51828: AddedToken("<|29.26|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51829: AddedToken("<|29.28|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51830: AddedToken("<|29.30|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51831: AddedToken("<|29.32|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51832: AddedToken("<|29.34|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51833: AddedToken("<|29.36|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51834: AddedToken("<|29.38|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51835: AddedToken("<|29.40|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51836: AddedToken("<|29.42|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51837: AddedToken("<|29.44|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51838: AddedToken("<|29.46|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51839: AddedToken("<|29.48|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51840: AddedToken("<|29.50|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51841: AddedToken("<|29.52|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51842: AddedToken("<|29.54|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51843: AddedToken("<|29.56|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51844: AddedToken("<|29.58|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51845: AddedToken("<|29.60|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51846: AddedToken("<|29.62|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51847: AddedToken("<|29.64|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51848: AddedToken("<|29.66|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51849: AddedToken("<|29.68|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51850: AddedToken("<|29.70|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51851: AddedToken("<|29.72|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51852: AddedToken("<|29.74|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51853: AddedToken("<|29.76|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51854: AddedToken("<|29.78|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51855: AddedToken("<|29.80|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51856: AddedToken("<|29.82|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51857: AddedToken("<|29.84|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51858: AddedToken("<|29.86|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51859: AddedToken("<|29.88|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51860: AddedToken("<|29.90|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51861: AddedToken("<|29.92|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51862: AddedToken("<|29.94|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51863: AddedToken("<|29.96|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51864: AddedToken("<|29.98|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), 51865: AddedToken("<|30.00|>", rstrip=False, lstrip=False, single_word=False, normalized=True, special=False), } { "processor_class": "WhisperProcessor" } 06/17/2024 15:54:23 - INFO - __main__ - max_steps is given, it will override any value given in num_train_epochs 06/17/2024 15:54:26 - INFO - __main__ - ***** Running training ***** 06/17/2024 15:54:26 - INFO - __main__ - Num examples = 1600000 06/17/2024 15:54:26 - INFO - __main__ - Num epochs = 6 06/17/2024 15:54:26 - INFO - __main__ - Instantaneous batch size per device = 8 06/17/2024 15:54:26 - INFO - __main__ - Gradient accumulation steps = 1 06/17/2024 15:54:26 - INFO - __main__ - Total train batch size (w. parallel & distributed) = 16 06/17/2024 15:54:26 - INFO - __main__ - Total optimization steps = 100000 Train steps ... : 0%| | 0/100000 [00:00= 1.5 and < 2.0 but detected 2.3  [WARNING]  using untested triton version (2.3.1), only 1.0.0 is known to be compatible /opt/conda/lib/python3.10/site-packages/huggingface_hub/hf_api.py:3664: UserWarning: Warnings while validating metadata in README.md: - empty or missing yaml metadata in repo card warnings.warn(f"Warnings while validating metadata in README.md:\n{message}") 0%| | 0/8 [00:00= 1.5 and < 2.0 but detected 2.3  [WARNING]  using untested triton version (2.3.1), only 1.0.0 is known to be compatible Evaluating eval...: 0%| | 1/1900 [00:04<2:14:11, 4.24s/it] Evaluating eval...: 0%| | 2/1900 [00:05<1:19:57, 2.53s/it] Evaluating eval...: 0%| | 3/1900 [00:06<1:02:25, 1.97s/it] Evaluating eval...: 0%| | 4/1900 [00:08<52:48, 1.67s/it]  Evaluating eval...: 0%| | 5/1900 [00:09<47:23, 1.50s/it] Evaluating eval...: 0%| | 6/1900 [00:10<44:03, 1.40s/it] Evaluating eval...: 0%| | 7/1900 [00:11<41:45, 1.32s/it] Evaluating eval...: 0%| | 8/1900 [00:12<40:23, 1.28s/it] Evaluating eval...: 0%| | 9/1900 [00:14<39:08, 1.24s/it] Evaluating eval...: 1%| | 10/1900 [00:15<38:55, 1.24s/it] Evaluating eval...: 1%| | 11/1900 [00:16<39:03, 1.24s/it] Evaluating eval...: 1%| | 12/1900 [00:17<38:21, 1.22s/it] Evaluating eval...: 1%| | 13/1900 [00:18<38:26, 1.22s/it] Evaluating eval...: 1%| | 14/1900 [00:20<37:49, 1.20s/it] Evaluating eval...: 1%| | 15/1900 [00:21<37:32, 1.19s/it] Evaluating eval...: 1%| | 16/1900 [00:22<37:28, 1.19s/it] Evaluating eval...: 1%| | 17/1900 [00:23<37:43, 1.20s/it] Evaluating eval...: 1%| | 18/1900 [00:24<37:20, 1.19s/it] Evaluating eval...: 1%| | 19/1900 [00:25<36:47, 1.17s/it] Evaluating eval...: 1%| | 20/1900 [00:27<36:40, 1.17s/it] Evaluating eval...: 1%| | 21/1900 [00:28<37:16, 1.19s/it] Evaluating eval...: 1%| | 22/1900 [00:29<37:10, 1.19s/it] Evaluating eval...: 1%| | 23/1900 [00:30<36:50, 1.18s/it] Evaluating eval...: 1%|▏ | 24/1900 [00:31<37:21, 1.19s/it] Evaluating eval...: 1%|▏ | 25/1900 [00:33<36:41, 1.17s/it] Evaluating eval...: 1%|▏ | 26/1900 [00:34<36:17, 1.16s/it] Evaluating eval...: 1%|▏ | 27/1900 [00:35<37:08, 1.19s/it] Evaluating eval...: 1%|▏ | 28/1900 [00:36<36:57, 1.18s/it] Evaluating eval...: 2%|▏ | 29/1900 [00:37<36:48, 1.18s/it] Evaluating eval...: 2%|▏ | 30/1900 [00:38<36:58, 1.19s/it] Evaluating eval...: 2%|▏ | 31/1900 [00:40<36:43, 1.18s/it] Evaluating eval...: 2%|▏ | 32/1900 [00:41<36:39, 1.18s/it] Evaluating eval...: 2%|▏ | 33/1900 [00:42<36:50, 1.18s/it] Evaluating eval...: 2%|▏ | 34/1900 [00:43<37:28, 1.20s/it] Evaluating eval...: 2%|▏ | 35/1900 [00:44<37:51, 1.22s/it] Evaluating eval...: 2%|▏ | 36/1900 [00:46<38:15, 1.23s/it] Evaluating eval...: 2%|▏ | 37/1900 [00:47<38:00, 1.22s/it] Evaluating eval...: 2%|▏ | 38/1900 [00:48<37:35, 1.21s/it] Evaluating eval...: 2%|▏ | 39/1900 [00:49<37:23, 1.21s/it] Evaluating eval...: 2%|▏ | 40/1900 [00:51<37:08, 1.20s/it] Evaluating eval...: 2%|▏ | 41/1900 [00:52<36:53, 1.19s/it] Evaluating eval...: 2%|▏ | 42/1900 [00:53<37:32, 1.21s/it] Evaluating eval...: 2%|▏ | 43/1900 [00:54<37:12, 1.20s/it] Evaluating eval...: 2%|▏ | 44/1900 [00:55<37:08, 1.20s/it] Evaluating eval...: 2%|▏ | 45/1900 [00:56<36:33, 1.18s/it] Evaluating eval...: 2%|▏ | 46/1900 [00:58<36:17, 1.17s/it] Evaluating eval...: 2%|▏ | 47/1900 [00:59<35:49, 1.16s/it] Evaluating eval...: 3%|▎ | 48/1900 [01:00<35:38, 1.15s/it] Evaluating eval...: 3%|▎ | 49/1900 [01:01<35:32, 1.15s/it] Evaluating eval...: 3%|▎ | 50/1900 [01:02<36:28, 1.18s/it] Evaluating eval...: 3%|▎ | 51/1900 [01:03<36:20, 1.18s/it] Evaluating eval...: 3%|▎ | 52/1900 [01:05<36:06, 1.17s/it] Evaluating eval...: 3%|▎ | 53/1900 [01:06<35:56, 1.17s/it] Evaluating eval...: 3%|▎ | 54/1900 [01:07<36:33, 1.19s/it] Evaluating eval...: 3%|▎ | 55/1900 [01:08<36:51, 1.20s/it] Evaluating eval...: 3%|▎ | 56/1900 [01:09<37:08, 1.21s/it] Evaluating eval...: 3%|▎ | 57/1900 [01:11<37:04, 1.21s/it] Evaluating eval...: 3%|▎ | 58/1900 [01:12<37:13, 1.21s/it] Evaluating eval...: 3%|▎ | 59/1900 [01:13<36:57, 1.20s/it] Evaluating eval...: 3%|▎ | 60/1900 [01:14<36:19, 1.18s/it] Evaluating eval...: 3%|▎ | 61/1900 [01:15<37:13, 1.21s/it] Evaluating eval...: 3%|▎ | 62/1900 [01:17<36:41, 1.20s/it] Evaluating eval...: 3%|▎ | 63/1900 [01:18<36:36, 1.20s/it] Evaluating eval...: 3%|▎ | 64/1900 [01:19<36:28, 1.19s/it] Evaluating eval...: 3%|▎ | 65/1900 [01:20<36:02, 1.18s/it] Evaluating eval...: 3%|▎ | 66/1900 [01:21<35:43, 1.17s/it] Evaluating eval...: 4%|▎ | 67/1900 [01:22<35:41, 1.17s/it] Evaluating eval...: 4%|▎ | 68/1900 [01:24<36:53, 1.21s/it] Evaluating eval...: 4%|▎ | 69/1900 [01:25<36:11, 1.19s/it] Evaluating eval...: 4%|▎ | 70/1900 [01:26<36:41, 1.20s/it] Evaluating eval...: 4%|▎ | 71/1900 [01:27<36:46, 1.21s/it] Evaluating eval...: 4%|▍ | 72/1900 [01:29<37:10, 1.22s/it] Evaluating eval...: 4%|▍ | 73/1900 [01:30<37:04, 1.22s/it] Evaluating eval...: 4%|▍ | 74/1900 [01:31<36:58, 1.21s/it] Evaluating eval...: 4%|▍ | 75/1900 [01:32<36:20, 1.19s/it] Evaluating eval...: 4%|▍ | 76/1900 [01:33<36:14, 1.19s/it] Evaluating eval...: 4%|▍ | 77/1900 [01:35<36:11, 1.19s/it] Evaluating eval...: 4%|▍ | 78/1900 [01:36<36:19, 1.20s/it] Evaluating eval...: 4%|▍ | 79/1900 [01:37<36:19, 1.20s/it] Evaluating eval...: 4%|▍ | 80/1900 [01:38<36:11, 1.19s/it] Evaluating eval...: 4%|▍ | 81/1900 [01:39<36:03, 1.19s/it] Evaluating eval...: 4%|▍ | 82/1900 [01:41<36:39, 1.21s/it] Evaluating eval...: 4%|▍ | 83/1900 [01:42<36:56, 1.22s/it] Evaluating eval...: 4%|▍ | 84/1900 [01:43<36:55, 1.22s/it] Evaluating eval...: 4%|▍ | 85/1900 [01:44<36:37, 1.21s/it] Evaluating eval...: 5%|▍ | 86/1900 [01:45<35:55, 1.19s/it] Evaluating eval...: 5%|▍ | 87/1900 [01:47<36:03, 1.19s/it] Evaluating eval...: 5%|▍ | 88/1900 [01:48<35:59, 1.19s/it] Evaluating eval...: 5%|▍ | 89/1900 [01:50<45:23, 1.50s/it] Evaluating eval...: 5%|▍ | 90/1900 [01:51<42:22, 1.40s/it] Evaluating eval...: 5%|▍ | 91/1900 [01:52<40:49, 1.35s/it] Evaluating eval...: 5%|▍ | 92/1900 [01:54<38:52, 1.29s/it] Evaluating eval...: 5%|▍ | 93/1900 [01:55<37:53, 1.26s/it] Evaluating eval...: 5%|▍ | 94/1900 [01:56<36:42, 1.22s/it] Evaluating eval...: 5%|▌ | 95/1900 [01:57<35:55, 1.19s/it] Evaluating eval...: 5%|▌ | 96/1900 [01:58<36:47, 1.22s/it] Evaluating eval...: 5%|▌ | 97/1900 [01:59<36:04, 1.20s/it] Evaluating eval...: 5%|▌ | 98/1900 [02:01<36:34, 1.22s/it] Evaluating eval...: 5%|▌ | 99/1900 [02:02<36:12, 1.21s/it] Evaluating eval...: 5%|▌ | 100/1900 [02:03<36:01, 1.20s/it] Evaluating eval...: 5%|▌ | 101/1900 [02:04<36:51, 1.23s/it] Evaluating eval...: 5%|▌ | 102/1900 [02:06<37:12, 1.24s/it] Evaluating eval...: 5%|▌ | 103/1900 [02:07<36:39, 1.22s/it] Evaluating eval...: 5%|▌ | 104/1900 [02:08<36:07, 1.21s/it] Evaluating eval...: 6%|▌ | 105/1900 [02:09<35:52, 1.20s/it] Evaluating eval...: 6%|▌ | 106/1900 [02:10<35:10, 1.18s/it] Evaluating eval...: 6%|▌ | 107/1900 [02:12<35:26, 1.19s/it] Evaluating eval...: 6%|▌ | 108/1900 [02:13<34:58, 1.17s/it] Evaluating eval...: 6%|▌ | 109/1900 [02:14<35:08, 1.18s/it] Evaluating eval...: 6%|▌ | 110/1900 [02:15<34:51, 1.17s/it] Evaluating eval...: 6%|▌ | 111/1900 [02:16<35:09, 1.18s/it] Evaluating eval...: 6%|▌ | 112/1900 [02:17<35:44, 1.20s/it] Evaluating eval...: 6%|▌ | 113/1900 [02:19<35:38, 1.20s/it] Evaluating eval...: 6%|▌ | 114/1900 [02:20<35:07, 1.18s/it] Evaluating eval...: 6%|▌ | 115/1900 [02:21<34:50, 1.17s/it] Evaluating eval...: 6%|▌ | 116/1900 [02:22<34:23, 1.16s/it] Evaluating eval...: 6%|▌ | 117/1900 [02:23<34:39, 1.17s/it] Evaluating eval...: 6%|▌ | 118/1900 [02:24<35:21, 1.19s/it] Evaluating eval...: 6%|▋ | 119/1900 [02:26<35:22, 1.19s/it] Evaluating eval...: 6%|▋ | 120/1900 [02:27<35:43, 1.20s/it] Evaluating eval...: 6%|▋ | 121/1900 [02:28<35:09, 1.19s/it] Evaluating eval...: 6%|▋ | 122/1900 [02:29<35:14, 1.19s/it] Evaluating eval...: 6%|▋ | 123/1900 [02:30<35:17, 1.19s/it] Evaluating eval...: 7%|▋ | 124/1900 [02:32<35:34, 1.20s/it] Evaluating eval...: 7%|▋ | 125/1900 [02:33<35:47, 1.21s/it] Evaluating eval...: 7%|▋ | 126/1900 [02:34<35:54, 1.21s/it] Evaluating eval...: 7%|▋ | 127/1900 [02:35<36:01, 1.22s/it] Evaluating eval...: 7%|▋ | 128/1900 [02:37<35:32, 1.20s/it] Evaluating eval...: 7%|▋ | 129/1900 [02:38<35:13, 1.19s/it] Evaluating eval...: 7%|▋ | 130/1900 [02:39<34:48, 1.18s/it] Evaluating eval...: 7%|▋ | 131/1900 [02:40<35:03, 1.19s/it] Evaluating eval...: 7%|▋ | 132/1900 [02:41<35:20, 1.20s/it] Evaluating eval...: 7%|▋ | 133/1900 [02:42<34:51, 1.18s/it] Evaluating eval...: 7%|▋ | 134/1900 [02:44<34:46, 1.18s/it] Evaluating eval...: 7%|▋ | 135/1900 [02:45<35:04, 1.19s/it] Evaluating eval...: 7%|▋ | 136/1900 [02:46<35:43, 1.21s/it] Evaluating eval...: 7%|▋ | 137/1900 [02:47<36:10, 1.23s/it] Evaluating eval...: 7%|▋ | 138/1900 [02:49<35:52, 1.22s/it] Evaluating eval...: 7%|▋ | 139/1900 [02:50<35:28, 1.21s/it] Evaluating eval...: 7%|▋ | 140/1900 [02:51<35:52, 1.22s/it] Evaluating eval...: 7%|▋ | 141/1900 [02:52<35:29, 1.21s/it] Evaluating eval...: 7%|▋ | 142/1900 [02:53<36:21, 1.24s/it] Evaluating eval...: 8%|▊ | 143/1900 [02:55<36:13, 1.24s/it] Evaluating eval...: 8%|▊ | 144/1900 [02:56<35:15, 1.20s/it] Evaluating eval...: 8%|▊ | 145/1900 [02:57<35:18, 1.21s/it] Evaluating eval...: 8%|▊ | 146/1900 [02:58<34:48, 1.19s/it] Evaluating eval...: 8%|▊ | 147/1900 [02:59<35:15, 1.21s/it] Evaluating eval...: 8%|▊ | 148/1900 [03:01<34:40, 1.19s/it] Evaluating eval...: 8%|▊ | 149/1900 [03:02<34:49, 1.19s/it] Evaluating eval...: 8%|▊ | 150/1900 [03:03<35:33, 1.22s/it] Evaluating eval...: 8%|▊ | 151/1900 [03:04<35:08, 1.21s/it] Evaluating eval...: 8%|▊ | 152/1900 [03:05<35:17, 1.21s/it] Evaluating eval...: 8%|▊ | 153/1900 [03:07<35:28, 1.22s/it] Evaluating eval...: 8%|▊ | 154/1900 [03:08<35:11, 1.21s/it] Evaluating eval...: 8%|▊ | 155/1900 [03:09<34:56, 1.20s/it] Evaluating eval...: 8%|▊ | 156/1900 [03:10<34:54, 1.20s/it] Evaluating eval...: 8%|▊ | 157/1900 [03:12<36:15, 1.25s/it] Evaluating eval...: 8%|▊ | 158/1900 [03:13<35:59, 1.24s/it] Evaluating eval...: 8%|▊ | 159/1900 [03:14<35:01, 1.21s/it] Evaluating eval...: 8%|▊ | 160/1900 [03:15<34:27, 1.19s/it] Evaluating eval...: 8%|▊ | 161/1900 [03:16<34:46, 1.20s/it] Evaluating eval...: 9%|▊ | 162/1900 [03:18<34:38, 1.20s/it] Evaluating eval...: 9%|▊ | 163/1900 [03:19<34:08, 1.18s/it] Evaluating eval...: 9%|▊ | 164/1900 [03:20<34:25, 1.19s/it] Evaluating eval...: 9%|▊ | 165/1900 [03:21<34:32, 1.19s/it] Evaluating eval...: 9%|▊ | 166/1900 [03:22<34:11, 1.18s/it] Evaluating eval...: 9%|▉ | 167/1900 [03:24<35:05, 1.22s/it] Evaluating eval...: 9%|▉ | 168/1900 [03:25<34:27, 1.19s/it] Evaluating eval...: 9%|▉ | 169/1900 [03:26<34:28, 1.20s/it] Evaluating eval...: 9%|▉ | 170/1900 [03:27<34:16, 1.19s/it] Evaluating eval...: 9%|▉ | 171/1900 [03:28<34:27, 1.20s/it] Evaluating eval...: 9%|▉ | 172/1900 [03:29<34:13, 1.19s/it] Evaluating eval...: 9%|▉ | 173/1900 [03:31<34:26, 1.20s/it] Evaluating eval...: 9%|▉ | 174/1900 [03:32<34:51, 1.21s/it] Evaluating eval...: 9%|▉ | 175/1900 [03:33<34:09, 1.19s/it] Evaluating eval...: 9%|▉ | 176/1900 [03:34<33:43, 1.17s/it] Evaluating eval...: 9%|▉ | 177/1900 [03:36<42:57, 1.50s/it] Evaluating eval...: 9%|▉ | 178/1900 [03:38<40:44, 1.42s/it] Evaluating eval...: 9%|▉ | 179/1900 [03:39<38:23, 1.34s/it] Evaluating eval...: 9%|▉ | 180/1900 [03:40<37:11, 1.30s/it] Evaluating eval...: 10%|▉ | 181/1900 [03:41<36:14, 1.26s/it] Evaluating eval...: 10%|▉ | 182/1900 [03:43<44:25, 1.55s/it] Evaluating eval...: 10%|▉ | 183/1900 [03:45<41:40, 1.46s/it] Evaluating eval...: 10%|▉ | 184/1900 [03:46<39:11, 1.37s/it] Evaluating eval...: 10%|▉ | 185/1900 [03:47<37:44, 1.32s/it] Evaluating eval...: 10%|▉ | 186/1900 [03:48<36:16, 1.27s/it] Evaluating eval...: 10%|▉ | 187/1900 [03:49<36:06, 1.26s/it] Evaluating eval...: 10%|▉ | 188/1900 [03:51<35:36, 1.25s/it] Evaluating eval...: 10%|▉ | 189/1900 [03:52<34:45, 1.22s/it] Evaluating eval...: 10%|█ | 190/1900 [03:53<34:51, 1.22s/it] Evaluating eval...: 10%|█ | 191/1900 [03:54<34:23, 1.21s/it] Evaluating eval...: 10%|█ | 192/1900 [03:56<35:09, 1.24s/it] Evaluating eval...: 10%|█ | 193/1900 [03:57<35:05, 1.23s/it] Evaluating eval...: 10%|█ | 194/1900 [03:58<35:13, 1.24s/it] Evaluating eval...: 10%|█ | 195/1900 [03:59<35:17, 1.24s/it] Evaluating eval...: 10%|█ | 196/1900 [04:00<34:59, 1.23s/it] Evaluating eval...: 10%|█ | 197/1900 [04:02<35:32, 1.25s/it] Evaluating eval...: 10%|█ | 198/1900 [04:03<35:33, 1.25s/it] Evaluating eval...: 10%|█ | 199/1900 [04:04<34:43, 1.23s/it] Evaluating eval...: 11%|█ | 200/1900 [04:05<34:18, 1.21s/it] Evaluating eval...: 11%|█ | 201/1900 [04:06<33:45, 1.19s/it] Evaluating eval...: 11%|█ | 202/1900 [04:08<33:21, 1.18s/it] Evaluating eval...: 11%|█ | 203/1900 [04:09<33:40, 1.19s/it] Evaluating eval...: 11%|█ | 204/1900 [04:10<34:01, 1.20s/it] Evaluating eval...: 11%|█ | 205/1900 [04:11<34:10, 1.21s/it] Evaluating eval...: 11%|█ | 206/1900 [04:13<34:11, 1.21s/it] Evaluating eval...: 11%|█ | 207/1900 [04:14<34:28, 1.22s/it] Evaluating eval...: 11%|█ | 208/1900 [04:15<33:57, 1.20s/it] Evaluating eval...: 11%|█ | 209/1900 [04:16<33:32, 1.19s/it] Evaluating eval...: 11%|█ | 210/1900 [04:17<33:13, 1.18s/it] Evaluating eval...: 11%|█ | 211/1900 [04:18<33:19, 1.18s/it] Evaluating eval...: 11%|█ | 212/1900 [04:20<33:27, 1.19s/it] Evaluating eval...: 11%|█ | 213/1900 [04:21<33:57, 1.21s/it] Evaluating eval...: 11%|█▏ | 214/1900 [04:22<34:01, 1.21s/it] Evaluating eval...: 11%|█▏ | 215/1900 [04:23<33:44, 1.20s/it] Evaluating eval...: 11%|█▏ | 216/1900 [04:24<33:39, 1.20s/it] Evaluating eval...: 11%|█▏ | 217/1900 [04:26<33:47, 1.20s/it] Evaluating eval...: 11%|█▏ | 218/1900 [04:27<34:09, 1.22s/it] Evaluating eval...: 12%|█▏ | 219/1900 [04:28<34:28, 1.23s/it] Evaluating eval...: 12%|█▏ | 220/1900 [04:29<34:31, 1.23s/it] Evaluating eval...: 12%|█▏ | 221/1900 [04:31<34:03, 1.22s/it] Evaluating eval...: 12%|█▏ | 222/1900 [04:32<33:40, 1.20s/it] Evaluating eval...: 12%|█▏ | 223/1900 [04:33<33:16, 1.19s/it] Evaluating eval...: 12%|█▏ | 224/1900 [04:34<32:51, 1.18s/it] Evaluating eval...: 12%|█▏ | 225/1900 [04:35<32:44, 1.17s/it] Evaluating eval...: 12%|█▏ | 226/1900 [04:36<32:50, 1.18s/it] Evaluating eval...: 12%|█▏ | 227/1900 [04:38<32:45, 1.18s/it] Evaluating eval...: 12%|█▏ | 228/1900 [04:39<33:30, 1.20s/it] Evaluating eval...: 12%|█▏ | 229/1900 [04:40<33:01, 1.19s/it] Evaluating eval...: 12%|█▏ | 230/1900 [04:41<33:00, 1.19s/it] Evaluating eval...: 12%|█▏ | 231/1900 [04:42<33:13, 1.19s/it] Evaluating eval...: 12%|█▏ | 232/1900 [04:44<32:47, 1.18s/it] Evaluating eval...: 12%|█▏ | 233/1900 [04:45<33:03, 1.19s/it] Evaluating eval...: 12%|█▏ | 234/1900 [04:46<33:07, 1.19s/it] Evaluating eval...: 12%|█▏ | 235/1900 [04:47<33:07, 1.19s/it] Evaluating eval...: 12%|█▏ | 236/1900 [04:48<33:27, 1.21s/it] Evaluating eval...: 12%|█▏ | 237/1900 [04:50<33:42, 1.22s/it] Evaluating eval...: 13%|█▎ | 238/1900 [04:51<33:43, 1.22s/it] Evaluating eval...: 13%|█▎ | 239/1900 [04:52<34:12, 1.24s/it] Evaluating eval...: 13%|█▎ | 240/1900 [04:53<33:36, 1.21s/it] Evaluating eval...: 13%|█▎ | 241/1900 [04:55<33:18, 1.20s/it] Evaluating eval...: 13%|█▎ | 242/1900 [04:56<33:12, 1.20s/it] Evaluating eval...: 13%|█▎ | 243/1900 [04:57<32:49, 1.19s/it] Evaluating eval...: 13%|█▎ | 244/1900 [04:58<32:28, 1.18s/it] Evaluating eval...: 13%|█▎ | 245/1900 [04:59<33:26, 1.21s/it] Evaluating eval...: 13%|█▎ | 246/1900 [05:01<33:22, 1.21s/it] Evaluating eval...: 13%|█▎ | 247/1900 [05:02<33:21, 1.21s/it] Evaluating eval...: 13%|█▎ | 248/1900 [05:03<33:22, 1.21s/it] Evaluating eval...: 13%|█▎ | 249/1900 [05:04<32:42, 1.19s/it] Evaluating eval...: 13%|█▎ | 250/1900 [05:05<33:00, 1.20s/it] Evaluating eval...: 13%|█▎ | 251/1900 [05:07<33:38, 1.22s/it] Evaluating eval...: 13%|█▎ | 252/1900 [05:08<32:54, 1.20s/it] Evaluating eval...: 13%|█▎ | 253/1900 [05:09<33:30, 1.22s/it] Evaluating eval...: 13%|█▎ | 254/1900 [05:10<33:24, 1.22s/it] Evaluating eval...: 13%|█▎ | 255/1900 [05:11<33:18, 1.21s/it] Evaluating eval...: 13%|█▎ | 256/1900 [05:13<32:44, 1.19s/it] Evaluating eval...: 14%|█▎ | 257/1900 [05:14<32:19, 1.18s/it] Evaluating eval...: 14%|█▎ | 258/1900 [05:15<32:37, 1.19s/it] Evaluating eval...: 14%|█▎ | 259/1900 [05:16<32:29, 1.19s/it] Evaluating eval...: 14%|█▎ | 260/1900 [05:17<32:29, 1.19s/it] Evaluating eval...: 14%|█▎ | 261/1900 [05:18<32:27, 1.19s/it] Evaluating eval...: 14%|█▍ | 262/1900 [05:20<32:11, 1.18s/it] Evaluating eval...: 14%|█▍ | 263/1900 [05:21<32:27, 1.19s/it] Evaluating eval...: 14%|█▍ | 264/1900 [05:22<32:08, 1.18s/it] Evaluating eval...: 14%|█▍ | 265/1900 [05:23<32:38, 1.20s/it] Evaluating eval...: 14%|█▍ | 266/1900 [05:24<32:37, 1.20s/it] Evaluating eval...: 14%|█▍ | 267/1900 [05:26<33:06, 1.22s/it] Evaluating eval...: 14%|█▍ | 268/1900 [05:27<32:42, 1.20s/it] Evaluating eval...: 14%|█▍ | 269/1900 [05:28<32:34, 1.20s/it] Evaluating eval...: 14%|█▍ | 270/1900 [05:29<32:08, 1.18s/it] Evaluating eval...: 14%|█▍ | 271/1900 [05:30<31:43, 1.17s/it] Evaluating eval...: 14%|█▍ | 272/1900 [05:32<32:12, 1.19s/it] Evaluating eval...: 14%|█▍ | 273/1900 [05:33<32:24, 1.20s/it] Evaluating eval...: 14%|█▍ | 274/1900 [05:34<32:25, 1.20s/it] Evaluating eval...: 14%|█▍ | 275/1900 [05:35<32:27, 1.20s/it] Evaluating eval...: 15%|█▍ | 276/1900 [05:36<33:11, 1.23s/it] Evaluating eval...: 15%|█▍ | 277/1900 [05:38<32:38, 1.21s/it] Evaluating eval...: 15%|█▍ | 278/1900 [05:39<32:04, 1.19s/it] Evaluating eval...: 15%|█▍ | 279/1900 [05:41<38:30, 1.43s/it] Evaluating eval...: 15%|█▍ | 280/1900 [05:42<37:08, 1.38s/it] Evaluating eval...: 15%|█▍ | 281/1900 [05:43<35:46, 1.33s/it] Evaluating eval...: 15%|█▍ | 282/1900 [05:44<35:02, 1.30s/it] Evaluating eval...: 15%|█▍ | 283/1900 [05:46<34:25, 1.28s/it] Evaluating eval...: 15%|█▍ | 284/1900 [05:47<33:50, 1.26s/it] Evaluating eval...: 15%|█▌ | 285/1900 [05:48<33:04, 1.23s/it] Evaluating eval...: 15%|█▌ | 286/1900 [05:49<33:51, 1.26s/it] Evaluating eval...: 15%|█▌ | 287/1900 [05:51<33:12, 1.24s/it] Evaluating eval...: 15%|█▌ | 288/1900 [05:53<42:10, 1.57s/it] Evaluating eval...: 15%|█▌ | 289/1900 [05:54<39:16, 1.46s/it] Evaluating eval...: 15%|█▌ | 290/1900 [05:55<36:54, 1.38s/it] Evaluating eval...: 15%|█▌ | 291/1900 [05:57<35:20, 1.32s/it] Evaluating eval...: 15%|█▌ | 292/1900 [05:58<34:27, 1.29s/it] Evaluating eval...: 15%|█▌ | 293/1900 [05:59<33:22, 1.25s/it] Evaluating eval...: 15%|█▌ | 294/1900 [06:00<32:38, 1.22s/it] Evaluating eval...: 16%|█▌ | 295/1900 [06:01<32:27, 1.21s/it] Evaluating eval...: 16%|█▌ | 296/1900 [06:02<32:29, 1.22s/it] Evaluating eval...: 16%|█▌ | 297/1900 [06:04<32:32, 1.22s/it] Evaluating eval...: 16%|█▌ | 298/1900 [06:05<32:25, 1.21s/it] Evaluating eval...: 16%|█▌ | 299/1900 [06:06<31:55, 1.20s/it] Evaluating eval...: 16%|█▌ | 300/1900 [06:07<32:01, 1.20s/it] Evaluating eval...: 16%|█▌ | 301/1900 [06:09<32:40, 1.23s/it] Evaluating eval...: 16%|█▌ | 302/1900 [06:10<32:35, 1.22s/it] Evaluating eval...: 16%|█▌ | 303/1900 [06:11<32:05, 1.21s/it] Evaluating eval...: 16%|█▌ | 304/1900 [06:12<31:42, 1.19s/it] Evaluating eval...: 16%|█▌ | 305/1900 [06:13<32:05, 1.21s/it] Evaluating eval...: 16%|█▌ | 306/1900 [06:14<31:48, 1.20s/it] Evaluating eval...: 16%|█▌ | 307/1900 [06:16<31:54, 1.20s/it] Evaluating eval...: 16%|█▌ | 308/1900 [06:17<31:47, 1.20s/it] Evaluating eval...: 16%|█▋ | 309/1900 [06:18<32:02, 1.21s/it] Evaluating eval...: 16%|█▋ | 310/1900 [06:19<32:17, 1.22s/it] Evaluating eval...: 16%|█▋ | 311/1900 [06:21<32:34, 1.23s/it] Evaluating eval...: 16%|█▋ | 312/1900 [06:22<32:14, 1.22s/it] Evaluating eval...: 16%|█▋ | 313/1900 [06:23<31:50, 1.20s/it] Evaluating eval...: 17%|█▋ | 314/1900 [06:24<31:36, 1.20s/it] Evaluating eval...: 17%|█▋ | 315/1900 [06:25<32:06, 1.22s/it] Evaluating eval...: 17%|█▋ | 316/1900 [06:27<31:51, 1.21s/it] Evaluating eval...: 17%|█▋ | 317/1900 [06:28<32:09, 1.22s/it] Evaluating eval...: 17%|█▋ | 318/1900 [06:29<31:59, 1.21s/it] Evaluating eval...: 17%|█▋ | 319/1900 [06:30<31:45, 1.21s/it] Evaluating eval...: 17%|█▋ | 320/1900 [06:31<31:33, 1.20s/it] Evaluating eval...: 17%|█▋ | 321/1900 [06:33<31:04, 1.18s/it] Evaluating eval...: 17%|█▋ | 322/1900 [06:34<31:16, 1.19s/it] Evaluating eval...: 17%|█▋ | 323/1900 [06:35<31:47, 1.21s/it] Evaluating eval...: 17%|█▋ | 324/1900 [06:36<31:03, 1.18s/it] Evaluating eval...: 17%|█▋ | 325/1900 [06:37<31:01, 1.18s/it] Evaluating eval...: 17%|█▋ | 326/1900 [06:39<30:53, 1.18s/it] Evaluating eval...: 17%|█▋ | 327/1900 [06:40<30:45, 1.17s/it] Evaluating eval...: 17%|█▋ | 328/1900 [06:41<31:12, 1.19s/it] Evaluating eval...: 17%|█▋ | 329/1900 [06:42<30:51, 1.18s/it] Evaluating eval...: 17%|█▋ | 330/1900 [06:43<31:19, 1.20s/it] Evaluating eval...: 17%|█▋ | 331/1900 [06:45<32:24, 1.24s/it] Evaluating eval...: 17%|█▋ | 332/1900 [06:46<32:09, 1.23s/it] Evaluating eval...: 18%|█▊ | 333/1900 [06:47<32:10, 1.23s/it] Evaluating eval...: 18%|█▊ | 334/1900 [06:48<31:46, 1.22s/it] Evaluating eval...: 18%|█▊ | 335/1900 [06:49<31:05, 1.19s/it] Evaluating eval...: 18%|█▊ | 336/1900 [06:51<31:18, 1.20s/it] Evaluating eval...: 18%|█▊ | 337/1900 [06:52<30:55, 1.19s/it] Evaluating eval...: 18%|█▊ | 338/1900 [06:53<31:33, 1.21s/it] Evaluating eval...: 18%|█▊ | 339/1900 [06:54<31:34, 1.21s/it] Evaluating eval...: 18%|█▊ | 340/1900 [06:55<31:14, 1.20s/it] Evaluating eval...: 18%|█▊ | 341/1900 [06:57<31:36, 1.22s/it] Evaluating eval...: 18%|█▊ | 342/1900 [06:58<31:02, 1.20s/it] Evaluating eval...: 18%|█▊ | 343/1900 [06:59<30:53, 1.19s/it] Evaluating eval...: 18%|█▊ | 344/1900 [07:00<30:54, 1.19s/it] Evaluating eval...: 18%|█▊ | 345/1900 [07:01<31:07, 1.20s/it] Evaluating eval...: 18%|█▊ | 346/1900 [07:03<30:59, 1.20s/it] Evaluating eval...: 18%|█▊ | 347/1900 [07:04<30:48, 1.19s/it] Evaluating eval...: 18%|█▊ | 348/1900 [07:05<30:27, 1.18s/it] Evaluating eval...: 18%|█▊ | 349/1900 [07:06<30:15, 1.17s/it] Evaluating eval...: 18%|█▊ | 350/1900 [07:07<30:20, 1.17s/it] Evaluating eval...: 18%|█▊ | 351/1900 [07:09<30:52, 1.20s/it] Evaluating eval...: 19%|█▊ | 352/1900 [07:10<31:12, 1.21s/it] Evaluating eval...: 19%|█▊ | 353/1900 [07:11<31:51, 1.24s/it] Evaluating eval...: 19%|█▊ | 354/1900 [07:12<31:54, 1.24s/it] Evaluating eval...: 19%|█▊ | 355/1900 [07:14<31:48, 1.24s/it] Evaluating eval...: 19%|█▊ | 356/1900 [07:15<31:41, 1.23s/it] Evaluating eval...: 19%|█▉ | 357/1900 [07:16<31:02, 1.21s/it] Evaluating eval...: 19%|█▉ | 358/1900 [07:17<31:02, 1.21s/it] Evaluating eval...: 19%|█▉ | 359/1900 [07:18<30:54, 1.20s/it] Evaluating eval...: 19%|█▉ | 360/1900 [07:20<30:59, 1.21s/it] Evaluating eval...: 19%|█▉ | 361/1900 [07:21<30:44, 1.20s/it] Evaluating eval...: 19%|█▉ | 362/1900 [07:22<31:30, 1.23s/it] Evaluating eval...: 19%|█▉ | 363/1900 [07:23<30:53, 1.21s/it] Evaluating eval...: 19%|█▉ | 364/1900 [07:24<30:39, 1.20s/it] Evaluating eval...: 19%|█▉ | 365/1900 [07:26<30:37, 1.20s/it] Evaluating eval...: 19%|█▉ | 366/1900 [07:27<30:18, 1.19s/it] Evaluating eval...: 19%|█▉ | 367/1900 [07:28<31:26, 1.23s/it] Evaluating eval...: 19%|█▉ | 368/1900 [07:29<32:35, 1.28s/it] Evaluating eval...: 19%|█▉ | 369/1900 [07:31<31:50, 1.25s/it] Evaluating eval...: 19%|█▉ | 370/1900 [07:32<31:08, 1.22s/it] Evaluating eval...: 20%|█▉ | 371/1900 [07:33<30:47, 1.21s/it] Evaluating eval...: 20%|█▉ | 372/1900 [07:34<30:31, 1.20s/it] Evaluating eval...: 20%|█▉ | 373/1900 [07:35<30:13, 1.19s/it] Evaluating eval...: 20%|█▉ | 374/1900 [07:36<29:47, 1.17s/it] Evaluating eval...: 20%|█▉ | 375/1900 [07:38<29:32, 1.16s/it] Evaluating eval...: 20%|█▉ | 376/1900 [07:39<30:12, 1.19s/it] Evaluating eval...: 20%|█▉ | 377/1900 [07:40<30:39, 1.21s/it] Evaluating eval...: 20%|█▉ | 378/1900 [07:41<30:44, 1.21s/it] Evaluating eval...: 20%|█▉ | 379/1900 [07:42<30:51, 1.22s/it] Evaluating eval...: 20%|██ | 380/1900 [07:44<31:05, 1.23s/it] Evaluating eval...: 20%|██ | 381/1900 [07:45<31:00, 1.22s/it] Evaluating eval...: 20%|██ | 382/1900 [07:46<31:06, 1.23s/it] Evaluating eval...: 20%|██ | 383/1900 [07:47<30:24, 1.20s/it] Evaluating eval...: 20%|██ | 384/1900 [07:49<30:42, 1.22s/it] Evaluating eval...: 20%|██ | 385/1900 [07:50<30:23, 1.20s/it] Evaluating eval...: 20%|██ | 386/1900 [07:51<30:48, 1.22s/it] Evaluating eval...: 20%|██ | 387/1900 [07:52<30:50, 1.22s/it] Evaluating eval...: 20%|██ | 388/1900 [07:53<30:28, 1.21s/it] Evaluating eval...: 20%|██ | 389/1900 [07:55<30:27, 1.21s/it] Evaluating eval...: 21%|██ | 390/1900 [07:56<30:06, 1.20s/it] Evaluating eval...: 21%|██ | 391/1900 [07:57<30:11, 1.20s/it] Evaluating eval...: 21%|██ | 392/1900 [07:58<29:59, 1.19s/it] Evaluating eval...: 21%|██ | 393/1900 [07:59<29:33, 1.18s/it] Evaluating eval...: 21%|██ | 394/1900 [08:01<29:45, 1.19s/it] Evaluating eval...: 21%|██ | 395/1900 [08:02<29:41, 1.18s/it] Evaluating eval...: 21%|██ | 396/1900 [08:03<30:05, 1.20s/it] Evaluating eval...: 21%|██ | 397/1900 [08:04<30:05, 1.20s/it] Evaluating eval...: 21%|██ | 398/1900 [08:05<29:40, 1.19s/it] Evaluating eval...: 21%|██ | 399/1900 [08:07<30:18, 1.21s/it] Evaluating eval...: 21%|██ | 400/1900 [08:08<29:57, 1.20s/it] Evaluating eval...: 21%|██ | 401/1900 [08:09<30:15, 1.21s/it] Evaluating eval...: 21%|██ | 402/1900 [08:10<29:59, 1.20s/it] Evaluating eval...: 21%|██ | 403/1900 [08:11<30:15, 1.21s/it] Evaluating eval...: 21%|██▏ | 404/1900 [08:13<30:28, 1.22s/it] Evaluating eval...: 21%|██▏ | 405/1900 [08:14<30:26, 1.22s/it] Evaluating eval...: 21%|██▏ | 406/1900 [08:15<30:37, 1.23s/it] Evaluating eval...: 21%|██▏ | 407/1900 [08:16<30:49, 1.24s/it] Evaluating eval...: 21%|██▏ | 408/1900 [08:18<31:09, 1.25s/it] Evaluating eval...: 22%|██▏ | 409/1900 [08:19<30:54, 1.24s/it] Evaluating eval...: 22%|██▏ | 410/1900 [08:20<30:26, 1.23s/it] Evaluating eval...: 22%|██▏ | 411/1900 [08:21<30:32, 1.23s/it] Evaluating eval...: 22%|██▏ | 412/1900 [08:22<30:01, 1.21s/it] Evaluating eval...: 22%|██▏ | 413/1900 [08:24<30:29, 1.23s/it] Evaluating eval...: 22%|██▏ | 414/1900 [08:25<30:16, 1.22s/it] Evaluating eval...: 22%|██▏ | 415/1900 [08:26<29:32, 1.19s/it] Evaluating eval...: 22%|██▏ | 416/1900 [08:27<29:09, 1.18s/it] Evaluating eval...: 22%|██▏ | 417/1900 [08:29<29:56, 1.21s/it] Evaluating eval...: 22%|██▏ | 418/1900 [08:30<29:35, 1.20s/it] Evaluating eval...: 22%|██▏ | 419/1900 [08:31<29:14, 1.18s/it] Evaluating eval...: 22%|██▏ | 420/1900 [08:32<29:24, 1.19s/it] Evaluating eval...: 22%|██▏ | 421/1900 [08:33<29:41, 1.20s/it] Evaluating eval...: 22%|██▏ | 422/1900 [08:34<29:49, 1.21s/it] Evaluating eval...: 22%|██▏ | 423/1900 [08:36<29:59, 1.22s/it] Evaluating eval...: 22%|██▏ | 424/1900 [08:37<30:17, 1.23s/it] Evaluating eval...: 22%|██▏ | 425/1900 [08:38<30:19, 1.23s/it] Evaluating eval...: 22%|██▏ | 426/1900 [08:39<30:25, 1.24s/it] Evaluating eval...: 22%|██▏ | 427/1900 [08:41<30:05, 1.23s/it] Evaluating eval...: 23%|██▎ | 428/1900 [08:42<29:21, 1.20s/it] Evaluating eval...: 23%|██▎ | 429/1900 [08:43<30:02, 1.23s/it] Evaluating eval...: 23%|██▎ | 430/1900 [08:44<29:27, 1.20s/it] Evaluating eval...: 23%|██▎ | 431/1900 [08:45<29:20, 1.20s/it] Evaluating eval...: 23%|██▎ | 432/1900 [08:47<29:42, 1.21s/it] Evaluating eval...: 23%|██▎ | 433/1900 [08:48<29:39, 1.21s/it] Evaluating eval...: 23%|██▎ | 434/1900 [08:49<31:03, 1.27s/it] Evaluating eval...: 23%|██▎ | 435/1900 [08:50<30:11, 1.24s/it] Evaluating eval...: 23%|██▎ | 436/1900 [08:52<30:05, 1.23s/it] Evaluating eval...: 23%|██▎ | 437/1900 [08:53<29:25, 1.21s/it] Evaluating eval...: 23%|██▎ | 438/1900 [08:54<29:12, 1.20s/it] Evaluating eval...: 23%|██▎ | 439/1900 [08:55<29:23, 1.21s/it] Evaluating eval...: 23%|██▎ | 440/1900 [08:56<29:02, 1.19s/it] Evaluating eval...: 23%|██▎ | 441/1900 [08:58<28:57, 1.19s/it] Evaluating eval...: 23%|██▎ | 442/1900 [08:59<28:46, 1.18s/it] Evaluating eval...: 23%|██▎ | 443/1900 [09:00<28:53, 1.19s/it] Evaluating eval...: 23%|██▎ | 444/1900 [09:01<29:03, 1.20s/it] Evaluating eval...: 23%|██▎ | 445/1900 [09:02<29:25, 1.21s/it] Evaluating eval...: 23%|██▎ | 446/1900 [09:04<29:20, 1.21s/it] Evaluating eval...: 24%|██▎ | 447/1900 [09:05<28:51, 1.19s/it] Evaluating eval...: 24%|██▎ | 448/1900 [09:06<28:32, 1.18s/it] Evaluating eval...: 24%|██▎ | 449/1900 [09:07<28:33, 1.18s/it] Evaluating eval...: 24%|██▎ | 450/1900 [09:08<28:34, 1.18s/it] Evaluating eval...: 24%|██▎ | 451/1900 [09:10<29:04, 1.20s/it] Evaluating eval...: 24%|██▍ | 452/1900 [09:11<28:42, 1.19s/it] Evaluating eval...: 24%|██▍ | 453/1900 [09:12<29:29, 1.22s/it] Evaluating eval...: 24%|██▍ | 454/1900 [09:13<29:42, 1.23s/it] Evaluating eval...: 24%|██▍ | 455/1900 [09:14<29:23, 1.22s/it] Evaluating eval...: 24%|██▍ | 456/1900 [09:16<29:38, 1.23s/it] Evaluating eval...: 24%|██▍ | 457/1900 [09:17<29:28, 1.23s/it] Evaluating eval...: 24%|██▍ | 458/1900 [09:18<29:35, 1.23s/it] Evaluating eval...: 24%|██▍ | 459/1900 [09:19<28:57, 1.21s/it] Evaluating eval...: 24%|██▍ | 460/1900 [09:20<28:41, 1.20s/it] Evaluating eval...: 24%|██▍ | 461/1900 [09:22<29:11, 1.22s/it] Evaluating eval...: 24%|██▍ | 462/1900 [09:23<29:15, 1.22s/it] Evaluating eval...: 24%|██▍ | 463/1900 [09:24<29:07, 1.22s/it] Evaluating eval...: 24%|██▍ | 464/1900 [09:25<28:56, 1.21s/it] Evaluating eval...: 24%|██▍ | 465/1900 [09:27<28:47, 1.20s/it] Evaluating eval...: 25%|██▍ | 466/1900 [09:28<28:26, 1.19s/it] Evaluating eval...: 25%|██▍ | 467/1900 [09:29<28:22, 1.19s/it] Evaluating eval...: 25%|██▍ | 468/1900 [09:30<28:36, 1.20s/it] Evaluating eval...: 25%|██▍ | 469/1900 [09:31<28:40, 1.20s/it] Evaluating eval...: 25%|██▍ | 470/1900 [09:33<28:31, 1.20s/it] Evaluating eval...: 25%|██▍ | 471/1900 [09:34<28:31, 1.20s/it] Evaluating eval...: 25%|██▍ | 472/1900 [09:35<29:23, 1.23s/it] Evaluating eval...: 25%|██▍ | 473/1900 [09:36<28:50, 1.21s/it] Evaluating eval...: 25%|██▍ | 474/1900 [09:37<28:40, 1.21s/it] Evaluating eval...: 25%|██▌ | 475/1900 [09:39<28:28, 1.20s/it] Evaluating eval...: 25%|██▌ | 476/1900 [09:40<28:25, 1.20s/it] Evaluating eval...: 25%|██▌ | 477/1900 [09:41<28:49, 1.22s/it] Evaluating eval...: 25%|██▌ | 478/1900 [09:42<28:33, 1.20s/it] Evaluating eval...: 25%|██▌ | 479/1900 [09:43<28:42, 1.21s/it] Evaluating eval...: 25%|██▌ | 480/1900 [09:45<29:04, 1.23s/it] Evaluating eval...: 25%|██▌ | 481/1900 [09:46<30:03, 1.27s/it] Evaluating eval...: 25%|██▌ | 482/1900 [09:47<29:23, 1.24s/it] Evaluating eval...: 25%|██▌ | 483/1900 [09:48<28:49, 1.22s/it] Evaluating eval...: 25%|██▌ | 484/1900 [09:50<28:52, 1.22s/it] Evaluating eval...: 26%|██▌ | 485/1900 [09:51<28:27, 1.21s/it] Evaluating eval...: 26%|██▌ | 486/1900 [09:52<27:50, 1.18s/it] Evaluating eval...: 26%|██▌ | 487/1900 [09:53<27:49, 1.18s/it] Evaluating eval...: 26%|██▌ | 488/1900 [09:54<28:05, 1.19s/it] Evaluating eval...: 26%|██▌ | 489/1900 [09:56<28:14, 1.20s/it] Evaluating eval...: 26%|██▌ | 490/1900 [09:57<27:53, 1.19s/it] Evaluating eval...: 26%|██▌ | 491/1900 [09:58<28:06, 1.20s/it] Evaluating eval...: 26%|██▌ | 492/1900 [09:59<27:58, 1.19s/it] Evaluating eval...: 26%|██▌ | 493/1900 [10:00<28:08, 1.20s/it] Evaluating eval...: 26%|██▌ | 494/1900 [10:02<27:54, 1.19s/it] Evaluating eval...: 26%|██▌ | 495/1900 [10:03<27:45, 1.19s/it] Evaluating eval...: 26%|██▌ | 496/1900 [10:04<27:59, 1.20s/it] Evaluating eval...: 26%|██▌ | 497/1900 [10:05<28:31, 1.22s/it] Evaluating eval...: 26%|██▌ | 498/1900 [10:07<29:27, 1.26s/it] Evaluating eval...: 26%|██▋ | 499/1900 [10:08<29:11, 1.25s/it] Evaluating eval...: 26%|██▋ | 500/1900 [10:09<28:46, 1.23s/it] Evaluating eval...: 26%|██▋ | 501/1900 [10:10<28:53, 1.24s/it] Evaluating eval...: 26%|██▋ | 502/1900 [10:11<28:58, 1.24s/it] Evaluating eval...: 26%|██▋ | 503/1900 [10:13<29:33, 1.27s/it] Evaluating eval...: 27%|██▋ | 504/1900 [10:14<30:04, 1.29s/it] Evaluating eval...: 27%|██▋ | 505/1900 [10:15<29:43, 1.28s/it] Evaluating eval...: 27%|██▋ | 506/1900 [10:17<29:05, 1.25s/it] Evaluating eval...: 27%|██▋ | 507/1900 [10:18<28:22, 1.22s/it] Evaluating eval...: 27%|██▋ | 508/1900 [10:19<28:49, 1.24s/it] Evaluating eval...: 27%|██▋ | 509/1900 [10:20<29:21, 1.27s/it] Evaluating eval...: 27%|██▋ | 510/1900 [10:22<28:56, 1.25s/it] Evaluating eval...: 27%|██▋ | 511/1900 [10:23<28:18, 1.22s/it] Evaluating eval...: 27%|██▋ | 512/1900 [10:24<28:07, 1.22s/it] Evaluating eval...: 27%|██▋ | 513/1900 [10:25<27:34, 1.19s/it] Evaluating eval...: 27%|██▋ | 514/1900 [10:26<27:14, 1.18s/it] Evaluating eval...: 27%|██▋ | 515/1900 [10:27<27:23, 1.19s/it] Evaluating eval...: 27%|██▋ | 516/1900 [10:29<27:11, 1.18s/it] Evaluating eval...: 27%|██▋ | 517/1900 [10:30<26:59, 1.17s/it] Evaluating eval...: 27%|██▋ | 518/1900 [10:31<27:34, 1.20s/it] Evaluating eval...: 27%|██▋ | 519/1900 [10:32<28:16, 1.23s/it] Evaluating eval...: 27%|██▋ | 520/1900 [10:33<28:03, 1.22s/it] Evaluating eval...: 27%|██▋ | 521/1900 [10:35<28:35, 1.24s/it] Evaluating eval...: 27%|██▋ | 522/1900 [10:36<27:58, 1.22s/it] Evaluating eval...: 28%|██▊ | 523/1900 [10:37<28:19, 1.23s/it] Evaluating eval...: 28%|██▊ | 524/1900 [10:38<28:07, 1.23s/it] Evaluating eval...: 28%|██▊ | 525/1900 [10:40<27:46, 1.21s/it] Evaluating eval...: 28%|██▊ | 526/1900 [10:41<27:35, 1.20s/it] Evaluating eval...: 28%|██▊ | 527/1900 [10:42<28:28, 1.24s/it] Evaluating eval...: 28%|██▊ | 528/1900 [10:43<28:21, 1.24s/it] Evaluating eval...: 28%|██▊ | 529/1900 [10:45<28:25, 1.24s/it] Evaluating eval...: 28%|██▊ | 530/1900 [10:46<27:57, 1.22s/it] Evaluating eval...: 28%|██▊ | 531/1900 [10:47<27:51, 1.22s/it] Evaluating eval...: 28%|██▊ | 532/1900 [10:48<28:06, 1.23s/it] Evaluating eval...: 28%|██▊ | 533/1900 [10:49<27:41, 1.22s/it] Evaluating eval...: 28%|██▊ | 534/1900 [10:51<27:24, 1.20s/it] Evaluating eval...: 28%|██▊ | 535/1900 [10:52<27:00, 1.19s/it] Evaluating eval...: 28%|██▊ | 536/1900 [10:53<27:09, 1.19s/it] Evaluating eval...: 28%|██▊ | 537/1900 [10:54<27:16, 1.20s/it] Evaluating eval...: 28%|██▊ | 538/1900 [10:55<27:14, 1.20s/it] Evaluating eval...: 28%|██▊ | 539/1900 [10:57<27:17, 1.20s/it] Evaluating eval...: 28%|██▊ | 540/1900 [10:58<27:18, 1.20s/it] Evaluating eval...: 28%|██▊ | 541/1900 [10:59<26:53, 1.19s/it] Evaluating eval...: 29%|██▊ | 542/1900 [11:00<27:14, 1.20s/it] Evaluating eval...: 29%|██▊ | 543/1900 [11:01<26:45, 1.18s/it] Evaluating eval...: 29%|██▊ | 544/1900 [11:03<26:43, 1.18s/it] Evaluating eval...: 29%|██▊ | 545/1900 [11:04<27:43, 1.23s/it] Evaluating eval...: 29%|██▊ | 546/1900 [11:05<27:22, 1.21s/it] Evaluating eval...: 29%|██▉ | 547/1900 [11:06<27:21, 1.21s/it] Evaluating eval...: 29%|██▉ | 548/1900 [11:07<27:27, 1.22s/it] Evaluating eval...: 29%|██▉ | 549/1900 [11:09<27:45, 1.23s/it] Evaluating eval...: 29%|██▉ | 550/1900 [11:10<28:15, 1.26s/it] Evaluating eval...: 29%|██▉ | 551/1900 [11:11<27:59, 1.24s/it] Evaluating eval...: 29%|██▉ | 552/1900 [11:12<27:53, 1.24s/it] Evaluating eval...: 29%|██▉ | 553/1900 [11:14<27:31, 1.23s/it] Evaluating eval...: 29%|██▉ | 554/1900 [11:15<27:01, 1.20s/it] Evaluating eval...: 29%|██▉ | 555/1900 [11:16<26:52, 1.20s/it] Evaluating eval...: 29%|██▉ | 556/1900 [11:17<26:47, 1.20s/it] Evaluating eval...: 29%|██▉ | 557/1900 [11:18<26:40, 1.19s/it] Evaluating eval...: 29%|██▉ | 558/1900 [11:20<27:02, 1.21s/it] Evaluating eval...: 29%|██▉ | 559/1900 [11:21<26:41, 1.19s/it] Evaluating eval...: 29%|██▉ | 560/1900 [11:22<26:56, 1.21s/it] Evaluating eval...: 30%|██▉ | 561/1900 [11:23<26:37, 1.19s/it] Evaluating eval...: 30%|██▉ | 562/1900 [11:24<27:11, 1.22s/it] Evaluating eval...: 30%|██▉ | 563/1900 [11:26<27:48, 1.25s/it] Evaluating eval...: 30%|██▉ | 564/1900 [11:27<28:22, 1.27s/it] Evaluating eval...: 30%|██▉ | 565/1900 [11:28<27:51, 1.25s/it] Evaluating eval...: 30%|██▉ | 566/1900 [11:30<27:53, 1.25s/it] Evaluating eval...: 30%|██▉ | 567/1900 [11:31<28:13, 1.27s/it] Evaluating eval...: 30%|██▉ | 568/1900 [11:32<28:14, 1.27s/it] Evaluating eval...: 30%|██▉ | 569/1900 [11:33<27:44, 1.25s/it] Evaluating eval...: 30%|███ | 570/1900 [11:36<34:27, 1.55s/it] Evaluating eval...: 30%|███ | 571/1900 [11:37<31:45, 1.43s/it] Evaluating eval...: 30%|███ | 572/1900 [11:38<30:07, 1.36s/it] Evaluating eval...: 30%|███ | 573/1900 [11:39<29:01, 1.31s/it] Evaluating eval...: 30%|███ | 574/1900 [11:40<28:19, 1.28s/it] Evaluating eval...: 30%|███ | 575/1900 [11:42<27:31, 1.25s/it] Evaluating eval...: 30%|███ | 576/1900 [11:43<27:35, 1.25s/it] Evaluating eval...: 30%|███ | 577/1900 [11:44<27:07, 1.23s/it] Evaluating eval...: 30%|███ | 578/1900 [11:45<26:52, 1.22s/it] Evaluating eval...: 30%|███ | 579/1900 [11:46<26:48, 1.22s/it] Evaluating eval...: 31%|███ | 580/1900 [11:48<26:42, 1.21s/it] Evaluating eval...: 31%|███ | 581/1900 [11:49<26:18, 1.20s/it] Evaluating eval...: 31%|███ | 582/1900 [11:51<33:02, 1.50s/it] Evaluating eval...: 31%|███ | 583/1900 [11:52<30:44, 1.40s/it] Evaluating eval...: 31%|███ | 584/1900 [11:53<29:09, 1.33s/it] Evaluating eval...: 31%|███ | 585/1900 [11:54<28:10, 1.29s/it] Evaluating eval...: 31%|███ | 586/1900 [11:56<27:33, 1.26s/it] Evaluating eval...: 31%|███ | 587/1900 [11:57<26:48, 1.22s/it] Evaluating eval...: 31%|███ | 588/1900 [11:58<26:24, 1.21s/it] Evaluating eval...: 31%|███ | 589/1900 [11:59<26:55, 1.23s/it] Evaluating eval...: 31%|███ | 590/1900 [12:00<26:32, 1.22s/it] Evaluating eval...: 31%|███ | 591/1900 [12:02<26:09, 1.20s/it] Evaluating eval...: 31%|███ | 592/1900 [12:03<26:51, 1.23s/it] Evaluating eval...: 31%|███ | 593/1900 [12:04<26:53, 1.23s/it] Evaluating eval...: 31%|███▏ | 594/1900 [12:05<26:45, 1.23s/it] Evaluating eval...: 31%|███▏ | 595/1900 [12:07<26:28, 1.22s/it] Evaluating eval...: 31%|███▏ | 596/1900 [12:08<26:30, 1.22s/it] Evaluating eval...: 31%|███▏ | 597/1900 [12:09<26:48, 1.23s/it] Evaluating eval...: 31%|███▏ | 598/1900 [12:10<26:22, 1.22s/it] Evaluating eval...: 32%|███▏ | 599/1900 [12:11<26:01, 1.20s/it] Evaluating eval...: 32%|███▏ | 600/1900 [12:13<25:59, 1.20s/it] Evaluating eval...: 32%|███▏ | 601/1900 [12:14<26:25, 1.22s/it] Evaluating eval...: 32%|███▏ | 602/1900 [12:15<25:58, 1.20s/it] Evaluating eval...: 32%|███▏ | 603/1900 [12:16<25:54, 1.20s/it] Evaluating eval...: 32%|███▏ | 604/1900 [12:17<25:48, 1.20s/it] Evaluating eval...: 32%|███▏ | 605/1900 [12:19<25:47, 1.20s/it] Evaluating eval...: 32%|███▏ | 606/1900 [12:20<26:28, 1.23s/it] Evaluating eval...: 32%|███▏ | 607/1900 [12:21<26:01, 1.21s/it] Evaluating eval...: 32%|███▏ | 608/1900 [12:22<26:27, 1.23s/it] Evaluating eval...: 32%|███▏ | 609/1900 [12:24<26:35, 1.24s/it] Evaluating eval...: 32%|███▏ | 610/1900 [12:25<26:00, 1.21s/it] Evaluating eval...: 32%|███▏ | 611/1900 [12:26<25:38, 1.19s/it] Evaluating eval...: 32%|███▏ | 612/1900 [12:27<26:06, 1.22s/it] Evaluating eval...: 32%|███▏ | 613/1900 [12:28<25:51, 1.21s/it] Evaluating eval...: 32%|███▏ | 614/1900 [12:30<25:56, 1.21s/it] Evaluating eval...: 32%|███▏ | 615/1900 [12:31<25:42, 1.20s/it] Evaluating eval...: 32%|███▏ | 616/1900 [12:32<25:27, 1.19s/it] Evaluating eval...: 32%|███▏ | 617/1900 [12:33<25:04, 1.17s/it] Evaluating eval...: 33%|███▎ | 618/1900 [12:34<24:57, 1.17s/it] Evaluating eval...: 33%|███▎ | 619/1900 [12:35<25:15, 1.18s/it] Evaluating eval...: 33%|███▎ | 620/1900 [12:37<25:10, 1.18s/it] Evaluating eval...: 33%|███▎ | 621/1900 [12:38<25:35, 1.20s/it] Evaluating eval...: 33%|███▎ | 622/1900 [12:39<25:37, 1.20s/it] Evaluating eval...: 33%|███▎ | 623/1900 [12:40<25:45, 1.21s/it] Evaluating eval...: 33%|███▎ | 624/1900 [12:42<26:05, 1.23s/it] Evaluating eval...: 33%|███▎ | 625/1900 [12:43<26:11, 1.23s/it] Evaluating eval...: 33%|███▎ | 626/1900 [12:44<25:37, 1.21s/it] Evaluating eval...: 33%|███▎ | 627/1900 [12:45<25:12, 1.19s/it] Evaluating eval...: 33%|███▎ | 628/1900 [12:46<25:10, 1.19s/it] Evaluating eval...: 33%|███▎ | 629/1900 [12:48<25:28, 1.20s/it] Evaluating eval...: 33%|███▎ | 630/1900 [12:49<25:30, 1.21s/it] Evaluating eval...: 33%|███▎ | 631/1900 [12:50<26:02, 1.23s/it] Evaluating eval...: 33%|███▎ | 632/1900 [12:51<25:38, 1.21s/it] Evaluating eval...: 33%|███▎ | 633/1900 [12:52<25:14, 1.20s/it] Evaluating eval...: 33%|███▎ | 634/1900 [12:53<24:46, 1.17s/it] Evaluating eval...: 33%|███▎ | 635/1900 [12:55<24:50, 1.18s/it] Evaluating eval...: 33%|███▎ | 636/1900 [12:56<25:16, 1.20s/it] Evaluating eval...: 34%|███▎ | 637/1900 [12:57<25:31, 1.21s/it] Evaluating eval...: 34%|███▎ | 638/1900 [12:58<25:41, 1.22s/it] Evaluating eval...: 34%|███▎ | 639/1900 [13:00<25:36, 1.22s/it] Evaluating eval...: 34%|███▎ | 640/1900 [13:01<25:53, 1.23s/it] Evaluating eval...: 34%|███▎ | 641/1900 [13:02<25:38, 1.22s/it] Evaluating eval...: 34%|███▍ | 642/1900 [13:03<25:33, 1.22s/it] Evaluating eval...: 34%|███▍ | 643/1900 [13:05<25:52, 1.23s/it] Evaluating eval...: 34%|███▍ | 644/1900 [13:06<25:44, 1.23s/it] Evaluating eval...: 34%|███▍ | 645/1900 [13:07<26:11, 1.25s/it] Evaluating eval...: 34%|███▍ | 646/1900 [13:08<26:13, 1.25s/it] Evaluating eval...: 34%|███▍ | 647/1900 [13:10<25:48, 1.24s/it] Evaluating eval...: 34%|███▍ | 648/1900 [13:11<25:22, 1.22s/it] Evaluating eval...: 34%|███▍ | 649/1900 [13:12<25:23, 1.22s/it] Evaluating eval...: 34%|███▍ | 650/1900 [13:13<25:38, 1.23s/it] Evaluating eval...: 34%|███▍ | 651/1900 [13:14<25:35, 1.23s/it] Evaluating eval...: 34%|███▍ | 652/1900 [13:16<25:07, 1.21s/it] Evaluating eval...: 34%|███▍ | 653/1900 [13:17<24:45, 1.19s/it] Evaluating eval...: 34%|███▍ | 654/1900 [13:18<25:36, 1.23s/it] Evaluating eval...: 34%|███▍ | 655/1900 [13:19<25:41, 1.24s/it] Evaluating eval...: 35%|███▍ | 656/1900 [13:21<25:28, 1.23s/it] Evaluating eval...: 35%|███▍ | 657/1900 [13:22<25:17, 1.22s/it] Evaluating eval...: 35%|███▍ | 658/1900 [13:23<25:27, 1.23s/it] Evaluating eval...: 35%|███▍ | 659/1900 [13:24<25:24, 1.23s/it] Evaluating eval...: 35%|███▍ | 660/1900 [13:25<25:03, 1.21s/it] Evaluating eval...: 35%|███▍ | 661/1900 [13:27<25:10, 1.22s/it] Evaluating eval...: 35%|███▍ | 662/1900 [13:28<25:23, 1.23s/it] Evaluating eval...: 35%|███▍ | 663/1900 [13:29<25:19, 1.23s/it] Evaluating eval...: 35%|███▍ | 664/1900 [13:30<24:59, 1.21s/it] Evaluating eval...: 35%|███▌ | 665/1900 [13:31<24:40, 1.20s/it] Evaluating eval...: 35%|███▌ | 666/1900 [13:33<24:24, 1.19s/it] Evaluating eval...: 35%|███▌ | 667/1900 [13:34<26:26, 1.29s/it] Evaluating eval...: 35%|███▌ | 668/1900 [13:35<25:52, 1.26s/it] Evaluating eval...: 35%|███▌ | 669/1900 [13:36<25:17, 1.23s/it] Evaluating eval...: 35%|███▌ | 670/1900 [13:38<25:18, 1.23s/it] Evaluating eval...: 35%|███▌ | 671/1900 [13:39<25:15, 1.23s/it] Evaluating eval...: 35%|███▌ | 672/1900 [13:40<24:56, 1.22s/it] Evaluating eval...: 35%|███▌ | 673/1900 [13:41<24:33, 1.20s/it] Evaluating eval...: 35%|███▌ | 674/1900 [13:42<24:27, 1.20s/it] Evaluating eval...: 36%|███▌ | 675/1900 [13:44<24:32, 1.20s/it] Evaluating eval...: 36%|███▌ | 676/1900 [13:45<24:31, 1.20s/it] Evaluating eval...: 36%|███▌ | 677/1900 [13:46<24:18, 1.19s/it] Evaluating eval...: 36%|███▌ | 678/1900 [13:47<24:46, 1.22s/it] Evaluating eval...: 36%|███▌ | 679/1900 [13:48<24:29, 1.20s/it] Evaluating eval...: 36%|███▌ | 680/1900 [13:50<24:48, 1.22s/it] Evaluating eval...: 36%|███▌ | 681/1900 [13:51<25:35, 1.26s/it] Evaluating eval...: 36%|███▌ | 682/1900 [13:52<25:23, 1.25s/it] Evaluating eval...: 36%|███▌ | 683/1900 [13:54<25:11, 1.24s/it] Evaluating eval...: 36%|███▌ | 684/1900 [13:55<24:42, 1.22s/it] Evaluating eval...: 36%|███▌ | 685/1900 [13:56<24:22, 1.20s/it] Evaluating eval...: 36%|███▌ | 686/1900 [13:57<24:39, 1.22s/it] Evaluating eval...: 36%|███▌ | 687/1900 [13:58<24:37, 1.22s/it] Evaluating eval...: 36%|███▌ | 688/1900 [14:00<24:10, 1.20s/it] Evaluating eval...: 36%|███▋ | 689/1900 [14:01<23:57, 1.19s/it] Evaluating eval...: 36%|███▋ | 690/1900 [14:02<24:06, 1.20s/it] Evaluating eval...: 36%|███▋ | 691/1900 [14:03<24:16, 1.20s/it] Evaluating eval...: 36%|███▋ | 692/1900 [14:04<23:58, 1.19s/it] Evaluating eval...: 36%|███▋ | 693/1900 [14:06<24:14, 1.21s/it] Evaluating eval...: 37%|███▋ | 694/1900 [14:07<24:15, 1.21s/it] Evaluating eval...: 37%|███▋ | 695/1900 [14:08<24:41, 1.23s/it] Evaluating eval...: 37%|███▋ | 696/1900 [14:09<24:27, 1.22s/it] Evaluating eval...: 37%|███▋ | 697/1900 [14:10<24:05, 1.20s/it] Evaluating eval...: 37%|███▋ | 698/1900 [14:12<24:17, 1.21s/it] Evaluating eval...: 37%|███▋ | 699/1900 [14:13<24:15, 1.21s/it] Evaluating eval...: 37%|███▋ | 700/1900 [14:14<23:46, 1.19s/it] Evaluating eval...: 37%|███▋ | 701/1900 [14:15<23:55, 1.20s/it] Evaluating eval...: 37%|███▋ | 702/1900 [14:16<24:03, 1.21s/it] Evaluating eval...: 37%|███▋ | 703/1900 [14:18<23:42, 1.19s/it] Evaluating eval...: 37%|███▋ | 704/1900 [14:19<23:54, 1.20s/it] Evaluating eval...: 37%|███▋ | 705/1900 [14:20<23:52, 1.20s/it] Evaluating eval...: 37%|███▋ | 706/1900 [14:21<23:41, 1.19s/it] Evaluating eval...: 37%|███▋ | 707/1900 [14:22<23:31, 1.18s/it] Evaluating eval...: 37%|███▋ | 708/1900 [14:24<24:07, 1.21s/it] Evaluating eval...: 37%|███▋ | 709/1900 [14:25<23:46, 1.20s/it] Evaluating eval...: 37%|███▋ | 710/1900 [14:26<23:47, 1.20s/it] Evaluating eval...: 37%|███▋ | 711/1900 [14:27<24:21, 1.23s/it] Evaluating eval...: 37%|███▋ | 712/1900 [14:29<24:31, 1.24s/it] Evaluating eval...: 38%|███▊ | 713/1900 [14:30<24:59, 1.26s/it] Evaluating eval...: 38%|███▊ | 714/1900 [14:31<24:19, 1.23s/it] Evaluating eval...: 38%|███▊ | 715/1900 [14:32<24:02, 1.22s/it] Evaluating eval...: 38%|███▊ | 716/1900 [14:33<23:52, 1.21s/it] Evaluating eval...: 38%|███▊ | 717/1900 [14:35<23:34, 1.20s/it] Evaluating eval...: 38%|███▊ | 718/1900 [14:36<23:43, 1.20s/it] Evaluating eval...: 38%|███▊ | 719/1900 [14:37<23:49, 1.21s/it] Evaluating eval...: 38%|███▊ | 720/1900 [14:38<23:32, 1.20s/it] Evaluating eval...: 38%|███▊ | 721/1900 [14:39<24:04, 1.22s/it] Evaluating eval...: 38%|███▊ | 722/1900 [14:41<23:51, 1.22s/it] Evaluating eval...: 38%|███▊ | 723/1900 [14:42<23:47, 1.21s/it] Evaluating eval...: 38%|███▊ | 724/1900 [14:43<23:29, 1.20s/it] Evaluating eval...: 38%|███▊ | 725/1900 [14:44<23:18, 1.19s/it] Evaluating eval...: 38%|███▊ | 726/1900 [14:45<23:17, 1.19s/it] Evaluating eval...: 38%|███▊ | 727/1900 [14:47<23:15, 1.19s/it] Evaluating eval...: 38%|███▊ | 728/1900 [14:48<23:49, 1.22s/it] Evaluating eval...: 38%|███▊ | 729/1900 [14:49<23:28, 1.20s/it] Evaluating eval...: 38%|███▊ | 730/1900 [14:50<23:49, 1.22s/it] Evaluating eval...: 38%|███▊ | 731/1900 [14:51<23:39, 1.21s/it] Evaluating eval...: 39%|███▊ | 732/1900 [14:53<23:39, 1.22s/it] Evaluating eval...: 39%|███▊ | 733/1900 [14:54<23:42, 1.22s/it] Evaluating eval...: 39%|███▊ | 734/1900 [14:55<23:30, 1.21s/it] Evaluating eval...: 39%|███▊ | 735/1900 [14:56<23:01, 1.19s/it] Evaluating eval...: 39%|███▊ | 736/1900 [14:57<22:54, 1.18s/it] Evaluating eval...: 39%|███▉ | 737/1900 [14:59<22:58, 1.19s/it] Evaluating eval...: 39%|███▉ | 738/1900 [15:00<23:07, 1.19s/it] Evaluating eval...: 39%|███▉ | 739/1900 [15:01<23:17, 1.20s/it] Evaluating eval...: 39%|███▉ | 740/1900 [15:02<23:13, 1.20s/it] Evaluating eval...: 39%|███▉ | 741/1900 [15:04<24:24, 1.26s/it] Evaluating eval...: 39%|███▉ | 742/1900 [15:05<24:07, 1.25s/it] Evaluating eval...: 39%|███▉ | 743/1900 [15:06<23:58, 1.24s/it] Evaluating eval...: 39%|███▉ | 744/1900 [15:07<23:33, 1.22s/it] Evaluating eval...: 39%|███▉ | 745/1900 [15:09<23:45, 1.23s/it] Evaluating eval...: 39%|███▉ | 746/1900 [15:10<23:37, 1.23s/it] Evaluating eval...: 39%|███▉ | 747/1900 [15:11<23:59, 1.25s/it] Evaluating eval...: 39%|███▉ | 748/1900 [15:12<24:00, 1.25s/it] Evaluating eval...: 39%|███▉ | 749/1900 [15:14<24:44, 1.29s/it] Evaluating eval...: 39%|███▉ | 750/1900 [15:15<24:43, 1.29s/it] Evaluating eval...: 40%|███▉ | 751/1900 [15:16<24:40, 1.29s/it] Evaluating eval...: 40%|███▉ | 752/1900 [15:17<24:28, 1.28s/it] Evaluating eval...: 40%|███▉ | 753/1900 [15:19<24:43, 1.29s/it] Evaluating eval...: 40%|███▉ | 754/1900 [15:20<24:06, 1.26s/it] Evaluating eval...: 40%|███▉ | 755/1900 [15:21<23:37, 1.24s/it] Evaluating eval...: 40%|███▉ | 756/1900 [15:23<24:20, 1.28s/it] Evaluating eval...: 40%|███▉ | 757/1900 [15:24<24:14, 1.27s/it] Evaluating eval...: 40%|███▉ | 758/1900 [15:25<24:38, 1.29s/it] Evaluating eval...: 40%|███▉ | 759/1900 [15:26<24:22, 1.28s/it] Evaluating eval...: 40%|████ | 760/1900 [15:28<24:08, 1.27s/it] Evaluating eval...: 40%|████ | 761/1900 [15:29<23:48, 1.25s/it] Evaluating eval...: 40%|████ | 762/1900 [15:30<23:11, 1.22s/it] Evaluating eval...: 40%|████ | 763/1900 [15:31<23:02, 1.22s/it] Evaluating eval...: 40%|████ | 764/1900 [15:32<22:44, 1.20s/it] Evaluating eval...: 40%|████ | 765/1900 [15:34<23:00, 1.22s/it] Evaluating eval...: 40%|████ | 766/1900 [15:35<22:54, 1.21s/it] Evaluating eval...: 40%|████ | 767/1900 [15:36<23:11, 1.23s/it] Evaluating eval...: 40%|████ | 768/1900 [15:38<24:21, 1.29s/it] Evaluating eval...: 40%|████ | 769/1900 [15:39<24:04, 1.28s/it] Evaluating eval...: 41%|████ | 770/1900 [15:40<23:22, 1.24s/it] Evaluating eval...: 41%|████ | 771/1900 [15:41<23:26, 1.25s/it] Evaluating eval...: 41%|████ | 772/1900 [15:42<23:32, 1.25s/it] Evaluating eval...: 41%|████ | 773/1900 [15:44<23:11, 1.23s/it] Evaluating eval...: 41%|████ | 774/1900 [15:45<22:43, 1.21s/it] Evaluating eval...: 41%|████ | 775/1900 [15:46<22:57, 1.22s/it] Evaluating eval...: 41%|████ | 776/1900 [15:47<23:11, 1.24s/it] Evaluating eval...: 41%|████ | 777/1900 [15:49<23:27, 1.25s/it] Evaluating eval...: 41%|████ | 778/1900 [15:50<22:56, 1.23s/it] Evaluating eval...: 41%|████ | 779/1900 [15:51<22:33, 1.21s/it] Evaluating eval...: 41%|████ | 780/1900 [15:52<23:13, 1.24s/it] Evaluating eval...: 41%|████ | 781/1900 [15:53<22:50, 1.22s/it] Evaluating eval...: 41%|████ | 782/1900 [15:55<23:27, 1.26s/it] Evaluating eval...: 41%|████ | 783/1900 [15:56<23:15, 1.25s/it] Evaluating eval...: 41%|████▏ | 784/1900 [15:57<22:55, 1.23s/it] Evaluating eval...: 41%|████▏ | 785/1900 [15:58<22:42, 1.22s/it] Evaluating eval...: 41%|████▏ | 786/1900 [16:00<22:42, 1.22s/it] Evaluating eval...: 41%|████▏ | 787/1900 [16:01<22:47, 1.23s/it] Evaluating eval...: 41%|████▏ | 788/1900 [16:02<22:40, 1.22s/it] Evaluating eval...: 42%|████▏ | 789/1900 [16:03<23:06, 1.25s/it] Evaluating eval...: 42%|████▏ | 790/1900 [16:05<23:05, 1.25s/it] Evaluating eval...: 42%|████▏ | 791/1900 [16:06<22:59, 1.24s/it] Evaluating eval...: 42%|████▏ | 792/1900 [16:07<23:31, 1.27s/it] Evaluating eval...: 42%|████▏ | 793/1900 [16:08<23:11, 1.26s/it] Evaluating eval...: 42%|████▏ | 794/1900 [16:10<22:48, 1.24s/it] Evaluating eval...: 42%|████▏ | 795/1900 [16:11<22:45, 1.24s/it] Evaluating eval...: 42%|████▏ | 796/1900 [16:12<22:16, 1.21s/it] Evaluating eval...: 42%|████▏ | 797/1900 [16:13<22:15, 1.21s/it] Evaluating eval...: 42%|████▏ | 798/1900 [16:14<22:04, 1.20s/it] Evaluating eval...: 42%|████▏ | 799/1900 [16:16<22:00, 1.20s/it] Evaluating eval...: 42%|████▏ | 800/1900 [16:17<22:36, 1.23s/it] Evaluating eval...: 42%|████▏ | 801/1900 [16:18<22:24, 1.22s/it] Evaluating eval...: 42%|████▏ | 802/1900 [16:19<22:05, 1.21s/it] Evaluating eval...: 42%|████▏ | 803/1900 [16:21<22:50, 1.25s/it] Evaluating eval...: 42%|████▏ | 804/1900 [16:22<22:25, 1.23s/it] Evaluating eval...: 42%|████▏ | 805/1900 [16:23<22:44, 1.25s/it] Evaluating eval...: 42%|████▏ | 806/1900 [16:24<22:15, 1.22s/it] Evaluating eval...: 42%|████▏ | 807/1900 [16:25<22:05, 1.21s/it] Evaluating eval...: 43%|████▎ | 808/1900 [16:27<22:25, 1.23s/it] Evaluating eval...: 43%|████▎ | 809/1900 [16:28<22:41, 1.25s/it] Evaluating eval...: 43%|████▎ | 810/1900 [16:29<22:32, 1.24s/it] Evaluating eval...: 43%|████▎ | 811/1900 [16:30<22:18, 1.23s/it] Evaluating eval...: 43%|████▎ | 812/1900 [16:32<22:21, 1.23s/it] Evaluating eval...: 43%|████▎ | 813/1900 [16:33<22:02, 1.22s/it] Evaluating eval...: 43%|████▎ | 814/1900 [16:34<22:01, 1.22s/it] Evaluating eval...: 43%|████▎ | 815/1900 [16:35<21:58, 1.22s/it] Evaluating eval...: 43%|████▎ | 816/1900 [16:37<22:02, 1.22s/it] Evaluating eval...: 43%|████▎ | 817/1900 [16:38<21:46, 1.21s/it] Evaluating eval...: 43%|████▎ | 818/1900 [16:39<21:39, 1.20s/it] Evaluating eval...: 43%|████▎ | 819/1900 [16:40<21:55, 1.22s/it] Evaluating eval...: 43%|████▎ | 820/1900 [16:41<21:51, 1.21s/it] Evaluating eval...: 43%|████▎ | 821/1900 [16:43<21:34, 1.20s/it] Evaluating eval...: 43%|████▎ | 822/1900 [16:44<21:44, 1.21s/it] Evaluating eval...: 43%|████▎ | 823/1900 [16:45<21:43, 1.21s/it] Evaluating eval...: 43%|████▎ | 824/1900 [16:46<21:35, 1.20s/it] Evaluating eval...: 43%|████▎ | 825/1900 [16:47<21:27, 1.20s/it] Evaluating eval...: 43%|████▎ | 826/1900 [16:49<21:53, 1.22s/it] Evaluating eval...: 44%|████▎ | 827/1900 [16:50<21:46, 1.22s/it] Evaluating eval...: 44%|████▎ | 828/1900 [16:51<22:15, 1.25s/it] Evaluating eval...: 44%|████▎ | 829/1900 [16:52<21:55, 1.23s/it] Evaluating eval...: 44%|████▎ | 830/1900 [16:54<22:30, 1.26s/it] Evaluating eval...: 44%|████▎ | 831/1900 [16:55<22:03, 1.24s/it] Evaluating eval...: 44%|████▍ | 832/1900 [16:56<22:16, 1.25s/it] Evaluating eval...: 44%|████▍ | 833/1900 [16:57<22:22, 1.26s/it] Evaluating eval...: 44%|████▍ | 834/1900 [16:59<21:45, 1.22s/it] Evaluating eval...: 44%|████▍ | 835/1900 [17:00<21:59, 1.24s/it] Evaluating eval...: 44%|████▍ | 836/1900 [17:01<22:02, 1.24s/it] Evaluating eval...: 44%|████▍ | 837/1900 [17:02<21:45, 1.23s/it] Evaluating eval...: 44%|████▍ | 838/1900 [17:03<21:24, 1.21s/it] Evaluating eval...: 44%|████▍ | 839/1900 [17:05<21:05, 1.19s/it] Evaluating eval...: 44%|████▍ | 840/1900 [17:06<21:18, 1.21s/it] Evaluating eval...: 44%|████▍ | 841/1900 [17:07<21:48, 1.24s/it] Evaluating eval...: 44%|████▍ | 842/1900 [17:08<21:39, 1.23s/it] Evaluating eval...: 44%|████▍ | 843/1900 [17:10<21:25, 1.22s/it] Evaluating eval...: 44%|████▍ | 844/1900 [17:11<21:02, 1.20s/it] Evaluating eval...: 44%|████▍ | 845/1900 [17:12<20:56, 1.19s/it] Evaluating eval...: 45%|████▍ | 846/1900 [17:13<21:35, 1.23s/it] Evaluating eval...: 45%|████▍ | 847/1900 [17:14<21:16, 1.21s/it] Evaluating eval...: 45%|████▍ | 848/1900 [17:16<21:10, 1.21s/it] Evaluating eval...: 45%|████▍ | 849/1900 [17:17<21:03, 1.20s/it] Evaluating eval...: 45%|████▍ | 850/1900 [17:18<21:07, 1.21s/it] Evaluating eval...: 45%|████▍ | 851/1900 [17:19<20:50, 1.19s/it] Evaluating eval...: 45%|████▍ | 852/1900 [17:20<21:31, 1.23s/it] Evaluating eval...: 45%|████▍ | 853/1900 [17:22<21:24, 1.23s/it] Evaluating eval...: 45%|████▍ | 854/1900 [17:23<21:13, 1.22s/it] Evaluating eval...: 45%|████▌ | 855/1900 [17:24<21:01, 1.21s/it] Evaluating eval...: 45%|████▌ | 856/1900 [17:25<20:50, 1.20s/it] Evaluating eval...: 45%|████▌ | 857/1900 [17:26<20:40, 1.19s/it] Evaluating eval...: 45%|████▌ | 858/1900 [17:28<20:57, 1.21s/it] Evaluating eval...: 45%|████▌ | 859/1900 [17:29<20:49, 1.20s/it] Evaluating eval...: 45%|████▌ | 860/1900 [17:30<20:53, 1.21s/it] Evaluating eval...: 45%|████▌ | 861/1900 [17:31<21:10, 1.22s/it] Evaluating eval...: 45%|████▌ | 862/1900 [17:33<21:08, 1.22s/it] Evaluating eval...: 45%|████▌ | 863/1900 [17:34<20:40, 1.20s/it] Evaluating eval...: 45%|████▌ | 864/1900 [17:35<20:27, 1.18s/it] Evaluating eval...: 46%|████▌ | 865/1900 [17:36<20:18, 1.18s/it] Evaluating eval...: 46%|████▌ | 866/1900 [17:37<20:25, 1.18s/it] Evaluating eval...: 46%|████▌ | 867/1900 [17:38<20:46, 1.21s/it] Evaluating eval...: 46%|████▌ | 868/1900 [17:40<21:00, 1.22s/it] Evaluating eval...: 46%|████▌ | 869/1900 [17:41<20:35, 1.20s/it] Evaluating eval...: 46%|████▌ | 870/1900 [17:42<20:41, 1.20s/it] Evaluating eval...: 46%|████▌ | 871/1900 [17:43<21:03, 1.23s/it] Evaluating eval...: 46%|████▌ | 872/1900 [17:45<20:57, 1.22s/it] Evaluating eval...: 46%|████▌ | 873/1900 [17:46<21:00, 1.23s/it] Evaluating eval...: 46%|████▌ | 874/1900 [17:47<21:12, 1.24s/it] Evaluating eval...: 46%|████▌ | 875/1900 [17:48<21:09, 1.24s/it] Evaluating eval...: 46%|████▌ | 876/1900 [17:49<20:57, 1.23s/it] Evaluating eval...: 46%|████▌ | 877/1900 [17:51<20:36, 1.21s/it] Evaluating eval...: 46%|████▌ | 878/1900 [17:52<20:45, 1.22s/it] Evaluating eval...: 46%|████▋ | 879/1900 [17:53<20:28, 1.20s/it] Evaluating eval...: 46%|████▋ | 880/1900 [17:54<20:13, 1.19s/it] Evaluating eval...: 46%|████▋ | 881/1900 [17:55<20:02, 1.18s/it] Evaluating eval...: 46%|████▋ | 882/1900 [17:57<20:14, 1.19s/it] Evaluating eval...: 46%|████▋ | 883/1900 [17:58<20:21, 1.20s/it] Evaluating eval...: 47%|████▋ | 884/1900 [17:59<20:18, 1.20s/it] Evaluating eval...: 47%|████▋ | 885/1900 [18:00<20:16, 1.20s/it] Evaluating eval...: 47%|████▋ | 886/1900 [18:01<20:02, 1.19s/it] Evaluating eval...: 47%|████▋ | 887/1900 [18:03<19:55, 1.18s/it] Evaluating eval...: 47%|████▋ | 888/1900 [18:04<20:16, 1.20s/it] Evaluating eval...: 47%|████▋ | 889/1900 [18:05<20:07, 1.19s/it] Evaluating eval...: 47%|████▋ | 890/1900 [18:06<20:12, 1.20s/it] Evaluating eval...: 47%|████▋ | 891/1900 [18:08<20:55, 1.24s/it] Evaluating eval...: 47%|████▋ | 892/1900 [18:09<20:47, 1.24s/it] Evaluating eval...: 47%|████▋ | 893/1900 [18:10<20:32, 1.22s/it] Evaluating eval...: 47%|████▋ | 894/1900 [18:11<20:18, 1.21s/it] Evaluating eval...: 47%|████▋ | 895/1900 [18:12<20:28, 1.22s/it] Evaluating eval...: 47%|████▋ | 896/1900 [18:14<20:17, 1.21s/it] Evaluating eval...: 47%|████▋ | 897/1900 [18:15<20:05, 1.20s/it] Evaluating eval...: 47%|████▋ | 898/1900 [18:16<20:44, 1.24s/it] Evaluating eval...: 47%|████▋ | 899/1900 [18:17<20:12, 1.21s/it] Evaluating eval...: 47%|████▋ | 900/1900 [18:18<20:18, 1.22s/it] Evaluating eval...: 47%|████▋ | 901/1900 [18:20<20:00, 1.20s/it] Evaluating eval...: 47%|████▋ | 902/1900 [18:21<20:25, 1.23s/it] Evaluating eval...: 48%|████▊ | 903/1900 [18:22<20:28, 1.23s/it] Evaluating eval...: 48%|████▊ | 904/1900 [18:23<20:13, 1.22s/it] Evaluating eval...: 48%|████▊ | 905/1900 [18:25<20:00, 1.21s/it] Evaluating eval...: 48%|████▊ | 906/1900 [18:26<20:08, 1.22s/it] Evaluating eval...: 48%|████▊ | 907/1900 [18:27<20:45, 1.25s/it] Evaluating eval...: 48%|████▊ | 908/1900 [18:28<20:20, 1.23s/it] Evaluating eval...: 48%|████▊ | 909/1900 [18:29<20:16, 1.23s/it] Evaluating eval...: 48%|████▊ | 910/1900 [18:31<20:03, 1.22s/it] Evaluating eval...: 48%|████▊ | 911/1900 [18:32<20:17, 1.23s/it] Evaluating eval...: 48%|████▊ | 912/1900 [18:33<20:22, 1.24s/it] Evaluating eval...: 48%|████▊ | 913/1900 [18:34<20:14, 1.23s/it] Evaluating eval...: 48%|████▊ | 914/1900 [18:36<20:13, 1.23s/it] Evaluating eval...: 48%|████▊ | 915/1900 [18:37<20:34, 1.25s/it] Evaluating eval...: 48%|████▊ | 916/1900 [18:38<20:10, 1.23s/it] Evaluating eval...: 48%|████▊ | 917/1900 [18:39<19:54, 1.21s/it] Evaluating eval...: 48%|████▊ | 918/1900 [18:41<20:12, 1.23s/it] Evaluating eval...: 48%|████▊ | 919/1900 [18:42<20:09, 1.23s/it] Evaluating eval...: 48%|████▊ | 920/1900 [18:43<19:51, 1.22s/it] Evaluating eval...: 48%|████▊ | 921/1900 [18:44<19:44, 1.21s/it] Evaluating eval...: 49%|████▊ | 922/1900 [18:45<19:25, 1.19s/it] Evaluating eval...: 49%|████▊ | 923/1900 [18:47<19:57, 1.23s/it] Evaluating eval...: 49%|████▊ | 924/1900 [18:48<19:31, 1.20s/it] Evaluating eval...: 49%|████▊ | 925/1900 [18:49<19:45, 1.22s/it] Evaluating eval...: 49%|████▊ | 926/1900 [18:50<19:27, 1.20s/it] Evaluating eval...: 49%|████▉ | 927/1900 [18:51<19:11, 1.18s/it] Evaluating eval...: 49%|████▉ | 928/1900 [18:53<19:39, 1.21s/it] Evaluating eval...: 49%|████▉ | 929/1900 [18:54<19:15, 1.19s/it] Evaluating eval...: 49%|████▉ | 930/1900 [18:55<19:00, 1.18s/it] Evaluating eval...: 49%|████▉ | 931/1900 [18:56<19:09, 1.19s/it] Evaluating eval...: 49%|████▉ | 932/1900 [18:57<19:37, 1.22s/it] Evaluating eval...: 49%|████▉ | 933/1900 [18:59<19:34, 1.21s/it] Evaluating eval...: 49%|████▉ | 934/1900 [19:00<19:21, 1.20s/it] Evaluating eval...: 49%|████▉ | 935/1900 [19:01<19:33, 1.22s/it] Evaluating eval...: 49%|████▉ | 936/1900 [19:02<20:08, 1.25s/it] Evaluating eval...: 49%|████▉ | 937/1900 [19:04<20:05, 1.25s/it] Evaluating eval...: 49%|████▉ | 938/1900 [19:05<20:05, 1.25s/it] Evaluating eval...: 49%|████▉ | 939/1900 [19:06<19:53, 1.24s/it] Evaluating eval...: 49%|████▉ | 940/1900 [19:07<19:34, 1.22s/it] Evaluating eval...: 50%|████▉ | 941/1900 [19:09<19:38, 1.23s/it] Evaluating eval...: 50%|████▉ | 942/1900 [19:10<20:06, 1.26s/it] Evaluating eval...: 50%|████▉ | 943/1900 [19:11<19:44, 1.24s/it] Evaluating eval...: 50%|████▉ | 944/1900 [19:12<19:21, 1.21s/it] Evaluating eval...: 50%|████▉ | 945/1900 [19:13<19:00, 1.19s/it] Evaluating eval...: 50%|████▉ | 946/1900 [19:15<19:18, 1.21s/it] Evaluating eval...: 50%|████▉ | 947/1900 [19:16<19:09, 1.21s/it] Evaluating eval...: 50%|████▉ | 948/1900 [19:17<18:54, 1.19s/it] Evaluating eval...: 50%|████▉ | 949/1900 [19:18<18:56, 1.20s/it] Evaluating eval...: 50%|█████ | 950/1900 [19:19<18:54, 1.19s/it] Evaluating eval...: 50%|█████ | 951/1900 [19:21<19:06, 1.21s/it] Evaluating eval...: 50%|█████ | 952/1900 [19:22<19:29, 1.23s/it] Evaluating eval...: 50%|█████ | 953/1900 [19:23<19:05, 1.21s/it] Evaluating eval...: 50%|█████ | 954/1900 [19:24<18:56, 1.20s/it] Evaluating eval...: 50%|█████ | 955/1900 [19:25<19:18, 1.23s/it] Evaluating eval...: 50%|█████ | 956/1900 [19:27<18:57, 1.21s/it] Evaluating eval...: 50%|█████ | 957/1900 [19:28<18:41, 1.19s/it] Evaluating eval...: 50%|█████ | 958/1900 [19:29<18:51, 1.20s/it] Evaluating eval...: 50%|█████ | 959/1900 [19:30<18:50, 1.20s/it] Evaluating eval...: 51%|█████ | 960/1900 [19:31<18:55, 1.21s/it] Evaluating eval...: 51%|█████ | 961/1900 [19:33<19:29, 1.25s/it] Evaluating eval...: 51%|█████ | 962/1900 [19:34<19:13, 1.23s/it] Evaluating eval...: 51%|█████ | 963/1900 [19:35<19:25, 1.24s/it] Evaluating eval...: 51%|█████ | 964/1900 [19:37<19:25, 1.25s/it] Evaluating eval...: 51%|█████ | 965/1900 [19:38<19:16, 1.24s/it] Evaluating eval...: 51%|█████ | 966/1900 [19:39<18:51, 1.21s/it] Evaluating eval...: 51%|█████ | 967/1900 [19:40<18:39, 1.20s/it] Evaluating eval...: 51%|█████ | 968/1900 [19:41<18:34, 1.20s/it] Evaluating eval...: 51%|█████ | 969/1900 [19:42<18:34, 1.20s/it] Evaluating eval...: 51%|█████ | 970/1900 [19:44<18:58, 1.22s/it] Evaluating eval...: 51%|█████ | 971/1900 [19:45<18:40, 1.21s/it] Evaluating eval...: 51%|█████ | 972/1900 [19:46<19:08, 1.24s/it] Evaluating eval...: 51%|█████ | 973/1900 [19:47<18:51, 1.22s/it] Evaluating eval...: 51%|█████▏ | 974/1900 [19:49<18:37, 1.21s/it] Evaluating eval...: 51%|█████▏ | 975/1900 [19:50<19:00, 1.23s/it] Evaluating eval...: 51%|█████▏ | 976/1900 [19:51<19:06, 1.24s/it] Evaluating eval...: 51%|█████▏ | 977/1900 [19:52<18:44, 1.22s/it] Evaluating eval...: 51%|█████▏ | 978/1900 [19:53<18:45, 1.22s/it] Evaluating eval...: 52%|█████▏ | 979/1900 [19:55<18:40, 1.22s/it] Evaluating eval...: 52%|█████▏ | 980/1900 [19:56<18:33, 1.21s/it] Evaluating eval...: 52%|█████▏ | 981/1900 [19:57<18:15, 1.19s/it] Evaluating eval...: 52%|█████▏ | 982/1900 [19:58<18:03, 1.18s/it] Evaluating eval...: 52%|█████▏ | 983/1900 [19:59<18:25, 1.21s/it] Evaluating eval...: 52%|█████▏ | 984/1900 [20:01<18:18, 1.20s/it] Evaluating eval...: 52%|█████▏ | 985/1900 [20:02<18:19, 1.20s/it] Evaluating eval...: 52%|█████▏ | 986/1900 [20:03<18:09, 1.19s/it] Evaluating eval...: 52%|█████▏ | 987/1900 [20:04<18:17, 1.20s/it] Evaluating eval...: 52%|█████▏ | 988/1900 [20:05<18:05, 1.19s/it] Evaluating eval...: 52%|█████▏ | 989/1900 [20:07<18:16, 1.20s/it] Evaluating eval...: 52%|█████▏ | 990/1900 [20:08<18:34, 1.22s/it] Evaluating eval...: 52%|█████▏ | 991/1900 [20:09<18:21, 1.21s/it] Evaluating eval...: 52%|█████▏ | 992/1900 [20:10<18:10, 1.20s/it] Evaluating eval...: 52%|█████▏ | 993/1900 [20:11<18:11, 1.20s/it] Evaluating eval...: 52%|█████▏ | 994/1900 [20:13<17:56, 1.19s/it] Evaluating eval...: 52%|█████▏ | 995/1900 [20:14<18:22, 1.22s/it] Evaluating eval...: 52%|█████▏ | 996/1900 [20:15<18:06, 1.20s/it] Evaluating eval...: 52%|█████▏ | 997/1900 [20:16<18:06, 1.20s/it] Evaluating eval...: 53%|█████▎ | 998/1900 [20:17<18:00, 1.20s/it] Evaluating eval...: 53%|█████▎ | 999/1900 [20:19<17:57, 1.20s/it] Evaluating eval...: 53%|█████▎ | 1000/1900 [20:20<17:49, 1.19s/it] Evaluating eval...: 53%|█████▎ | 1001/1900 [20:21<17:52, 1.19s/it] Evaluating eval...: 53%|█████▎ | 1002/1900 [20:22<18:04, 1.21s/it] Evaluating eval...: 53%|█████▎ | 1003/1900 [20:24<18:10, 1.22s/it] Evaluating eval...: 53%|█████▎ | 1004/1900 [20:25<18:08, 1.22s/it] Evaluating eval...: 53%|█████▎ | 1005/1900 [20:26<17:53, 1.20s/it] Evaluating eval...: 53%|█████▎ | 1006/1900 [20:27<17:55, 1.20s/it] Evaluating eval...: 53%|█████▎ | 1007/1900 [20:28<17:47, 1.20s/it] Evaluating eval...: 53%|█████▎ | 1008/1900 [20:29<17:37, 1.19s/it] Evaluating eval...: 53%|█████▎ | 1009/1900 [20:31<17:37, 1.19s/it] Evaluating eval...: 53%|█████▎ | 1010/1900 [20:32<17:22, 1.17s/it] Evaluating eval...: 53%|█████▎ | 1011/1900 [20:33<17:30, 1.18s/it] Evaluating eval...: 53%|█████▎ | 1012/1900 [20:34<18:24, 1.24s/it] Evaluating eval...: 53%|█████▎ | 1013/1900 [20:36<18:06, 1.22s/it] Evaluating eval...: 53%|█████▎ | 1014/1900 [20:37<18:28, 1.25s/it] Evaluating eval...: 53%|█████▎ | 1015/1900 [20:38<18:11, 1.23s/it] Evaluating eval...: 53%|█████▎ | 1016/1900 [20:40<19:10, 1.30s/it] Evaluating eval...: 54%|█████▎ | 1017/1900 [20:41<18:58, 1.29s/it] Evaluating eval...: 54%|█████▎ | 1018/1900 [20:42<18:45, 1.28s/it] Evaluating eval...: 54%|█████▎ | 1019/1900 [20:44<23:42, 1.61s/it] Evaluating eval...: 54%|█████▎ | 1020/1900 [20:46<22:10, 1.51s/it] Evaluating eval...: 54%|█████▎ | 1021/1900 [20:47<20:48, 1.42s/it] Evaluating eval...: 54%|█████▍ | 1022/1900 [20:48<20:10, 1.38s/it] Evaluating eval...: 54%|█████▍ | 1023/1900 [20:49<19:42, 1.35s/it] Evaluating eval...: 54%|█████▍ | 1024/1900 [20:51<19:11, 1.31s/it] Evaluating eval...: 54%|█████▍ | 1025/1900 [20:52<18:30, 1.27s/it] Evaluating eval...: 54%|█████▍ | 1026/1900 [20:53<18:28, 1.27s/it] Evaluating eval...: 54%|█████▍ | 1027/1900 [20:54<18:25, 1.27s/it] Evaluating eval...: 54%|█████▍ | 1028/1900 [20:56<18:04, 1.24s/it] Evaluating eval...: 54%|█████▍ | 1029/1900 [20:57<17:49, 1.23s/it] Evaluating eval...: 54%|█████▍ | 1030/1900 [20:58<17:32, 1.21s/it] Evaluating eval...: 54%|█████▍ | 1031/1900 [20:59<17:51, 1.23s/it] Evaluating eval...: 54%|█████▍ | 1032/1900 [21:00<17:36, 1.22s/it] Evaluating eval...: 54%|█████▍ | 1033/1900 [21:02<17:20, 1.20s/it] Evaluating eval...: 54%|█████▍ | 1034/1900 [21:03<17:50, 1.24s/it] Evaluating eval...: 54%|█████▍ | 1035/1900 [21:04<17:37, 1.22s/it] Evaluating eval...: 55%|█████▍ | 1036/1900 [21:05<17:38, 1.22s/it] Evaluating eval...: 55%|█████▍ | 1037/1900 [21:07<17:38, 1.23s/it] Evaluating eval...: 55%|█████▍ | 1038/1900 [21:08<17:44, 1.24s/it] Evaluating eval...: 55%|█████▍ | 1039/1900 [21:09<17:47, 1.24s/it] Evaluating eval...: 55%|█████▍ | 1040/1900 [21:10<17:29, 1.22s/it] Evaluating eval...: 55%|█████▍ | 1041/1900 [21:11<17:36, 1.23s/it] Evaluating eval...: 55%|█████▍ | 1042/1900 [21:13<17:37, 1.23s/it] Evaluating eval...: 55%|█████▍ | 1043/1900 [21:14<17:17, 1.21s/it] Evaluating eval...: 55%|█████▍ | 1044/1900 [21:15<17:11, 1.21s/it] Evaluating eval...: 55%|█████▌ | 1045/1900 [21:16<16:59, 1.19s/it] Evaluating eval...: 55%|█████▌ | 1046/1900 [21:17<16:50, 1.18s/it] Evaluating eval...: 55%|█████▌ | 1047/1900 [21:19<16:45, 1.18s/it] Evaluating eval...: 55%|█████▌ | 1048/1900 [21:20<16:48, 1.18s/it] Evaluating eval...: 55%|█████▌ | 1049/1900 [21:21<16:47, 1.18s/it] Evaluating eval...: 55%|█████▌ | 1050/1900 [21:22<18:20, 1.29s/it] Evaluating eval...: 55%|█████▌ | 1051/1900 [21:24<18:12, 1.29s/it] Evaluating eval...: 55%|█████▌ | 1052/1900 [21:25<17:59, 1.27s/it] Evaluating eval...: 55%|█████▌ | 1053/1900 [21:26<17:38, 1.25s/it] Evaluating eval...: 55%|█████▌ | 1054/1900 [21:27<17:24, 1.23s/it] Evaluating eval...: 56%|█████▌ | 1055/1900 [21:29<17:01, 1.21s/it] Evaluating eval...: 56%|█████▌ | 1056/1900 [21:30<16:59, 1.21s/it] Evaluating eval...: 56%|█████▌ | 1057/1900 [21:31<17:14, 1.23s/it] Evaluating eval...: 56%|█████▌ | 1058/1900 [21:32<17:20, 1.24s/it] Evaluating eval...: 56%|█████▌ | 1059/1900 [21:33<16:55, 1.21s/it] Evaluating eval...: 56%|█████▌ | 1060/1900 [21:35<16:40, 1.19s/it] Evaluating eval...: 56%|█████▌ | 1061/1900 [21:36<16:48, 1.20s/it] Evaluating eval...: 56%|█████▌ | 1062/1900 [21:37<16:37, 1.19s/it] Evaluating eval...: 56%|█████▌ | 1063/1900 [21:38<16:37, 1.19s/it] Evaluating eval...: 56%|█████▌ | 1064/1900 [21:39<16:45, 1.20s/it] Evaluating eval...: 56%|█████▌ | 1065/1900 [21:41<16:52, 1.21s/it] Evaluating eval...: 56%|█████▌ | 1066/1900 [21:42<16:50, 1.21s/it] Evaluating eval...: 56%|█████▌ | 1067/1900 [21:43<17:14, 1.24s/it] Evaluating eval...: 56%|█████▌ | 1068/1900 [21:44<16:55, 1.22s/it] Evaluating eval...: 56%|█████▋ | 1069/1900 [21:46<16:53, 1.22s/it] Evaluating eval...: 56%|█████▋ | 1070/1900 [21:47<16:39, 1.20s/it] Evaluating eval...: 56%|█████▋ | 1071/1900 [21:48<17:07, 1.24s/it] Evaluating eval...: 56%|█████▋ | 1072/1900 [21:49<17:12, 1.25s/it] Evaluating eval...: 56%|█████▋ | 1073/1900 [21:50<16:50, 1.22s/it] Evaluating eval...: 57%|█████▋ | 1074/1900 [21:52<16:36, 1.21s/it] Evaluating eval...: 57%|█████▋ | 1075/1900 [21:53<16:35, 1.21s/it] Evaluating eval...: 57%|█████▋ | 1076/1900 [21:54<16:36, 1.21s/it] Evaluating eval...: 57%|█████▋ | 1077/1900 [21:55<16:32, 1.21s/it] Evaluating eval...: 57%|█████▋ | 1078/1900 [21:56<16:09, 1.18s/it] Evaluating eval...: 57%|█████▋ | 1079/1900 [21:58<16:34, 1.21s/it] Evaluating eval...: 57%|█████▋ | 1080/1900 [21:59<17:04, 1.25s/it] Evaluating eval...: 57%|█████▋ | 1081/1900 [22:00<16:51, 1.23s/it] Evaluating eval...: 57%|█████▋ | 1082/1900 [22:01<16:42, 1.23s/it] Evaluating eval...: 57%|█████▋ | 1083/1900 [22:03<16:59, 1.25s/it] Evaluating eval...: 57%|█████▋ | 1084/1900 [22:04<16:44, 1.23s/it] Evaluating eval...: 57%|█████▋ | 1085/1900 [22:05<16:51, 1.24s/it] Evaluating eval...: 57%|█████▋ | 1086/1900 [22:06<16:49, 1.24s/it] Evaluating eval...: 57%|█████▋ | 1087/1900 [22:08<16:32, 1.22s/it] Evaluating eval...: 57%|█████▋ | 1088/1900 [22:09<16:28, 1.22s/it] Evaluating eval...: 57%|█████▋ | 1089/1900 [22:10<16:38, 1.23s/it] Evaluating eval...: 57%|█████▋ | 1090/1900 [22:11<16:17, 1.21s/it] Evaluating eval...: 57%|█████▋ | 1091/1900 [22:12<16:06, 1.19s/it] Evaluating eval...: 57%|█████▋ | 1092/1900 [22:14<16:29, 1.22s/it] Evaluating eval...: 58%|█████▊ | 1093/1900 [22:15<16:13, 1.21s/it] Evaluating eval...: 58%|█████▊ | 1094/1900 [22:16<16:14, 1.21s/it] Evaluating eval...: 58%|█████▊ | 1095/1900 [22:17<16:04, 1.20s/it] Evaluating eval...: 58%|█████▊ | 1096/1900 [22:18<15:49, 1.18s/it] Evaluating eval...: 58%|█████▊ | 1097/1900 [22:19<15:43, 1.18s/it] Evaluating eval...: 58%|█████▊ | 1098/1900 [22:21<16:16, 1.22s/it] Evaluating eval...: 58%|█████▊ | 1099/1900 [22:22<16:44, 1.25s/it] Evaluating eval...: 58%|█████▊ | 1100/1900 [22:23<16:34, 1.24s/it] Evaluating eval...: 58%|█████▊ | 1101/1900 [22:25<16:12, 1.22s/it] Evaluating eval...: 58%|█████▊ | 1102/1900 [22:26<16:05, 1.21s/it] Evaluating eval...: 58%|█████▊ | 1103/1900 [22:27<16:31, 1.24s/it] Evaluating eval...: 58%|█████▊ | 1104/1900 [22:28<16:10, 1.22s/it] Evaluating eval...: 58%|█████▊ | 1105/1900 [22:30<17:58, 1.36s/it] Evaluating eval...: 58%|█████▊ | 1106/1900 [22:31<17:31, 1.32s/it] Evaluating eval...: 58%|█████▊ | 1107/1900 [22:32<17:25, 1.32s/it] Evaluating eval...: 58%|█████▊ | 1108/1900 [22:34<17:07, 1.30s/it] Evaluating eval...: 58%|█████▊ | 1109/1900 [22:35<16:39, 1.26s/it] Evaluating eval...: 58%|█████▊ | 1110/1900 [22:36<16:18, 1.24s/it] Evaluating eval...: 58%|█████▊ | 1111/1900 [22:37<16:36, 1.26s/it] Evaluating eval...: 59%|█████▊ | 1112/1900 [22:39<16:20, 1.24s/it] Evaluating eval...: 59%|█████▊ | 1113/1900 [22:40<16:12, 1.24s/it] Evaluating eval...: 59%|█████▊ | 1114/1900 [22:41<16:12, 1.24s/it] Evaluating eval...: 59%|█████▊ | 1115/1900 [22:42<16:16, 1.24s/it] Evaluating eval...: 59%|█████▊ | 1116/1900 [22:43<16:05, 1.23s/it] Evaluating eval...: 59%|█████▉ | 1117/1900 [22:45<16:00, 1.23s/it] Evaluating eval...: 59%|█████▉ | 1118/1900 [22:46<15:53, 1.22s/it] Evaluating eval...: 59%|█████▉ | 1119/1900 [22:47<15:54, 1.22s/it] Evaluating eval...: 59%|█████▉ | 1120/1900 [22:48<15:56, 1.23s/it] Evaluating eval...: 59%|█████▉ | 1121/1900 [22:50<15:56, 1.23s/it] Evaluating eval...: 59%|█████▉ | 1122/1900 [22:51<15:35, 1.20s/it] Evaluating eval...: 59%|█████▉ | 1123/1900 [22:52<15:47, 1.22s/it] Evaluating eval...: 59%|█████▉ | 1124/1900 [22:53<15:46, 1.22s/it] Evaluating eval...: 59%|█████▉ | 1125/1900 [22:54<15:35, 1.21s/it] Evaluating eval...: 59%|█████▉ | 1126/1900 [22:56<15:31, 1.20s/it] Evaluating eval...: 59%|█████▉ | 1127/1900 [22:57<15:32, 1.21s/it] Evaluating eval...: 59%|█████▉ | 1128/1900 [22:58<15:54, 1.24s/it] Evaluating eval...: 59%|█████▉ | 1129/1900 [22:59<15:48, 1.23s/it] Evaluating eval...: 59%|█████▉ | 1130/1900 [23:01<15:36, 1.22s/it] Evaluating eval...: 60%|█████▉ | 1131/1900 [23:02<15:29, 1.21s/it] Evaluating eval...: 60%|█████▉ | 1132/1900 [23:03<15:37, 1.22s/it] Evaluating eval...: 60%|█████▉ | 1133/1900 [23:04<15:45, 1.23s/it] Evaluating eval...: 60%|█████▉ | 1134/1900 [23:05<15:39, 1.23s/it] Evaluating eval...: 60%|█████▉ | 1135/1900 [23:07<16:03, 1.26s/it] Evaluating eval...: 60%|█████▉ | 1136/1900 [23:08<15:44, 1.24s/it] Evaluating eval...: 60%|█████▉ | 1137/1900 [23:09<15:30, 1.22s/it] Evaluating eval...: 60%|█████▉ | 1138/1900 [23:10<15:54, 1.25s/it] Evaluating eval...: 60%|█████▉ | 1139/1900 [23:12<15:54, 1.25s/it] Evaluating eval...: 60%|██████ | 1140/1900 [23:13<15:52, 1.25s/it] Evaluating eval...: 60%|██████ | 1141/1900 [23:14<15:51, 1.25s/it] Evaluating eval...: 60%|██████ | 1142/1900 [23:15<15:25, 1.22s/it] Evaluating eval...: 60%|██████ | 1143/1900 [23:17<15:09, 1.20s/it] Evaluating eval...: 60%|██████ | 1144/1900 [23:18<15:05, 1.20s/it] Evaluating eval...: 60%|██████ | 1145/1900 [23:19<15:19, 1.22s/it] Evaluating eval...: 60%|██████ | 1146/1900 [23:20<15:25, 1.23s/it] Evaluating eval...: 60%|██████ | 1147/1900 [23:22<15:40, 1.25s/it] Evaluating eval...: 60%|██████ | 1148/1900 [23:23<15:40, 1.25s/it] Evaluating eval...: 60%|██████ | 1149/1900 [23:24<15:17, 1.22s/it] Evaluating eval...: 61%|██████ | 1150/1900 [23:25<15:17, 1.22s/it] Evaluating eval...: 61%|██████ | 1151/1900 [23:26<15:03, 1.21s/it] Evaluating eval...: 61%|██████ | 1152/1900 [23:27<14:54, 1.20s/it] Evaluating eval...: 61%|██████ | 1153/1900 [23:29<15:08, 1.22s/it] Evaluating eval...: 61%|██████ | 1154/1900 [23:30<14:56, 1.20s/it] Evaluating eval...: 61%|██████ | 1155/1900 [23:31<15:02, 1.21s/it] Evaluating eval...: 61%|██████ | 1156/1900 [23:32<14:53, 1.20s/it] Evaluating eval...: 61%|██████ | 1157/1900 [23:34<14:51, 1.20s/it] Evaluating eval...: 61%|██████ | 1158/1900 [23:35<15:13, 1.23s/it] Evaluating eval...: 61%|██████ | 1159/1900 [23:36<15:08, 1.23s/it] Evaluating eval...: 61%|██████ | 1160/1900 [23:37<15:16, 1.24s/it] Evaluating eval...: 61%|██████ | 1161/1900 [23:39<15:23, 1.25s/it] Evaluating eval...: 61%|██████ | 1162/1900 [23:40<15:08, 1.23s/it] Evaluating eval...: 61%|██████ | 1163/1900 [23:41<15:00, 1.22s/it] Evaluating eval...: 61%|██████▏ | 1164/1900 [23:42<14:43, 1.20s/it] Evaluating eval...: 61%|██████▏ | 1165/1900 [23:43<14:38, 1.20s/it] Evaluating eval...: 61%|██████▏ | 1166/1900 [23:45<14:43, 1.20s/it] Evaluating eval...: 61%|██████▏ | 1167/1900 [23:46<14:53, 1.22s/it] Evaluating eval...: 61%|██████▏ | 1168/1900 [23:47<14:58, 1.23s/it] Evaluating eval...: 62%|██████▏ | 1169/1900 [23:48<14:52, 1.22s/it] Evaluating eval...: 62%|██████▏ | 1170/1900 [23:49<14:50, 1.22s/it] Evaluating eval...: 62%|██████▏ | 1171/1900 [23:51<15:06, 1.24s/it] Evaluating eval...: 62%|██████▏ | 1172/1900 [23:52<15:08, 1.25s/it] Evaluating eval...: 62%|██████▏ | 1173/1900 [23:53<14:53, 1.23s/it] Evaluating eval...: 62%|██████▏ | 1174/1900 [23:54<14:38, 1.21s/it] Evaluating eval...: 62%|██████▏ | 1175/1900 [23:56<14:48, 1.23s/it] Evaluating eval...: 62%|██████▏ | 1176/1900 [23:57<14:57, 1.24s/it] Evaluating eval...: 62%|██████▏ | 1177/1900 [23:58<14:36, 1.21s/it] Evaluating eval...: 62%|██████▏ | 1178/1900 [23:59<14:24, 1.20s/it] Evaluating eval...: 62%|██████▏ | 1179/1900 [24:00<14:28, 1.20s/it] Evaluating eval...: 62%|██████▏ | 1180/1900 [24:02<14:37, 1.22s/it] Evaluating eval...: 62%|██████▏ | 1181/1900 [24:03<14:24, 1.20s/it] Evaluating eval...: 62%|██████▏ | 1182/1900 [24:04<14:43, 1.23s/it] Evaluating eval...: 62%|██████▏ | 1183/1900 [24:05<14:31, 1.21s/it] Evaluating eval...: 62%|██████▏ | 1184/1900 [24:07<14:36, 1.22s/it] Evaluating eval...: 62%|██████▏ | 1185/1900 [24:08<14:34, 1.22s/it] Evaluating eval...: 62%|██████▏ | 1186/1900 [24:09<14:35, 1.23s/it] Evaluating eval...: 62%|██████▏ | 1187/1900 [24:10<14:26, 1.22s/it] Evaluating eval...: 63%|██████▎ | 1188/1900 [24:11<14:18, 1.21s/it] Evaluating eval...: 63%|██████▎ | 1189/1900 [24:13<14:15, 1.20s/it] Evaluating eval...: 63%|██████▎ | 1190/1900 [24:14<14:07, 1.19s/it] Evaluating eval...: 63%|██████▎ | 1191/1900 [24:15<14:13, 1.20s/it] Evaluating eval...: 63%|██████▎ | 1192/1900 [24:16<14:32, 1.23s/it] Evaluating eval...: 63%|██████▎ | 1193/1900 [24:18<14:23, 1.22s/it] Evaluating eval...: 63%|██████▎ | 1194/1900 [24:19<14:29, 1.23s/it] Evaluating eval...: 63%|██████▎ | 1195/1900 [24:20<14:21, 1.22s/it] Evaluating eval...: 63%|██████▎ | 1196/1900 [24:21<14:16, 1.22s/it] Evaluating eval...: 63%|██████▎ | 1197/1900 [24:22<14:16, 1.22s/it] Evaluating eval...: 63%|██████▎ | 1198/1900 [24:24<14:12, 1.21s/it] Evaluating eval...: 63%|██████▎ | 1199/1900 [24:25<14:31, 1.24s/it] Evaluating eval...: 63%|██████▎ | 1200/1900 [24:26<14:25, 1.24s/it] Evaluating eval...: 63%|██████▎ | 1201/1900 [24:27<14:20, 1.23s/it] Evaluating eval...: 63%|██████▎ | 1202/1900 [24:28<14:01, 1.21s/it] Evaluating eval...: 63%|██████▎ | 1203/1900 [24:30<14:20, 1.23s/it] Evaluating eval...: 63%|██████▎ | 1204/1900 [24:31<14:21, 1.24s/it] Evaluating eval...: 63%|██████▎ | 1205/1900 [24:32<14:14, 1.23s/it] Evaluating eval...: 63%|██████▎ | 1206/1900 [24:34<14:21, 1.24s/it] Evaluating eval...: 64%|██████▎ | 1207/1900 [24:35<14:10, 1.23s/it] Evaluating eval...: 64%|██████▎ | 1208/1900 [24:36<14:01, 1.22s/it] Evaluating eval...: 64%|██████▎ | 1209/1900 [24:37<13:43, 1.19s/it] Evaluating eval...: 64%|██████▎ | 1210/1900 [24:38<13:53, 1.21s/it] Evaluating eval...: 64%|██████▎ | 1211/1900 [24:40<13:56, 1.21s/it] Evaluating eval...: 64%|██████▍ | 1212/1900 [24:41<13:55, 1.21s/it] Evaluating eval...: 64%|██████▍ | 1213/1900 [24:42<13:44, 1.20s/it] Evaluating eval...: 64%|██████▍ | 1214/1900 [24:43<13:38, 1.19s/it] Evaluating eval...: 64%|██████▍ | 1215/1900 [24:44<13:32, 1.19s/it] Evaluating eval...: 64%|██████▍ | 1216/1900 [24:45<13:37, 1.19s/it] Evaluating eval...: 64%|██████▍ | 1217/1900 [24:47<13:46, 1.21s/it] Evaluating eval...: 64%|██████▍ | 1218/1900 [24:48<13:55, 1.23s/it] Evaluating eval...: 64%|██████▍ | 1219/1900 [24:49<13:45, 1.21s/it] Evaluating eval...: 64%|██████▍ | 1220/1900 [24:50<13:56, 1.23s/it] Evaluating eval...: 64%|██████▍ | 1221/1900 [24:52<13:52, 1.23s/it] Evaluating eval...: 64%|██████▍ | 1222/1900 [24:53<13:53, 1.23s/it] Evaluating eval...: 64%|██████▍ | 1223/1900 [24:54<13:47, 1.22s/it] Evaluating eval...: 64%|██████▍ | 1224/1900 [24:55<13:29, 1.20s/it] Evaluating eval...: 64%|██████▍ | 1225/1900 [24:56<13:38, 1.21s/it] Evaluating eval...: 65%|██████▍ | 1226/1900 [24:58<13:31, 1.20s/it] Evaluating eval...: 65%|██████▍ | 1227/1900 [24:59<13:36, 1.21s/it] Evaluating eval...: 65%|██████▍ | 1228/1900 [25:00<13:20, 1.19s/it] Evaluating eval...: 65%|██████▍ | 1229/1900 [25:01<13:17, 1.19s/it] Evaluating eval...: 65%|██████▍ | 1230/1900 [25:02<13:11, 1.18s/it] Evaluating eval...: 65%|██████▍ | 1231/1900 [25:04<13:21, 1.20s/it] Evaluating eval...: 65%|██████▍ | 1232/1900 [25:05<13:23, 1.20s/it] Evaluating eval...: 65%|██████▍ | 1233/1900 [25:06<13:16, 1.19s/it] Evaluating eval...: 65%|██████▍ | 1234/1900 [25:07<13:28, 1.21s/it] Evaluating eval...: 65%|██████▌ | 1235/1900 [25:08<13:34, 1.22s/it] Evaluating eval...: 65%|██████▌ | 1236/1900 [25:10<13:32, 1.22s/it] Evaluating eval...: 65%|██████▌ | 1237/1900 [25:11<13:24, 1.21s/it] Evaluating eval...: 65%|██████▌ | 1238/1900 [25:12<13:21, 1.21s/it] Evaluating eval...: 65%|██████▌ | 1239/1900 [25:13<13:35, 1.23s/it] Evaluating eval...: 65%|██████▌ | 1240/1900 [25:15<13:51, 1.26s/it] Evaluating eval...: 65%|██████▌ | 1241/1900 [25:16<13:30, 1.23s/it] Evaluating eval...: 65%|██████▌ | 1242/1900 [25:17<13:27, 1.23s/it] Evaluating eval...: 65%|██████▌ | 1243/1900 [25:18<13:47, 1.26s/it] Evaluating eval...: 65%|██████▌ | 1244/1900 [25:20<13:25, 1.23s/it] Evaluating eval...: 66%|██████▌ | 1245/1900 [25:21<13:13, 1.21s/it] Evaluating eval...: 66%|██████▌ | 1246/1900 [25:22<13:23, 1.23s/it] Evaluating eval...: 66%|██████▌ | 1247/1900 [25:23<13:08, 1.21s/it] Evaluating eval...: 66%|██████▌ | 1248/1900 [25:24<12:58, 1.19s/it] Evaluating eval...: 66%|██████▌ | 1249/1900 [25:26<13:10, 1.21s/it] Evaluating eval...: 66%|██████▌ | 1250/1900 [25:27<13:06, 1.21s/it] Evaluating eval...: 66%|██████▌ | 1251/1900 [25:28<12:58, 1.20s/it] Evaluating eval...: 66%|██████▌ | 1252/1900 [25:29<12:49, 1.19s/it] Evaluating eval...: 66%|██████▌ | 1253/1900 [25:30<12:53, 1.20s/it] Evaluating eval...: 66%|██████▌ | 1254/1900 [25:32<12:51, 1.19s/it] Evaluating eval...: 66%|██████▌ | 1255/1900 [25:33<13:09, 1.22s/it] Evaluating eval...: 66%|██████▌ | 1256/1900 [25:34<13:15, 1.24s/it] Evaluating eval...: 66%|██████▌ | 1257/1900 [25:35<12:56, 1.21s/it] Evaluating eval...: 66%|██████▌ | 1258/1900 [25:36<12:59, 1.21s/it] Evaluating eval...: 66%|██████▋ | 1259/1900 [25:38<13:06, 1.23s/it] Evaluating eval...: 66%|██████▋ | 1260/1900 [25:39<13:07, 1.23s/it] Evaluating eval...: 66%|██████▋ | 1261/1900 [25:40<13:07, 1.23s/it] Evaluating eval...: 66%|██████▋ | 1262/1900 [25:41<12:52, 1.21s/it] Evaluating eval...: 66%|██████▋ | 1263/1900 [25:43<12:48, 1.21s/it] Evaluating eval...: 67%|██████▋ | 1264/1900 [25:44<12:43, 1.20s/it] Evaluating eval...: 67%|██████▋ | 1265/1900 [25:45<12:39, 1.20s/it] Evaluating eval...: 67%|██████▋ | 1266/1900 [25:46<12:57, 1.23s/it] Evaluating eval...: 67%|██████▋ | 1267/1900 [25:47<12:47, 1.21s/it] Evaluating eval...: 67%|██████▋ | 1268/1900 [25:49<12:44, 1.21s/it] Evaluating eval...: 67%|██████▋ | 1269/1900 [25:50<12:44, 1.21s/it] Evaluating eval...: 67%|██████▋ | 1270/1900 [25:51<12:29, 1.19s/it] Evaluating eval...: 67%|██████▋ | 1271/1900 [25:52<12:31, 1.20s/it] Evaluating eval...: 67%|██████▋ | 1272/1900 [25:53<12:20, 1.18s/it] Evaluating eval...: 67%|██████▋ | 1273/1900 [25:55<12:23, 1.19s/it] Evaluating eval...: 67%|██████▋ | 1274/1900 [25:56<12:28, 1.20s/it] Evaluating eval...: 67%|██████▋ | 1275/1900 [25:57<12:23, 1.19s/it] Evaluating eval...: 67%|██████▋ | 1276/1900 [25:58<12:24, 1.19s/it] Evaluating eval...: 67%|██████▋ | 1277/1900 [25:59<12:21, 1.19s/it] Evaluating eval...: 67%|██████▋ | 1278/1900 [26:00<12:16, 1.18s/it] Evaluating eval...: 67%|██████▋ | 1279/1900 [26:02<12:09, 1.17s/it] Evaluating eval...: 67%|██████▋ | 1280/1900 [26:03<12:06, 1.17s/it] Evaluating eval...: 67%|██████▋ | 1281/1900 [26:04<11:58, 1.16s/it] Evaluating eval...: 67%|██████▋ | 1282/1900 [26:05<11:56, 1.16s/it] Evaluating eval...: 68%|██████▊ | 1283/1900 [26:06<12:02, 1.17s/it] Evaluating eval...: 68%|██████▊ | 1284/1900 [26:07<12:04, 1.18s/it] Evaluating eval...: 68%|██████▊ | 1285/1900 [26:09<12:15, 1.20s/it] Evaluating eval...: 68%|██████▊ | 1286/1900 [26:10<12:12, 1.19s/it] Evaluating eval...: 68%|██████▊ | 1287/1900 [26:11<12:26, 1.22s/it] Evaluating eval...: 68%|██████▊ | 1288/1900 [26:12<12:27, 1.22s/it] Evaluating eval...: 68%|██████▊ | 1289/1900 [26:14<12:15, 1.20s/it] Evaluating eval...: 68%|██████▊ | 1290/1900 [26:15<12:12, 1.20s/it] Evaluating eval...: 68%|██████▊ | 1291/1900 [26:16<12:14, 1.21s/it] Evaluating eval...: 68%|██████▊ | 1292/1900 [26:17<12:25, 1.23s/it] Evaluating eval...: 68%|██████▊ | 1293/1900 [26:18<12:24, 1.23s/it] Evaluating eval...: 68%|██████▊ | 1294/1900 [26:20<12:25, 1.23s/it] Evaluating eval...: 68%|██████▊ | 1295/1900 [26:21<12:11, 1.21s/it] Evaluating eval...: 68%|██████▊ | 1296/1900 [26:22<12:12, 1.21s/it] Evaluating eval...: 68%|██████▊ | 1297/1900 [26:23<11:57, 1.19s/it] Evaluating eval...: 68%|██████▊ | 1298/1900 [26:24<12:07, 1.21s/it] Evaluating eval...: 68%|██████▊ | 1299/1900 [26:26<12:03, 1.20s/it] Evaluating eval...: 68%|██████▊ | 1300/1900 [26:27<12:14, 1.22s/it] Evaluating eval...: 68%|██████▊ | 1301/1900 [26:28<12:10, 1.22s/it] Evaluating eval...: 69%|██████▊ | 1302/1900 [26:29<12:11, 1.22s/it] Evaluating eval...: 69%|██████▊ | 1303/1900 [26:31<12:11, 1.23s/it] Evaluating eval...: 69%|██████▊ | 1304/1900 [26:32<12:09, 1.22s/it] Evaluating eval...: 69%|██████▊ | 1305/1900 [26:33<12:02, 1.21s/it] Evaluating eval...: 69%|██████▊ | 1306/1900 [26:34<12:05, 1.22s/it] Evaluating eval...: 69%|██████▉ | 1307/1900 [26:35<11:53, 1.20s/it] Evaluating eval...: 69%|██████▉ | 1308/1900 [26:37<11:51, 1.20s/it] Evaluating eval...: 69%|██████▉ | 1309/1900 [26:38<11:48, 1.20s/it] Evaluating eval...: 69%|██████▉ | 1310/1900 [26:39<11:43, 1.19s/it] Evaluating eval...: 69%|██████▉ | 1311/1900 [26:40<11:44, 1.20s/it] Evaluating eval...: 69%|██████▉ | 1312/1900 [26:41<11:51, 1.21s/it] Evaluating eval...: 69%|██████▉ | 1313/1900 [26:43<11:53, 1.22s/it] Evaluating eval...: 69%|██████▉ | 1314/1900 [26:44<11:46, 1.21s/it] Evaluating eval...: 69%|██████▉ | 1315/1900 [26:45<11:46, 1.21s/it] Evaluating eval...: 69%|██████▉ | 1316/1900 [26:46<11:48, 1.21s/it] Evaluating eval...: 69%|██████▉ | 1317/1900 [26:47<11:43, 1.21s/it] Evaluating eval...: 69%|██████▉ | 1318/1900 [26:49<11:51, 1.22s/it] Evaluating eval...: 69%|██████▉ | 1319/1900 [26:50<11:48, 1.22s/it] Evaluating eval...: 69%|██████▉ | 1320/1900 [26:51<11:37, 1.20s/it] Evaluating eval...: 70%|██████▉ | 1321/1900 [26:52<11:41, 1.21s/it] Evaluating eval...: 70%|██████▉ | 1322/1900 [26:54<11:39, 1.21s/it] Evaluating eval...: 70%|██████▉ | 1323/1900 [26:55<11:35, 1.20s/it] Evaluating eval...: 70%|██████▉ | 1324/1900 [26:56<11:27, 1.19s/it] Evaluating eval...: 70%|██████▉ | 1325/1900 [26:57<11:20, 1.18s/it] Evaluating eval...: 70%|██████▉ | 1326/1900 [26:58<11:14, 1.18s/it] Evaluating eval...: 70%|██████▉ | 1327/1900 [26:59<11:10, 1.17s/it] Evaluating eval...: 70%|██████▉ | 1328/1900 [27:01<11:30, 1.21s/it] Evaluating eval...: 70%|██████▉ | 1329/1900 [27:02<11:25, 1.20s/it] Evaluating eval...: 70%|███████ | 1330/1900 [27:03<11:32, 1.22s/it] Evaluating eval...: 70%|███████ | 1331/1900 [27:04<11:25, 1.20s/it] Evaluating eval...: 70%|███████ | 1332/1900 [27:06<11:25, 1.21s/it] Evaluating eval...: 70%|███████ | 1333/1900 [27:07<11:20, 1.20s/it] Evaluating eval...: 70%|███████ | 1334/1900 [27:08<11:20, 1.20s/it] Evaluating eval...: 70%|███████ | 1335/1900 [27:09<11:20, 1.20s/it] Evaluating eval...: 70%|███████ | 1336/1900 [27:10<11:24, 1.21s/it] Evaluating eval...: 70%|███████ | 1337/1900 [27:12<11:37, 1.24s/it] Evaluating eval...: 70%|███████ | 1338/1900 [27:13<11:26, 1.22s/it] Evaluating eval...: 70%|███████ | 1339/1900 [27:14<11:19, 1.21s/it] Evaluating eval...: 71%|███████ | 1340/1900 [27:15<11:15, 1.21s/it] Evaluating eval...: 71%|███████ | 1341/1900 [27:16<11:05, 1.19s/it] Evaluating eval...: 71%|███████ | 1342/1900 [27:18<11:21, 1.22s/it] Evaluating eval...: 71%|███████ | 1343/1900 [27:19<11:17, 1.22s/it] Evaluating eval...: 71%|███████ | 1344/1900 [27:20<11:15, 1.22s/it] Evaluating eval...: 71%|███████ | 1345/1900 [27:21<11:19, 1.23s/it] Evaluating eval...: 71%|███████ | 1346/1900 [27:23<11:33, 1.25s/it] Evaluating eval...: 71%|███████ | 1347/1900 [27:24<11:26, 1.24s/it] Evaluating eval...: 71%|███████ | 1348/1900 [27:25<11:11, 1.22s/it] Evaluating eval...: 71%|███████ | 1349/1900 [27:26<11:24, 1.24s/it] Evaluating eval...: 71%|███████ | 1350/1900 [27:28<11:16, 1.23s/it] Evaluating eval...: 71%|███████ | 1351/1900 [27:29<11:16, 1.23s/it] Evaluating eval...: 71%|███████ | 1352/1900 [27:30<11:13, 1.23s/it] Evaluating eval...: 71%|███████ | 1353/1900 [27:31<11:21, 1.25s/it] Evaluating eval...: 71%|███████▏ | 1354/1900 [27:32<11:15, 1.24s/it] Evaluating eval...: 71%|███████▏ | 1355/1900 [27:34<11:06, 1.22s/it] Evaluating eval...: 71%|███████▏ | 1356/1900 [27:35<11:14, 1.24s/it] Evaluating eval...: 71%|███████▏ | 1357/1900 [27:36<11:02, 1.22s/it] Evaluating eval...: 71%|███████▏ | 1358/1900 [27:37<10:53, 1.21s/it] Evaluating eval...: 72%|███████▏ | 1359/1900 [27:39<10:55, 1.21s/it] Evaluating eval...: 72%|███████▏ | 1360/1900 [27:40<10:51, 1.21s/it] Evaluating eval...: 72%|███████▏ | 1361/1900 [27:41<11:15, 1.25s/it] Evaluating eval...: 72%|███████▏ | 1362/1900 [27:42<10:59, 1.23s/it] Evaluating eval...: 72%|███████▏ | 1363/1900 [27:43<11:01, 1.23s/it] Evaluating eval...: 72%|███████▏ | 1364/1900 [27:45<10:52, 1.22s/it] Evaluating eval...: 72%|███████▏ | 1365/1900 [27:46<10:48, 1.21s/it] Evaluating eval...: 72%|███████▏ | 1366/1900 [27:47<10:39, 1.20s/it] Evaluating eval...: 72%|███████▏ | 1367/1900 [27:48<10:48, 1.22s/it] Evaluating eval...: 72%|███████▏ | 1368/1900 [27:50<10:54, 1.23s/it] Evaluating eval...: 72%|███████▏ | 1369/1900 [27:51<10:48, 1.22s/it] Evaluating eval...: 72%|███████▏ | 1370/1900 [27:52<10:42, 1.21s/it] Evaluating eval...: 72%|███████▏ | 1371/1900 [27:53<10:42, 1.22s/it] Evaluating eval...: 72%|███████▏ | 1372/1900 [27:54<10:38, 1.21s/it] Evaluating eval...: 72%|███████▏ | 1373/1900 [27:56<10:30, 1.20s/it] Evaluating eval...: 72%|███████▏ | 1374/1900 [27:57<10:27, 1.19s/it] Evaluating eval...: 72%|███████▏ | 1375/1900 [27:58<10:30, 1.20s/it] Evaluating eval...: 72%|███████▏ | 1376/1900 [27:59<10:30, 1.20s/it] Evaluating eval...: 72%|███████▏ | 1377/1900 [28:00<10:23, 1.19s/it] Evaluating eval...: 73%|███████▎ | 1378/1900 [28:01<10:14, 1.18s/it] Evaluating eval...: 73%|███████▎ | 1379/1900 [28:03<10:15, 1.18s/it] Evaluating eval...: 73%|███████▎ | 1380/1900 [28:04<10:19, 1.19s/it] Evaluating eval...: 73%|███████▎ | 1381/1900 [28:05<10:30, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1382/1900 [28:06<10:27, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1383/1900 [28:08<10:27, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1384/1900 [28:09<10:21, 1.20s/it] Evaluating eval...: 73%|███████▎ | 1385/1900 [28:10<10:21, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1386/1900 [28:11<10:21, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1387/1900 [28:12<10:13, 1.20s/it] Evaluating eval...: 73%|███████▎ | 1388/1900 [28:14<10:08, 1.19s/it] Evaluating eval...: 73%|███████▎ | 1389/1900 [28:15<10:03, 1.18s/it] Evaluating eval...: 73%|███████▎ | 1390/1900 [28:16<10:14, 1.20s/it] Evaluating eval...: 73%|███████▎ | 1391/1900 [28:17<10:17, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1392/1900 [28:18<10:10, 1.20s/it] Evaluating eval...: 73%|███████▎ | 1393/1900 [28:20<10:03, 1.19s/it] Evaluating eval...: 73%|███████▎ | 1394/1900 [28:21<10:12, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1395/1900 [28:22<10:09, 1.21s/it] Evaluating eval...: 73%|███████▎ | 1396/1900 [28:23<10:09, 1.21s/it] Evaluating eval...: 74%|███████▎ | 1397/1900 [28:24<10:00, 1.19s/it] Evaluating eval...: 74%|███████▎ | 1398/1900 [28:26<10:03, 1.20s/it] Evaluating eval...: 74%|███████▎ | 1399/1900 [28:27<10:02, 1.20s/it] Evaluating eval...: 74%|███████▎ | 1400/1900 [28:28<09:53, 1.19s/it] Evaluating eval...: 74%|███████▎ | 1401/1900 [28:29<10:03, 1.21s/it] Evaluating eval...: 74%|███████▍ | 1402/1900 [28:30<09:52, 1.19s/it] Evaluating eval...: 74%|███████▍ | 1403/1900 [28:31<09:44, 1.18s/it] Evaluating eval...: 74%|███████▍ | 1404/1900 [28:33<09:41, 1.17s/it] Evaluating eval...: 74%|███████▍ | 1405/1900 [28:34<09:37, 1.17s/it] Evaluating eval...: 74%|███████▍ | 1406/1900 [28:35<09:40, 1.18s/it] Evaluating eval...: 74%|███████▍ | 1407/1900 [28:36<09:49, 1.20s/it] Evaluating eval...: 74%|███████▍ | 1408/1900 [28:37<09:57, 1.21s/it] Evaluating eval...: 74%|███████▍ | 1409/1900 [28:39<09:56, 1.22s/it] Evaluating eval...: 74%|███████▍ | 1410/1900 [28:40<09:49, 1.20s/it] Evaluating eval...: 74%|███████▍ | 1411/1900 [28:41<09:52, 1.21s/it] Evaluating eval...: 74%|███████▍ | 1412/1900 [28:42<09:46, 1.20s/it] Evaluating eval...: 74%|███████▍ | 1413/1900 [28:43<09:43, 1.20s/it] Evaluating eval...: 74%|███████▍ | 1414/1900 [28:45<09:41, 1.20s/it] Evaluating eval...: 74%|███████▍ | 1415/1900 [28:46<09:37, 1.19s/it] Evaluating eval...: 75%|███████▍ | 1416/1900 [28:47<09:30, 1.18s/it] Evaluating eval...: 75%|███████▍ | 1417/1900 [28:48<09:32, 1.19s/it] Evaluating eval...: 75%|███████▍ | 1418/1900 [28:49<09:27, 1.18s/it] Evaluating eval...: 75%|███████▍ | 1419/1900 [28:51<09:42, 1.21s/it] Evaluating eval...: 75%|███████▍ | 1420/1900 [28:52<09:46, 1.22s/it] Evaluating eval...: 75%|███████▍ | 1421/1900 [28:53<09:39, 1.21s/it] Evaluating eval...: 75%|███████▍ | 1422/1900 [28:54<09:46, 1.23s/it] Evaluating eval...: 75%|███████▍ | 1423/1900 [28:56<09:44, 1.23s/it] Evaluating eval...: 75%|███████▍ | 1424/1900 [28:57<09:53, 1.25s/it] Evaluating eval...: 75%|███████▌ | 1425/1900 [28:58<09:41, 1.22s/it] Evaluating eval...: 75%|███████▌ | 1426/1900 [28:59<09:36, 1.22s/it] Evaluating eval...: 75%|███████▌ | 1427/1900 [29:00<09:26, 1.20s/it] Evaluating eval...: 75%|███████▌ | 1428/1900 [29:02<09:38, 1.23s/it] Evaluating eval...: 75%|███████▌ | 1429/1900 [29:03<09:41, 1.23s/it] Evaluating eval...: 75%|███████▌ | 1430/1900 [29:04<09:37, 1.23s/it] Evaluating eval...: 75%|███████▌ | 1431/1900 [29:05<09:39, 1.23s/it] Evaluating eval...: 75%|███████▌ | 1432/1900 [29:07<10:29, 1.35s/it] Evaluating eval...: 75%|███████▌ | 1433/1900 [29:08<10:06, 1.30s/it] Evaluating eval...: 75%|███████▌ | 1434/1900 [29:09<09:53, 1.27s/it] Evaluating eval...: 76%|███████▌ | 1435/1900 [29:11<09:41, 1.25s/it] Evaluating eval...: 76%|███████▌ | 1436/1900 [29:12<09:34, 1.24s/it] Evaluating eval...: 76%|███████▌ | 1437/1900 [29:13<09:25, 1.22s/it] Evaluating eval...: 76%|███████▌ | 1438/1900 [29:14<09:13, 1.20s/it] Evaluating eval...: 76%|███████▌ | 1439/1900 [29:15<09:15, 1.21s/it] Evaluating eval...: 76%|███████▌ | 1440/1900 [29:17<09:23, 1.23s/it] Evaluating eval...: 76%|███████▌ | 1441/1900 [29:18<09:17, 1.21s/it] Evaluating eval...: 76%|███████▌ | 1442/1900 [29:19<09:18, 1.22s/it] Evaluating eval...: 76%|███████▌ | 1443/1900 [29:20<09:26, 1.24s/it] Evaluating eval...: 76%|███████▌ | 1444/1900 [29:22<09:18, 1.22s/it] Evaluating eval...: 76%|███████▌ | 1445/1900 [29:23<09:14, 1.22s/it] Evaluating eval...: 76%|███████▌ | 1446/1900 [29:24<09:12, 1.22s/it] Evaluating eval...: 76%|███████▌ | 1447/1900 [29:25<09:04, 1.20s/it] Evaluating eval...: 76%|███████▌ | 1448/1900 [29:26<09:00, 1.20s/it] Evaluating eval...: 76%|███████▋ | 1449/1900 [29:28<09:05, 1.21s/it] Evaluating eval...: 76%|███████▋ | 1450/1900 [29:29<09:09, 1.22s/it] Evaluating eval...: 76%|███████▋ | 1451/1900 [29:30<09:11, 1.23s/it] Evaluating eval...: 76%|███████▋ | 1452/1900 [29:31<09:05, 1.22s/it] Evaluating eval...: 76%|███████▋ | 1453/1900 [29:32<09:02, 1.21s/it] Evaluating eval...: 77%|███████▋ | 1454/1900 [29:34<09:09, 1.23s/it] Evaluating eval...: 77%|███████▋ | 1455/1900 [29:35<09:06, 1.23s/it] Evaluating eval...: 77%|███████▋ | 1456/1900 [29:36<09:13, 1.25s/it] Evaluating eval...: 77%|███████▋ | 1457/1900 [29:37<09:05, 1.23s/it] Evaluating eval...: 77%|███████▋ | 1458/1900 [29:39<09:06, 1.24s/it] Evaluating eval...: 77%|███████▋ | 1459/1900 [29:40<08:59, 1.22s/it] Evaluating eval...: 77%|███████▋ | 1460/1900 [29:41<08:54, 1.21s/it] Evaluating eval...: 77%|███████▋ | 1461/1900 [29:42<08:52, 1.21s/it] Evaluating eval...: 77%|███████▋ | 1462/1900 [29:43<08:56, 1.22s/it] Evaluating eval...: 77%|███████▋ | 1463/1900 [29:45<08:52, 1.22s/it] Evaluating eval...: 77%|███████▋ | 1464/1900 [29:46<08:59, 1.24s/it] Evaluating eval...: 77%|███████▋ | 1465/1900 [29:47<08:51, 1.22s/it] Evaluating eval...: 77%|███████▋ | 1466/1900 [29:48<08:54, 1.23s/it] Evaluating eval...: 77%|███████▋ | 1467/1900 [29:50<08:47, 1.22s/it] Evaluating eval...: 77%|███████▋ | 1468/1900 [29:51<08:48, 1.22s/it] Evaluating eval...: 77%|███████▋ | 1469/1900 [29:52<08:52, 1.24s/it] Evaluating eval...: 77%|███████▋ | 1470/1900 [29:53<08:42, 1.21s/it] Evaluating eval...: 77%|███████▋ | 1471/1900 [29:55<08:46, 1.23s/it] Evaluating eval...: 77%|███████▋ | 1472/1900 [29:56<08:42, 1.22s/it] Evaluating eval...: 78%|███████▊ | 1473/1900 [29:57<08:42, 1.22s/it] Evaluating eval...: 78%|███████▊ | 1474/1900 [29:58<08:47, 1.24s/it] Evaluating eval...: 78%|███████▊ | 1475/1900 [29:59<08:43, 1.23s/it] Evaluating eval...: 78%|███████▊ | 1476/1900 [30:01<08:42, 1.23s/it] Evaluating eval...: 78%|███████▊ | 1477/1900 [30:02<08:38, 1.23s/it] Evaluating eval...: 78%|███████▊ | 1478/1900 [30:03<08:47, 1.25s/it] Evaluating eval...: 78%|███████▊ | 1479/1900 [30:04<08:51, 1.26s/it] Evaluating eval...: 78%|███████▊ | 1480/1900 [30:06<08:45, 1.25s/it] Evaluating eval...: 78%|███████▊ | 1481/1900 [30:07<08:38, 1.24s/it] Evaluating eval...: 78%|███████▊ | 1482/1900 [30:08<08:30, 1.22s/it] Evaluating eval...: 78%|███████▊ | 1483/1900 [30:09<08:22, 1.21s/it] Evaluating eval...: 78%|███████▊ | 1484/1900 [30:11<08:25, 1.22s/it] Evaluating eval...: 78%|███████▊ | 1485/1900 [30:12<08:33, 1.24s/it] Evaluating eval...: 78%|███████▊ | 1486/1900 [30:13<08:26, 1.22s/it] Evaluating eval...: 78%|███████▊ | 1487/1900 [30:14<08:33, 1.24s/it] Evaluating eval...: 78%|███████▊ | 1488/1900 [30:15<08:23, 1.22s/it] Evaluating eval...: 78%|███████▊ | 1489/1900 [30:17<08:16, 1.21s/it] Evaluating eval...: 78%|███████▊ | 1490/1900 [30:18<08:15, 1.21s/it] Evaluating eval...: 78%|███████▊ | 1491/1900 [30:19<08:12, 1.20s/it] Evaluating eval...: 79%|███████▊ | 1492/1900 [30:20<08:15, 1.21s/it] Evaluating eval...: 79%|███████▊ | 1493/1900 [30:22<08:24, 1.24s/it] Evaluating eval...: 79%|███████▊ | 1494/1900 [30:23<08:12, 1.21s/it] Evaluating eval...: 79%|███████▊ | 1495/1900 [30:24<08:05, 1.20s/it] Evaluating eval...: 79%|███████▊ | 1496/1900 [30:25<07:59, 1.19s/it] Evaluating eval...: 79%|███████▉ | 1497/1900 [30:26<07:53, 1.17s/it] Evaluating eval...: 79%|███████▉ | 1498/1900 [30:27<07:56, 1.19s/it] Evaluating eval...: 79%|███████▉ | 1499/1900 [30:29<07:58, 1.19s/it] Evaluating eval...: 79%|███████▉ | 1500/1900 [30:30<07:55, 1.19s/it] Evaluating eval...: 79%|███████▉ | 1501/1900 [30:31<07:51, 1.18s/it] Evaluating eval...: 79%|███████▉ | 1502/1900 [30:32<07:53, 1.19s/it] Evaluating eval...: 79%|███████▉ | 1503/1900 [30:33<07:54, 1.20s/it] Evaluating eval...: 79%|███████▉ | 1504/1900 [30:35<07:51, 1.19s/it] Evaluating eval...: 79%|███████▉ | 1505/1900 [30:36<07:50, 1.19s/it] Evaluating eval...: 79%|███████▉ | 1506/1900 [30:37<08:01, 1.22s/it] Evaluating eval...: 79%|███████▉ | 1507/1900 [30:38<07:54, 1.21s/it] Evaluating eval...: 79%|███████▉ | 1508/1900 [30:39<07:59, 1.22s/it] Evaluating eval...: 79%|███████▉ | 1509/1900 [30:41<07:56, 1.22s/it] Evaluating eval...: 79%|███████▉ | 1510/1900 [30:42<07:50, 1.21s/it] Evaluating eval...: 80%|███████▉ | 1511/1900 [30:43<07:52, 1.21s/it] Evaluating eval...: 80%|███████▉ | 1512/1900 [30:44<07:54, 1.22s/it] Evaluating eval...: 80%|███████▉ | 1513/1900 [30:46<07:59, 1.24s/it] Evaluating eval...: 80%|███████▉ | 1514/1900 [30:47<07:57, 1.24s/it] Evaluating eval...: 80%|███████▉ | 1515/1900 [30:48<08:09, 1.27s/it] Evaluating eval...: 80%|███████▉ | 1516/1900 [30:49<08:06, 1.27s/it] Evaluating eval...: 80%|███████▉ | 1517/1900 [30:51<07:52, 1.23s/it] Evaluating eval...: 80%|███████▉ | 1518/1900 [30:52<07:42, 1.21s/it] Evaluating eval...: 80%|███████▉ | 1519/1900 [30:53<07:35, 1.19s/it] Evaluating eval...: 80%|████████ | 1520/1900 [30:54<07:36, 1.20s/it] Evaluating eval...: 80%|████████ | 1521/1900 [30:55<07:41, 1.22s/it] Evaluating eval...: 80%|████████ | 1522/1900 [30:57<07:36, 1.21s/it] Evaluating eval...: 80%|████████ | 1523/1900 [30:58<07:39, 1.22s/it] Evaluating eval...: 80%|████████ | 1524/1900 [30:59<07:49, 1.25s/it] Evaluating eval...: 80%|████████ | 1525/1900 [31:00<07:42, 1.23s/it] Evaluating eval...: 80%|████████ | 1526/1900 [31:01<07:33, 1.21s/it] Evaluating eval...: 80%|████████ | 1527/1900 [31:03<07:33, 1.22s/it] Evaluating eval...: 80%|████████ | 1528/1900 [31:04<07:41, 1.24s/it] Evaluating eval...: 80%|████████ | 1529/1900 [31:05<07:34, 1.22s/it] Evaluating eval...: 81%|████████ | 1530/1900 [31:07<07:45, 1.26s/it] Evaluating eval...: 81%|████████ | 1531/1900 [31:08<07:38, 1.24s/it] Evaluating eval...: 81%|████████ | 1532/1900 [31:09<07:44, 1.26s/it] Evaluating eval...: 81%|████████ | 1533/1900 [31:10<07:33, 1.23s/it] Evaluating eval...: 81%|████████ | 1534/1900 [31:11<07:34, 1.24s/it] Evaluating eval...: 81%|████████ | 1535/1900 [31:13<07:27, 1.23s/it] Evaluating eval...: 81%|████████ | 1536/1900 [31:14<07:20, 1.21s/it] Evaluating eval...: 81%|████████ | 1537/1900 [31:15<07:23, 1.22s/it] Evaluating eval...: 81%|████████ | 1538/1900 [31:16<07:18, 1.21s/it] Evaluating eval...: 81%|████████ | 1539/1900 [31:18<07:24, 1.23s/it] Evaluating eval...: 81%|████████ | 1540/1900 [31:19<07:17, 1.21s/it] Evaluating eval...: 81%|████████ | 1541/1900 [31:20<07:28, 1.25s/it] Evaluating eval...: 81%|████████ | 1542/1900 [31:21<07:20, 1.23s/it] Evaluating eval...: 81%|████████ | 1543/1900 [31:22<07:14, 1.22s/it] Evaluating eval...: 81%|████████▏ | 1544/1900 [31:24<07:14, 1.22s/it] Evaluating eval...: 81%|████████▏ | 1545/1900 [31:25<07:08, 1.21s/it] Evaluating eval...: 81%|████████▏ | 1546/1900 [31:26<07:08, 1.21s/it] Evaluating eval...: 81%|████████▏ | 1547/1900 [31:27<07:11, 1.22s/it] Evaluating eval...: 81%|████████▏ | 1548/1900 [31:29<07:09, 1.22s/it] Evaluating eval...: 82%|████████▏ | 1549/1900 [31:30<07:05, 1.21s/it] Evaluating eval...: 82%|████████▏ | 1550/1900 [31:31<07:13, 1.24s/it] Evaluating eval...: 82%|████████▏ | 1551/1900 [31:32<07:05, 1.22s/it] Evaluating eval...: 82%|████████▏ | 1552/1900 [31:33<06:58, 1.20s/it] Evaluating eval...: 82%|████████▏ | 1553/1900 [31:35<06:59, 1.21s/it] Evaluating eval...: 82%|████████▏ | 1554/1900 [31:36<06:57, 1.21s/it] Evaluating eval...: 82%|████████▏ | 1555/1900 [31:37<06:54, 1.20s/it] Evaluating eval...: 82%|████████▏ | 1556/1900 [31:38<07:04, 1.23s/it] Evaluating eval...: 82%|████████▏ | 1557/1900 [31:40<07:00, 1.23s/it] Evaluating eval...: 82%|████████▏ | 1558/1900 [31:41<07:02, 1.23s/it] Evaluating eval...: 82%|████████▏ | 1559/1900 [31:42<07:02, 1.24s/it] Evaluating eval...: 82%|████████▏ | 1560/1900 [31:43<06:52, 1.21s/it] Evaluating eval...: 82%|████████▏ | 1561/1900 [31:45<07:04, 1.25s/it] Evaluating eval...: 82%|████████▏ | 1562/1900 [31:46<07:06, 1.26s/it] Evaluating eval...: 82%|████████▏ | 1563/1900 [31:47<07:08, 1.27s/it] Evaluating eval...: 82%|████████▏ | 1564/1900 [31:48<06:56, 1.24s/it] Evaluating eval...: 82%|████████▏ | 1565/1900 [31:49<06:51, 1.23s/it] Evaluating eval...: 82%|████████▏ | 1566/1900 [31:51<06:52, 1.23s/it] Evaluating eval...: 82%|████████▏ | 1567/1900 [31:52<06:49, 1.23s/it] Evaluating eval...: 83%|████████▎ | 1568/1900 [31:54<08:37, 1.56s/it] Evaluating eval...: 83%|████████▎ | 1569/1900 [31:55<08:04, 1.46s/it] Evaluating eval...: 83%|████████▎ | 1570/1900 [31:57<07:37, 1.39s/it] Evaluating eval...: 83%|████████▎ | 1571/1900 [31:58<07:18, 1.33s/it] Evaluating eval...: 83%|████████▎ | 1572/1900 [31:59<07:13, 1.32s/it] Evaluating eval...: 83%|████████▎ | 1573/1900 [32:00<06:57, 1.28s/it] Evaluating eval...: 83%|████████▎ | 1574/1900 [32:02<06:47, 1.25s/it] Evaluating eval...: 83%|████████▎ | 1575/1900 [32:03<06:39, 1.23s/it] Evaluating eval...: 83%|████████▎ | 1576/1900 [32:04<06:30, 1.21s/it] Evaluating eval...: 83%|████████▎ | 1577/1900 [32:05<06:32, 1.22s/it] Evaluating eval...: 83%|████████▎ | 1578/1900 [32:06<06:26, 1.20s/it] Evaluating eval...: 83%|████████▎ | 1579/1900 [32:07<06:24, 1.20s/it] Evaluating eval...: 83%|████████▎ | 1580/1900 [32:09<06:28, 1.21s/it] Evaluating eval...: 83%|████████▎ | 1581/1900 [32:10<06:34, 1.24s/it] Evaluating eval...: 83%|████████▎ | 1582/1900 [32:11<06:35, 1.24s/it] Evaluating eval...: 83%|████████▎ | 1583/1900 [32:13<06:34, 1.25s/it] Evaluating eval...: 83%|████████▎ | 1584/1900 [32:14<06:43, 1.28s/it] Evaluating eval...: 83%|████████▎ | 1585/1900 [32:15<06:37, 1.26s/it] Evaluating eval...: 83%|████████▎ | 1586/1900 [32:16<06:29, 1.24s/it] Evaluating eval...: 84%|████████▎ | 1587/1900 [32:17<06:21, 1.22s/it] Evaluating eval...: 84%|████████▎ | 1588/1900 [32:19<06:15, 1.20s/it] Evaluating eval...: 84%|████████▎ | 1589/1900 [32:20<06:15, 1.21s/it] Evaluating eval...: 84%|████████▎ | 1590/1900 [32:21<06:12, 1.20s/it] Evaluating eval...: 84%|████████▎ | 1591/1900 [32:22<06:17, 1.22s/it] Evaluating eval...: 84%|████████▍ | 1592/1900 [32:23<06:10, 1.20s/it] Evaluating eval...: 84%|████████▍ | 1593/1900 [32:25<06:16, 1.22s/it] Evaluating eval...: 84%|████████▍ | 1594/1900 [32:26<06:20, 1.24s/it] Evaluating eval...: 84%|████████▍ | 1595/1900 [32:27<06:20, 1.25s/it] Evaluating eval...: 84%|████████▍ | 1596/1900 [32:29<06:19, 1.25s/it] Evaluating eval...: 84%|████████▍ | 1597/1900 [32:30<06:16, 1.24s/it] Evaluating eval...: 84%|████████▍ | 1598/1900 [32:31<06:05, 1.21s/it] Evaluating eval...: 84%|████████▍ | 1599/1900 [32:32<05:58, 1.19s/it] Evaluating eval...: 84%|████████▍ | 1600/1900 [32:33<05:52, 1.17s/it] Evaluating eval...: 84%|████████▍ | 1601/1900 [32:34<05:50, 1.17s/it] Evaluating eval...: 84%|████████▍ | 1602/1900 [32:36<05:53, 1.19s/it] Evaluating eval...: 84%|████████▍ | 1603/1900 [32:37<05:57, 1.20s/it] Evaluating eval...: 84%|████████▍ | 1604/1900 [32:38<06:08, 1.25s/it] Evaluating eval...: 84%|████████▍ | 1605/1900 [32:39<06:01, 1.22s/it] Evaluating eval...: 85%|████████▍ | 1606/1900 [32:41<06:03, 1.24s/it] Evaluating eval...: 85%|████████▍ | 1607/1900 [32:42<05:58, 1.22s/it] Evaluating eval...: 85%|████████▍ | 1608/1900 [32:43<05:56, 1.22s/it] Evaluating eval...: 85%|████████▍ | 1609/1900 [32:44<06:05, 1.26s/it] Evaluating eval...: 85%|████████▍ | 1610/1900 [32:46<05:59, 1.24s/it] Evaluating eval...: 85%|████████▍ | 1611/1900 [32:47<05:52, 1.22s/it] Evaluating eval...: 85%|████████▍ | 1612/1900 [32:48<05:48, 1.21s/it] Evaluating eval...: 85%|████████▍ | 1613/1900 [32:49<05:43, 1.20s/it] Evaluating eval...: 85%|████████▍ | 1614/1900 [32:50<05:46, 1.21s/it] Evaluating eval...: 85%|████████▌ | 1615/1900 [32:52<05:46, 1.21s/it] Evaluating eval...: 85%|████████▌ | 1616/1900 [32:53<05:40, 1.20s/it] Evaluating eval...: 85%|████████▌ | 1617/1900 [32:54<05:45, 1.22s/it] Evaluating eval...: 85%|████████▌ | 1618/1900 [32:55<05:48, 1.24s/it] Evaluating eval...: 85%|████████▌ | 1619/1900 [32:56<05:47, 1.24s/it] Evaluating eval...: 85%|████████▌ | 1620/1900 [32:58<05:44, 1.23s/it] Evaluating eval...: 85%|████████▌ | 1621/1900 [32:59<05:37, 1.21s/it] Evaluating eval...: 85%|████████▌ | 1622/1900 [33:00<05:34, 1.20s/it] Evaluating eval...: 85%|████████▌ | 1623/1900 [33:01<05:34, 1.21s/it] Evaluating eval...: 85%|████████▌ | 1624/1900 [33:02<05:29, 1.19s/it] Evaluating eval...: 86%|████████▌ | 1625/1900 [33:04<05:33, 1.21s/it] Evaluating eval...: 86%|████████▌ | 1626/1900 [33:05<05:36, 1.23s/it] Evaluating eval...: 86%|████████▌ | 1627/1900 [33:06<05:36, 1.23s/it] Evaluating eval...: 86%|████████▌ | 1628/1900 [33:07<05:34, 1.23s/it] Evaluating eval...: 86%|████████▌ | 1629/1900 [33:09<05:33, 1.23s/it] Evaluating eval...: 86%|████████▌ | 1630/1900 [33:10<05:31, 1.23s/it] Evaluating eval...: 86%|████████▌ | 1631/1900 [33:11<05:37, 1.26s/it] Evaluating eval...: 86%|████████▌ | 1632/1900 [33:12<05:28, 1.22s/it] Evaluating eval...: 86%|████████▌ | 1633/1900 [33:14<05:31, 1.24s/it] Evaluating eval...: 86%|████████▌ | 1634/1900 [33:15<05:28, 1.23s/it] Evaluating eval...: 86%|████████▌ | 1635/1900 [33:16<05:20, 1.21s/it] Evaluating eval...: 86%|████████▌ | 1636/1900 [33:17<05:18, 1.21s/it] Evaluating eval...: 86%|████████▌ | 1637/1900 [33:18<05:23, 1.23s/it] Evaluating eval...: 86%|████████▌ | 1638/1900 [33:20<05:15, 1.20s/it] Evaluating eval...: 86%|████████▋ | 1639/1900 [33:21<05:15, 1.21s/it] Evaluating eval...: 86%|████████▋ | 1640/1900 [33:22<05:13, 1.21s/it] Evaluating eval...: 86%|████████▋ | 1641/1900 [33:23<05:16, 1.22s/it] Evaluating eval...: 86%|████████▋ | 1642/1900 [33:25<05:16, 1.23s/it] Evaluating eval...: 86%|████████▋ | 1643/1900 [33:26<05:21, 1.25s/it] Evaluating eval...: 87%|████████▋ | 1644/1900 [33:27<05:10, 1.21s/it] Evaluating eval...: 87%|████████▋ | 1645/1900 [33:28<05:03, 1.19s/it] Evaluating eval...: 87%|████████▋ | 1646/1900 [33:29<05:09, 1.22s/it] Evaluating eval...: 87%|████████▋ | 1647/1900 [33:31<05:11, 1.23s/it] Evaluating eval...: 87%|████████▋ | 1648/1900 [33:32<05:09, 1.23s/it] Evaluating eval...: 87%|████████▋ | 1649/1900 [33:33<05:03, 1.21s/it] Evaluating eval...: 87%|████████▋ | 1650/1900 [33:34<05:03, 1.22s/it] Evaluating eval...: 87%|████████▋ | 1651/1900 [33:35<04:59, 1.20s/it] Evaluating eval...: 87%|████████▋ | 1652/1900 [33:37<04:58, 1.20s/it] Evaluating eval...: 87%|████████▋ | 1653/1900 [33:38<04:55, 1.20s/it] Evaluating eval...: 87%|████████▋ | 1654/1900 [33:39<04:53, 1.19s/it] Evaluating eval...: 87%|████████▋ | 1655/1900 [33:40<05:03, 1.24s/it] Evaluating eval...: 87%|████████▋ | 1656/1900 [33:42<04:59, 1.23s/it] Evaluating eval...: 87%|████████▋ | 1657/1900 [33:43<04:55, 1.22s/it] Evaluating eval...: 87%|████████▋ | 1658/1900 [33:44<04:58, 1.23s/it] Evaluating eval...: 87%|████████▋ | 1659/1900 [33:45<05:03, 1.26s/it] Evaluating eval...: 87%|████████▋ | 1660/1900 [33:47<05:02, 1.26s/it] Evaluating eval...: 87%|████████▋ | 1661/1900 [33:48<04:59, 1.26s/it] Evaluating eval...: 87%|████████▋ | 1662/1900 [33:49<04:51, 1.23s/it] Evaluating eval...: 88%|████████▊ | 1663/1900 [33:50<04:45, 1.21s/it] Evaluating eval...: 88%|████████▊ | 1664/1900 [33:51<04:46, 1.22s/it] Evaluating eval...: 88%|████████▊ | 1665/1900 [33:53<04:45, 1.22s/it] Evaluating eval...: 88%|████████▊ | 1666/1900 [33:54<05:07, 1.31s/it] Evaluating eval...: 88%|████████▊ | 1667/1900 [33:56<05:07, 1.32s/it] Evaluating eval...: 88%|████████▊ | 1668/1900 [33:57<04:57, 1.28s/it] Evaluating eval...: 88%|████████▊ | 1669/1900 [33:58<04:54, 1.27s/it] Evaluating eval...: 88%|████████▊ | 1670/1900 [33:59<04:54, 1.28s/it] Evaluating eval...: 88%|████████▊ | 1671/1900 [34:00<04:45, 1.25s/it] Evaluating eval...: 88%|████████▊ | 1672/1900 [34:02<04:42, 1.24s/it] Evaluating eval...: 88%|████████▊ | 1673/1900 [34:03<04:52, 1.29s/it] Evaluating eval...: 88%|████████▊ | 1674/1900 [34:04<04:51, 1.29s/it] Evaluating eval...: 88%|████████▊ | 1675/1900 [34:06<04:47, 1.28s/it] Evaluating eval...: 88%|████████▊ | 1676/1900 [34:07<04:40, 1.25s/it] Evaluating eval...: 88%|████████▊ | 1677/1900 [34:08<04:34, 1.23s/it] Evaluating eval...: 88%|████████▊ | 1678/1900 [34:09<04:28, 1.21s/it] Evaluating eval...: 88%|████████▊ | 1679/1900 [34:10<04:32, 1.23s/it] Evaluating eval...: 88%|████████▊ | 1680/1900 [34:12<04:32, 1.24s/it] Evaluating eval...: 88%|████████▊ | 1681/1900 [34:13<04:32, 1.24s/it] Evaluating eval...: 89%|████████▊ | 1682/1900 [34:14<04:29, 1.24s/it] Evaluating eval...: 89%|████████▊ | 1683/1900 [34:15<04:27, 1.23s/it] Evaluating eval...: 89%|████████▊ | 1684/1900 [34:17<04:22, 1.22s/it] Evaluating eval...: 89%|████████▊ | 1685/1900 [34:18<04:18, 1.20s/it] Evaluating eval...: 89%|████████▊ | 1686/1900 [34:19<04:19, 1.21s/it] Evaluating eval...: 89%|████████▉ | 1687/1900 [34:20<04:16, 1.21s/it] Evaluating eval...: 89%|████████▉ | 1688/1900 [34:21<04:20, 1.23s/it] Evaluating eval...: 89%|████████▉ | 1689/1900 [34:23<04:14, 1.21s/it] Evaluating eval...: 89%|████████▉ | 1690/1900 [34:24<04:13, 1.21s/it] Evaluating eval...: 89%|████████▉ | 1691/1900 [34:25<04:18, 1.24s/it] Evaluating eval...: 89%|████████▉ | 1692/1900 [34:26<04:15, 1.23s/it] Evaluating eval...: 89%|████████▉ | 1693/1900 [34:28<04:15, 1.23s/it] Evaluating eval...: 89%|████████▉ | 1694/1900 [34:29<04:18, 1.25s/it] Evaluating eval...: 89%|████████▉ | 1695/1900 [34:30<04:13, 1.24s/it] Evaluating eval...: 89%|████████▉ | 1696/1900 [34:31<04:08, 1.22s/it] Evaluating eval...: 89%|████████▉ | 1697/1900 [34:33<04:12, 1.24s/it] Evaluating eval...: 89%|████████▉ | 1698/1900 [34:34<04:12, 1.25s/it] Evaluating eval...: 89%|████████▉ | 1699/1900 [34:35<04:05, 1.22s/it] Evaluating eval...: 89%|████████▉ | 1700/1900 [34:36<04:02, 1.21s/it] Evaluating eval...: 90%|████████▉ | 1701/1900 [34:37<04:06, 1.24s/it] Evaluating eval...: 90%|████████▉ | 1702/1900 [34:39<04:04, 1.24s/it] Evaluating eval...: 90%|████████▉ | 1703/1900 [34:40<04:03, 1.23s/it] Evaluating eval...: 90%|████████▉ | 1704/1900 [34:41<03:59, 1.22s/it] Evaluating eval...: 90%|████████▉ | 1705/1900 [34:42<03:53, 1.20s/it] Evaluating eval...: 90%|████████▉ | 1706/1900 [34:43<03:53, 1.20s/it] Evaluating eval...: 90%|████████▉ | 1707/1900 [34:45<03:49, 1.19s/it] Evaluating eval...: 90%|████████▉ | 1708/1900 [34:46<03:51, 1.20s/it] Evaluating eval...: 90%|████████▉ | 1709/1900 [34:47<03:50, 1.21s/it] Evaluating eval...: 90%|█████████ | 1710/1900 [34:48<03:49, 1.21s/it] Evaluating eval...: 90%|█████████ | 1711/1900 [34:49<03:45, 1.19s/it] Evaluating eval...: 90%|█████████ | 1712/1900 [34:51<03:42, 1.18s/it] Evaluating eval...: 90%|█████████ | 1713/1900 [34:52<03:39, 1.17s/it] Evaluating eval...: 90%|█████████ | 1714/1900 [34:53<03:36, 1.16s/it] Evaluating eval...: 90%|█████████ | 1715/1900 [34:54<03:39, 1.19s/it] Evaluating eval...: 90%|█████████ | 1716/1900 [34:55<03:40, 1.20s/it] Evaluating eval...: 90%|█████████ | 1717/1900 [34:58<04:48, 1.58s/it] Evaluating eval...: 90%|█████████ | 1718/1900 [34:59<04:28, 1.48s/it] Evaluating eval...: 90%|█████████ | 1719/1900 [35:00<04:11, 1.39s/it] Evaluating eval...: 91%|█████████ | 1720/1900 [35:02<04:04, 1.36s/it] Evaluating eval...: 91%|█████████ | 1721/1900 [35:03<03:54, 1.31s/it] Evaluating eval...: 91%|█████████ | 1722/1900 [35:04<03:49, 1.29s/it] Evaluating eval...: 91%|█████████ | 1723/1900 [35:05<03:40, 1.25s/it] Evaluating eval...: 91%|█████████ | 1724/1900 [35:06<03:39, 1.25s/it] Evaluating eval...: 91%|█████████ | 1725/1900 [35:08<03:36, 1.24s/it] Evaluating eval...: 91%|█████████ | 1726/1900 [35:09<03:35, 1.24s/it] Evaluating eval...: 91%|█████████ | 1727/1900 [35:10<03:33, 1.23s/it] Evaluating eval...: 91%|█████████ | 1728/1900 [35:11<03:26, 1.20s/it] Evaluating eval...: 91%|█████████ | 1729/1900 [35:12<03:23, 1.19s/it] Evaluating eval...: 91%|█████████ | 1730/1900 [35:14<03:24, 1.20s/it] Evaluating eval...: 91%|█████████ | 1731/1900 [35:15<03:22, 1.20s/it] Evaluating eval...: 91%|█████████ | 1732/1900 [35:16<03:19, 1.19s/it] Evaluating eval...: 91%|█████████ | 1733/1900 [35:17<03:19, 1.19s/it] Evaluating eval...: 91%|█████████▏| 1734/1900 [35:18<03:16, 1.18s/it] Evaluating eval...: 91%|█████████▏| 1735/1900 [35:19<03:15, 1.18s/it] Evaluating eval...: 91%|█████████▏| 1736/1900 [35:21<03:20, 1.22s/it] Evaluating eval...: 91%|█████████▏| 1737/1900 [35:22<03:16, 1.21s/it] Evaluating eval...: 91%|█████████▏| 1738/1900 [35:23<03:13, 1.19s/it] Evaluating eval...: 92%|█████████▏| 1739/1900 [35:24<03:15, 1.21s/it] Evaluating eval...: 92%|█████████▏| 1740/1900 [35:26<03:13, 1.21s/it] Evaluating eval...: 92%|█████████▏| 1741/1900 [35:27<03:14, 1.22s/it] Evaluating eval...: 92%|█████████▏| 1742/1900 [35:28<03:10, 1.20s/it] Evaluating eval...: 92%|█████████▏| 1743/1900 [35:29<03:09, 1.21s/it] Evaluating eval...: 92%|█████████▏| 1744/1900 [35:30<03:07, 1.20s/it] Evaluating eval...: 92%|█████████▏| 1745/1900 [35:31<03:02, 1.18s/it] Evaluating eval...: 92%|█████████▏| 1746/1900 [35:33<03:06, 1.21s/it] Evaluating eval...: 92%|█████████▏| 1747/1900 [35:34<03:04, 1.20s/it] Evaluating eval...: 92%|█████████▏| 1748/1900 [35:35<03:02, 1.20s/it] Evaluating eval...: 92%|█████████▏| 1749/1900 [35:36<03:05, 1.23s/it] Evaluating eval...: 92%|█████████▏| 1750/1900 [35:38<03:04, 1.23s/it] Evaluating eval...: 92%|█████████▏| 1751/1900 [35:39<03:02, 1.22s/it] Evaluating eval...: 92%|█████████▏| 1752/1900 [35:40<02:59, 1.21s/it] Evaluating eval...: 92%|█████████▏| 1753/1900 [35:41<02:54, 1.19s/it] Evaluating eval...: 92%|█████████▏| 1754/1900 [35:42<02:56, 1.21s/it] Evaluating eval...: 92%|█████████▏| 1755/1900 [35:44<02:57, 1.22s/it] Evaluating eval...: 92%|█████████▏| 1756/1900 [35:45<03:00, 1.25s/it] Evaluating eval...: 92%|█████████▏| 1757/1900 [35:46<02:59, 1.25s/it] Evaluating eval...: 93%|█████████▎| 1758/1900 [35:48<02:56, 1.25s/it] Evaluating eval...: 93%|█████████▎| 1759/1900 [35:49<02:51, 1.22s/it] Evaluating eval...: 93%|█████████▎| 1760/1900 [35:50<02:48, 1.20s/it] Evaluating eval...: 93%|█████████▎| 1761/1900 [35:51<02:48, 1.21s/it] Evaluating eval...: 93%|█████████▎| 1762/1900 [35:52<02:46, 1.21s/it] Evaluating eval...: 93%|█████████▎| 1763/1900 [35:53<02:43, 1.19s/it] Evaluating eval...: 93%|█████████▎| 1764/1900 [35:55<02:47, 1.23s/it] Evaluating eval...: 93%|█████████▎| 1765/1900 [35:56<02:46, 1.23s/it] Evaluating eval...: 93%|█████████▎| 1766/1900 [35:57<02:44, 1.23s/it] Evaluating eval...: 93%|█████████▎| 1767/1900 [35:58<02:41, 1.22s/it] Evaluating eval...: 93%|█████████▎| 1768/1900 [36:00<02:44, 1.25s/it] Evaluating eval...: 93%|█████████▎| 1769/1900 [36:01<02:43, 1.25s/it] Evaluating eval...: 93%|█████████▎| 1770/1900 [36:02<02:43, 1.26s/it] Evaluating eval...: 93%|█████████▎| 1771/1900 [36:04<02:42, 1.26s/it] Evaluating eval...: 93%|█████████▎| 1772/1900 [36:05<02:38, 1.24s/it] Evaluating eval...: 93%|█████████▎| 1773/1900 [36:06<02:37, 1.24s/it] Evaluating eval...: 93%|█████████▎| 1774/1900 [36:07<02:34, 1.22s/it] Evaluating eval...: 93%|█████████▎| 1775/1900 [36:08<02:34, 1.23s/it] Evaluating eval...: 93%|█████████▎| 1776/1900 [36:10<02:30, 1.22s/it] Evaluating eval...: 94%|█████████▎| 1777/1900 [36:11<02:27, 1.20s/it] Evaluating eval...: 94%|█████████▎| 1778/1900 [36:12<02:25, 1.19s/it] Evaluating eval...: 94%|█████████▎| 1779/1900 [36:13<02:23, 1.19s/it] Evaluating eval...: 94%|█████████▎| 1780/1900 [36:14<02:22, 1.18s/it] Evaluating eval...: 94%|█████████▎| 1781/1900 [36:15<02:19, 1.17s/it] Evaluating eval...: 94%|█████████▍| 1782/1900 [36:17<02:20, 1.19s/it] Evaluating eval...: 94%|█████████▍| 1783/1900 [36:18<02:21, 1.21s/it] Evaluating eval...: 94%|█████████▍| 1784/1900 [36:19<02:19, 1.21s/it] Evaluating eval...: 94%|█████████▍| 1785/1900 [36:20<02:16, 1.19s/it] Evaluating eval...: 94%|█████████▍| 1786/1900 [36:21<02:14, 1.18s/it] Evaluating eval...: 94%|█████████▍| 1787/1900 [36:23<02:13, 1.18s/it] Evaluating eval...: 94%|█████████▍| 1788/1900 [36:24<02:13, 1.19s/it] Evaluating eval...: 94%|█████████▍| 1789/1900 [36:25<02:10, 1.18s/it] Evaluating eval...: 94%|█████████▍| 1790/1900 [36:26<02:12, 1.21s/it] Evaluating eval...: 94%|█████████▍| 1791/1900 [36:27<02:11, 1.20s/it] Evaluating eval...: 94%|█████████▍| 1792/1900 [36:29<02:08, 1.19s/it] Evaluating eval...: 94%|█████████▍| 1793/1900 [36:30<02:12, 1.24s/it] Evaluating eval...: 94%|█████████▍| 1794/1900 [36:31<02:08, 1.21s/it] Evaluating eval...: 94%|█████████▍| 1795/1900 [36:32<02:07, 1.21s/it] Evaluating eval...: 95%|█████████▍| 1796/1900 [36:33<02:04, 1.19s/it] Evaluating eval...: 95%|█████████▍| 1797/1900 [36:35<02:04, 1.20s/it] Evaluating eval...: 95%|█████████▍| 1798/1900 [36:36<02:08, 1.26s/it] Evaluating eval...: 95%|█████████▍| 1799/1900 [36:37<02:06, 1.25s/it] Evaluating eval...: 95%|█████████▍| 1800/1900 [36:38<02:03, 1.23s/it] Evaluating eval...: 95%|█████████▍| 1801/1900 [36:40<01:59, 1.20s/it] Evaluating eval...: 95%|█████████▍| 1802/1900 [36:41<01:59, 1.22s/it] Evaluating eval...: 95%|█████████▍| 1803/1900 [36:42<01:58, 1.22s/it] Evaluating eval...: 95%|█████████▍| 1804/1900 [36:43<01:55, 1.20s/it] Evaluating eval...: 95%|█████████▌| 1805/1900 [36:44<01:54, 1.20s/it] Evaluating eval...: 95%|█████████▌| 1806/1900 [36:46<01:53, 1.20s/it] Evaluating eval...: 95%|█████████▌| 1807/1900 [36:47<01:52, 1.20s/it] Evaluating eval...: 95%|█████████▌| 1808/1900 [36:48<01:49, 1.19s/it] Evaluating eval...: 95%|█████████▌| 1809/1900 [36:49<01:46, 1.17s/it] Evaluating eval...: 95%|█████████▌| 1810/1900 [36:50<01:46, 1.18s/it] Evaluating eval...: 95%|█████████▌| 1811/1900 [36:52<01:46, 1.20s/it] Evaluating eval...: 95%|█████████▌| 1812/1900 [36:53<01:45, 1.20s/it] Evaluating eval...: 95%|█████████▌| 1813/1900 [36:54<01:44, 1.20s/it] Evaluating eval...: 95%|█████████▌| 1814/1900 [36:55<01:43, 1.21s/it] Evaluating eval...: 96%|█████████▌| 1815/1900 [36:56<01:41, 1.19s/it] Evaluating eval...: 96%|█████████▌| 1816/1900 [36:58<01:41, 1.21s/it] Evaluating eval...: 96%|█████████▌| 1817/1900 [36:59<01:41, 1.23s/it] Evaluating eval...: 96%|█████████▌| 1818/1900 [37:00<01:39, 1.22s/it] Evaluating eval...: 96%|█████████▌| 1819/1900 [37:01<01:38, 1.21s/it] Evaluating eval...: 96%|█████████▌| 1820/1900 [37:02<01:36, 1.21s/it] Evaluating eval...: 96%|█████████▌| 1821/1900 [37:04<01:35, 1.21s/it] Evaluating eval...: 96%|█████████▌| 1822/1900 [37:05<01:33, 1.20s/it] Evaluating eval...: 96%|█████████▌| 1823/1900 [37:06<01:31, 1.19s/it] Evaluating eval...: 96%|█████████▌| 1824/1900 [37:07<01:31, 1.20s/it] Evaluating eval...: 96%|█████████▌| 1825/1900 [37:08<01:30, 1.21s/it] Evaluating eval...: 96%|█████████▌| 1826/1900 [37:10<01:29, 1.21s/it] Evaluating eval...: 96%|█████████▌| 1827/1900 [37:11<01:30, 1.24s/it] Evaluating eval...: 96%|█████████▌| 1828/1900 [37:12<01:28, 1.23s/it] Evaluating eval...: 96%|█████████▋| 1829/1900 [37:14<01:31, 1.29s/it] Evaluating eval...: 96%|█████████▋| 1830/1900 [37:15<01:27, 1.25s/it] Evaluating eval...: 96%|█████████▋| 1831/1900 [37:16<01:24, 1.23s/it] Evaluating eval...: 96%|█████████▋| 1832/1900 [37:17<01:22, 1.21s/it] Evaluating eval...: 96%|█████████▋| 1833/1900 [37:18<01:20, 1.20s/it] Evaluating eval...: 97%|█████████▋| 1834/1900 [37:20<01:19, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1835/1900 [37:21<01:18, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1836/1900 [37:22<01:17, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1837/1900 [37:23<01:18, 1.24s/it] Evaluating eval...: 97%|█████████▋| 1838/1900 [37:24<01:15, 1.22s/it] Evaluating eval...: 97%|█████████▋| 1839/1900 [37:26<01:13, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1840/1900 [37:27<01:12, 1.22s/it] Evaluating eval...: 97%|█████████▋| 1841/1900 [37:28<01:11, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1842/1900 [37:29<01:10, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1843/1900 [37:30<01:08, 1.20s/it] Evaluating eval...: 97%|█████████▋| 1844/1900 [37:32<01:07, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1845/1900 [37:33<01:06, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1846/1900 [37:34<01:05, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1847/1900 [37:35<01:04, 1.21s/it] Evaluating eval...: 97%|█████████▋| 1848/1900 [37:37<01:04, 1.25s/it] Evaluating eval...: 97%|█████████▋| 1849/1900 [37:38<01:03, 1.24s/it] Evaluating eval...: 97%|█████████▋| 1850/1900 [37:39<01:01, 1.22s/it] Evaluating eval...: 97%|█████████▋| 1851/1900 [37:40<00:59, 1.22s/it] Evaluating eval...: 97%|█████████▋| 1852/1900 [37:41<00:57, 1.21s/it] Evaluating eval...: 98%|█████████▊| 1853/1900 [37:43<00:56, 1.21s/it] Evaluating eval...: 98%|█████████▊| 1854/1900 [37:44<00:55, 1.20s/it] Evaluating eval...: 98%|█████████▊| 1855/1900 [37:45<00:56, 1.25s/it] Evaluating eval...: 98%|█████████▊| 1856/1900 [37:46<00:53, 1.23s/it] Evaluating eval...: 98%|█████████▊| 1857/1900 [37:48<00:52, 1.22s/it] Evaluating eval...: 98%|█████████▊| 1858/1900 [37:49<00:51, 1.22s/it] Evaluating eval...: 98%|█████████▊| 1859/1900 [37:50<00:49, 1.20s/it] Evaluating eval...: 98%|█████████▊| 1860/1900 [37:51<00:48, 1.21s/it] Evaluating eval...: 98%|█████████▊| 1861/1900 [37:52<00:46, 1.20s/it] Evaluating eval...: 98%|█████████▊| 1862/1900 [37:54<00:45, 1.19s/it] Evaluating eval...: 98%|█████████▊| 1863/1900 [37:55<00:44, 1.20s/it] Evaluating eval...: 98%|█████████▊| 1864/1900 [37:56<00:43, 1.20s/it] Evaluating eval...: 98%|█████████▊| 1865/1900 [37:57<00:41, 1.19s/it] Evaluating eval...: 98%|█████████▊| 1866/1900 [37:58<00:41, 1.21s/it] Evaluating eval...: 98%|█████████▊| 1867/1900 [38:00<00:40, 1.22s/it] Evaluating eval...: 98%|█████████▊| 1868/1900 [38:01<00:38, 1.22s/it] Evaluating eval...: 98%|█████████▊| 1869/1900 [38:02<00:38, 1.25s/it] Evaluating eval...: 98%|█████████▊| 1870/1900 [38:03<00:37, 1.24s/it] Evaluating eval...: 98%|█████████▊| 1871/1900 [38:05<00:36, 1.25s/it] Evaluating eval...: 99%|█████████▊| 1872/1900 [38:06<00:35, 1.27s/it] Evaluating eval...: 99%|█████████▊| 1873/1900 [38:07<00:34, 1.27s/it] Evaluating eval...: 99%|█████████▊| 1874/1900 [38:08<00:32, 1.24s/it] Evaluating eval...: 99%|█████████▊| 1875/1900 [38:10<00:31, 1.25s/it] Evaluating eval...: 99%|█████████▊| 1876/1900 [38:11<00:29, 1.23s/it] Evaluating eval...: 99%|█████████▉| 1877/1900 [38:12<00:28, 1.23s/it] Evaluating eval...: 99%|█████████▉| 1878/1900 [38:13<00:26, 1.22s/it] Evaluating eval...: 99%|█████████▉| 1879/1900 [38:15<00:25, 1.21s/it] Evaluating eval...: 99%|█████████▉| 1880/1900 [38:16<00:24, 1.20s/it] Evaluating eval...: 99%|█████████▉| 1881/1900 [38:17<00:22, 1.21s/it] Evaluating eval...: 99%|█████████▉| 1882/1900 [38:18<00:21, 1.22s/it] Evaluating eval...: 99%|█████████▉| 1883/1900 [38:19<00:21, 1.25s/it] Evaluating eval...: 99%|█████████▉| 1884/1900 [38:21<00:19, 1.25s/it] Evaluating eval...: 99%|█████████▉| 1885/1900 [38:22<00:18, 1.22s/it] Evaluating eval...: 99%|█████████▉| 1886/1900 [38:23<00:17, 1.24s/it] Evaluating eval...: 99%|█████████▉| 1887/1900 [38:24<00:15, 1.21s/it] Evaluating eval...: 99%|█████████▉| 1888/1900 [38:26<00:14, 1.21s/it] Evaluating eval...: 99%|█████████▉| 1889/1900 [38:27<00:13, 1.21s/it] Evaluating eval...: 99%|█████████▉| 1890/1900 [38:28<00:11, 1.19s/it] Evaluating eval...: 100%|█████████▉| 1891/1900 [38:29<00:10, 1.19s/it] Evaluating eval...: 100%|█████████▉| 1892/1900 [38:30<00:09, 1.20s/it] Evaluating eval...: 100%|█████████▉| 1893/1900 [38:31<00:08, 1.19s/it] Evaluating eval...: 100%|█████████▉| 1894/1900 [38:33<00:07, 1.18s/it] Evaluating eval...: 100%|█████████▉| 1895/1900 [38:34<00:05, 1.19s/it] Evaluating eval...: 100%|█████████▉| 1896/1900 [38:35<00:04, 1.19s/it] Evaluating eval...: 100%|█████████▉| 1897/1900 [38:36<00:03, 1.19s/it] Evaluating eval...: 100%|█████████▉| 1898/1900 [38:37<00:02, 1.21s/it] Evaluating eval...: 100%|█████████▉| 1899/1900 [38:39<00:01, 1.21s/it] Evaluating eval...: 100%|██████████| 1900/1900 [38:40<00:00, 1.33s/it] Evaluating eval...: 100%|██████████| 1900/1900 [38:40<00:00, 1.22s/it] Eval results for step (5000 / 100000 | Eval Loss: 1.7768317461013794 | Eval wer: 51.30624345539222 | Eval wer_ortho: 54.39490001716444 |) Eval results for step (5000 / 100000 | Eval Loss: 1.7768317461013794 | Eval wer: 51.30624345539222 | Eval wer_ortho: 54.39490001716444 |) Train steps ... : 5%|▌ | 5000/100000 [1:37:58<15:26:15, 1.71it/s] Train steps ... : 5%|▌ | 5001/100000 [1:37:59<23378:05:06, 885.92s/it] Train steps ... : 5%|▌ | 5002/100000 [1:37:59<16369:07:11, 620.32s/it] Train steps ... : 5%|▌ | 5003/100000 [1:38:00<11462:54:19, 434.40s/it] Train steps ... : 5%|▌ | 5004/100000 [1:38:00<8028:34:10, 304.25s/it] Train steps ... : 5%|▌ | 5005/100000 [1:38:01<5624:33:58, 213.15s/it] Train steps ... : 5%|▌ | 5006/100000 [1:38:02<3941:46:44, 149.38s/it] Train steps ... : 5%|▌ | 5007/100000 [1:38:02<2763:50:28, 104.74s/it] Train steps ... : 5%|▌ | 5008/100000 [1:38:03<1939:16:34, 73.49s/it] Train steps ... : 5%|▌ | 5009/100000 [1:38:03<1362:05:52, 51.62s/it] Train steps ... : 5%|▌ | 5010/100000 [1:38:04<958:04:47, 36.31s/it] Train steps ... : 5%|▌ | 5011/100000 [1:38:04<675:15:27, 25.59s/it] Train steps ... : 5%|▌ | 5012/100000 [1:38:05<477:17:41, 18.09s/it] Train steps ... : 5%|▌ | 5013/100000 [1:38:06<338:42:50, 12.84s/it] Train steps ... : 5%|▌ | 5014/100000 [1:38:06<241:42:21, 9.16s/it] Train steps ... : 5%|▌ | 5015/100000 [1:38:07<173:48:56, 6.59s/it] Train steps ... : 5%|▌ | 5016/100000 [1:38:07<126:19:05, 4.79s/it] Train steps ... : 5%|▌ | 5017/100000 [1:38:08<93:02:30, 3.53s/it] Train steps ... : 5%|▌ | 5018/100000 [1:38:09<69:44:40, 2.64s/it] Train steps ... : 5%|▌ | 5019/100000 [1:38:09<53:26:47, 2.03s/it] Train steps ... : 5%|▌ | 5020/100000 [1:38:10<42:02:42, 1.59s/it] Train steps ... : 5%|▌ | 5021/100000 [1:38:10<34:03:54, 1.29s/it] Train steps ... : 5%|▌ | 5022/100000 [1:38:11<28:28:09, 1.08s/it] Train steps ... : 5%|▌ | 5023/100000 [1:38:11<24:33:08, 1.07it/s] Train steps ... : 5%|▌ | 5024/100000 [1:38:12<21:48:48, 1.21it/s] Train steps ... : 5%|▌ | 5025/100000 [1:38:13<19:52:50, 1.33it/s]Step... (5025 / 100000 | Loss: 1.7930963039398193, Learning Rate: 9.545226130653267e-05) Step... (5025 / 100000 | Loss: 1.5479848384857178, Learning Rate: 9.545226130653267e-05) Train steps ... : 5%|▌ | 5025/100000 [1:38:13<19:52:50, 1.33it/s] Train steps ... : 5%|▌ | 5026/100000 [1:38:13<18:32:47, 1.42it/s] Train steps ... : 5%|▌ | 5027/100000 [1:38:14<17:35:36, 1.50it/s] Train steps ... : 5%|▌ | 5028/100000 [1:38:14<16:55:48, 1.56it/s] Train steps ... : 5%|▌ | 5029/100000 [1:38:15<16:28:39, 1.60it/s] Train steps ... : 5%|▌ | 5030/100000 [1:38:16<16:08:49, 1.63it/s] Train steps ... : 5%|▌ | 5031/100000 [1:38:16<15:55:20, 1.66it/s] Train steps ... : 5%|▌ | 5032/100000 [1:38:17<15:45:26, 1.67it/s] Train steps ... : 5%|▌ | 5033/100000 [1:38:17<15:39:23, 1.68it/s] Train steps ... : 5%|▌ | 5034/100000 [1:38:18<15:34:41, 1.69it/s] Train steps ... : 5%|▌ | 5035/100000 [1:38:18<15:30:50, 1.70it/s] Train steps ... : 5%|▌ | 5036/100000 [1:38:19<15:28:23, 1.70it/s] Train steps ... : 5%|▌ | 5037/100000 [1:38:20<15:26:45, 1.71it/s] Train steps ... : 5%|▌ | 5038/100000 [1:38:20<15:26:35, 1.71it/s] Train steps ... : 5%|▌ | 5039/100000 [1:38:21<15:26:39, 1.71it/s] Train steps ... : 5%|▌ | 5040/100000 [1:38:21<15:24:46, 1.71it/s] Train steps ... : 5%|▌ | 5041/100000 [1:38:22<15:31:01, 1.70it/s] Train steps ... : 5%|▌ | 5042/100000 [1:38:23<15:27:05, 1.71it/s] Train steps ... : 5%|▌ | 5043/100000 [1:38:23<15:26:41, 1.71it/s] Train steps ... : 5%|▌ | 5044/100000 [1:38:24<15:27:33, 1.71it/s] Train steps ... : 5%|▌ | 5045/100000 [1:38:24<15:25:50, 1.71it/s] Train steps ... : 5%|▌ | 5046/100000 [1:38:25<15:26:37, 1.71it/s] Train steps ... : 5%|▌ | 5047/100000 [1:38:26<15:24:54, 1.71it/s] Train steps ... : 5%|▌ | 5048/100000 [1:38:26<15:25:30, 1.71it/s] Train steps ... : 5%|▌ | 5049/100000 [1:38:27<15:24:42, 1.71it/s] Train steps ... : 5%|▌ | 5050/100000 [1:38:27<15:24:20, 1.71it/s]Step... (5050 / 100000 | Loss: 1.924727439880371, Learning Rate: 9.542713567839196e-05) Step... (5050 / 100000 | Loss: 1.961743950843811, Learning Rate: 9.542713567839196e-05) Train steps ... : 5%|▌ | 5050/100000 [1:38:28<15:24:20, 1.71it/s] Train steps ... : 5%|▌ | 5051/100000 [1:38:28<15:25:30, 1.71it/s] Train steps ... : 5%|▌ | 5052/100000 [1:38:28<15:24:37, 1.71it/s] Train steps ... : 5%|▌ | 5053/100000 [1:38:29<15:23:52, 1.71it/s] Train steps ... : 5%|▌ | 5054/100000 [1:38:30<15:23:50, 1.71it/s] Train steps ... : 5%|▌ | 5055/100000 [1:38:30<15:23:32, 1.71it/s] Train steps ... : 5%|▌ | 5056/100000 [1:38:31<15:24:17, 1.71it/s] Train steps ... : 5%|▌ | 5057/100000 [1:38:31<15:23:52, 1.71it/s] Train steps ... : 5%|▌ | 5058/100000 [1:38:32<15:24:03, 1.71it/s] Train steps ... : 5%|▌ | 5059/100000 [1:38:33<15:23:11, 1.71it/s] Train steps ... : 5%|▌ | 5060/100000 [1:38:33<15:23:13, 1.71it/s] Train steps ... : 5%|▌ | 5061/100000 [1:38:34<15:22:56, 1.71it/s] Train steps ... : 5%|▌ | 5062/100000 [1:38:34<15:23:01, 1.71it/s] Train steps ... : 5%|▌ | 5063/100000 [1:38:35<15:22:35, 1.72it/s] Train steps ... : 5%|▌ | 5064/100000 [1:38:35<15:22:40, 1.71it/s] Train steps ... : 5%|▌ | 5065/100000 [1:38:36<15:22:20, 1.72it/s] Train steps ... : 5%|▌ | 5066/100000 [1:38:37<15:22:04, 1.72it/s] Train steps ... : 5%|▌ | 5067/100000 [1:38:37<15:22:08, 1.72it/s] Train steps ... : 5%|▌ | 5068/100000 [1:38:38<15:22:34, 1.71it/s] Train steps ... : 5%|▌ | 5069/100000 [1:38:38<15:23:25, 1.71it/s] Train steps ... : 5%|▌ | 5070/100000 [1:38:39<15:24:06, 1.71it/s] Train steps ... : 5%|▌ | 5071/100000 [1:38:40<15:24:34, 1.71it/s] Train steps ... : 5%|▌ | 5072/100000 [1:38:40<15:25:01, 1.71it/s] Train steps ... : 5%|▌ | 5073/100000 [1:38:41<15:24:12, 1.71it/s] Train steps ... : 5%|▌ | 5074/100000 [1:38:41<15:23:36, 1.71it/s] Train steps ... : 5%|▌ | 5075/100000 [1:38:42<15:23:39, 1.71it/s]Step... (5075 / 100000 | Loss: 1.4128001928329468, Learning Rate: 9.540201005025126e-05) Step... (5075 / 100000 | Loss: 1.7889387607574463, Learning Rate: 9.540201005025126e-05) Train steps ... : 5%|▌ | 5075/100000 [1:38:42<15:23:39, 1.71it/s] Train steps ... : 5%|▌ | 5076/100000 [1:38:42<15:23:13, 1.71it/s] Train steps ... : 5%|▌ | 5077/100000 [1:38:43<15:23:09, 1.71it/s] Train steps ... : 5%|▌ | 5078/100000 [1:38:44<15:23:07, 1.71it/s] Train steps ... : 5%|▌ | 5079/100000 [1:38:44<15:23:06, 1.71it/s] Train steps ... : 5%|▌ | 5080/100000 [1:38:45<15:22:35, 1.71it/s] Train steps ... : 5%|▌ | 5081/100000 [1:38:45<15:22:37, 1.71it/s] Train steps ... : 5%|▌ | 5082/100000 [1:38:46<15:23:16, 1.71it/s] Train steps ... : 5%|▌ | 5083/100000 [1:38:47<15:22:36, 1.71it/s] Train steps ... : 5%|▌ | 5084/100000 [1:38:47<15:22:41, 1.71it/s] Train steps ... : 5%|▌ | 5085/100000 [1:38:48<15:24:17, 1.71it/s] Train steps ... : 5%|▌ | 5086/100000 [1:38:48<15:23:32, 1.71it/s] Train steps ... : 5%|▌ | 5087/100000 [1:38:49<15:24:22, 1.71it/s] Train steps ... : 5%|▌ | 5088/100000 [1:38:49<15:25:10, 1.71it/s] Train steps ... : 5%|▌ | 5089/100000 [1:38:50<15:23:58, 1.71it/s] Train steps ... : 5%|▌ | 5090/100000 [1:38:51<15:24:33, 1.71it/s] Train steps ... : 5%|▌ | 5091/100000 [1:38:51<15:23:45, 1.71it/s] Train steps ... : 5%|▌ | 5092/100000 [1:38:52<15:24:43, 1.71it/s] Train steps ... : 5%|▌ | 5093/100000 [1:38:52<15:24:08, 1.71it/s] Train steps ... : 5%|▌ | 5094/100000 [1:38:53<15:23:49, 1.71it/s] Train steps ... : 5%|▌ | 5095/100000 [1:38:54<15:23:13, 1.71it/s] Train steps ... : 5%|▌ | 5096/100000 [1:38:54<15:23:10, 1.71it/s] Train steps ... : 5%|▌ | 5097/100000 [1:38:55<15:23:07, 1.71it/s] Train steps ... : 5%|▌ | 5098/100000 [1:38:55<15:23:06, 1.71it/s] Train steps ... : 5%|▌ | 5099/100000 [1:38:56<15:24:02, 1.71it/s] Train steps ... : 5%|▌ | 5100/100000 [1:38:56<15:24:00, 1.71it/s]Step... (5100 / 100000 | Loss: 1.7390673160552979, Learning Rate: 9.537688442211056e-05) Step... (5100 / 100000 | Loss: 1.2045552730560303, Learning Rate: 9.537688442211056e-05) Train steps ... : 5%|▌ | 5100/100000 [1:38:57<15:24:00, 1.71it/s] Train steps ... : 5%|▌ | 5101/100000 [1:38:57<15:24:07, 1.71it/s] Train steps ... : 5%|▌ | 5102/100000 [1:38:58<15:24:43, 1.71it/s] Train steps ... : 5%|▌ | 5103/100000 [1:38:58<15:24:21, 1.71it/s] Train steps ... : 5%|▌ | 5104/100000 [1:38:59<15:28:37, 1.70it/s] Train steps ... : 5%|▌ | 5105/100000 [1:38:59<15:25:53, 1.71it/s] Train steps ... : 5%|▌ | 5106/100000 [1:39:00<15:25:55, 1.71it/s] Train steps ... : 5%|▌ | 5107/100000 [1:39:01<15:24:30, 1.71it/s] Train steps ... : 5%|▌ | 5108/100000 [1:39:01<15:25:31, 1.71it/s] Train steps ... : 5%|▌ | 5109/100000 [1:39:02<15:24:12, 1.71it/s] Train steps ... : 5%|▌ | 5110/100000 [1:39:02<15:23:21, 1.71it/s] Train steps ... : 5%|▌ | 5111/100000 [1:39:03<15:23:53, 1.71it/s] Train steps ... : 5%|▌ | 5112/100000 [1:39:03<15:23:55, 1.71it/s] Train steps ... : 5%|▌ | 5113/100000 [1:39:04<15:23:40, 1.71it/s] Train steps ... : 5%|▌ | 5114/100000 [1:39:05<15:23:56, 1.71it/s] Train steps ... : 5%|▌ | 5115/100000 [1:39:05<15:23:12, 1.71it/s] Train steps ... : 5%|▌ | 5116/100000 [1:39:06<15:22:23, 1.71it/s] Train steps ... : 5%|▌ | 5117/100000 [1:39:06<15:22:05, 1.71it/s] Train steps ... : 5%|▌ | 5118/100000 [1:39:07<15:22:12, 1.71it/s] Train steps ... : 5%|▌ | 5119/100000 [1:39:08<15:22:51, 1.71it/s] Train steps ... : 5%|▌ | 5120/100000 [1:39:08<15:22:54, 1.71it/s] Train steps ... : 5%|▌ | 5121/100000 [1:39:09<15:22:18, 1.71it/s] Train steps ... : 5%|▌ | 5122/100000 [1:39:09<15:23:41, 1.71it/s] Train steps ... : 5%|▌ | 5123/100000 [1:39:10<15:24:51, 1.71it/s] Train steps ... : 5%|▌ | 5124/100000 [1:39:10<15:23:48, 1.71it/s] Train steps ... : 5%|▌ | 5125/100000 [1:39:11<15:23:21, 1.71it/s]Step... (5125 / 100000 | Loss: 1.5833299160003662, Learning Rate: 9.535175879396985e-05) Step... (5125 / 100000 | Loss: 1.8563196659088135, Learning Rate: 9.535175879396985e-05) Train steps ... : 5%|▌ | 5125/100000 [1:39:11<15:23:21, 1.71it/s] Train steps ... : 5%|▌ | 5126/100000 [1:39:12<15:23:42, 1.71it/s] Train steps ... : 5%|▌ | 5127/100000 [1:39:12<15:22:56, 1.71it/s] Train steps ... : 5%|▌ | 5128/100000 [1:39:13<15:23:09, 1.71it/s] Train steps ... : 5%|▌ | 5129/100000 [1:39:13<15:22:37, 1.71it/s] Train steps ... : 5%|▌ | 5130/100000 [1:39:14<15:22:52, 1.71it/s] Train steps ... : 5%|▌ | 5131/100000 [1:39:15<15:22:41, 1.71it/s] Train steps ... : 5%|▌ | 5132/100000 [1:39:15<15:21:57, 1.71it/s] Train steps ... : 5%|▌ | 5133/100000 [1:39:16<15:22:00, 1.71it/s] Train steps ... : 5%|▌ | 5134/100000 [1:39:16<15:22:18, 1.71it/s] Train steps ... : 5%|▌ | 5135/100000 [1:39:17<15:22:59, 1.71it/s] Train steps ... : 5%|▌ | 5136/100000 [1:39:17<15:22:49, 1.71it/s] Train steps ... : 5%|▌ | 5137/100000 [1:39:18<15:23:31, 1.71it/s] Train steps ... : 5%|▌ | 5138/100000 [1:39:19<15:24:11, 1.71it/s] Train steps ... : 5%|▌ | 5139/100000 [1:39:19<15:23:56, 1.71it/s] Train steps ... : 5%|▌ | 5140/100000 [1:39:20<15:23:08, 1.71it/s] Train steps ... : 5%|▌ | 5141/100000 [1:39:20<15:24:10, 1.71it/s] Train steps ... : 5%|▌ | 5142/100000 [1:39:21<15:23:38, 1.71it/s] Train steps ... : 5%|▌ | 5143/100000 [1:39:22<15:22:26, 1.71it/s] Train steps ... : 5%|▌ | 5144/100000 [1:39:22<15:22:20, 1.71it/s] Train steps ... : 5%|▌ | 5145/100000 [1:39:23<15:22:32, 1.71it/s] Train steps ... : 5%|▌ | 5146/100000 [1:39:23<15:24:50, 1.71it/s] Train steps ... : 5%|▌ | 5147/100000 [1:39:24<15:24:19, 1.71it/s] Train steps ... : 5%|▌ | 5148/100000 [1:39:24<15:24:01, 1.71it/s] Train steps ... : 5%|▌ | 5149/100000 [1:39:25<15:23:12, 1.71it/s] Train steps ... : 5%|▌ | 5150/100000 [1:39:26<15:22:03, 1.71it/s]Step... (5150 / 100000 | Loss: 1.6941912174224854, Learning Rate: 9.532663316582915e-05) Step... (5150 / 100000 | Loss: 1.77498459815979, Learning Rate: 9.532663316582915e-05) Train steps ... : 5%|▌ | 5150/100000 [1:39:26<15:22:03, 1.71it/s] Train steps ... : 5%|▌ | 5151/100000 [1:39:26<15:22:54, 1.71it/s] Train steps ... : 5%|▌ | 5152/100000 [1:39:27<15:22:18, 1.71it/s] Train steps ... : 5%|▌ | 5153/100000 [1:39:27<15:22:08, 1.71it/s] Train steps ... : 5%|▌ | 5154/100000 [1:39:28<15:23:43, 1.71it/s] Train steps ... : 5%|▌ | 5155/100000 [1:39:29<15:23:44, 1.71it/s] Train steps ... : 5%|▌ | 5156/100000 [1:39:29<15:23:30, 1.71it/s] Train steps ... : 5%|▌ | 5157/100000 [1:39:30<15:23:24, 1.71it/s] Train steps ... : 5%|▌ | 5158/100000 [1:39:30<15:22:45, 1.71it/s] Train steps ... : 5%|▌ | 5159/100000 [1:39:31<15:23:36, 1.71it/s] Train steps ... : 5%|▌ | 5160/100000 [1:39:32<15:23:40, 1.71it/s] Train steps ... : 5%|▌ | 5161/100000 [1:39:32<15:22:44, 1.71it/s] Train steps ... : 5%|▌ | 5162/100000 [1:39:33<15:23:33, 1.71it/s] Train steps ... : 5%|▌ | 5163/100000 [1:39:33<15:24:22, 1.71it/s] Train steps ... : 5%|▌ | 5164/100000 [1:39:34<15:23:09, 1.71it/s] Train steps ... : 5%|▌ | 5165/100000 [1:39:34<15:24:07, 1.71it/s] Train steps ... : 5%|▌ | 5166/100000 [1:39:35<15:23:34, 1.71it/s] Train steps ... : 5%|▌ | 5167/100000 [1:39:36<15:23:43, 1.71it/s] Train steps ... : 5%|▌ | 5168/100000 [1:39:36<15:23:09, 1.71it/s] Train steps ... : 5%|▌ | 5169/100000 [1:39:37<15:22:33, 1.71it/s] Train steps ... : 5%|▌ | 5170/100000 [1:39:37<15:22:09, 1.71it/s] Train steps ... : 5%|▌ | 5171/100000 [1:39:38<15:23:29, 1.71it/s] Train steps ... : 5%|▌ | 5172/100000 [1:39:39<15:23:18, 1.71it/s] Train steps ... : 5%|▌ | 5173/100000 [1:39:39<15:23:03, 1.71it/s] Train steps ... : 5%|▌ | 5174/100000 [1:39:40<15:23:33, 1.71it/s] Train steps ... : 5%|▌ | 5175/100000 [1:39:40<15:22:56, 1.71it/s]Step... (5175 / 100000 | Loss: 2.090515613555908, Learning Rate: 9.530150753768845e-05) Step... (5175 / 100000 | Loss: 1.239489197731018, Learning Rate: 9.530150753768845e-05) Train steps ... : 5%|▌ | 5175/100000 [1:39:41<15:22:56, 1.71it/s] Train steps ... : 5%|▌ | 5176/100000 [1:39:41<15:23:18, 1.71it/s] Train steps ... : 5%|▌ | 5177/100000 [1:39:41<15:23:25, 1.71it/s] Train steps ... : 5%|▌ | 5178/100000 [1:39:42<15:22:25, 1.71it/s] Train steps ... : 5%|▌ | 5179/100000 [1:39:43<15:23:15, 1.71it/s] Train steps ... : 5%|▌ | 5180/100000 [1:39:43<15:23:59, 1.71it/s] Train steps ... : 5%|▌ | 5181/100000 [1:39:44<15:24:02, 1.71it/s] Train steps ... : 5%|▌ | 5182/100000 [1:39:44<15:24:07, 1.71it/s] Train steps ... : 5%|▌ | 5183/100000 [1:39:45<15:24:21, 1.71it/s] Train steps ... : 5%|▌ | 5184/100000 [1:39:46<15:22:27, 1.71it/s] Train steps ... : 5%|▌ | 5185/100000 [1:39:46<15:23:11, 1.71it/s] Train steps ... : 5%|▌ | 5186/100000 [1:39:47<15:22:31, 1.71it/s] Train steps ... : 5%|▌ | 5187/100000 [1:39:47<15:23:16, 1.71it/s] Train steps ... : 5%|▌ | 5188/100000 [1:39:48<15:23:40, 1.71it/s] Train steps ... : 5%|▌ | 5189/100000 [1:39:48<15:22:52, 1.71it/s] Train steps ... : 5%|▌ | 5190/100000 [1:39:49<15:22:26, 1.71it/s] Train steps ... : 5%|▌ | 5191/100000 [1:39:50<15:22:06, 1.71it/s] Train steps ... : 5%|▌ | 5192/100000 [1:39:50<15:22:15, 1.71it/s] Train steps ... : 5%|▌ | 5193/100000 [1:39:51<15:22:09, 1.71it/s] Train steps ... : 5%|▌ | 5194/100000 [1:39:51<15:22:23, 1.71it/s] Train steps ... : 5%|▌ | 5195/100000 [1:39:52<15:22:08, 1.71it/s] Train steps ... : 5%|▌ | 5196/100000 [1:39:53<15:21:56, 1.71it/s] Train steps ... : 5%|▌ | 5197/100000 [1:39:53<15:21:46, 1.71it/s] Train steps ... : 5%|▌ | 5198/100000 [1:39:54<15:21:39, 1.71it/s] Train steps ... : 5%|▌ | 5199/100000 [1:39:54<15:22:20, 1.71it/s] Train steps ... : 5%|▌ | 5200/100000 [1:39:55<15:22:25, 1.71it/s]Step... (5200 / 100000 | Loss: 1.8295040130615234, Learning Rate: 9.527638190954774e-05) Step... (5200 / 100000 | Loss: 1.5030512809753418, Learning Rate: 9.527638190954774e-05) Train steps ... : 5%|▌ | 5200/100000 [1:39:55<15:22:25, 1.71it/s] Train steps ... : 5%|▌ | 5201/100000 [1:39:55<15:24:09, 1.71it/s] Train steps ... : 5%|▌ | 5202/100000 [1:39:56<15:22:53, 1.71it/s] Train steps ... : 5%|▌ | 5203/100000 [1:39:57<15:25:31, 1.71it/s] Train steps ... : 5%|▌ | 5204/100000 [1:39:57<15:24:06, 1.71it/s] Train steps ... : 5%|▌ | 5205/100000 [1:39:58<15:23:46, 1.71it/s] Train steps ... : 5%|▌ | 5206/100000 [1:39:58<15:24:41, 1.71it/s] Train steps ... : 5%|▌ | 5207/100000 [1:39:59<15:23:30, 1.71it/s] Train steps ... : 5%|▌ | 5208/100000 [1:40:00<15:22:50, 1.71it/s] Train steps ... : 5%|▌ | 5209/100000 [1:40:00<15:23:37, 1.71it/s] Train steps ... : 5%|▌ | 5210/100000 [1:40:01<15:23:27, 1.71it/s] Train steps ... : 5%|▌ | 5211/100000 [1:40:01<15:22:43, 1.71it/s] Train steps ... : 5%|▌ | 5212/100000 [1:40:02<15:22:11, 1.71it/s] Train steps ... : 5%|▌ | 5213/100000 [1:40:02<15:22:14, 1.71it/s] Train steps ... : 5%|▌ | 5214/100000 [1:40:03<15:22:12, 1.71it/s] Train steps ... : 5%|▌ | 5215/100000 [1:40:04<15:22:10, 1.71it/s] Train steps ... : 5%|▌ | 5216/100000 [1:40:04<15:21:47, 1.71it/s] Train steps ... : 5%|▌ | 5217/100000 [1:40:05<15:22:03, 1.71it/s] Train steps ... : 5%|▌ | 5218/100000 [1:40:05<15:22:40, 1.71it/s] Train steps ... : 5%|▌ | 5219/100000 [1:40:06<15:23:15, 1.71it/s] Train steps ... : 5%|▌ | 5220/100000 [1:40:07<15:22:35, 1.71it/s] Train steps ... : 5%|▌ | 5221/100000 [1:40:07<15:21:36, 1.71it/s] Train steps ... : 5%|▌ | 5222/100000 [1:40:08<15:21:16, 1.71it/s] Train steps ... : 5%|▌ | 5223/100000 [1:40:08<15:22:07, 1.71it/s] Train steps ... : 5%|▌ | 5224/100000 [1:40:09<15:21:28, 1.71it/s] Train steps ... : 5%|▌ | 5225/100000 [1:40:09<15:22:30, 1.71it/s]Step... (5225 / 100000 | Loss: 1.5383152961730957, Learning Rate: 9.525125628140704e-05) Step... (5225 / 100000 | Loss: 1.7101922035217285, Learning Rate: 9.525125628140704e-05) Train steps ... : 5%|▌ | 5225/100000 [1:40:10<15:22:30, 1.71it/s] Train steps ... : 5%|▌ | 5226/100000 [1:40:10<15:22:44, 1.71it/s] Train steps ... : 5%|▌ | 5227/100000 [1:40:11<15:22:49, 1.71it/s] Train steps ... : 5%|▌ | 5228/100000 [1:40:11<15:22:55, 1.71it/s] Train steps ... : 5%|▌ | 5229/100000 [1:40:12<15:22:34, 1.71it/s] Train steps ... : 5%|▌ | 5230/100000 [1:40:12<15:23:28, 1.71it/s] Train steps ... : 5%|▌ | 5231/100000 [1:40:13<15:22:58, 1.71it/s] Train steps ... : 5%|▌ | 5232/100000 [1:40:14<15:24:27, 1.71it/s] Train steps ... : 5%|▌ | 5233/100000 [1:40:14<15:23:04, 1.71it/s] Train steps ... : 5%|▌ | 5234/100000 [1:40:15<15:23:04, 1.71it/s] Train steps ... : 5%|▌ | 5235/100000 [1:40:15<15:22:52, 1.71it/s] Train steps ... : 5%|▌ | 5236/100000 [1:40:16<15:21:49, 1.71it/s] Train steps ... : 5%|▌ | 5237/100000 [1:40:16<15:23:40, 1.71it/s] Train steps ... : 5%|▌ | 5238/100000 [1:40:17<15:21:34, 1.71it/s] Train steps ... : 5%|▌ | 5239/100000 [1:40:18<15:21:30, 1.71it/s] Train steps ... : 5%|▌ | 5240/100000 [1:40:18<15:21:19, 1.71it/s] Train steps ... : 5%|▌ | 5241/100000 [1:40:19<15:22:28, 1.71it/s] Train steps ... : 5%|▌ | 5242/100000 [1:40:19<15:21:49, 1.71it/s] Train steps ... : 5%|▌ | 5243/100000 [1:40:20<15:23:33, 1.71it/s] Train steps ... : 5%|▌ | 5244/100000 [1:40:21<15:22:47, 1.71it/s] Train steps ... : 5%|▌ | 5245/100000 [1:40:21<15:22:01, 1.71it/s] Train steps ... : 5%|▌ | 5246/100000 [1:40:22<15:22:19, 1.71it/s] Train steps ... : 5%|▌ | 5247/100000 [1:40:22<15:22:25, 1.71it/s] Train steps ... : 5%|▌ | 5248/100000 [1:40:23<15:21:09, 1.71it/s] Train steps ... : 5%|▌ | 5249/100000 [1:40:23<15:23:57, 1.71it/s] Train steps ... : 5%|▌ | 5250/100000 [1:40:24<15:22:36, 1.71it/s]Step... (5250 / 100000 | Loss: 1.5396788120269775, Learning Rate: 9.522613065326634e-05) Step... (5250 / 100000 | Loss: 1.5076544284820557, Learning Rate: 9.522613065326634e-05) Train steps ... : 5%|▌ | 5250/100000 [1:40:24<15:22:36, 1.71it/s] Train steps ... : 5%|▌ | 5251/100000 [1:40:25<15:21:54, 1.71it/s] Train steps ... : 5%|▌ | 5252/100000 [1:40:25<15:22:24, 1.71it/s] Train steps ... : 5%|▌ | 5253/100000 [1:40:26<15:23:09, 1.71it/s] Train steps ... : 5%|▌ | 5254/100000 [1:40:26<15:22:11, 1.71it/s] Train steps ... : 5%|▌ | 5255/100000 [1:40:27<15:22:12, 1.71it/s] Train steps ... : 5%|▌ | 5256/100000 [1:40:28<15:21:56, 1.71it/s] Train steps ... : 5%|▌ | 5257/100000 [1:40:28<15:21:46, 1.71it/s] Train steps ... : 5%|▌ | 5258/100000 [1:40:29<15:23:17, 1.71it/s] Train steps ... : 5%|▌ | 5259/100000 [1:40:29<15:22:34, 1.71it/s] Train steps ... : 5%|▌ | 5260/100000 [1:40:30<15:21:51, 1.71it/s] Train steps ... : 5%|▌ | 5261/100000 [1:40:30<15:21:17, 1.71it/s] Train steps ... : 5%|▌ | 5262/100000 [1:40:31<15:21:53, 1.71it/s] Train steps ... : 5%|▌ | 5263/100000 [1:40:32<15:21:40, 1.71it/s] Train steps ... : 5%|▌ | 5264/100000 [1:40:32<15:22:27, 1.71it/s] Train steps ... : 5%|▌ | 5265/100000 [1:40:33<15:21:52, 1.71it/s] Train steps ... : 5%|▌ | 5266/100000 [1:40:33<15:21:50, 1.71it/s] Train steps ... : 5%|▌ | 5267/100000 [1:40:34<15:22:32, 1.71it/s] Train steps ... : 5%|▌ | 5268/100000 [1:40:35<15:23:10, 1.71it/s] Train steps ... : 5%|▌ | 5269/100000 [1:40:35<15:21:41, 1.71it/s] Train steps ... : 5%|▌ | 5270/100000 [1:40:36<15:23:41, 1.71it/s] Train steps ... : 5%|▌ | 5271/100000 [1:40:36<15:22:29, 1.71it/s] Train steps ... : 5%|▌ | 5272/100000 [1:40:37<15:22:12, 1.71it/s] Train steps ... : 5%|▌ | 5273/100000 [1:40:38<15:22:22, 1.71it/s] Train steps ... : 5%|▌ | 5274/100000 [1:40:38<15:23:29, 1.71it/s] Train steps ... : 5%|▌ | 5275/100000 [1:40:39<15:23:20, 1.71it/s]Step... (5275 / 100000 | Loss: 1.7926857471466064, Learning Rate: 9.520100502512563e-05) Step... (5275 / 100000 | Loss: 1.2105822563171387, Learning Rate: 9.520100502512563e-05) Train steps ... : 5%|▌ | 5275/100000 [1:40:39<15:23:20, 1.71it/s] Train steps ... : 5%|▌ | 5276/100000 [1:40:39<15:23:02, 1.71it/s] Train steps ... : 5%|▌ | 5277/100000 [1:40:40<15:23:06, 1.71it/s] Train steps ... : 5%|▌ | 5278/100000 [1:40:40<15:24:27, 1.71it/s] Train steps ... : 5%|▌ | 5279/100000 [1:40:41<15:22:57, 1.71it/s] Train steps ... : 5%|▌ | 5280/100000 [1:40:42<15:23:05, 1.71it/s] Train steps ... : 5%|▌ | 5281/100000 [1:40:42<15:22:19, 1.71it/s] Train steps ... : 5%|▌ | 5282/100000 [1:40:43<15:21:33, 1.71it/s] Train steps ... : 5%|▌ | 5283/100000 [1:40:43<15:22:49, 1.71it/s] Train steps ... : 5%|▌ | 5284/100000 [1:40:44<15:23:24, 1.71it/s] Train steps ... : 5%|▌ | 5285/100000 [1:40:45<15:22:16, 1.71it/s] Train steps ... : 5%|▌ | 5286/100000 [1:40:45<15:22:37, 1.71it/s] Train steps ... : 5%|▌ | 5287/100000 [1:40:46<15:21:58, 1.71it/s] Train steps ... : 5%|▌ | 5288/100000 [1:40:46<15:21:42, 1.71it/s] Train steps ... : 5%|▌ | 5289/100000 [1:40:47<15:21:41, 1.71it/s] Train steps ... : 5%|▌ | 5290/100000 [1:40:47<15:21:22, 1.71it/s] Train steps ... : 5%|▌ | 5291/100000 [1:40:48<15:23:21, 1.71it/s] Train steps ... : 5%|▌ | 5292/100000 [1:40:49<15:24:26, 1.71it/s] Train steps ... : 5%|▌ | 5293/100000 [1:40:49<15:23:23, 1.71it/s] Train steps ... : 5%|▌ | 5294/100000 [1:40:50<15:22:53, 1.71it/s] Train steps ... : 5%|▌ | 5295/100000 [1:40:50<15:24:25, 1.71it/s] Train steps ... : 5%|▌ | 5296/100000 [1:40:51<15:24:27, 1.71it/s] Train steps ... : 5%|▌ | 5297/100000 [1:40:52<15:25:42, 1.71it/s] Train steps ... : 5%|▌ | 5298/100000 [1:40:52<15:23:38, 1.71it/s] Train steps ... : 5%|▌ | 5299/100000 [1:40:53<15:24:06, 1.71it/s] Train steps ... : 5%|▌ | 5300/100000 [1:40:53<15:24:20, 1.71it/s]Step... (5300 / 100000 | Loss: 1.597320795059204, Learning Rate: 9.517587939698493e-05) Step... (5300 / 100000 | Loss: 1.8078997135162354, Learning Rate: 9.517587939698493e-05) Train steps ... : 5%|▌ | 5300/100000 [1:40:54<15:24:20, 1.71it/s] Train steps ... : 5%|▌ | 5301/100000 [1:40:54<15:24:13, 1.71it/s] Train steps ... : 5%|▌ | 5302/100000 [1:40:54<15:22:51, 1.71it/s] Train steps ... : 5%|▌ | 5303/100000 [1:40:55<15:22:25, 1.71it/s] Train steps ... : 5%|▌ | 5304/100000 [1:40:56<15:22:26, 1.71it/s] Train steps ... : 5%|▌ | 5305/100000 [1:40:56<15:22:32, 1.71it/s] Train steps ... : 5%|▌ | 5306/100000 [1:40:57<15:22:08, 1.71it/s] Train steps ... : 5%|▌ | 5307/100000 [1:40:57<15:22:27, 1.71it/s] Train steps ... : 5%|▌ | 5308/100000 [1:40:58<15:21:34, 1.71it/s] Train steps ... : 5%|▌ | 5309/100000 [1:40:59<15:22:06, 1.71it/s] Train steps ... : 5%|▌ | 5310/100000 [1:40:59<15:21:22, 1.71it/s] Train steps ... : 5%|▌ | 5311/100000 [1:41:00<15:22:12, 1.71it/s] Train steps ... : 5%|▌ | 5312/100000 [1:41:00<15:22:46, 1.71it/s] Train steps ... : 5%|▌ | 5313/100000 [1:41:01<15:22:52, 1.71it/s] Train steps ... : 5%|▌ | 5314/100000 [1:41:01<15:23:45, 1.71it/s] Train steps ... : 5%|▌ | 5315/100000 [1:41:02<15:23:00, 1.71it/s] Train steps ... : 5%|▌ | 5316/100000 [1:41:03<15:22:48, 1.71it/s] Train steps ... : 5%|▌ | 5317/100000 [1:41:03<15:22:37, 1.71it/s] Train steps ... : 5%|▌ | 5318/100000 [1:41:04<15:22:12, 1.71it/s] Train steps ... : 5%|▌ | 5319/100000 [1:41:04<15:21:23, 1.71it/s] Train steps ... : 5%|▌ | 5320/100000 [1:41:05<15:21:57, 1.71it/s] Train steps ... : 5%|▌ | 5321/100000 [1:41:06<15:22:26, 1.71it/s] Train steps ... : 5%|▌ | 5322/100000 [1:41:06<15:23:16, 1.71it/s] Train steps ... : 5%|▌ | 5323/100000 [1:41:07<15:22:03, 1.71it/s] Train steps ... : 5%|▌ | 5324/100000 [1:41:07<15:22:44, 1.71it/s] Train steps ... : 5%|▌ | 5325/100000 [1:41:08<15:21:12, 1.71it/s]Step... (5325 / 100000 | Loss: 1.4301620721817017, Learning Rate: 9.515075376884423e-05) Step... (5325 / 100000 | Loss: 1.5182695388793945, Learning Rate: 9.515075376884423e-05) Train steps ... : 5%|▌ | 5325/100000 [1:41:08<15:21:12, 1.71it/s] Train steps ... : 5%|▌ | 5326/100000 [1:41:08<15:22:22, 1.71it/s] Train steps ... : 5%|▌ | 5327/100000 [1:41:09<15:22:44, 1.71it/s] Train steps ... : 5%|▌ | 5328/100000 [1:41:10<15:23:26, 1.71it/s] Train steps ... : 5%|▌ | 5329/100000 [1:41:10<15:23:06, 1.71it/s] Train steps ... : 5%|▌ | 5330/100000 [1:41:11<15:23:14, 1.71it/s] Train steps ... : 5%|▌ | 5331/100000 [1:41:11<15:21:26, 1.71it/s] Train steps ... : 5%|▌ | 5332/100000 [1:41:12<15:22:13, 1.71it/s] Train steps ... : 5%|▌ | 5333/100000 [1:41:13<15:21:10, 1.71it/s] Train steps ... : 5%|▌ | 5334/100000 [1:41:13<15:21:44, 1.71it/s] Train steps ... : 5%|▌ | 5335/100000 [1:41:14<15:21:24, 1.71it/s] Train steps ... : 5%|▌ | 5336/100000 [1:41:14<15:22:25, 1.71it/s] Train steps ... : 5%|▌ | 5337/100000 [1:41:15<15:21:35, 1.71it/s] Train steps ... : 5%|▌ | 5338/100000 [1:41:16<15:21:37, 1.71it/s] Train steps ... : 5%|▌ | 5339/100000 [1:41:16<15:23:00, 1.71it/s] Train steps ... : 5%|▌ | 5340/100000 [1:41:17<15:20:53, 1.71it/s] Train steps ... : 5%|▌ | 5341/100000 [1:41:17<15:21:24, 1.71it/s] Train steps ... : 5%|▌ | 5342/100000 [1:41:18<15:22:19, 1.71it/s] Train steps ... : 5%|▌ | 5343/100000 [1:41:18<15:21:49, 1.71it/s] Train steps ... : 5%|▌ | 5344/100000 [1:41:19<15:21:27, 1.71it/s] Train steps ... : 5%|▌ | 5345/100000 [1:41:20<15:21:25, 1.71it/s] Train steps ... : 5%|▌ | 5346/100000 [1:41:20<15:22:42, 1.71it/s] Train steps ... : 5%|▌ | 5347/100000 [1:41:21<15:22:33, 1.71it/s] Train steps ... : 5%|▌ | 5348/100000 [1:41:21<15:22:12, 1.71it/s] Train steps ... : 5%|▌ | 5349/100000 [1:41:22<15:22:30, 1.71it/s] Train steps ... : 5%|▌ | 5350/100000 [1:41:23<15:22:21, 1.71it/s]Step... (5350 / 100000 | Loss: 1.8576492071151733, Learning Rate: 9.512562814070352e-05) Step... (5350 / 100000 | Loss: 1.4931281805038452, Learning Rate: 9.512562814070352e-05) Train steps ... : 5%|▌ | 5350/100000 [1:41:23<15:22:21, 1.71it/s] Train steps ... : 5%|▌ | 5351/100000 [1:41:23<15:23:04, 1.71it/s] Train steps ... : 5%|▌ | 5352/100000 [1:41:24<15:22:18, 1.71it/s] Train steps ... : 5%|▌ | 5353/100000 [1:41:24<15:21:19, 1.71it/s] Train steps ... : 5%|▌ | 5354/100000 [1:41:25<15:23:03, 1.71it/s] Train steps ... : 5%|▌ | 5355/100000 [1:41:25<15:22:52, 1.71it/s] Train steps ... : 5%|▌ | 5356/100000 [1:41:26<15:22:44, 1.71it/s] Train steps ... : 5%|▌ | 5357/100000 [1:41:27<15:22:36, 1.71it/s] Train steps ... : 5%|▌ | 5358/100000 [1:41:27<15:21:21, 1.71it/s] Train steps ... : 5%|▌ | 5359/100000 [1:41:28<15:21:28, 1.71it/s] Train steps ... : 5%|▌ | 5360/100000 [1:41:28<15:21:03, 1.71it/s] Train steps ... : 5%|▌ | 5361/100000 [1:41:29<15:20:36, 1.71it/s] Train steps ... : 5%|▌ | 5362/100000 [1:41:30<15:21:05, 1.71it/s] Train steps ... : 5%|▌ | 5363/100000 [1:41:30<15:21:06, 1.71it/s] Train steps ... : 5%|▌ | 5364/100000 [1:41:31<15:20:08, 1.71it/s] Train steps ... : 5%|▌ | 5365/100000 [1:41:31<15:20:09, 1.71it/s] Train steps ... : 5%|▌ | 5366/100000 [1:41:32<15:21:34, 1.71it/s] Train steps ... : 5%|▌ | 5367/100000 [1:41:32<15:22:09, 1.71it/s] Train steps ... : 5%|▌ | 5368/100000 [1:41:33<15:22:25, 1.71it/s] Train steps ... : 5%|▌ | 5369/100000 [1:41:34<15:23:33, 1.71it/s] Train steps ... : 5%|▌ | 5370/100000 [1:41:34<15:22:05, 1.71it/s] Train steps ... : 5%|▌ | 5371/100000 [1:41:35<15:21:42, 1.71it/s] Train steps ... : 5%|▌ | 5372/100000 [1:41:35<15:21:32, 1.71it/s] Train steps ... : 5%|▌ | 5373/100000 [1:41:36<15:22:24, 1.71it/s] Train steps ... : 5%|▌ | 5374/100000 [1:41:37<15:22:27, 1.71it/s] Train steps ... : 5%|▌ | 5375/100000 [1:41:37<15:22:10, 1.71it/s]Step... (5375 / 100000 | Loss: 1.8573908805847168, Learning Rate: 9.510050251256282e-05) Step... (5375 / 100000 | Loss: 1.5028845071792603, Learning Rate: 9.510050251256282e-05) Train steps ... : 5%|▌ | 5375/100000 [1:41:37<15:22:10, 1.71it/s] Train steps ... : 5%|▌ | 5376/100000 [1:41:38<15:22:09, 1.71it/s] Train steps ... : 5%|▌ | 5377/100000 [1:41:38<15:21:28, 1.71it/s] Train steps ... : 5%|▌ | 5378/100000 [1:41:39<15:20:43, 1.71it/s] Train steps ... : 5%|▌ | 5379/100000 [1:41:39<15:20:18, 1.71it/s] Train steps ... : 5%|▌ | 5380/100000 [1:41:40<15:21:05, 1.71it/s] Train steps ... : 5%|▌ | 5381/100000 [1:41:41<15:20:23, 1.71it/s] Train steps ... : 5%|▌ | 5382/100000 [1:41:41<15:20:31, 1.71it/s] Train steps ... : 5%|▌ | 5383/100000 [1:41:42<15:20:49, 1.71it/s] Train steps ... : 5%|▌ | 5384/100000 [1:41:42<15:21:04, 1.71it/s] Train steps ... : 5%|▌ | 5385/100000 [1:41:43<15:20:54, 1.71it/s] Train steps ... : 5%|▌ | 5386/100000 [1:41:44<15:20:10, 1.71it/s] Train steps ... : 5%|▌ | 5387/100000 [1:41:44<15:19:56, 1.71it/s] Train steps ... : 5%|▌ | 5388/100000 [1:41:45<15:20:31, 1.71it/s] Train steps ... : 5%|▌ | 5389/100000 [1:41:45<15:21:03, 1.71it/s] Train steps ... : 5%|▌ | 5390/100000 [1:41:46<15:20:27, 1.71it/s] Train steps ... : 5%|▌ | 5391/100000 [1:41:46<15:20:00, 1.71it/s] Train steps ... : 5%|▌ | 5392/100000 [1:41:47<15:19:17, 1.72it/s] Train steps ... : 5%|▌ | 5393/100000 [1:41:48<15:19:22, 1.72it/s] Train steps ... : 5%|▌ | 5394/100000 [1:41:48<15:19:33, 1.71it/s] Train steps ... : 5%|▌ | 5395/100000 [1:41:49<15:20:49, 1.71it/s] Train steps ... : 5%|▌ | 5396/100000 [1:41:49<15:21:16, 1.71it/s] Train steps ... : 5%|▌ | 5397/100000 [1:41:50<15:21:44, 1.71it/s] Train steps ... : 5%|▌ | 5398/100000 [1:41:51<15:21:09, 1.71it/s] Train steps ... : 5%|▌ | 5399/100000 [1:41:51<15:21:04, 1.71it/s] Train steps ... : 5%|▌ | 5400/100000 [1:41:52<15:20:24, 1.71it/s]Step... (5400 / 100000 | Loss: 1.856158971786499, Learning Rate: 9.507537688442212e-05) Step... (5400 / 100000 | Loss: 1.551166296005249, Learning Rate: 9.507537688442212e-05) Train steps ... : 5%|▌ | 5400/100000 [1:41:52<15:20:24, 1.71it/s] Train steps ... : 5%|▌ | 5401/100000 [1:41:52<15:20:35, 1.71it/s] Train steps ... : 5%|▌ | 5402/100000 [1:41:53<15:21:15, 1.71it/s] Train steps ... : 5%|▌ | 5403/100000 [1:41:53<15:20:32, 1.71it/s] Train steps ... : 5%|▌ | 5404/100000 [1:41:54<15:20:56, 1.71it/s] Train steps ... : 5%|▌ | 5405/100000 [1:41:55<15:20:53, 1.71it/s] Train steps ... : 5%|▌ | 5406/100000 [1:41:55<15:21:26, 1.71it/s] Train steps ... : 5%|▌ | 5407/100000 [1:41:56<15:21:50, 1.71it/s] Train steps ... : 5%|▌ | 5408/100000 [1:41:56<15:21:15, 1.71it/s] Train steps ... : 5%|▌ | 5409/100000 [1:41:57<15:21:15, 1.71it/s] Train steps ... : 5%|▌ | 5410/100000 [1:41:58<15:21:54, 1.71it/s] Train steps ... : 5%|▌ | 5411/100000 [1:41:58<15:21:38, 1.71it/s] Train steps ... : 5%|▌ | 5412/100000 [1:41:59<15:21:10, 1.71it/s] Train steps ... : 5%|▌ | 5413/100000 [1:41:59<15:20:31, 1.71it/s] Train steps ... : 5%|▌ | 5414/100000 [1:42:00<15:20:58, 1.71it/s] Train steps ... : 5%|▌ | 5415/100000 [1:42:00<15:20:17, 1.71it/s] Train steps ... : 5%|▌ | 5416/100000 [1:42:01<15:20:16, 1.71it/s] Train steps ... : 5%|▌ | 5417/100000 [1:42:02<15:19:26, 1.71it/s] Train steps ... : 5%|▌ | 5418/100000 [1:42:02<15:19:57, 1.71it/s] Train steps ... : 5%|▌ | 5419/100000 [1:42:03<15:20:31, 1.71it/s] Train steps ... : 5%|▌ | 5420/100000 [1:42:03<15:21:01, 1.71it/s] Train steps ... : 5%|▌ | 5421/100000 [1:42:04<15:20:27, 1.71it/s] Train steps ... : 5%|▌ | 5422/100000 [1:42:05<15:21:10, 1.71it/s] Train steps ... : 5%|▌ | 5423/100000 [1:42:05<15:21:55, 1.71it/s] Train steps ... : 5%|▌ | 5424/100000 [1:42:06<15:21:19, 1.71it/s] Train steps ... : 5%|▌ | 5425/100000 [1:42:06<15:21:07, 1.71it/s]Step... (5425 / 100000 | Loss: 1.3391718864440918, Learning Rate: 9.505025125628141e-05) Step... (5425 / 100000 | Loss: 1.3393096923828125, Learning Rate: 9.505025125628141e-05) Train steps ... : 5%|▌ | 5425/100000 [1:42:07<15:21:07, 1.71it/s] Train steps ... : 5%|▌ | 5426/100000 [1:42:07<15:22:02, 1.71it/s] Train steps ... : 5%|▌ | 5427/100000 [1:42:08<15:21:30, 1.71it/s] Train steps ... : 5%|▌ | 5428/100000 [1:42:08<15:21:06, 1.71it/s] Train steps ... : 5%|▌ | 5429/100000 [1:42:09<15:20:52, 1.71it/s] Train steps ... : 5%|▌ | 5430/100000 [1:42:09<15:20:14, 1.71it/s] Train steps ... : 5%|▌ | 5431/100000 [1:42:10<15:20:04, 1.71it/s] Train steps ... : 5%|▌ | 5432/100000 [1:42:10<15:19:54, 1.71it/s] Train steps ... : 5%|▌ | 5433/100000 [1:42:11<15:19:52, 1.71it/s] Train steps ... : 5%|▌ | 5434/100000 [1:42:12<15:19:45, 1.71it/s] Train steps ... : 5%|▌ | 5435/100000 [1:42:12<15:21:30, 1.71it/s] Train steps ... : 5%|▌ | 5436/100000 [1:42:13<15:24:56, 1.70it/s] Train steps ... : 5%|▌ | 5437/100000 [1:42:13<15:22:41, 1.71it/s] Train steps ... : 5%|▌ | 5438/100000 [1:42:14<15:22:21, 1.71it/s] Train steps ... : 5%|▌ | 5439/100000 [1:42:15<15:22:10, 1.71it/s] Train steps ... : 5%|▌ | 5440/100000 [1:42:15<15:21:47, 1.71it/s] Train steps ... : 5%|▌ | 5441/100000 [1:42:16<15:20:51, 1.71it/s] Train steps ... : 5%|▌ | 5442/100000 [1:42:16<15:20:04, 1.71it/s] Train steps ... : 5%|▌ | 5443/100000 [1:42:17<15:21:16, 1.71it/s] Train steps ... : 5%|▌ | 5444/100000 [1:42:17<15:20:54, 1.71it/s] Train steps ... : 5%|▌ | 5445/100000 [1:42:18<15:23:17, 1.71it/s] Train steps ... : 5%|▌ | 5446/100000 [1:42:19<15:22:58, 1.71it/s] Train steps ... : 5%|▌ | 5447/100000 [1:42:19<15:22:07, 1.71it/s] Train steps ... : 5%|▌ | 5448/100000 [1:42:20<15:21:21, 1.71it/s] Train steps ... : 5%|▌ | 5449/100000 [1:42:20<15:24:18, 1.70it/s] Train steps ... : 5%|▌ | 5450/100000 [1:42:21<15:21:36, 1.71it/s]Step... (5450 / 100000 | Loss: 1.5259242057800293, Learning Rate: 9.502512562814071e-05) Step... (5450 / 100000 | Loss: 1.3063077926635742, Learning Rate: 9.502512562814071e-05) Train steps ... : 5%|▌ | 5450/100000 [1:42:21<15:21:36, 1.71it/s] Train steps ... : 5%|▌ | 5451/100000 [1:42:22<15:22:13, 1.71it/s] Train steps ... : 5%|▌ | 5452/100000 [1:42:22<15:21:20, 1.71it/s] Train steps ... : 5%|▌ | 5453/100000 [1:42:23<15:21:23, 1.71it/s] Train steps ... : 5%|▌ | 5454/100000 [1:42:23<15:21:40, 1.71it/s] Train steps ... : 5%|▌ | 5455/100000 [1:42:24<15:21:06, 1.71it/s] Train steps ... : 5%|▌ | 5456/100000 [1:42:24<15:20:58, 1.71it/s] Train steps ... : 5%|▌ | 5457/100000 [1:42:25<15:20:36, 1.71it/s] Train steps ... : 5%|▌ | 5458/100000 [1:42:26<15:21:28, 1.71it/s] Train steps ... : 5%|▌ | 5459/100000 [1:42:26<15:22:19, 1.71it/s] Train steps ... : 5%|▌ | 5460/100000 [1:42:27<15:21:41, 1.71it/s] Train steps ... : 5%|▌ | 5461/100000 [1:42:27<15:21:32, 1.71it/s] Train steps ... : 5%|▌ | 5462/100000 [1:42:28<15:21:36, 1.71it/s] Train steps ... : 5%|▌ | 5463/100000 [1:42:29<15:22:19, 1.71it/s] Train steps ... : 5%|▌ | 5464/100000 [1:42:29<15:21:00, 1.71it/s] Train steps ... : 5%|▌ | 5465/100000 [1:42:30<15:20:25, 1.71it/s] Train steps ... : 5%|▌ | 5466/100000 [1:42:30<15:21:09, 1.71it/s] Train steps ... : 5%|▌ | 5467/100000 [1:42:31<15:20:24, 1.71it/s] Train steps ... : 5%|▌ | 5468/100000 [1:42:31<15:23:28, 1.71it/s] Train steps ... : 5%|▌ | 5469/100000 [1:42:32<15:22:18, 1.71it/s] Train steps ... : 5%|▌ | 5470/100000 [1:42:33<15:21:17, 1.71it/s] Train steps ... : 5%|▌ | 5471/100000 [1:42:33<15:20:50, 1.71it/s] Train steps ... : 5%|▌ | 5472/100000 [1:42:34<15:22:25, 1.71it/s] Train steps ... : 5%|▌ | 5473/100000 [1:42:34<15:21:08, 1.71it/s] Train steps ... : 5%|▌ | 5474/100000 [1:42:35<15:21:24, 1.71it/s] Train steps ... : 5%|▌ | 5475/100000 [1:42:36<15:21:05, 1.71it/s]Step... (5475 / 100000 | Loss: 2.0566277503967285, Learning Rate: 9.5e-05) Step... (5475 / 100000 | Loss: 2.0590195655822754, Learning Rate: 9.5e-05) Train steps ... : 5%|▌ | 5475/100000 [1:42:36<15:21:05, 1.71it/s] Train steps ... : 5%|▌ | 5476/100000 [1:42:36<15:21:14, 1.71it/s] Train steps ... : 5%|▌ | 5477/100000 [1:42:37<15:20:39, 1.71it/s] Train steps ... : 5%|▌ | 5478/100000 [1:42:37<15:21:19, 1.71it/s] Train steps ... : 5%|▌ | 5479/100000 [1:42:38<15:20:00, 1.71it/s] Train steps ... : 5%|▌ | 5480/100000 [1:42:39<15:21:37, 1.71it/s] Train steps ... : 5%|▌ | 5481/100000 [1:42:39<15:20:31, 1.71it/s] Train steps ... : 5%|▌ | 5482/100000 [1:42:40<15:19:58, 1.71it/s] Train steps ... : 5%|▌ | 5483/100000 [1:42:40<15:19:28, 1.71it/s] Train steps ... : 5%|▌ | 5484/100000 [1:42:41<15:23:20, 1.71it/s] Train steps ... : 5%|▌ | 5485/100000 [1:42:41<15:21:09, 1.71it/s] Train steps ... : 5%|▌ | 5486/100000 [1:42:42<15:21:23, 1.71it/s] Train steps ... : 5%|▌ | 5487/100000 [1:42:43<15:21:51, 1.71it/s] Train steps ... : 5%|▌ | 5488/100000 [1:42:43<15:20:41, 1.71it/s] Train steps ... : 5%|▌ | 5489/100000 [1:42:44<15:21:23, 1.71it/s] Train steps ... : 5%|▌ | 5490/100000 [1:42:44<15:20:19, 1.71it/s] Train steps ... : 5%|▌ | 5491/100000 [1:42:45<15:20:53, 1.71it/s] Train steps ... : 5%|▌ | 5492/100000 [1:42:46<15:20:06, 1.71it/s] Train steps ... : 5%|▌ | 5493/100000 [1:42:46<15:21:02, 1.71it/s] Train steps ... : 5%|▌ | 5494/100000 [1:42:47<15:20:06, 1.71it/s] Train steps ... : 5%|▌ | 5495/100000 [1:42:47<15:19:42, 1.71it/s] Train steps ... : 5%|▌ | 5496/100000 [1:42:48<15:19:33, 1.71it/s] Train steps ... : 5%|▌ | 5497/100000 [1:42:48<15:20:39, 1.71it/s] Train steps ... : 5%|▌ | 5498/100000 [1:42:49<15:23:33, 1.71it/s] Train steps ... : 5%|▌ | 5499/100000 [1:42:50<15:22:57, 1.71it/s] Train steps ... : 6%|▌ | 5500/100000 [1:42:50<15:22:50, 1.71it/s]Step... (5500 / 100000 | Loss: 1.529461145401001, Learning Rate: 9.49748743718593e-05) Step... (5500 / 100000 | Loss: 1.608020305633545, Learning Rate: 9.49748743718593e-05) Train steps ... : 6%|▌ | 5500/100000 [1:42:51<15:22:50, 1.71it/s] Train steps ... : 6%|▌ | 5501/100000 [1:42:51<15:23:43, 1.71it/s] Train steps ... : 6%|▌ | 5502/100000 [1:42:51<15:21:45, 1.71it/s] Train steps ... : 6%|▌ | 5503/100000 [1:42:52<15:21:08, 1.71it/s] Train steps ... : 6%|▌ | 5504/100000 [1:42:53<15:23:12, 1.71it/s] Train steps ... : 6%|▌ | 5505/100000 [1:42:53<15:20:19, 1.71it/s] Train steps ... : 6%|▌ | 5506/100000 [1:42:54<15:20:20, 1.71it/s] Train steps ... : 6%|▌ | 5507/100000 [1:42:54<15:21:04, 1.71it/s] Train steps ... : 6%|▌ | 5508/100000 [1:42:55<15:22:42, 1.71it/s] Train steps ... : 6%|▌ | 5509/100000 [1:42:55<15:22:08, 1.71it/s] Train steps ... : 6%|▌ | 5510/100000 [1:42:56<15:21:27, 1.71it/s] Train steps ... : 6%|▌ | 5511/100000 [1:42:57<15:20:56, 1.71it/s] Train steps ... : 6%|▌ | 5512/100000 [1:42:57<15:20:52, 1.71it/s] Train steps ... : 6%|▌ | 5513/100000 [1:42:58<15:22:01, 1.71it/s] Train steps ... : 6%|▌ | 5514/100000 [1:42:58<15:24:42, 1.70it/s] Train steps ... : 6%|▌ | 5515/100000 [1:42:59<15:21:24, 1.71it/s] Train steps ... : 6%|▌ | 5516/100000 [1:43:00<15:21:14, 1.71it/s] Train steps ... : 6%|▌ | 5517/100000 [1:43:00<15:22:44, 1.71it/s] Train steps ... : 6%|▌ | 5518/100000 [1:43:01<15:20:21, 1.71it/s] Train steps ... : 6%|▌ | 5519/100000 [1:43:01<15:21:42, 1.71it/s] Train steps ... : 6%|▌ | 5520/100000 [1:43:02<15:25:20, 1.70it/s] Train steps ... : 6%|▌ | 5521/100000 [1:43:02<15:25:45, 1.70it/s] Train steps ... : 6%|▌ | 5522/100000 [1:43:03<15:24:42, 1.70it/s] Train steps ... : 6%|▌ | 5523/100000 [1:43:04<15:23:39, 1.70it/s] Train steps ... : 6%|▌ | 5524/100000 [1:43:04<15:26:06, 1.70it/s] Train steps ... : 6%|▌ | 5525/100000 [1:43:05<15:22:50, 1.71it/s]Step... (5525 / 100000 | Loss: 1.581154465675354, Learning Rate: 9.49497487437186e-05) Step... (5525 / 100000 | Loss: 1.4517600536346436, Learning Rate: 9.49497487437186e-05) Train steps ... : 6%|▌ | 5525/100000 [1:43:05<15:22:50, 1.71it/s] Train steps ... : 6%|▌ | 5526/100000 [1:43:05<15:23:04, 1.71it/s] Train steps ... : 6%|▌ | 5527/100000 [1:43:06<15:21:17, 1.71it/s] Train steps ... : 6%|▌ | 5528/100000 [1:43:07<15:21:22, 1.71it/s] Train steps ... : 6%|▌ | 5529/100000 [1:43:07<15:20:59, 1.71it/s] Train steps ... : 6%|▌ | 5530/100000 [1:43:08<15:22:49, 1.71it/s] Train steps ... : 6%|▌ | 5531/100000 [1:43:08<15:22:24, 1.71it/s] Train steps ... : 6%|▌ | 5532/100000 [1:43:09<15:22:12, 1.71it/s] Train steps ... : 6%|▌ | 5533/100000 [1:43:10<15:21:51, 1.71it/s] Train steps ... : 6%|▌ | 5534/100000 [1:43:10<15:23:24, 1.71it/s] Train steps ... : 6%|▌ | 5535/100000 [1:43:11<15:23:14, 1.71it/s] Train steps ... : 6%|▌ | 5536/100000 [1:43:11<15:21:40, 1.71it/s] Train steps ... : 6%|▌ | 5537/100000 [1:43:12<15:22:57, 1.71it/s] Train steps ... : 6%|▌ | 5538/100000 [1:43:12<15:20:30, 1.71it/s] Train steps ... : 6%|▌ | 5539/100000 [1:43:13<15:22:29, 1.71it/s] Train steps ... : 6%|▌ | 5540/100000 [1:43:14<15:21:46, 1.71it/s] Train steps ... : 6%|▌ | 5541/100000 [1:43:14<15:22:26, 1.71it/s] Train steps ... : 6%|▌ | 5542/100000 [1:43:15<15:25:04, 1.70it/s] Train steps ... : 6%|▌ | 5543/100000 [1:43:15<15:22:53, 1.71it/s] Train steps ... : 6%|▌ | 5544/100000 [1:43:16<15:24:15, 1.70it/s] Train steps ... : 6%|▌ | 5545/100000 [1:43:17<15:21:27, 1.71it/s] Train steps ... : 6%|▌ | 5546/100000 [1:43:17<15:21:33, 1.71it/s] Train steps ... : 6%|▌ | 5547/100000 [1:43:18<15:21:00, 1.71it/s] Train steps ... : 6%|▌ | 5548/100000 [1:43:18<15:21:45, 1.71it/s] Train steps ... : 6%|▌ | 5549/100000 [1:43:19<15:19:57, 1.71it/s] Train steps ... : 6%|▌ | 5550/100000 [1:43:19<15:21:13, 1.71it/s]Step... (5550 / 100000 | Loss: 1.1407448053359985, Learning Rate: 9.49246231155779e-05) Step... (5550 / 100000 | Loss: 1.5878925323486328, Learning Rate: 9.49246231155779e-05) Train steps ... : 6%|▌ | 5550/100000 [1:43:20<15:21:13, 1.71it/s] Train steps ... : 6%|▌ | 5551/100000 [1:43:20<15:20:39, 1.71it/s] Train steps ... : 6%|▌ | 5552/100000 [1:43:21<15:21:01, 1.71it/s] Train steps ... : 6%|▌ | 5553/100000 [1:43:21<15:20:17, 1.71it/s] Train steps ... : 6%|▌ | 5554/100000 [1:43:22<15:21:18, 1.71it/s] Train steps ... : 6%|▌ | 5555/100000 [1:43:22<15:20:38, 1.71it/s] Train steps ... : 6%|▌ | 5556/100000 [1:43:23<15:20:24, 1.71it/s] Train steps ... : 6%|▌ | 5557/100000 [1:43:24<15:20:51, 1.71it/s] Train steps ... : 6%|▌ | 5558/100000 [1:43:24<15:21:14, 1.71it/s] Train steps ... : 6%|▌ | 5559/100000 [1:43:25<15:21:01, 1.71it/s] Train steps ... : 6%|▌ | 5560/100000 [1:43:25<15:20:24, 1.71it/s] Train steps ... : 6%|▌ | 5561/100000 [1:43:26<15:20:53, 1.71it/s] Train steps ... : 6%|▌ | 5562/100000 [1:43:27<15:22:01, 1.71it/s] Train steps ... : 6%|▌ | 5563/100000 [1:43:27<15:21:38, 1.71it/s] Train steps ... : 6%|▌ | 5564/100000 [1:43:28<15:21:43, 1.71it/s] Train steps ... : 6%|▌ | 5565/100000 [1:43:28<15:20:09, 1.71it/s] Train steps ... : 6%|▌ | 5566/100000 [1:43:29<15:20:39, 1.71it/s] Train steps ... : 6%|▌ | 5567/100000 [1:43:29<15:20:21, 1.71it/s] Train steps ... : 6%|▌ | 5568/100000 [1:43:30<15:21:44, 1.71it/s] Train steps ... : 6%|▌ | 5569/100000 [1:43:31<15:20:07, 1.71it/s] Train steps ... : 6%|▌ | 5570/100000 [1:43:31<15:19:48, 1.71it/s] Train steps ... : 6%|▌ | 5571/100000 [1:43:32<15:18:37, 1.71it/s] Train steps ... : 6%|▌ | 5572/100000 [1:43:32<15:18:20, 1.71it/s] Train steps ... : 6%|▌ | 5573/100000 [1:43:33<15:21:33, 1.71it/s] Train steps ... : 6%|▌ | 5574/100000 [1:43:34<15:21:41, 1.71it/s] Train steps ... : 6%|▌ | 5575/100000 [1:43:34<15:23:18, 1.70it/s]Step... (5575 / 100000 | Loss: 1.631526231765747, Learning Rate: 9.489949748743719e-05) Step... (5575 / 100000 | Loss: 1.4795958995819092, Learning Rate: 9.489949748743719e-05) Train steps ... : 6%|▌ | 5575/100000 [1:43:34<15:23:18, 1.70it/s] Train steps ... : 6%|▌ | 5576/100000 [1:43:35<15:24:50, 1.70it/s] Train steps ... : 6%|▌ | 5577/100000 [1:43:35<15:21:51, 1.71it/s] Train steps ... : 6%|▌ | 5578/100000 [1:43:36<15:20:28, 1.71it/s] Train steps ... : 6%|▌ | 5579/100000 [1:43:36<15:20:36, 1.71it/s] Train steps ... : 6%|▌ | 5580/100000 [1:43:37<15:20:12, 1.71it/s] Train steps ... : 6%|▌ | 5581/100000 [1:43:38<15:23:31, 1.70it/s] Train steps ... : 6%|▌ | 5582/100000 [1:43:38<15:20:58, 1.71it/s] Train steps ... : 6%|▌ | 5583/100000 [1:43:39<15:20:26, 1.71it/s] Train steps ... : 6%|▌ | 5584/100000 [1:43:39<15:19:58, 1.71it/s] Train steps ... : 6%|▌ | 5585/100000 [1:43:40<15:21:01, 1.71it/s] Train steps ... : 6%|▌ | 5586/100000 [1:43:41<15:20:04, 1.71it/s] Train steps ... : 6%|▌ | 5587/100000 [1:43:41<15:21:13, 1.71it/s] Train steps ... : 6%|▌ | 5588/100000 [1:43:42<15:21:11, 1.71it/s] Train steps ... : 6%|▌ | 5589/100000 [1:43:42<15:21:54, 1.71it/s] Train steps ... : 6%|▌ | 5590/100000 [1:43:43<15:20:18, 1.71it/s] Train steps ... : 6%|▌ | 5591/100000 [1:43:43<15:19:40, 1.71it/s] Train steps ... : 6%|▌ | 5592/100000 [1:43:44<15:21:32, 1.71it/s] Train steps ... : 6%|▌ | 5593/100000 [1:43:45<15:23:46, 1.70it/s] Train steps ... : 6%|▌ | 5594/100000 [1:43:45<15:22:08, 1.71it/s] Train steps ... : 6%|▌ | 5595/100000 [1:43:46<15:22:48, 1.71it/s] Train steps ... : 6%|▌ | 5596/100000 [1:43:46<15:21:36, 1.71it/s] Train steps ... : 6%|▌ | 5597/100000 [1:43:47<15:23:31, 1.70it/s] Train steps ... : 6%|▌ | 5598/100000 [1:43:48<15:20:52, 1.71it/s] Train steps ... : 6%|▌ | 5599/100000 [1:43:48<15:20:40, 1.71it/s] Train steps ... : 6%|▌ | 5600/100000 [1:43:49<15:20:04, 1.71it/s]Step... (5600 / 100000 | Loss: 1.2664506435394287, Learning Rate: 9.487437185929649e-05) Step... (5600 / 100000 | Loss: 1.460883378982544, Learning Rate: 9.487437185929649e-05) Train steps ... : 6%|▌ | 5600/100000 [1:43:49<15:20:04, 1.71it/s] Train steps ... : 6%|▌ | 5601/100000 [1:43:49<15:20:45, 1.71it/s] Train steps ... : 6%|▌ | 5602/100000 [1:43:50<15:20:42, 1.71it/s] Train steps ... : 6%|▌ | 5603/100000 [1:43:51<15:21:30, 1.71it/s] Train steps ... : 6%|▌ | 5604/100000 [1:43:51<15:21:42, 1.71it/s] Train steps ... : 6%|▌ | 5605/100000 [1:43:52<15:21:46, 1.71it/s] Train steps ... : 6%|▌ | 5606/100000 [1:43:52<15:20:57, 1.71it/s] Train steps ... : 6%|▌ | 5607/100000 [1:43:53<15:20:55, 1.71it/s] Train steps ... : 6%|▌ | 5608/100000 [1:43:53<15:24:17, 1.70it/s] Train steps ... : 6%|▌ | 5609/100000 [1:43:54<15:22:25, 1.71it/s] Train steps ... : 6%|▌ | 5610/100000 [1:43:55<15:20:31, 1.71it/s] Train steps ... : 6%|▌ | 5611/100000 [1:43:55<15:20:40, 1.71it/s] Train steps ... : 6%|▌ | 5612/100000 [1:43:56<15:20:42, 1.71it/s] Train steps ... : 6%|▌ | 5613/100000 [1:43:56<15:18:57, 1.71it/s] Train steps ... : 6%|▌ | 5614/100000 [1:43:57<15:19:50, 1.71it/s] Train steps ... : 6%|▌ | 5615/100000 [1:43:58<15:21:13, 1.71it/s] Train steps ... : 6%|▌ | 5616/100000 [1:43:58<15:20:44, 1.71it/s] Train steps ... : 6%|▌ | 5617/100000 [1:43:59<15:22:17, 1.71it/s] Train steps ... : 6%|▌ | 5618/100000 [1:43:59<15:21:14, 1.71it/s] Train steps ... : 6%|▌ | 5619/100000 [1:44:00<15:20:25, 1.71it/s] Train steps ... : 6%|▌ | 5620/100000 [1:44:00<15:22:07, 1.71it/s] Train steps ... : 6%|▌ | 5621/100000 [1:44:01<15:22:17, 1.71it/s] Train steps ... : 6%|▌ | 5622/100000 [1:44:02<15:20:38, 1.71it/s] Train steps ... : 6%|▌ | 5623/100000 [1:44:02<15:21:09, 1.71it/s] Train steps ... : 6%|▌ | 5624/100000 [1:44:03<15:21:36, 1.71it/s] Train steps ... : 6%|▌ | 5625/100000 [1:44:03<15:21:14, 1.71it/s]Step... (5625 / 100000 | Loss: 1.870214581489563, Learning Rate: 9.484924623115578e-05) Step... (5625 / 100000 | Loss: 1.5672430992126465, Learning Rate: 9.484924623115578e-05) Train steps ... : 6%|▌ | 5625/100000 [1:44:04<15:21:14, 1.71it/s] Train steps ... : 6%|▌ | 5626/100000 [1:44:04<15:22:25, 1.71it/s] Train steps ... : 6%|▌ | 5627/100000 [1:44:05<15:22:07, 1.71it/s] Train steps ... : 6%|▌ | 5628/100000 [1:44:05<15:22:15, 1.71it/s] Train steps ... : 6%|▌ | 5629/100000 [1:44:06<15:21:45, 1.71it/s] Train steps ... : 6%|▌ | 5630/100000 [1:44:06<15:20:52, 1.71it/s] Train steps ... : 6%|▌ | 5631/100000 [1:44:07<15:21:59, 1.71it/s] Train steps ... : 6%|▌ | 5632/100000 [1:44:07<15:22:52, 1.70it/s] Train steps ... : 6%|▌ | 5633/100000 [1:44:08<15:20:54, 1.71it/s] Train steps ... : 6%|▌ | 5634/100000 [1:44:09<15:21:37, 1.71it/s] Train steps ... : 6%|▌ | 5635/100000 [1:44:09<15:24:15, 1.70it/s] Train steps ... : 6%|▌ | 5636/100000 [1:44:10<15:24:45, 1.70it/s] Train steps ... : 6%|▌ | 5637/100000 [1:44:10<15:24:28, 1.70it/s] Train steps ... : 6%|▌ | 5638/100000 [1:44:11<15:24:10, 1.70it/s] Train steps ... : 6%|▌ | 5639/100000 [1:44:12<15:25:38, 1.70it/s] Train steps ... : 6%|▌ | 5640/100000 [1:44:12<15:24:08, 1.70it/s] Train steps ... : 6%|▌ | 5641/100000 [1:44:13<15:21:09, 1.71it/s] Train steps ... : 6%|▌ | 5642/100000 [1:44:13<15:20:48, 1.71it/s] Train steps ... : 6%|▌ | 5643/100000 [1:44:14<15:22:15, 1.71it/s] Train steps ... : 6%|▌ | 5644/100000 [1:44:15<15:21:03, 1.71it/s] Train steps ... : 6%|▌ | 5645/100000 [1:44:15<15:22:51, 1.70it/s] Train steps ... : 6%|▌ | 5646/100000 [1:44:16<15:22:03, 1.71it/s] Train steps ... : 6%|▌ | 5647/100000 [1:44:16<15:21:18, 1.71it/s] Train steps ... : 6%|▌ | 5648/100000 [1:44:17<15:21:38, 1.71it/s] Train steps ... : 6%|▌ | 5649/100000 [1:44:17<15:20:59, 1.71it/s] Train steps ... : 6%|▌ | 5650/100000 [1:44:18<15:21:19, 1.71it/s]Step... (5650 / 100000 | Loss: 1.7891013622283936, Learning Rate: 9.482412060301508e-05) Step... (5650 / 100000 | Loss: 2.034867286682129, Learning Rate: 9.482412060301508e-05) Train steps ... : 6%|▌ | 5650/100000 [1:44:18<15:21:19, 1.71it/s] Train steps ... : 6%|▌ | 5651/100000 [1:44:19<15:23:19, 1.70it/s] Train steps ... : 6%|▌ | 5652/100000 [1:44:19<15:23:37, 1.70it/s] Train steps ... : 6%|▌ | 5653/100000 [1:44:20<15:22:06, 1.71it/s] Train steps ... : 6%|▌ | 5654/100000 [1:44:20<15:21:38, 1.71it/s] Train steps ... : 6%|▌ | 5655/100000 [1:44:21<15:20:09, 1.71it/s] Train steps ... : 6%|▌ | 5656/100000 [1:44:22<15:20:07, 1.71it/s] Train steps ... : 6%|▌ | 5657/100000 [1:44:22<15:19:18, 1.71it/s] Train steps ... : 6%|▌ | 5658/100000 [1:44:23<15:21:35, 1.71it/s] Train steps ... : 6%|▌ | 5659/100000 [1:44:23<15:20:55, 1.71it/s] Train steps ... : 6%|▌ | 5660/100000 [1:44:24<15:21:26, 1.71it/s] Train steps ... : 6%|▌ | 5661/100000 [1:44:25<15:22:27, 1.70it/s] Train steps ... : 6%|▌ | 5662/100000 [1:44:25<15:23:30, 1.70it/s] Train steps ... : 6%|▌ | 5663/100000 [1:44:26<15:22:15, 1.70it/s] Train steps ... : 6%|▌ | 5664/100000 [1:44:26<15:21:05, 1.71it/s] Train steps ... : 6%|▌ | 5665/100000 [1:44:27<15:19:35, 1.71it/s] Train steps ... : 6%|▌ | 5666/100000 [1:44:27<15:19:04, 1.71it/s] Train steps ... : 6%|▌ | 5667/100000 [1:44:28<15:20:56, 1.71it/s] Train steps ... : 6%|▌ | 5668/100000 [1:44:29<15:24:19, 1.70it/s] Train steps ... : 6%|▌ | 5669/100000 [1:44:29<15:22:39, 1.70it/s] Train steps ... : 6%|▌ | 5670/100000 [1:44:30<15:24:23, 1.70it/s] Train steps ... : 6%|▌ | 5671/100000 [1:44:30<15:19:36, 1.71it/s] Train steps ... : 6%|▌ | 5672/100000 [1:44:31<15:20:55, 1.71it/s] Train steps ... : 6%|▌ | 5673/100000 [1:44:32<15:19:38, 1.71it/s] Train steps ... : 6%|▌ | 5674/100000 [1:44:32<15:20:16, 1.71it/s] Train steps ... : 6%|▌ | 5675/100000 [1:44:33<15:20:34, 1.71it/s]Step... (5675 / 100000 | Loss: 1.7422969341278076, Learning Rate: 9.479899497487438e-05) Step... (5675 / 100000 | Loss: 1.4587082862854004, Learning Rate: 9.479899497487438e-05) Train steps ... : 6%|▌ | 5675/100000 [1:44:33<15:20:34, 1.71it/s] Train steps ... : 6%|▌ | 5676/100000 [1:44:33<15:22:11, 1.70it/s] Train steps ... : 6%|▌ | 5677/100000 [1:44:34<15:23:28, 1.70it/s] Train steps ... : 6%|▌ | 5678/100000 [1:44:34<15:20:35, 1.71it/s] Train steps ... : 6%|▌ | 5679/100000 [1:44:35<15:19:39, 1.71it/s] Train steps ... : 6%|▌ | 5680/100000 [1:44:36<15:19:39, 1.71it/s] Train steps ... : 6%|▌ | 5681/100000 [1:44:36<15:21:37, 1.71it/s] Train steps ... : 6%|▌ | 5682/100000 [1:44:37<15:21:52, 1.71it/s] Train steps ... : 6%|▌ | 5683/100000 [1:44:37<15:22:32, 1.70it/s] Train steps ... : 6%|▌ | 5684/100000 [1:44:38<15:20:54, 1.71it/s] Train steps ... : 6%|▌ | 5685/100000 [1:44:39<15:21:59, 1.70it/s] Train steps ... : 6%|▌ | 5686/100000 [1:44:39<15:21:40, 1.71it/s] Train steps ... : 6%|▌ | 5687/100000 [1:44:40<15:22:45, 1.70it/s] Train steps ... : 6%|▌ | 5688/100000 [1:44:40<15:20:20, 1.71it/s] Train steps ... : 6%|▌ | 5689/100000 [1:44:41<15:21:18, 1.71it/s] Train steps ... : 6%|▌ | 5690/100000 [1:44:41<15:20:43, 1.71it/s] Train steps ... : 6%|▌ | 5691/100000 [1:44:42<15:22:15, 1.70it/s] Train steps ... : 6%|▌ | 5692/100000 [1:44:43<15:21:02, 1.71it/s] Train steps ... : 6%|▌ | 5693/100000 [1:44:43<15:21:58, 1.70it/s] Train steps ... : 6%|▌ | 5694/100000 [1:44:44<15:20:01, 1.71it/s] Train steps ... : 6%|▌ | 5695/100000 [1:44:44<15:19:50, 1.71it/s] Train steps ... : 6%|▌ | 5696/100000 [1:44:45<15:18:58, 1.71it/s] Train steps ... : 6%|▌ | 5697/100000 [1:44:46<15:19:39, 1.71it/s] Train steps ... : 6%|▌ | 5698/100000 [1:44:46<15:19:33, 1.71it/s] Train steps ... : 6%|▌ | 5699/100000 [1:44:47<15:20:10, 1.71it/s] Train steps ... : 6%|▌ | 5700/100000 [1:44:47<15:20:33, 1.71it/s]Step... (5700 / 100000 | Loss: 1.7315512895584106, Learning Rate: 9.477386934673366e-05) Step... (5700 / 100000 | Loss: 1.8764550685882568, Learning Rate: 9.477386934673366e-05) Train steps ... : 6%|▌ | 5700/100000 [1:44:48<15:20:33, 1.71it/s] Train steps ... : 6%|▌ | 5701/100000 [1:44:48<15:19:59, 1.71it/s] Train steps ... : 6%|▌ | 5702/100000 [1:44:49<15:20:57, 1.71it/s] Train steps ... : 6%|▌ | 5703/100000 [1:44:49<15:21:13, 1.71it/s] Train steps ... : 6%|▌ | 5704/100000 [1:44:50<15:18:48, 1.71it/s] Train steps ... : 6%|▌ | 5705/100000 [1:44:50<15:21:53, 1.70it/s] Train steps ... : 6%|▌ | 5706/100000 [1:44:51<15:20:29, 1.71it/s] Train steps ... : 6%|▌ | 5707/100000 [1:44:51<15:21:15, 1.71it/s] Train steps ... : 6%|▌ | 5708/100000 [1:44:52<15:19:49, 1.71it/s] Train steps ... : 6%|▌ | 5709/100000 [1:44:53<15:20:57, 1.71it/s] Train steps ... : 6%|▌ | 5710/100000 [1:44:53<15:22:55, 1.70it/s] Train steps ... : 6%|▌ | 5711/100000 [1:44:54<15:20:39, 1.71it/s] Train steps ... : 6%|▌ | 5712/100000 [1:44:54<15:20:39, 1.71it/s] Train steps ... : 6%|▌ | 5713/100000 [1:44:55<15:21:10, 1.71it/s] Train steps ... : 6%|▌ | 5714/100000 [1:44:56<15:23:09, 1.70it/s] Train steps ... : 6%|▌ | 5715/100000 [1:44:56<15:18:41, 1.71it/s] Train steps ... : 6%|▌ | 5716/100000 [1:44:57<15:23:32, 1.70it/s] Train steps ... : 6%|▌ | 5717/100000 [1:44:57<15:21:40, 1.70it/s] Train steps ... : 6%|▌ | 5718/100000 [1:44:58<15:24:48, 1.70it/s] Train steps ... : 6%|▌ | 5719/100000 [1:44:58<15:21:57, 1.70it/s] Train steps ... : 6%|▌ | 5720/100000 [1:44:59<15:24:49, 1.70it/s] Train steps ... : 6%|▌ | 5721/100000 [1:45:00<15:20:17, 1.71it/s] Train steps ... : 6%|▌ | 5722/100000 [1:45:00<15:20:36, 1.71it/s] Train steps ... : 6%|▌ | 5723/100000 [1:45:01<15:19:41, 1.71it/s] Train steps ... : 6%|▌ | 5724/100000 [1:45:01<15:19:32, 1.71it/s] Train steps ... : 6%|▌ | 5725/100000 [1:45:02<15:18:32, 1.71it/s]Step... (5725 / 100000 | Loss: 1.8188775777816772, Learning Rate: 9.474874371859297e-05) Step... (5725 / 100000 | Loss: 1.6878893375396729, Learning Rate: 9.474874371859297e-05) Train steps ... : 6%|▌ | 5725/100000 [1:45:02<15:18:32, 1.71it/s] Train steps ... : 6%|▌ | 5726/100000 [1:45:03<15:20:14, 1.71it/s] Train steps ... : 6%|▌ | 5727/100000 [1:45:03<15:18:31, 1.71it/s] Train steps ... : 6%|▌ | 5728/100000 [1:45:04<15:19:06, 1.71it/s] Train steps ... : 6%|▌ | 5729/100000 [1:45:04<15:18:06, 1.71it/s] Train steps ... : 6%|▌ | 5730/100000 [1:45:05<15:20:17, 1.71it/s] Train steps ... : 6%|▌ | 5731/100000 [1:45:06<15:20:25, 1.71it/s] Train steps ... : 6%|▌ | 5732/100000 [1:45:06<15:20:28, 1.71it/s] Train steps ... : 6%|▌ | 5733/100000 [1:45:07<15:21:30, 1.70it/s] Train steps ... : 6%|▌ | 5734/100000 [1:45:07<15:18:29, 1.71it/s] Train steps ... : 6%|▌ | 5735/100000 [1:45:08<15:18:38, 1.71it/s] Train steps ... : 6%|▌ | 5736/100000 [1:45:08<15:18:44, 1.71it/s] Train steps ... : 6%|▌ | 5737/100000 [1:45:09<15:18:31, 1.71it/s] Train steps ... : 6%|▌ | 5738/100000 [1:45:10<15:21:50, 1.70it/s] Train steps ... : 6%|▌ | 5739/100000 [1:45:10<15:22:42, 1.70it/s] Train steps ... : 6%|▌ | 5740/100000 [1:45:11<15:24:49, 1.70it/s] Train steps ... : 6%|▌ | 5741/100000 [1:45:11<15:20:35, 1.71it/s] Train steps ... : 6%|▌ | 5742/100000 [1:45:12<15:22:48, 1.70it/s] Train steps ... : 6%|▌ | 5743/100000 [1:45:13<15:20:46, 1.71it/s] Train steps ... : 6%|▌ | 5744/100000 [1:45:13<15:21:45, 1.70it/s] Train steps ... : 6%|▌ | 5745/100000 [1:45:14<15:20:32, 1.71it/s] Train steps ... : 6%|▌ | 5746/100000 [1:45:14<15:19:13, 1.71it/s] Train steps ... : 6%|▌ | 5747/100000 [1:45:15<15:20:44, 1.71it/s] Train steps ... : 6%|▌ | 5748/100000 [1:45:15<15:20:32, 1.71it/s] Train steps ... : 6%|▌ | 5749/100000 [1:45:16<15:19:39, 1.71it/s] Train steps ... : 6%|▌ | 5750/100000 [1:45:17<15:21:16, 1.71it/s]Step... (5750 / 100000 | Loss: 1.5957229137420654, Learning Rate: 9.472361809045227e-05) Step... (5750 / 100000 | Loss: 1.6692612171173096, Learning Rate: 9.472361809045227e-05) Train steps ... : 6%|▌ | 5750/100000 [1:45:17<15:21:16, 1.71it/s] Train steps ... : 6%|▌ | 5751/100000 [1:45:17<15:22:34, 1.70it/s] Train steps ... : 6%|▌ | 5752/100000 [1:45:18<15:19:17, 1.71it/s] Train steps ... : 6%|▌ | 5753/100000 [1:45:18<15:19:10, 1.71it/s] Train steps ... : 6%|▌ | 5754/100000 [1:45:19<15:19:12, 1.71it/s] Train steps ... : 6%|▌ | 5755/100000 [1:45:20<15:18:25, 1.71it/s] Train steps ... : 6%|▌ | 5756/100000 [1:45:20<15:19:07, 1.71it/s] Train steps ... : 6%|▌ | 5757/100000 [1:45:21<15:19:57, 1.71it/s] Train steps ... : 6%|▌ | 5758/100000 [1:45:21<15:20:46, 1.71it/s] Train steps ... : 6%|▌ | 5759/100000 [1:45:22<15:20:53, 1.71it/s] Train steps ... : 6%|▌ | 5760/100000 [1:45:23<15:18:57, 1.71it/s] Train steps ... : 6%|▌ | 5761/100000 [1:45:23<15:18:31, 1.71it/s] Train steps ... : 6%|▌ | 5762/100000 [1:45:24<15:19:01, 1.71it/s] Train steps ... : 6%|▌ | 5763/100000 [1:45:24<15:19:06, 1.71it/s] Train steps ... : 6%|▌ | 5764/100000 [1:45:25<15:18:15, 1.71it/s] Train steps ... : 6%|▌ | 5765/100000 [1:45:25<15:18:46, 1.71it/s] Train steps ... : 6%|▌ | 5766/100000 [1:45:26<15:18:24, 1.71it/s] Train steps ... : 6%|▌ | 5767/100000 [1:45:27<15:19:44, 1.71it/s] Train steps ... : 6%|▌ | 5768/100000 [1:45:27<15:20:11, 1.71it/s] Train steps ... : 6%|▌ | 5769/100000 [1:45:28<15:21:59, 1.70it/s] Train steps ... : 6%|▌ | 5770/100000 [1:45:28<15:20:59, 1.71it/s] Train steps ... : 6%|▌ | 5771/100000 [1:45:29<15:22:14, 1.70it/s] Train steps ... : 6%|▌ | 5772/100000 [1:45:30<15:20:25, 1.71it/s] Train steps ... : 6%|▌ | 5773/100000 [1:45:30<15:20:23, 1.71it/s] Train steps ... : 6%|▌ | 5774/100000 [1:45:31<15:20:52, 1.71it/s] Train steps ... : 6%|▌ | 5775/100000 [1:45:31<15:19:26, 1.71it/s]Step... (5775 / 100000 | Loss: 1.6779179573059082, Learning Rate: 9.469849246231156e-05) Step... (5775 / 100000 | Loss: 1.0633233785629272, Learning Rate: 9.469849246231156e-05) Train steps ... : 6%|▌ | 5775/100000 [1:45:32<15:19:26, 1.71it/s] Train steps ... : 6%|▌ | 5776/100000 [1:45:32<15:20:45, 1.71it/s] Train steps ... : 6%|▌ | 5777/100000 [1:45:32<15:21:41, 1.70it/s] Train steps ... : 6%|▌ | 5778/100000 [1:45:33<15:18:47, 1.71it/s] Train steps ... : 6%|▌ | 5779/100000 [1:45:34<15:19:37, 1.71it/s] Train steps ... : 6%|▌ | 5780/100000 [1:45:34<15:18:56, 1.71it/s] Train steps ... : 6%|▌ | 5781/100000 [1:45:35<15:19:39, 1.71it/s] Train steps ... : 6%|▌ | 5782/100000 [1:45:35<15:22:28, 1.70it/s] Train steps ... : 6%|▌ | 5783/100000 [1:45:36<15:19:54, 1.71it/s] Train steps ... : 6%|▌ | 5784/100000 [1:45:37<15:20:42, 1.71it/s] Train steps ... : 6%|▌ | 5785/100000 [1:45:37<15:20:01, 1.71it/s] Train steps ... : 6%|▌ | 5786/100000 [1:45:38<15:19:49, 1.71it/s] Train steps ... : 6%|▌ | 5787/100000 [1:45:38<15:21:09, 1.70it/s] Train steps ... : 6%|▌ | 5788/100000 [1:45:39<15:21:18, 1.70it/s] Train steps ... : 6%|▌ | 5789/100000 [1:45:40<15:21:44, 1.70it/s] Train steps ... : 6%|▌ | 5790/100000 [1:45:40<15:19:38, 1.71it/s] Train steps ... : 6%|▌ | 5791/100000 [1:45:41<15:22:22, 1.70it/s] Train steps ... : 6%|▌ | 5792/100000 [1:45:41<15:18:42, 1.71it/s] Train steps ... : 6%|▌ | 5793/100000 [1:45:42<15:20:19, 1.71it/s] Train steps ... : 6%|▌ | 5794/100000 [1:45:42<15:19:24, 1.71it/s] Train steps ... : 6%|▌ | 5795/100000 [1:45:43<15:19:49, 1.71it/s] Train steps ... : 6%|▌ | 5796/100000 [1:45:44<15:22:11, 1.70it/s] Train steps ... : 6%|▌ | 5797/100000 [1:45:44<15:19:15, 1.71it/s] Train steps ... : 6%|▌ | 5798/100000 [1:45:45<15:18:04, 1.71it/s] Train steps ... : 6%|▌ | 5799/100000 [1:45:45<15:18:18, 1.71it/s] Train steps ... : 6%|▌ | 5800/100000 [1:45:46<15:18:12, 1.71it/s]Step... (5800 / 100000 | Loss: 1.4024498462677002, Learning Rate: 9.467336683417086e-05) Step... (5800 / 100000 | Loss: 1.23079514503479, Learning Rate: 9.467336683417086e-05) Train steps ... : 6%|▌ | 5800/100000 [1:45:46<15:18:12, 1.71it/s] Train steps ... : 6%|▌ | 5801/100000 [1:45:47<15:20:26, 1.71it/s] Train steps ... : 6%|▌ | 5802/100000 [1:45:47<15:18:17, 1.71it/s] Train steps ... : 6%|▌ | 5803/100000 [1:45:48<15:18:21, 1.71it/s] Train steps ... : 6%|▌ | 5804/100000 [1:45:48<15:17:58, 1.71it/s] Train steps ... : 6%|▌ | 5805/100000 [1:45:49<15:17:23, 1.71it/s] Train steps ... : 6%|▌ | 5806/100000 [1:45:49<15:17:25, 1.71it/s] Train steps ... : 6%|▌ | 5807/100000 [1:45:50<15:17:25, 1.71it/s] Train steps ... : 6%|▌ | 5808/100000 [1:45:51<15:19:59, 1.71it/s] Train steps ... : 6%|▌ | 5809/100000 [1:45:51<15:17:41, 1.71it/s] Train steps ... : 6%|▌ | 5810/100000 [1:45:52<15:20:40, 1.71it/s] Train steps ... : 6%|▌ | 5811/100000 [1:45:52<15:17:12, 1.71it/s] Train steps ... : 6%|▌ | 5812/100000 [1:45:53<15:23:26, 1.70it/s] Train steps ... : 6%|▌ | 5813/100000 [1:45:54<15:20:43, 1.70it/s] Train steps ... : 6%|▌ | 5814/100000 [1:45:54<15:20:25, 1.71it/s] Train steps ... : 6%|▌ | 5815/100000 [1:45:55<15:21:07, 1.70it/s] Train steps ... : 6%|▌ | 5816/100000 [1:45:55<15:20:20, 1.71it/s] Train steps ... : 6%|▌ | 5817/100000 [1:45:56<15:20:17, 1.71it/s] Train steps ... : 6%|▌ | 5818/100000 [1:45:56<15:22:21, 1.70it/s] Train steps ... : 6%|▌ | 5819/100000 [1:45:57<15:19:21, 1.71it/s] Train steps ... : 6%|▌ | 5820/100000 [1:45:58<15:18:04, 1.71it/s] Train steps ... : 6%|▌ | 5821/100000 [1:45:58<15:20:38, 1.70it/s] Train steps ... : 6%|▌ | 5822/100000 [1:45:59<15:17:14, 1.71it/s] Train steps ... : 6%|▌ | 5823/100000 [1:45:59<15:19:01, 1.71it/s] Train steps ... : 6%|▌ | 5824/100000 [1:46:00<15:21:05, 1.70it/s] Train steps ... : 6%|▌ | 5825/100000 [1:46:01<15:20:07, 1.71it/s]Step... (5825 / 100000 | Loss: 1.104354739189148, Learning Rate: 9.464824120603016e-05) Step... (5825 / 100000 | Loss: 1.5303372144699097, Learning Rate: 9.464824120603016e-05) Train steps ... : 6%|▌ | 5825/100000 [1:46:01<15:20:07, 1.71it/s] Train steps ... : 6%|▌ | 5826/100000 [1:46:01<15:19:11, 1.71it/s] Train steps ... : 6%|▌ | 5827/100000 [1:46:02<15:20:58, 1.70it/s] Train steps ... : 6%|▌ | 5828/100000 [1:46:02<15:19:41, 1.71it/s] Train steps ... : 6%|▌ | 5829/100000 [1:46:03<15:19:26, 1.71it/s] Train steps ... : 6%|▌ | 5830/100000 [1:46:04<15:19:57, 1.71it/s] Train steps ... : 6%|▌ | 5831/100000 [1:46:04<15:19:03, 1.71it/s] Train steps ... : 6%|▌ | 5832/100000 [1:46:05<15:18:06, 1.71it/s] Train steps ... : 6%|▌ | 5833/100000 [1:46:05<15:19:21, 1.71it/s] Train steps ... : 6%|▌ | 5834/100000 [1:46:06<15:19:10, 1.71it/s] Train steps ... : 6%|▌ | 5835/100000 [1:46:06<15:19:24, 1.71it/s] Train steps ... : 6%|▌ | 5836/100000 [1:46:07<15:18:36, 1.71it/s] Train steps ... : 6%|▌ | 5837/100000 [1:46:08<15:17:35, 1.71it/s] Train steps ... : 6%|▌ | 5838/100000 [1:46:08<15:16:50, 1.71it/s] Train steps ... : 6%|▌ | 5839/100000 [1:46:09<15:17:40, 1.71it/s] Train steps ... : 6%|▌ | 5840/100000 [1:46:09<15:20:45, 1.70it/s] Train steps ... : 6%|▌ | 5841/100000 [1:46:10<15:22:21, 1.70it/s] Train steps ... : 6%|▌ | 5842/100000 [1:46:11<15:20:09, 1.71it/s] Train steps ... : 6%|▌ | 5843/100000 [1:46:11<15:18:32, 1.71it/s] Train steps ... : 6%|▌ | 5844/100000 [1:46:12<15:19:29, 1.71it/s] Train steps ... : 6%|▌ | 5845/100000 [1:46:12<15:19:33, 1.71it/s] Train steps ... : 6%|▌ | 5846/100000 [1:46:13<15:20:45, 1.70it/s] Train steps ... : 6%|▌ | 5847/100000 [1:46:13<15:22:40, 1.70it/s] Train steps ... : 6%|▌ | 5848/100000 [1:46:14<15:19:05, 1.71it/s] Train steps ... : 6%|▌ | 5849/100000 [1:46:15<15:18:37, 1.71it/s] Train steps ... : 6%|▌ | 5850/100000 [1:46:15<15:22:30, 1.70it/s]Step... (5850 / 100000 | Loss: 1.3431055545806885, Learning Rate: 9.462311557788945e-05) Step... (5850 / 100000 | Loss: 1.7089340686798096, Learning Rate: 9.462311557788945e-05) Train steps ... : 6%|▌ | 5850/100000 [1:46:16<15:22:30, 1.70it/s] Train steps ... : 6%|▌ | 5851/100000 [1:46:16<15:22:25, 1.70it/s] Train steps ... : 6%|▌ | 5852/100000 [1:46:16<15:20:37, 1.70it/s] Train steps ... : 6%|▌ | 5853/100000 [1:46:17<15:18:54, 1.71it/s] Train steps ... : 6%|▌ | 5854/100000 [1:46:18<15:19:21, 1.71it/s] Train steps ... : 6%|▌ | 5855/100000 [1:46:18<15:20:01, 1.71it/s] Train steps ... : 6%|▌ | 5856/100000 [1:46:19<15:18:55, 1.71it/s] Train steps ... : 6%|▌ | 5857/100000 [1:46:19<15:22:09, 1.70it/s] Train steps ... : 6%|▌ | 5858/100000 [1:46:20<15:16:56, 1.71it/s] Train steps ... : 6%|▌ | 5859/100000 [1:46:21<15:16:35, 1.71it/s] Train steps ... : 6%|▌ | 5860/100000 [1:46:21<15:19:20, 1.71it/s] Train steps ... : 6%|▌ | 5861/100000 [1:46:22<15:20:10, 1.71it/s] Train steps ... : 6%|▌ | 5862/100000 [1:46:22<15:20:35, 1.70it/s] Train steps ... : 6%|▌ | 5863/100000 [1:46:23<15:18:45, 1.71it/s] Train steps ... : 6%|▌ | 5864/100000 [1:46:23<15:17:20, 1.71it/s] Train steps ... : 6%|▌ | 5865/100000 [1:46:24<15:16:31, 1.71it/s] Train steps ... : 6%|▌ | 5866/100000 [1:46:25<15:19:06, 1.71it/s] Train steps ... : 6%|▌ | 5867/100000 [1:46:25<15:17:56, 1.71it/s] Train steps ... : 6%|▌ | 5868/100000 [1:46:26<15:15:42, 1.71it/s] Train steps ... : 6%|▌ | 5869/100000 [1:46:26<15:16:24, 1.71it/s] Train steps ... : 6%|▌ | 5870/100000 [1:46:27<15:17:19, 1.71it/s] Train steps ... : 6%|▌ | 5871/100000 [1:46:28<15:16:18, 1.71it/s] Train steps ... : 6%|▌ | 5872/100000 [1:46:28<15:16:17, 1.71it/s] Train steps ... : 6%|▌ | 5873/100000 [1:46:29<15:16:10, 1.71it/s] Train steps ... : 6%|▌ | 5874/100000 [1:46:29<15:17:10, 1.71it/s] Train steps ... : 6%|▌ | 5875/100000 [1:46:30<15:18:04, 1.71it/s]Step... (5875 / 100000 | Loss: 1.6396321058273315, Learning Rate: 9.459798994974874e-05) Step... (5875 / 100000 | Loss: 1.0829219818115234, Learning Rate: 9.459798994974874e-05) Train steps ... : 6%|▌ | 5875/100000 [1:46:30<15:18:04, 1.71it/s] Train steps ... : 6%|▌ | 5876/100000 [1:46:30<15:19:04, 1.71it/s] Train steps ... : 6%|▌ | 5877/100000 [1:46:31<15:18:21, 1.71it/s] Train steps ... : 6%|▌ | 5878/100000 [1:46:32<15:17:52, 1.71it/s] Train steps ... : 6%|▌ | 5879/100000 [1:46:32<15:16:48, 1.71it/s] Train steps ... : 6%|▌ | 5880/100000 [1:46:33<15:16:45, 1.71it/s] Train steps ... : 6%|▌ | 5881/100000 [1:46:33<15:18:29, 1.71it/s] Train steps ... : 6%|▌ | 5882/100000 [1:46:34<15:17:21, 1.71it/s] Train steps ... : 6%|▌ | 5883/100000 [1:46:35<15:17:02, 1.71it/s] Train steps ... : 6%|▌ | 5884/100000 [1:46:35<15:16:21, 1.71it/s] Train steps ... : 6%|▌ | 5885/100000 [1:46:36<15:17:36, 1.71it/s] Train steps ... : 6%|▌ | 5886/100000 [1:46:36<15:17:25, 1.71it/s] Train steps ... : 6%|▌ | 5887/100000 [1:46:37<15:16:46, 1.71it/s] Train steps ... : 6%|▌ | 5888/100000 [1:46:37<15:16:10, 1.71it/s] Train steps ... : 6%|▌ | 5889/100000 [1:46:38<15:17:14, 1.71it/s] Train steps ... : 6%|▌ | 5890/100000 [1:46:39<15:18:14, 1.71it/s] Train steps ... : 6%|▌ | 5891/100000 [1:46:39<15:16:09, 1.71it/s] Train steps ... : 6%|▌ | 5892/100000 [1:46:40<15:16:46, 1.71it/s] Train steps ... : 6%|▌ | 5893/100000 [1:46:40<15:17:24, 1.71it/s] Train steps ... : 6%|▌ | 5894/100000 [1:46:41<15:17:28, 1.71it/s] Train steps ... : 6%|▌ | 5895/100000 [1:46:42<15:17:12, 1.71it/s] Train steps ... : 6%|▌ | 5896/100000 [1:46:42<15:16:18, 1.71it/s] Train steps ... : 6%|▌ | 5897/100000 [1:46:43<15:16:52, 1.71it/s] Train steps ... : 6%|▌ | 5898/100000 [1:46:43<15:16:12, 1.71it/s] Train steps ... : 6%|▌ | 5899/100000 [1:46:44<15:15:22, 1.71it/s] Train steps ... : 6%|▌ | 5900/100000 [1:46:44<15:15:08, 1.71it/s]Step... (5900 / 100000 | Loss: 1.275050163269043, Learning Rate: 9.457286432160805e-05) Step... (5900 / 100000 | Loss: 1.8392488956451416, Learning Rate: 9.457286432160805e-05) Train steps ... : 6%|▌ | 5900/100000 [1:46:45<15:15:08, 1.71it/s] Train steps ... : 6%|▌ | 5901/100000 [1:46:45<15:15:15, 1.71it/s] Train steps ... : 6%|▌ | 5902/100000 [1:46:46<15:15:50, 1.71it/s] Train steps ... : 6%|▌ | 5903/100000 [1:46:46<15:18:14, 1.71it/s] Train steps ... : 6%|▌ | 5904/100000 [1:46:47<15:16:53, 1.71it/s] Train steps ... : 6%|▌ | 5905/100000 [1:46:47<15:17:07, 1.71it/s] Train steps ... : 6%|▌ | 5906/100000 [1:46:48<15:16:05, 1.71it/s] Train steps ... : 6%|▌ | 5907/100000 [1:46:49<15:15:53, 1.71it/s] Train steps ... : 6%|▌ | 5908/100000 [1:46:49<15:17:55, 1.71it/s] Train steps ... : 6%|▌ | 5909/100000 [1:46:50<15:17:19, 1.71it/s] Train steps ... : 6%|▌ | 5910/100000 [1:46:50<15:17:40, 1.71it/s] Train steps ... : 6%|▌ | 5911/100000 [1:46:51<15:16:47, 1.71it/s] Train steps ... : 6%|▌ | 5912/100000 [1:46:52<15:16:33, 1.71it/s] Train steps ... : 6%|▌ | 5913/100000 [1:46:52<15:16:27, 1.71it/s] Train steps ... : 6%|▌ | 5914/100000 [1:46:53<15:17:25, 1.71it/s] Train steps ... : 6%|▌ | 5915/100000 [1:46:53<15:16:07, 1.71it/s] Train steps ... : 6%|▌ | 5916/100000 [1:46:54<15:17:31, 1.71it/s] Train steps ... : 6%|▌ | 5917/100000 [1:46:54<15:17:41, 1.71it/s] Train steps ... : 6%|▌ | 5918/100000 [1:46:55<15:18:07, 1.71it/s] Train steps ... : 6%|▌ | 5919/100000 [1:46:56<15:17:24, 1.71it/s] Train steps ... : 6%|▌ | 5920/100000 [1:46:56<15:15:50, 1.71it/s] Train steps ... : 6%|▌ | 5921/100000 [1:46:57<15:16:51, 1.71it/s] Train steps ... : 6%|▌ | 5922/100000 [1:46:57<15:17:05, 1.71it/s] Train steps ... : 6%|▌ | 5923/100000 [1:46:58<15:16:20, 1.71it/s] Train steps ... : 6%|▌ | 5924/100000 [1:46:59<15:16:34, 1.71it/s] Train steps ... : 6%|▌ | 5925/100000 [1:46:59<15:16:19, 1.71it/s]Step... (5925 / 100000 | Loss: 1.515782356262207, Learning Rate: 9.454773869346733e-05) Step... (5925 / 100000 | Loss: 1.771012306213379, Learning Rate: 9.454773869346733e-05) Train steps ... : 6%|▌ | 5925/100000 [1:46:59<15:16:19, 1.71it/s] Train steps ... : 6%|▌ | 5926/100000 [1:47:00<15:16:54, 1.71it/s] Train steps ... : 6%|▌ | 5927/100000 [1:47:00<15:17:23, 1.71it/s] Train steps ... : 6%|▌ | 5928/100000 [1:47:01<15:16:14, 1.71it/s] Train steps ... : 6%|▌ | 5929/100000 [1:47:01<15:16:41, 1.71it/s] Train steps ... : 6%|▌ | 5930/100000 [1:47:02<15:16:06, 1.71it/s] Train steps ... : 6%|▌ | 5931/100000 [1:47:03<15:15:33, 1.71it/s] Train steps ... : 6%|▌ | 5932/100000 [1:47:03<15:16:08, 1.71it/s] Train steps ... : 6%|▌ | 5933/100000 [1:47:04<15:15:30, 1.71it/s] Train steps ... : 6%|▌ | 5934/100000 [1:47:04<15:15:57, 1.71it/s] Train steps ... : 6%|▌ | 5935/100000 [1:47:05<15:14:59, 1.71it/s] Train steps ... : 6%|▌ | 5936/100000 [1:47:06<15:14:23, 1.71it/s] Train steps ... : 6%|▌ | 5937/100000 [1:47:06<15:14:26, 1.71it/s] Train steps ... : 6%|▌ | 5938/100000 [1:47:07<15:13:43, 1.72it/s] Train steps ... : 6%|▌ | 5939/100000 [1:47:07<15:14:01, 1.72it/s] Train steps ... : 6%|▌ | 5940/100000 [1:47:08<15:15:20, 1.71it/s] Train steps ... : 6%|▌ | 5941/100000 [1:47:08<15:15:56, 1.71it/s] Train steps ... : 6%|▌ | 5942/100000 [1:47:09<15:15:19, 1.71it/s] Train steps ... : 6%|▌ | 5943/100000 [1:47:10<15:15:25, 1.71it/s] Train steps ... : 6%|▌ | 5944/100000 [1:47:10<15:14:48, 1.71it/s] Train steps ... : 6%|▌ | 5945/100000 [1:47:11<15:15:35, 1.71it/s] Train steps ... : 6%|▌ | 5946/100000 [1:47:11<15:15:11, 1.71it/s] Train steps ... : 6%|▌ | 5947/100000 [1:47:12<15:15:12, 1.71it/s] Train steps ... : 6%|▌ | 5948/100000 [1:47:13<15:14:57, 1.71it/s] Train steps ... : 6%|▌ | 5949/100000 [1:47:13<15:15:48, 1.71it/s] Train steps ... : 6%|▌ | 5950/100000 [1:47:14<15:15:29, 1.71it/s]Step... (5950 / 100000 | Loss: 1.6833016872406006, Learning Rate: 9.452261306532664e-05) Step... (5950 / 100000 | Loss: 1.52228844165802, Learning Rate: 9.452261306532664e-05) Train steps ... : 6%|▌ | 5950/100000 [1:47:14<15:15:29, 1.71it/s] Train steps ... : 6%|▌ | 5951/100000 [1:47:14<15:16:08, 1.71it/s] Train steps ... : 6%|▌ | 5952/100000 [1:47:15<15:15:44, 1.71it/s] Train steps ... : 6%|▌ | 5953/100000 [1:47:15<15:15:25, 1.71it/s] Train steps ... : 6%|▌ | 5954/100000 [1:47:16<15:15:32, 1.71it/s] Train steps ... : 6%|▌ | 5955/100000 [1:47:17<15:16:54, 1.71it/s] Train steps ... : 6%|▌ | 5956/100000 [1:47:17<15:16:09, 1.71it/s] Train steps ... : 6%|▌ | 5957/100000 [1:47:18<15:16:18, 1.71it/s] Train steps ... : 6%|▌ | 5958/100000 [1:47:18<15:15:03, 1.71it/s] Train steps ... : 6%|▌ | 5959/100000 [1:47:19<15:15:36, 1.71it/s] Train steps ... : 6%|▌ | 5960/100000 [1:47:20<15:15:06, 1.71it/s] Train steps ... : 6%|▌ | 5961/100000 [1:47:20<15:14:53, 1.71it/s] Train steps ... : 6%|▌ | 5962/100000 [1:47:21<15:15:56, 1.71it/s] Train steps ... : 6%|▌ | 5963/100000 [1:47:21<15:15:58, 1.71it/s] Train steps ... : 6%|▌ | 5964/100000 [1:47:22<15:16:11, 1.71it/s] Train steps ... : 6%|▌ | 5965/100000 [1:47:22<15:14:54, 1.71it/s] Train steps ... : 6%|▌ | 5966/100000 [1:47:23<15:14:37, 1.71it/s] Train steps ... : 6%|▌ | 5967/100000 [1:47:24<15:14:40, 1.71it/s] Train steps ... : 6%|▌ | 5968/100000 [1:47:24<15:14:02, 1.71it/s] Train steps ... : 6%|▌ | 5969/100000 [1:47:25<15:13:51, 1.71it/s] Train steps ... : 6%|▌ | 5970/100000 [1:47:25<15:13:47, 1.72it/s] Train steps ... : 6%|▌ | 5971/100000 [1:47:26<15:14:37, 1.71it/s] Train steps ... : 6%|▌ | 5972/100000 [1:47:27<15:14:35, 1.71it/s] Train steps ... : 6%|▌ | 5973/100000 [1:47:27<15:14:35, 1.71it/s] Train steps ... : 6%|▌ | 5974/100000 [1:47:28<15:15:07, 1.71it/s] Train steps ... : 6%|▌ | 5975/100000 [1:47:28<15:14:09, 1.71it/s]Step... (5975 / 100000 | Loss: 1.661207675933838, Learning Rate: 9.449748743718594e-05) Step... (5975 / 100000 | Loss: 1.062423586845398, Learning Rate: 9.449748743718594e-05) Train steps ... : 6%|▌ | 5975/100000 [1:47:29<15:14:09, 1.71it/s] Train steps ... : 6%|▌ | 5976/100000 [1:47:29<15:15:22, 1.71it/s] Train steps ... : 6%|▌ | 5977/100000 [1:47:29<15:14:40, 1.71it/s] Train steps ... : 6%|▌ | 5978/100000 [1:47:30<15:15:32, 1.71it/s] Train steps ... : 6%|▌ | 5979/100000 [1:47:31<15:16:45, 1.71it/s] Train steps ... : 6%|▌ | 5980/100000 [1:47:31<15:16:08, 1.71it/s] Train steps ... : 6%|▌ | 5981/100000 [1:47:32<15:16:01, 1.71it/s] Train steps ... : 6%|▌ | 5982/100000 [1:47:32<15:16:49, 1.71it/s] Train steps ... : 6%|▌ | 5983/100000 [1:47:33<15:17:50, 1.71it/s] Train steps ... : 6%|▌ | 5984/100000 [1:47:34<15:16:05, 1.71it/s] Train steps ... : 6%|▌ | 5985/100000 [1:47:34<15:15:43, 1.71it/s] Train steps ... : 6%|▌ | 5986/100000 [1:47:35<15:16:01, 1.71it/s] Train steps ... : 6%|▌ | 5987/100000 [1:47:35<15:17:02, 1.71it/s] Train steps ... : 6%|▌ | 5988/100000 [1:47:36<15:15:28, 1.71it/s] Train steps ... : 6%|▌ | 5989/100000 [1:47:36<15:15:07, 1.71it/s] Train steps ... : 6%|▌ | 5990/100000 [1:47:37<15:16:10, 1.71it/s] Train steps ... : 6%|▌ | 5991/100000 [1:47:38<15:15:31, 1.71it/s] Train steps ... : 6%|▌ | 5992/100000 [1:47:38<15:14:49, 1.71it/s] Train steps ... : 6%|▌ | 5993/100000 [1:47:39<15:14:35, 1.71it/s] Train steps ... : 6%|▌ | 5994/100000 [1:47:39<15:16:50, 1.71it/s] Train steps ... : 6%|▌ | 5995/100000 [1:47:40<15:16:48, 1.71it/s] Train steps ... : 6%|▌ | 5996/100000 [1:47:41<15:16:32, 1.71it/s] Train steps ... : 6%|▌ | 5997/100000 [1:47:41<15:16:00, 1.71it/s] Train steps ... : 6%|▌ | 5998/100000 [1:47:42<15:17:08, 1.71it/s] Train steps ... : 6%|▌ | 5999/100000 [1:47:42<15:16:47, 1.71it/s] Train steps ... : 6%|▌ | 6000/100000 [1:47:43<15:15:54, 1.71it/s]Step... (6000 / 100000 | Loss: 1.4638898372650146, Learning Rate: 9.447236180904523e-05) Step... (6000 / 100000 | Loss: 1.7375283241271973, Learning Rate: 9.447236180904523e-05) Train steps ... : 6%|▌ | 6000/100000 [1:47:43<15:15:54, 1.71it/s] Train steps ... : 6%|▌ | 6001/100000 [1:47:44<15:16:22, 1.71it/s] Train steps ... : 6%|▌ | 6002/100000 [1:47:44<15:16:02, 1.71it/s] Train steps ... : 6%|▌ | 6003/100000 [1:47:45<15:15:26, 1.71it/s] Train steps ... : 6%|▌ | 6004/100000 [1:47:45<15:16:55, 1.71it/s] Train steps ... : 6%|▌ | 6005/100000 [1:47:46<15:16:48, 1.71it/s] Train steps ... : 6%|▌ | 6006/100000 [1:47:46<15:16:10, 1.71it/s] Train steps ... : 6%|▌ | 6007/100000 [1:47:47<15:15:42, 1.71it/s] Train steps ... : 6%|▌ | 6008/100000 [1:47:48<15:15:07, 1.71it/s] Train steps ... : 6%|▌ | 6009/100000 [1:47:48<15:14:56, 1.71it/s] Train steps ... : 6%|▌ | 6010/100000 [1:47:49<15:15:33, 1.71it/s] Train steps ... : 6%|▌ | 6011/100000 [1:47:49<15:15:32, 1.71it/s] Train steps ... : 6%|▌ | 6012/100000 [1:47:50<15:16:06, 1.71it/s] Train steps ... : 6%|▌ | 6013/100000 [1:47:51<15:16:21, 1.71it/s] Train steps ... : 6%|▌ | 6014/100000 [1:47:51<15:15:57, 1.71it/s] Train steps ... : 6%|▌ | 6015/100000 [1:47:52<15:15:12, 1.71it/s] Train steps ... : 6%|▌ | 6016/100000 [1:47:52<15:14:49, 1.71it/s] Train steps ... : 6%|▌ | 6017/100000 [1:47:53<15:15:56, 1.71it/s] Train steps ... : 6%|▌ | 6018/100000 [1:47:53<15:16:15, 1.71it/s] Train steps ... : 6%|▌ | 6019/100000 [1:47:54<15:16:39, 1.71it/s] Train steps ... : 6%|▌ | 6020/100000 [1:47:55<15:17:00, 1.71it/s] Train steps ... : 6%|▌ | 6021/100000 [1:47:55<15:17:21, 1.71it/s] Train steps ... : 6%|▌ | 6022/100000 [1:47:56<15:16:22, 1.71it/s] Train steps ... : 6%|▌ | 6023/100000 [1:47:56<15:16:40, 1.71it/s] Train steps ... : 6%|▌ | 6024/100000 [1:47:57<15:16:07, 1.71it/s] Train steps ... : 6%|▌ | 6025/100000 [1:47:58<15:17:02, 1.71it/s]Step... (6025 / 100000 | Loss: 1.378150463104248, Learning Rate: 9.444723618090453e-05) Step... (6025 / 100000 | Loss: 1.9941521883010864, Learning Rate: 9.444723618090453e-05) Train steps ... : 6%|▌ | 6025/100000 [1:47:58<15:17:02, 1.71it/s] Train steps ... : 6%|▌ | 6026/100000 [1:47:58<15:16:52, 1.71it/s] Train steps ... : 6%|▌ | 6027/100000 [1:47:59<15:17:13, 1.71it/s] Train steps ... : 6%|▌ | 6028/100000 [1:47:59<15:17:15, 1.71it/s] Train steps ... : 6%|▌ | 6029/100000 [1:48:00<15:16:56, 1.71it/s] Train steps ... : 6%|▌ | 6030/100000 [1:48:00<15:15:51, 1.71it/s] Train steps ... : 6%|▌ | 6031/100000 [1:48:01<15:15:21, 1.71it/s] Train steps ... : 6%|▌ | 6032/100000 [1:48:02<15:14:56, 1.71it/s] Train steps ... : 6%|▌ | 6033/100000 [1:48:02<15:14:50, 1.71it/s] Train steps ... : 6%|▌ | 6034/100000 [1:48:03<15:15:45, 1.71it/s] Train steps ... : 6%|▌ | 6035/100000 [1:48:03<15:15:21, 1.71it/s] Train steps ... : 6%|▌ | 6036/100000 [1:48:04<15:15:15, 1.71it/s] Train steps ... : 6%|▌ | 6037/100000 [1:48:05<15:14:45, 1.71it/s] Train steps ... : 6%|▌ | 6038/100000 [1:48:05<15:13:48, 1.71it/s] Train steps ... : 6%|▌ | 6039/100000 [1:48:06<15:13:52, 1.71it/s] Train steps ... : 6%|▌ | 6040/100000 [1:48:06<15:13:09, 1.71it/s] Train steps ... : 6%|▌ | 6041/100000 [1:48:07<15:13:12, 1.71it/s] Train steps ... : 6%|▌ | 6042/100000 [1:48:07<15:14:24, 1.71it/s] Train steps ... : 6%|▌ | 6043/100000 [1:48:08<15:13:55, 1.71it/s] Train steps ... : 6%|▌ | 6044/100000 [1:48:09<15:16:12, 1.71it/s] Train steps ... : 6%|▌ | 6045/100000 [1:48:09<15:15:37, 1.71it/s] Train steps ... : 6%|▌ | 6046/100000 [1:48:10<15:14:24, 1.71it/s] Train steps ... : 6%|▌ | 6047/100000 [1:48:10<15:14:44, 1.71it/s] Train steps ... : 6%|▌ | 6048/100000 [1:48:11<15:15:26, 1.71it/s] Train steps ... : 6%|▌ | 6049/100000 [1:48:12<15:15:48, 1.71it/s] Train steps ... : 6%|▌ | 6050/100000 [1:48:12<15:15:34, 1.71it/s]Step... (6050 / 100000 | Loss: 1.3701601028442383, Learning Rate: 9.442211055276381e-05) Step... (6050 / 100000 | Loss: 1.5694761276245117, Learning Rate: 9.442211055276381e-05) Train steps ... : 6%|▌ | 6050/100000 [1:48:12<15:15:34, 1.71it/s] Train steps ... : 6%|▌ | 6051/100000 [1:48:13<15:15:33, 1.71it/s] Train steps ... : 6%|▌ | 6052/100000 [1:48:13<15:15:20, 1.71it/s] Train steps ... : 6%|▌ | 6053/100000 [1:48:14<15:16:50, 1.71it/s] Train steps ... : 6%|▌ | 6054/100000 [1:48:14<15:14:40, 1.71it/s] Train steps ... : 6%|▌ | 6055/100000 [1:48:15<15:16:44, 1.71it/s] Train steps ... : 6%|▌ | 6056/100000 [1:48:16<15:15:48, 1.71it/s] Train steps ... : 6%|▌ | 6057/100000 [1:48:16<15:14:49, 1.71it/s] Train steps ... : 6%|▌ | 6058/100000 [1:48:17<15:16:06, 1.71it/s] Train steps ... : 6%|▌ | 6059/100000 [1:48:17<15:15:49, 1.71it/s] Train steps ... : 6%|▌ | 6060/100000 [1:48:18<15:14:58, 1.71it/s] Train steps ... : 6%|▌ | 6061/100000 [1:48:19<15:15:27, 1.71it/s] Train steps ... : 6%|▌ | 6062/100000 [1:48:19<15:16:28, 1.71it/s] Train steps ... : 6%|▌ | 6063/100000 [1:48:20<15:15:48, 1.71it/s] Train steps ... : 6%|▌ | 6064/100000 [1:48:20<15:15:55, 1.71it/s] Train steps ... : 6%|▌ | 6065/100000 [1:48:21<15:15:04, 1.71it/s] Train steps ... : 6%|▌ | 6066/100000 [1:48:22<15:15:00, 1.71it/s] Train steps ... : 6%|▌ | 6067/100000 [1:48:22<15:15:08, 1.71it/s] Train steps ... : 6%|▌ | 6068/100000 [1:48:23<15:15:00, 1.71it/s] Train steps ... : 6%|▌ | 6069/100000 [1:48:23<15:14:16, 1.71it/s] Train steps ... : 6%|▌ | 6070/100000 [1:48:24<15:14:39, 1.71it/s] Train steps ... : 6%|▌ | 6071/100000 [1:48:24<15:15:23, 1.71it/s] Train steps ... : 6%|▌ | 6072/100000 [1:48:25<15:16:26, 1.71it/s] Train steps ... : 6%|▌ | 6073/100000 [1:48:26<15:16:07, 1.71it/s] Train steps ... : 6%|▌ | 6074/100000 [1:48:26<15:15:16, 1.71it/s] Train steps ... : 6%|▌ | 6075/100000 [1:48:27<15:14:35, 1.71it/s]Step... (6075 / 100000 | Loss: 1.5818554162979126, Learning Rate: 9.439698492462312e-05) Step... (6075 / 100000 | Loss: 1.3524341583251953, Learning Rate: 9.439698492462312e-05) Train steps ... : 6%|▌ | 6075/100000 [1:48:27<15:14:35, 1.71it/s] Train steps ... : 6%|▌ | 6076/100000 [1:48:27<15:15:25, 1.71it/s] Train steps ... : 6%|▌ | 6077/100000 [1:48:28<15:16:55, 1.71it/s] Train steps ... : 6%|▌ | 6078/100000 [1:48:29<15:16:01, 1.71it/s] Train steps ... : 6%|▌ | 6079/100000 [1:48:29<15:14:46, 1.71it/s] Train steps ... : 6%|▌ | 6080/100000 [1:48:30<15:15:56, 1.71it/s] Train steps ... : 6%|▌ | 6081/100000 [1:48:30<15:17:06, 1.71it/s] Train steps ... : 6%|▌ | 6082/100000 [1:48:31<15:16:16, 1.71it/s] Train steps ... : 6%|▌ | 6083/100000 [1:48:31<15:15:01, 1.71it/s] Train steps ... : 6%|▌ | 6084/100000 [1:48:32<15:14:33, 1.71it/s] Train steps ... : 6%|▌ | 6085/100000 [1:48:33<15:15:12, 1.71it/s] Train steps ... : 6%|▌ | 6086/100000 [1:48:33<15:14:23, 1.71it/s] Train steps ... : 6%|▌ | 6087/100000 [1:48:34<15:14:16, 1.71it/s] Train steps ... : 6%|▌ | 6088/100000 [1:48:34<15:14:13, 1.71it/s] Train steps ... : 6%|▌ | 6089/100000 [1:48:35<15:14:59, 1.71it/s] Train steps ... : 6%|▌ | 6090/100000 [1:48:36<15:14:49, 1.71it/s] Train steps ... : 6%|▌ | 6091/100000 [1:48:36<15:14:35, 1.71it/s] Train steps ... : 6%|▌ | 6092/100000 [1:48:37<15:14:58, 1.71it/s] Train steps ... : 6%|▌ | 6093/100000 [1:48:37<15:14:04, 1.71it/s] Train steps ... : 6%|▌ | 6094/100000 [1:48:38<15:14:46, 1.71it/s] Train steps ... : 6%|▌ | 6095/100000 [1:48:38<15:14:52, 1.71it/s] Train steps ... : 6%|▌ | 6096/100000 [1:48:39<15:14:58, 1.71it/s] Train steps ... : 6%|▌ | 6097/100000 [1:48:40<15:14:38, 1.71it/s] Train steps ... : 6%|▌ | 6098/100000 [1:48:40<15:14:04, 1.71it/s] Train steps ... : 6%|▌ | 6099/100000 [1:48:41<15:13:28, 1.71it/s] Train steps ... : 6%|▌ | 6100/100000 [1:48:41<15:13:52, 1.71it/s]Step... (6100 / 100000 | Loss: 1.2130166292190552, Learning Rate: 9.437185929648241e-05) Step... (6100 / 100000 | Loss: 1.5746407508850098, Learning Rate: 9.437185929648241e-05) Train steps ... : 6%|▌ | 6100/100000 [1:48:42<15:13:52, 1.71it/s] Train steps ... : 6%|▌ | 6101/100000 [1:48:42<15:14:24, 1.71it/s] Train steps ... : 6%|▌ | 6102/100000 [1:48:43<15:15:00, 1.71it/s] Train steps ... : 6%|▌ | 6103/100000 [1:48:43<15:15:29, 1.71it/s] Train steps ... : 6%|▌ | 6104/100000 [1:48:44<15:14:45, 1.71it/s] Train steps ... : 6%|▌ | 6105/100000 [1:48:44<15:14:21, 1.71it/s] Train steps ... : 6%|▌ | 6106/100000 [1:48:45<15:13:35, 1.71it/s] Train steps ... : 6%|▌ | 6107/100000 [1:48:45<15:14:30, 1.71it/s] Train steps ... : 6%|▌ | 6108/100000 [1:48:46<15:14:13, 1.71it/s] Train steps ... : 6%|▌ | 6109/100000 [1:48:47<15:14:12, 1.71it/s] Train steps ... : 6%|▌ | 6110/100000 [1:48:47<15:13:13, 1.71it/s] Train steps ... : 6%|▌ | 6111/100000 [1:48:48<15:14:19, 1.71it/s] Train steps ... : 6%|▌ | 6112/100000 [1:48:48<15:14:39, 1.71it/s] Train steps ... : 6%|▌ | 6113/100000 [1:48:49<15:14:20, 1.71it/s] Train steps ... : 6%|▌ | 6114/100000 [1:48:50<15:14:10, 1.71it/s] Train steps ... : 6%|▌ | 6115/100000 [1:48:50<15:15:02, 1.71it/s] Train steps ... : 6%|▌ | 6116/100000 [1:48:51<15:14:42, 1.71it/s] Train steps ... : 6%|▌ | 6117/100000 [1:48:51<15:14:01, 1.71it/s] Train steps ... : 6%|▌ | 6118/100000 [1:48:52<15:14:55, 1.71it/s] Train steps ... : 6%|▌ | 6119/100000 [1:48:52<15:15:23, 1.71it/s] Train steps ... : 6%|▌ | 6120/100000 [1:48:53<15:15:36, 1.71it/s] Train steps ... : 6%|▌ | 6121/100000 [1:48:54<15:14:34, 1.71it/s] Train steps ... : 6%|▌ | 6122/100000 [1:48:54<15:15:48, 1.71it/s] Train steps ... : 6%|▌ | 6123/100000 [1:48:55<15:14:48, 1.71it/s] Train steps ... : 6%|▌ | 6124/100000 [1:48:55<15:15:20, 1.71it/s] Train steps ... : 6%|▌ | 6125/100000 [1:48:56<15:13:17, 1.71it/s]Step... (6125 / 100000 | Loss: 1.5611729621887207, Learning Rate: 9.434673366834172e-05) Step... (6125 / 100000 | Loss: 1.5439226627349854, Learning Rate: 9.434673366834172e-05) Train steps ... : 6%|▌ | 6125/100000 [1:48:56<15:13:17, 1.71it/s] Train steps ... : 6%|▌ | 6126/100000 [1:48:57<15:13:25, 1.71it/s] Train steps ... : 6%|▌ | 6127/100000 [1:48:57<15:12:57, 1.71it/s] Train steps ... : 6%|▌ | 6128/100000 [1:48:58<15:13:59, 1.71it/s] Train steps ... : 6%|▌ | 6129/100000 [1:48:58<15:13:42, 1.71it/s] Train steps ... : 6%|▌ | 6130/100000 [1:48:59<15:13:33, 1.71it/s] Train steps ... : 6%|▌ | 6131/100000 [1:48:59<15:15:07, 1.71it/s] Train steps ... : 6%|▌ | 6132/100000 [1:49:00<15:14:11, 1.71it/s] Train steps ... : 6%|▌ | 6133/100000 [1:49:01<15:14:26, 1.71it/s] Train steps ... : 6%|▌ | 6134/100000 [1:49:01<15:14:45, 1.71it/s] Train steps ... : 6%|▌ | 6135/100000 [1:49:02<15:14:49, 1.71it/s] Train steps ... : 6%|▌ | 6136/100000 [1:49:02<15:13:49, 1.71it/s] Train steps ... : 6%|▌ | 6137/100000 [1:49:03<15:14:05, 1.71it/s] Train steps ... : 6%|▌ | 6138/100000 [1:49:04<15:14:23, 1.71it/s] Train steps ... : 6%|▌ | 6139/100000 [1:49:04<15:14:13, 1.71it/s] Train steps ... : 6%|▌ | 6140/100000 [1:49:05<15:13:47, 1.71it/s] Train steps ... : 6%|▌ | 6141/100000 [1:49:05<15:13:26, 1.71it/s] Train steps ... : 6%|▌ | 6142/100000 [1:49:06<15:13:18, 1.71it/s] Train steps ... : 6%|▌ | 6143/100000 [1:49:07<15:12:38, 1.71it/s] Train steps ... : 6%|▌ | 6144/100000 [1:49:07<15:12:36, 1.71it/s] Train steps ... : 6%|▌ | 6145/100000 [1:49:08<15:13:15, 1.71it/s] Train steps ... : 6%|▌ | 6146/100000 [1:49:08<15:13:27, 1.71it/s] Train steps ... : 6%|▌ | 6147/100000 [1:49:09<15:13:37, 1.71it/s] Train steps ... : 6%|▌ | 6148/100000 [1:49:09<15:13:05, 1.71it/s] Train steps ... : 6%|▌ | 6149/100000 [1:49:10<15:14:25, 1.71it/s] Train steps ... : 6%|▌ | 6150/100000 [1:49:11<15:13:36, 1.71it/s]Step... (6150 / 100000 | Loss: 1.5386974811553955, Learning Rate: 9.432160804020101e-05) Step... (6150 / 100000 | Loss: 1.5190472602844238, Learning Rate: 9.432160804020101e-05) Train steps ... : 6%|▌ | 6150/100000 [1:49:11<15:13:36, 1.71it/s] Train steps ... : 6%|▌ | 6151/100000 [1:49:11<15:13:50, 1.71it/s] Train steps ... : 6%|▌ | 6152/100000 [1:49:12<15:15:03, 1.71it/s] Train steps ... : 6%|▌ | 6153/100000 [1:49:12<15:14:18, 1.71it/s] Train steps ... : 6%|▌ | 6154/100000 [1:49:13<15:13:31, 1.71it/s] Train steps ... : 6%|▌ | 6155/100000 [1:49:14<15:13:34, 1.71it/s] Train steps ... : 6%|▌ | 6156/100000 [1:49:14<15:13:27, 1.71it/s] Train steps ... : 6%|▌ | 6157/100000 [1:49:15<15:13:06, 1.71it/s] Train steps ... : 6%|▌ | 6158/100000 [1:49:15<15:13:39, 1.71it/s] Train steps ... : 6%|▌ | 6159/100000 [1:49:16<15:13:37, 1.71it/s] Train steps ... : 6%|▌ | 6160/100000 [1:49:16<15:12:45, 1.71it/s] Train steps ... : 6%|▌ | 6161/100000 [1:49:17<15:12:40, 1.71it/s] Train steps ... : 6%|▌ | 6162/100000 [1:49:18<15:14:04, 1.71it/s] Train steps ... : 6%|▌ | 6163/100000 [1:49:18<15:13:28, 1.71it/s] Train steps ... : 6%|▌ | 6164/100000 [1:49:19<15:13:26, 1.71it/s] Train steps ... : 6%|▌ | 6165/100000 [1:49:19<15:14:20, 1.71it/s] Train steps ... : 6%|▌ | 6166/100000 [1:49:20<15:13:54, 1.71it/s] Train steps ... : 6%|▌ | 6167/100000 [1:49:21<15:13:12, 1.71it/s] Train steps ... : 6%|▌ | 6168/100000 [1:49:21<15:12:36, 1.71it/s] Train steps ... : 6%|▌ | 6169/100000 [1:49:22<15:14:10, 1.71it/s] Train steps ... : 6%|▌ | 6170/100000 [1:49:22<15:14:22, 1.71it/s] Train steps ... : 6%|▌ | 6171/100000 [1:49:23<15:13:35, 1.71it/s] Train steps ... : 6%|▌ | 6172/100000 [1:49:23<15:14:50, 1.71it/s] Train steps ... : 6%|▌ | 6173/100000 [1:49:24<15:13:32, 1.71it/s] Train steps ... : 6%|▌ | 6174/100000 [1:49:25<15:14:25, 1.71it/s] Train steps ... : 6%|▌ | 6175/100000 [1:49:25<15:13:15, 1.71it/s]Step... (6175 / 100000 | Loss: 1.5648961067199707, Learning Rate: 9.429648241206031e-05) Step... (6175 / 100000 | Loss: 1.434834361076355, Learning Rate: 9.429648241206031e-05) Train steps ... : 6%|▌ | 6175/100000 [1:49:26<15:13:15, 1.71it/s] Train steps ... : 6%|▌ | 6176/100000 [1:49:26<15:14:34, 1.71it/s] Train steps ... : 6%|▌ | 6177/100000 [1:49:26<15:14:49, 1.71it/s] Train steps ... : 6%|▌ | 6178/100000 [1:49:27<15:14:25, 1.71it/s] Train steps ... : 6%|▌ | 6179/100000 [1:49:28<15:14:15, 1.71it/s] Train steps ... : 6%|▌ | 6180/100000 [1:49:28<15:13:19, 1.71it/s] Train steps ... : 6%|▌ | 6181/100000 [1:49:29<15:13:48, 1.71it/s] Train steps ... : 6%|▌ | 6182/100000 [1:49:29<15:13:59, 1.71it/s] Train steps ... : 6%|▌ | 6183/100000 [1:49:30<15:14:24, 1.71it/s] Train steps ... : 6%|▌ | 6184/100000 [1:49:30<15:14:04, 1.71it/s] Train steps ... : 6%|▌ | 6185/100000 [1:49:31<15:13:56, 1.71it/s] Train steps ... : 6%|▌ | 6186/100000 [1:49:32<15:13:14, 1.71it/s] Train steps ... : 6%|▌ | 6187/100000 [1:49:32<15:14:09, 1.71it/s] Train steps ... : 6%|▌ | 6188/100000 [1:49:33<15:13:51, 1.71it/s] Train steps ... : 6%|▌ | 6189/100000 [1:49:33<15:13:20, 1.71it/s] Train steps ... : 6%|▌ | 6190/100000 [1:49:34<15:12:49, 1.71it/s] Train steps ... : 6%|▌ | 6191/100000 [1:49:35<15:13:44, 1.71it/s] Train steps ... : 6%|▌ | 6192/100000 [1:49:35<15:13:38, 1.71it/s] Train steps ... : 6%|▌ | 6193/100000 [1:49:36<15:13:18, 1.71it/s] Train steps ... : 6%|▌ | 6194/100000 [1:49:36<15:13:02, 1.71it/s] Train steps ... : 6%|▌ | 6195/100000 [1:49:37<15:14:31, 1.71it/s] Train steps ... : 6%|▌ | 6196/100000 [1:49:37<15:15:08, 1.71it/s] Train steps ... : 6%|▌ | 6197/100000 [1:49:38<15:15:00, 1.71it/s] Train steps ... : 6%|▌ | 6198/100000 [1:49:39<15:14:43, 1.71it/s] Train steps ... : 6%|▌ | 6199/100000 [1:49:39<15:14:20, 1.71it/s] Train steps ... : 6%|▌ | 6200/100000 [1:49:40<15:14:33, 1.71it/s]Step... (6200 / 100000 | Loss: 1.7725276947021484, Learning Rate: 9.427135678391961e-05) Step... (6200 / 100000 | Loss: 1.4249000549316406, Learning Rate: 9.427135678391961e-05) Train steps ... : 6%|▌ | 6200/100000 [1:49:40<15:14:33, 1.71it/s] Train steps ... : 6%|▌ | 6201/100000 [1:49:40<15:14:25, 1.71it/s] Train steps ... : 6%|▌ | 6202/100000 [1:49:41<15:14:46, 1.71it/s] Train steps ... : 6%|▌ | 6203/100000 [1:49:42<15:13:27, 1.71it/s] Train steps ... : 6%|▌ | 6204/100000 [1:49:42<15:14:22, 1.71it/s] Train steps ... : 6%|▌ | 6205/100000 [1:49:43<15:13:32, 1.71it/s] Train steps ... : 6%|▌ | 6206/100000 [1:49:43<15:13:22, 1.71it/s] Train steps ... : 6%|▌ | 6207/100000 [1:49:44<15:12:58, 1.71it/s] Train steps ... : 6%|▌ | 6208/100000 [1:49:44<15:12:53, 1.71it/s] Train steps ... : 6%|▌ | 6209/100000 [1:49:45<15:13:08, 1.71it/s] Train steps ... : 6%|▌ | 6210/100000 [1:49:46<15:12:59, 1.71it/s] Train steps ... : 6%|▌ | 6211/100000 [1:49:46<15:13:06, 1.71it/s] Train steps ... : 6%|▌ | 6212/100000 [1:49:47<15:12:48, 1.71it/s] Train steps ... : 6%|▌ | 6213/100000 [1:49:47<15:13:48, 1.71it/s] Train steps ... : 6%|▌ | 6214/100000 [1:49:48<15:13:32, 1.71it/s] Train steps ... : 6%|▌ | 6215/100000 [1:49:49<15:13:21, 1.71it/s] Train steps ... : 6%|▌ | 6216/100000 [1:49:49<15:13:07, 1.71it/s] Train steps ... : 6%|▌ | 6217/100000 [1:49:50<15:12:52, 1.71it/s] Train steps ... : 6%|▌ | 6218/100000 [1:49:50<15:11:37, 1.71it/s] Train steps ... : 6%|▌ | 6219/100000 [1:49:51<15:11:28, 1.71it/s] Train steps ... : 6%|▌ | 6220/100000 [1:49:51<15:12:02, 1.71it/s] Train steps ... : 6%|▌ | 6221/100000 [1:49:52<15:12:19, 1.71it/s] Train steps ... : 6%|▌ | 6222/100000 [1:49:53<15:13:33, 1.71it/s] Train steps ... : 6%|▌ | 6223/100000 [1:49:53<15:13:00, 1.71it/s] Train steps ... : 6%|▌ | 6224/100000 [1:49:54<15:14:08, 1.71it/s] Train steps ... : 6%|▌ | 6225/100000 [1:49:54<15:13:14, 1.71it/s]Step... (6225 / 100000 | Loss: 2.0127131938934326, Learning Rate: 9.424623115577889e-05) Step... (6225 / 100000 | Loss: 1.2514925003051758, Learning Rate: 9.424623115577889e-05) Train steps ... : 6%|▌ | 6225/100000 [1:49:55<15:13:14, 1.71it/s] Train steps ... : 6%|▌ | 6226/100000 [1:49:55<15:14:40, 1.71it/s] Train steps ... : 6%|▌ | 6227/100000 [1:49:56<15:14:08, 1.71it/s] Train steps ... : 6%|▌ | 6228/100000 [1:49:56<15:13:10, 1.71it/s] Train steps ... : 6%|▌ | 6229/100000 [1:49:57<15:13:44, 1.71it/s] Train steps ... : 6%|▌ | 6230/100000 [1:49:57<15:13:45, 1.71it/s] Train steps ... : 6%|▌ | 6231/100000 [1:49:58<15:14:18, 1.71it/s] Train steps ... : 6%|▌ | 6232/100000 [1:49:59<15:13:33, 1.71it/s] Train steps ... : 6%|▌ | 6233/100000 [1:49:59<15:13:44, 1.71it/s] Train steps ... : 6%|▌ | 6234/100000 [1:50:00<15:14:01, 1.71it/s] Train steps ... : 6%|▌ | 6235/100000 [1:50:00<15:13:31, 1.71it/s] Train steps ... : 6%|▌ | 6236/100000 [1:50:01<15:13:56, 1.71it/s] Train steps ... : 6%|▌ | 6237/100000 [1:50:01<15:12:55, 1.71it/s] Train steps ... : 6%|▌ | 6238/100000 [1:50:02<15:14:44, 1.71it/s] Train steps ... : 6%|▌ | 6239/100000 [1:50:03<15:13:40, 1.71it/s] Train steps ... : 6%|▌ | 6240/100000 [1:50:03<15:14:13, 1.71it/s] Train steps ... : 6%|▌ | 6241/100000 [1:50:04<15:13:11, 1.71it/s] Train steps ... : 6%|▌ | 6242/100000 [1:50:04<15:13:13, 1.71it/s] Train steps ... : 6%|▌ | 6243/100000 [1:50:05<15:13:01, 1.71it/s] Train steps ... : 6%|▌ | 6244/100000 [1:50:06<15:12:01, 1.71it/s] Train steps ... : 6%|▌ | 6245/100000 [1:50:06<15:12:10, 1.71it/s] Train steps ... : 6%|▌ | 6246/100000 [1:50:07<15:12:44, 1.71it/s] Train steps ... : 6%|▌ | 6247/100000 [1:50:07<15:12:44, 1.71it/s] Train steps ... : 6%|▌ | 6248/100000 [1:50:08<15:13:11, 1.71it/s] Train steps ... : 6%|▌ | 6249/100000 [1:50:08<15:13:03, 1.71it/s] Train steps ... : 6%|▋ | 6250/100000 [1:50:09<15:14:01, 1.71it/s]Step... (6250 / 100000 | Loss: 1.2372266054153442, Learning Rate: 9.42211055276382e-05) Step... (6250 / 100000 | Loss: 1.490132212638855, Learning Rate: 9.42211055276382e-05) Train steps ... : 6%|▋ | 6250/100000 [1:50:09<15:14:01, 1.71it/s] Train steps ... : 6%|▋ | 6251/100000 [1:50:10<15:13:54, 1.71it/s] Train steps ... : 6%|▋ | 6252/100000 [1:50:10<15:14:45, 1.71it/s] Train steps ... : 6%|▋ | 6253/100000 [1:50:11<15:13:58, 1.71it/s] Train steps ... : 6%|▋ | 6254/100000 [1:50:11<15:12:55, 1.71it/s] Train steps ... : 6%|▋ | 6255/100000 [1:50:12<15:13:31, 1.71it/s] Train steps ... : 6%|▋ | 6256/100000 [1:50:13<15:15:25, 1.71it/s] Train steps ... : 6%|▋ | 6257/100000 [1:50:13<15:15:03, 1.71it/s] Train steps ... : 6%|▋ | 6258/100000 [1:50:14<15:14:46, 1.71it/s] Train steps ... : 6%|▋ | 6259/100000 [1:50:14<15:14:27, 1.71it/s] Train steps ... : 6%|▋ | 6260/100000 [1:50:15<15:13:13, 1.71it/s] Train steps ... : 6%|▋ | 6261/100000 [1:50:15<15:12:42, 1.71it/s] Train steps ... : 6%|▋ | 6262/100000 [1:50:16<15:12:15, 1.71it/s] Train steps ... : 6%|▋ | 6263/100000 [1:50:17<15:12:58, 1.71it/s] Train steps ... : 6%|▋ | 6264/100000 [1:50:17<15:13:33, 1.71it/s] Train steps ... : 6%|▋ | 6265/100000 [1:50:18<15:13:24, 1.71it/s] Train steps ... : 6%|▋ | 6266/100000 [1:50:18<15:12:33, 1.71it/s] Train steps ... : 6%|▋ | 6267/100000 [1:50:19<15:12:05, 1.71it/s] Train steps ... : 6%|▋ | 6268/100000 [1:50:20<15:13:07, 1.71it/s] Train steps ... : 6%|▋ | 6269/100000 [1:50:20<15:13:52, 1.71it/s] Train steps ... : 6%|▋ | 6270/100000 [1:50:21<15:14:29, 1.71it/s] Train steps ... : 6%|▋ | 6271/100000 [1:50:21<15:15:25, 1.71it/s] Train steps ... : 6%|▋ | 6272/100000 [1:50:22<15:15:41, 1.71it/s] Train steps ... : 6%|▋ | 6273/100000 [1:50:22<15:13:56, 1.71it/s] Train steps ... : 6%|▋ | 6274/100000 [1:50:23<15:13:23, 1.71it/s] Train steps ... : 6%|▋ | 6275/100000 [1:50:24<15:14:04, 1.71it/s]Step... (6275 / 100000 | Loss: 1.1212286949157715, Learning Rate: 9.419597989949748e-05) Step... (6275 / 100000 | Loss: 1.0852611064910889, Learning Rate: 9.419597989949748e-05) Train steps ... : 6%|▋ | 6275/100000 [1:50:24<15:14:04, 1.71it/s] Train steps ... : 6%|▋ | 6276/100000 [1:50:24<15:13:32, 1.71it/s] Train steps ... : 6%|▋ | 6277/100000 [1:50:25<15:13:18, 1.71it/s] Train steps ... : 6%|▋ | 6278/100000 [1:50:25<15:12:56, 1.71it/s] Train steps ... : 6%|▋ | 6279/100000 [1:50:26<15:12:43, 1.71it/s] Train steps ... : 6%|▋ | 6280/100000 [1:50:27<15:12:22, 1.71it/s] Train steps ... : 6%|▋ | 6281/100000 [1:50:27<15:12:52, 1.71it/s] Train steps ... : 6%|▋ | 6282/100000 [1:50:28<15:13:14, 1.71it/s] Train steps ... : 6%|▋ | 6283/100000 [1:50:28<15:14:12, 1.71it/s] Train steps ... : 6%|▋ | 6284/100000 [1:50:29<15:13:20, 1.71it/s] Train steps ... : 6%|▋ | 6285/100000 [1:50:30<15:12:20, 1.71it/s] Train steps ... : 6%|▋ | 6286/100000 [1:50:30<15:12:16, 1.71it/s] Train steps ... : 6%|▋ | 6287/100000 [1:50:31<15:13:18, 1.71it/s] Train steps ... : 6%|▋ | 6288/100000 [1:50:31<15:13:16, 1.71it/s] Train steps ... : 6%|▋ | 6289/100000 [1:50:32<15:12:18, 1.71it/s] Train steps ... : 6%|▋ | 6290/100000 [1:50:32<15:12:12, 1.71it/s] Train steps ... : 6%|▋ | 6291/100000 [1:50:33<15:12:54, 1.71it/s] Train steps ... : 6%|▋ | 6292/100000 [1:50:34<15:12:16, 1.71it/s] Train steps ... : 6%|▋ | 6293/100000 [1:50:34<15:12:02, 1.71it/s] Train steps ... : 6%|▋ | 6294/100000 [1:50:35<15:13:27, 1.71it/s] Train steps ... : 6%|▋ | 6295/100000 [1:50:35<15:12:51, 1.71it/s] Train steps ... : 6%|▋ | 6296/100000 [1:50:36<15:12:35, 1.71it/s] Train steps ... : 6%|▋ | 6297/100000 [1:50:37<15:12:32, 1.71it/s] Train steps ... : 6%|▋ | 6298/100000 [1:50:37<15:13:28, 1.71it/s] Train steps ... : 6%|▋ | 6299/100000 [1:50:38<15:13:49, 1.71it/s] Train steps ... : 6%|▋ | 6300/100000 [1:50:38<15:13:51, 1.71it/s]Step... (6300 / 100000 | Loss: 1.4393246173858643, Learning Rate: 9.41708542713568e-05) Step... (6300 / 100000 | Loss: 1.776949167251587, Learning Rate: 9.41708542713568e-05) Train steps ... : 6%|▋ | 6300/100000 [1:50:39<15:13:51, 1.71it/s] Train steps ... : 6%|▋ | 6301/100000 [1:50:39<15:13:38, 1.71it/s] Train steps ... : 6%|▋ | 6302/100000 [1:50:39<15:12:25, 1.71it/s] Train steps ... : 6%|▋ | 6303/100000 [1:50:40<15:13:40, 1.71it/s] Train steps ... : 6%|▋ | 6304/100000 [1:50:41<15:13:11, 1.71it/s] Train steps ... : 6%|▋ | 6305/100000 [1:50:41<15:12:27, 1.71it/s] Train steps ... : 6%|▋ | 6306/100000 [1:50:42<15:12:27, 1.71it/s] Train steps ... : 6%|▋ | 6307/100000 [1:50:42<15:11:52, 1.71it/s] Train steps ... : 6%|▋ | 6308/100000 [1:50:43<15:12:26, 1.71it/s] Train steps ... : 6%|▋ | 6309/100000 [1:50:44<15:12:19, 1.71it/s] Train steps ... : 6%|▋ | 6310/100000 [1:50:44<15:12:43, 1.71it/s] Train steps ... : 6%|▋ | 6311/100000 [1:50:45<15:13:19, 1.71it/s] Train steps ... : 6%|▋ | 6312/100000 [1:50:45<15:12:52, 1.71it/s] Train steps ... : 6%|▋ | 6313/100000 [1:50:46<15:13:25, 1.71it/s] Train steps ... : 6%|▋ | 6314/100000 [1:50:46<15:12:25, 1.71it/s] Train steps ... : 6%|▋ | 6315/100000 [1:50:47<15:13:34, 1.71it/s] Train steps ... : 6%|▋ | 6316/100000 [1:50:48<15:12:40, 1.71it/s] Train steps ... : 6%|▋ | 6317/100000 [1:50:48<15:13:18, 1.71it/s] Train steps ... : 6%|▋ | 6318/100000 [1:50:49<15:13:46, 1.71it/s] Train steps ... : 6%|▋ | 6319/100000 [1:50:49<15:13:44, 1.71it/s] Train steps ... : 6%|▋ | 6320/100000 [1:50:50<15:13:09, 1.71it/s] Train steps ... : 6%|▋ | 6321/100000 [1:50:51<15:14:04, 1.71it/s] Train steps ... : 6%|▋ | 6322/100000 [1:50:51<15:14:45, 1.71it/s] Train steps ... : 6%|▋ | 6323/100000 [1:50:52<15:14:19, 1.71it/s] Train steps ... : 6%|▋ | 6324/100000 [1:50:52<15:13:17, 1.71it/s] Train steps ... : 6%|▋ | 6325/100000 [1:50:53<15:13:04, 1.71it/s]Step... (6325 / 100000 | Loss: 1.1722685098648071, Learning Rate: 9.414572864321608e-05) Step... (6325 / 100000 | Loss: 1.2084897756576538, Learning Rate: 9.414572864321608e-05) Train steps ... : 6%|▋ | 6325/100000 [1:50:53<15:13:04, 1.71it/s] Train steps ... : 6%|▋ | 6326/100000 [1:50:53<15:14:00, 1.71it/s] Train steps ... : 6%|▋ | 6327/100000 [1:50:54<15:13:30, 1.71it/s] Train steps ... : 6%|▋ | 6328/100000 [1:50:55<15:13:39, 1.71it/s] Train steps ... : 6%|▋ | 6329/100000 [1:50:55<15:13:22, 1.71it/s] Train steps ... : 6%|▋ | 6330/100000 [1:50:56<15:12:28, 1.71it/s] Train steps ... : 6%|▋ | 6331/100000 [1:50:56<15:11:42, 1.71it/s] Train steps ... : 6%|▋ | 6332/100000 [1:50:57<15:13:19, 1.71it/s] Train steps ... : 6%|▋ | 6333/100000 [1:50:58<15:12:22, 1.71it/s] Train steps ... : 6%|▋ | 6334/100000 [1:50:58<15:13:25, 1.71it/s] Train steps ... : 6%|▋ | 6335/100000 [1:50:59<15:13:04, 1.71it/s] Train steps ... : 6%|▋ | 6336/100000 [1:50:59<15:13:16, 1.71it/s] Train steps ... : 6%|▋ | 6337/100000 [1:51:00<15:13:48, 1.71it/s] Train steps ... : 6%|▋ | 6338/100000 [1:51:00<15:12:47, 1.71it/s] Train steps ... : 6%|▋ | 6339/100000 [1:51:01<15:12:21, 1.71it/s] Train steps ... : 6%|▋ | 6340/100000 [1:51:02<15:13:12, 1.71it/s] Train steps ... : 6%|▋ | 6341/100000 [1:51:02<15:12:52, 1.71it/s] Train steps ... : 6%|▋ | 6342/100000 [1:51:03<15:12:29, 1.71it/s] Train steps ... : 6%|▋ | 6343/100000 [1:51:03<15:12:18, 1.71it/s] Train steps ... : 6%|▋ | 6344/100000 [1:51:04<15:13:14, 1.71it/s] Train steps ... : 6%|▋ | 6345/100000 [1:51:05<15:12:43, 1.71it/s] Train steps ... : 6%|▋ | 6346/100000 [1:51:05<15:12:07, 1.71it/s] Train steps ... : 6%|▋ | 6347/100000 [1:51:06<15:12:55, 1.71it/s] Train steps ... : 6%|▋ | 6348/100000 [1:51:06<15:11:42, 1.71it/s] Train steps ... : 6%|▋ | 6349/100000 [1:51:07<15:12:00, 1.71it/s] Train steps ... : 6%|▋ | 6350/100000 [1:51:08<15:12:43, 1.71it/s]Step... (6350 / 100000 | Loss: 1.581619143486023, Learning Rate: 9.412060301507539e-05) Step... (6350 / 100000 | Loss: 1.505341649055481, Learning Rate: 9.412060301507539e-05) Train steps ... : 6%|▋ | 6350/100000 [1:51:08<15:12:43, 1.71it/s] Train steps ... : 6%|▋ | 6351/100000 [1:51:08<15:12:12, 1.71it/s] Train steps ... : 6%|▋ | 6352/100000 [1:51:09<15:12:01, 1.71it/s] Train steps ... : 6%|▋ | 6353/100000 [1:51:09<15:13:36, 1.71it/s] Train steps ... : 6%|▋ | 6354/100000 [1:51:10<15:14:10, 1.71it/s] Train steps ... : 6%|▋ | 6355/100000 [1:51:10<15:13:25, 1.71it/s] Train steps ... : 6%|▋ | 6356/100000 [1:51:11<15:12:30, 1.71it/s] Train steps ... : 6%|▋ | 6357/100000 [1:51:12<15:11:57, 1.71it/s] Train steps ... : 6%|▋ | 6358/100000 [1:51:12<15:12:03, 1.71it/s] Train steps ... : 6%|▋ | 6359/100000 [1:51:13<15:12:25, 1.71it/s] Train steps ... : 6%|▋ | 6360/100000 [1:51:13<15:11:44, 1.71it/s] Train steps ... : 6%|▋ | 6361/100000 [1:51:14<15:12:46, 1.71it/s] Train steps ... : 6%|▋ | 6362/100000 [1:51:15<15:11:55, 1.71it/s] Train steps ... : 6%|▋ | 6363/100000 [1:51:15<15:13:28, 1.71it/s] Train steps ... : 6%|▋ | 6364/100000 [1:51:16<15:12:32, 1.71it/s] Train steps ... : 6%|▋ | 6365/100000 [1:51:16<15:12:52, 1.71it/s] Train steps ... : 6%|▋ | 6366/100000 [1:51:17<15:13:20, 1.71it/s] Train steps ... : 6%|▋ | 6367/100000 [1:51:17<15:13:05, 1.71it/s] Train steps ... : 6%|▋ | 6368/100000 [1:51:18<15:12:40, 1.71it/s] Train steps ... : 6%|▋ | 6369/100000 [1:51:19<15:12:28, 1.71it/s] Train steps ... : 6%|▋ | 6370/100000 [1:51:19<15:12:13, 1.71it/s] Train steps ... : 6%|▋ | 6371/100000 [1:51:20<15:12:13, 1.71it/s] Train steps ... : 6%|▋ | 6372/100000 [1:51:20<15:13:22, 1.71it/s] Train steps ... : 6%|▋ | 6373/100000 [1:51:21<15:12:21, 1.71it/s] Train steps ... : 6%|▋ | 6374/100000 [1:51:22<15:12:05, 1.71it/s] Train steps ... : 6%|▋ | 6375/100000 [1:51:22<15:13:26, 1.71it/s]Step... (6375 / 100000 | Loss: 1.6662226915359497, Learning Rate: 9.409547738693468e-05) Step... (6375 / 100000 | Loss: 1.6442198753356934, Learning Rate: 9.409547738693468e-05) Train steps ... : 6%|▋ | 6375/100000 [1:51:22<15:13:26, 1.71it/s] Train steps ... : 6%|▋ | 6376/100000 [1:51:23<15:13:23, 1.71it/s] Train steps ... : 6%|▋ | 6377/100000 [1:51:23<15:12:08, 1.71it/s] Train steps ... : 6%|▋ | 6378/100000 [1:51:24<15:14:27, 1.71it/s] Train steps ... : 6%|▋ | 6379/100000 [1:51:24<15:13:14, 1.71it/s] Train steps ... : 6%|▋ | 6380/100000 [1:51:25<15:13:47, 1.71it/s] Train steps ... : 6%|▋ | 6381/100000 [1:51:26<15:13:01, 1.71it/s] Train steps ... : 6%|▋ | 6382/100000 [1:51:26<15:12:13, 1.71it/s] Train steps ... : 6%|▋ | 6383/100000 [1:51:27<15:12:38, 1.71it/s] Train steps ... : 6%|▋ | 6384/100000 [1:51:27<15:12:05, 1.71it/s] Train steps ... : 6%|▋ | 6385/100000 [1:51:28<15:11:50, 1.71it/s] Train steps ... : 6%|▋ | 6386/100000 [1:51:29<15:12:28, 1.71it/s] Train steps ... : 6%|▋ | 6387/100000 [1:51:29<15:11:53, 1.71it/s] Train steps ... : 6%|▋ | 6388/100000 [1:51:30<15:11:51, 1.71it/s] Train steps ... : 6%|▋ | 6389/100000 [1:51:30<15:11:16, 1.71it/s] Train steps ... : 6%|▋ | 6390/100000 [1:51:31<15:12:14, 1.71it/s] Train steps ... : 6%|▋ | 6391/100000 [1:51:31<15:12:13, 1.71it/s] Train steps ... : 6%|▋ | 6392/100000 [1:51:32<15:11:45, 1.71it/s] Train steps ... : 6%|▋ | 6393/100000 [1:51:33<15:11:04, 1.71it/s] Train steps ... : 6%|▋ | 6394/100000 [1:51:33<15:11:26, 1.71it/s] Train steps ... : 6%|▋ | 6395/100000 [1:51:34<15:12:39, 1.71it/s] Train steps ... : 6%|▋ | 6396/100000 [1:51:34<15:12:59, 1.71it/s] Train steps ... : 6%|▋ | 6397/100000 [1:51:35<15:13:24, 1.71it/s] Train steps ... : 6%|▋ | 6398/100000 [1:51:36<15:12:45, 1.71it/s] Train steps ... : 6%|▋ | 6399/100000 [1:51:36<15:12:15, 1.71it/s] Train steps ... : 6%|▋ | 6400/100000 [1:51:37<15:11:37, 1.71it/s]Step... (6400 / 100000 | Loss: 1.634232759475708, Learning Rate: 9.407035175879397e-05) Step... (6400 / 100000 | Loss: 1.9212965965270996, Learning Rate: 9.407035175879397e-05) Train steps ... : 6%|▋ | 6400/100000 [1:51:37<15:11:37, 1.71it/s] Train steps ... : 6%|▋ | 6401/100000 [1:51:37<15:11:31, 1.71it/s] Train steps ... : 6%|▋ | 6402/100000 [1:51:38<15:11:36, 1.71it/s] Train steps ... : 6%|▋ | 6403/100000 [1:51:39<15:11:27, 1.71it/s] Train steps ... : 6%|▋ | 6404/100000 [1:51:39<15:11:00, 1.71it/s] Train steps ... : 6%|▋ | 6405/100000 [1:51:40<15:11:00, 1.71it/s] Train steps ... : 6%|▋ | 6406/100000 [1:51:40<15:11:14, 1.71it/s] Train steps ... : 6%|▋ | 6407/100000 [1:51:41<15:12:25, 1.71it/s] Train steps ... : 6%|▋ | 6408/100000 [1:51:41<15:11:58, 1.71it/s] Train steps ... : 6%|▋ | 6409/100000 [1:51:42<15:12:00, 1.71it/s] Train steps ... : 6%|▋ | 6410/100000 [1:51:43<15:11:14, 1.71it/s] Train steps ... : 6%|▋ | 6411/100000 [1:51:43<15:10:57, 1.71it/s] Train steps ... : 6%|▋ | 6412/100000 [1:51:44<15:10:58, 1.71it/s] Train steps ... : 6%|▋ | 6413/100000 [1:51:44<15:11:11, 1.71it/s] Train steps ... : 6%|▋ | 6414/100000 [1:51:45<15:11:13, 1.71it/s] Train steps ... : 6%|▋ | 6415/100000 [1:51:46<15:10:56, 1.71it/s] Train steps ... : 6%|▋ | 6416/100000 [1:51:46<15:10:51, 1.71it/s] Train steps ... : 6%|▋ | 6417/100000 [1:51:47<15:10:40, 1.71it/s] Train steps ... : 6%|▋ | 6418/100000 [1:51:47<15:10:36, 1.71it/s] Train steps ... : 6%|▋ | 6419/100000 [1:51:48<15:11:10, 1.71it/s] Train steps ... : 6%|▋ | 6420/100000 [1:51:48<15:11:37, 1.71it/s] Train steps ... : 6%|▋ | 6421/100000 [1:51:49<15:11:34, 1.71it/s] Train steps ... : 6%|▋ | 6422/100000 [1:51:50<15:11:38, 1.71it/s] Train steps ... : 6%|▋ | 6423/100000 [1:51:50<15:10:47, 1.71it/s] Train steps ... : 6%|▋ | 6424/100000 [1:51:51<15:10:26, 1.71it/s] Train steps ... : 6%|▋ | 6425/100000 [1:51:51<15:10:42, 1.71it/s]Step... (6425 / 100000 | Loss: 1.1470668315887451, Learning Rate: 9.404522613065328e-05) Step... (6425 / 100000 | Loss: 1.9007313251495361, Learning Rate: 9.404522613065328e-05) Train steps ... : 6%|▋ | 6425/100000 [1:51:52<15:10:42, 1.71it/s] Train steps ... : 6%|▋ | 6426/100000 [1:51:52<15:12:10, 1.71it/s] Train steps ... : 6%|▋ | 6427/100000 [1:51:53<15:12:12, 1.71it/s] Train steps ... : 6%|▋ | 6428/100000 [1:51:53<15:11:54, 1.71it/s] Train steps ... : 6%|▋ | 6429/100000 [1:51:54<15:11:22, 1.71it/s] Train steps ... : 6%|▋ | 6430/100000 [1:51:54<15:12:37, 1.71it/s] Train steps ... : 6%|▋ | 6431/100000 [1:51:55<15:12:34, 1.71it/s] Train steps ... : 6%|▋ | 6432/100000 [1:51:55<15:12:56, 1.71it/s] Train steps ... : 6%|▋ | 6433/100000 [1:51:56<15:14:15, 1.71it/s] Train steps ... : 6%|▋ | 6434/100000 [1:51:57<15:15:49, 1.70it/s] Train steps ... : 6%|▋ | 6435/100000 [1:51:57<15:14:07, 1.71it/s] Train steps ... : 6%|▋ | 6436/100000 [1:51:58<15:14:25, 1.71it/s] Train steps ... : 6%|▋ | 6437/100000 [1:51:58<15:13:34, 1.71it/s] Train steps ... : 6%|▋ | 6438/100000 [1:51:59<15:12:48, 1.71it/s] Train steps ... : 6%|▋ | 6439/100000 [1:52:00<15:12:27, 1.71it/s] Train steps ... : 6%|▋ | 6440/100000 [1:52:00<15:11:53, 1.71it/s] Train steps ... : 6%|▋ | 6441/100000 [1:52:01<15:11:00, 1.71it/s] Train steps ... : 6%|▋ | 6442/100000 [1:52:01<15:11:49, 1.71it/s] Train steps ... : 6%|▋ | 6443/100000 [1:52:02<15:11:41, 1.71it/s] Train steps ... : 6%|▋ | 6444/100000 [1:52:02<15:11:01, 1.71it/s] Train steps ... : 6%|▋ | 6445/100000 [1:52:03<15:11:06, 1.71it/s] Train steps ... : 6%|▋ | 6446/100000 [1:52:04<15:12:01, 1.71it/s] Train steps ... : 6%|▋ | 6447/100000 [1:52:04<15:12:14, 1.71it/s] Train steps ... : 6%|▋ | 6448/100000 [1:52:05<15:14:30, 1.70it/s] Train steps ... : 6%|▋ | 6449/100000 [1:52:05<15:13:50, 1.71it/s] Train steps ... : 6%|▋ | 6450/100000 [1:52:06<15:14:40, 1.70it/s]Step... (6450 / 100000 | Loss: 2.31699275970459, Learning Rate: 9.402010050251256e-05) Step... (6450 / 100000 | Loss: 1.4167163372039795, Learning Rate: 9.402010050251256e-05) Train steps ... : 6%|▋ | 6450/100000 [1:52:06<15:14:40, 1.70it/s] Train steps ... : 6%|▋ | 6451/100000 [1:52:07<15:13:48, 1.71it/s] Train steps ... : 6%|▋ | 6452/100000 [1:52:07<15:13:20, 1.71it/s] Train steps ... : 6%|▋ | 6453/100000 [1:52:08<15:12:21, 1.71it/s] Train steps ... : 6%|▋ | 6454/100000 [1:52:08<15:12:06, 1.71it/s] Train steps ... : 6%|▋ | 6455/100000 [1:52:09<15:11:56, 1.71it/s] Train steps ... : 6%|▋ | 6456/100000 [1:52:10<15:11:17, 1.71it/s] Train steps ... : 6%|▋ | 6457/100000 [1:52:10<15:11:54, 1.71it/s] Train steps ... : 6%|▋ | 6458/100000 [1:52:11<15:11:22, 1.71it/s] Train steps ... : 6%|▋ | 6459/100000 [1:52:11<15:11:38, 1.71it/s] Train steps ... : 6%|▋ | 6460/100000 [1:52:12<15:14:07, 1.71it/s] Train steps ... : 6%|▋ | 6461/100000 [1:52:12<15:12:18, 1.71it/s] Train steps ... : 6%|▋ | 6462/100000 [1:52:13<15:12:30, 1.71it/s] Train steps ... : 6%|▋ | 6463/100000 [1:52:14<15:11:32, 1.71it/s] Train steps ... : 6%|▋ | 6464/100000 [1:52:14<15:11:34, 1.71it/s] Train steps ... : 6%|▋ | 6465/100000 [1:52:15<15:10:52, 1.71it/s] Train steps ... : 6%|▋ | 6466/100000 [1:52:15<15:11:26, 1.71it/s] Train steps ... : 6%|▋ | 6467/100000 [1:52:16<15:12:59, 1.71it/s] Train steps ... : 6%|▋ | 6468/100000 [1:52:17<15:12:38, 1.71it/s] Train steps ... : 6%|▋ | 6469/100000 [1:52:17<15:12:32, 1.71it/s] Train steps ... : 6%|▋ | 6470/100000 [1:52:18<15:11:56, 1.71it/s] Train steps ... : 6%|▋ | 6471/100000 [1:52:18<15:11:57, 1.71it/s] Train steps ... : 6%|▋ | 6472/100000 [1:52:19<15:12:38, 1.71it/s] Train steps ... : 6%|▋ | 6473/100000 [1:52:19<15:12:07, 1.71it/s] Train steps ... : 6%|▋ | 6474/100000 [1:52:20<15:11:44, 1.71it/s] Train steps ... : 6%|▋ | 6475/100000 [1:52:21<15:11:54, 1.71it/s]Step... (6475 / 100000 | Loss: 1.6389362812042236, Learning Rate: 9.399497487437187e-05) Step... (6475 / 100000 | Loss: 1.8564374446868896, Learning Rate: 9.399497487437187e-05) Train steps ... : 6%|▋ | 6475/100000 [1:52:21<15:11:54, 1.71it/s] Train steps ... : 6%|▋ | 6476/100000 [1:52:21<15:11:56, 1.71it/s] Train steps ... : 6%|▋ | 6477/100000 [1:52:22<15:11:01, 1.71it/s] Train steps ... : 6%|▋ | 6478/100000 [1:52:22<15:10:24, 1.71it/s] Train steps ... : 6%|▋ | 6479/100000 [1:52:23<15:10:06, 1.71it/s] Train steps ... : 6%|▋ | 6480/100000 [1:52:24<15:10:48, 1.71it/s] Train steps ... : 6%|▋ | 6481/100000 [1:52:24<15:11:19, 1.71it/s] Train steps ... : 6%|▋ | 6482/100000 [1:52:25<15:11:16, 1.71it/s] Train steps ... : 6%|▋ | 6483/100000 [1:52:25<15:10:45, 1.71it/s] Train steps ... : 6%|▋ | 6484/100000 [1:52:26<15:10:42, 1.71it/s] Train steps ... : 6%|▋ | 6485/100000 [1:52:26<15:10:33, 1.71it/s] Train steps ... : 6%|▋ | 6486/100000 [1:52:27<15:10:04, 1.71it/s] Train steps ... : 6%|▋ | 6487/100000 [1:52:28<15:09:50, 1.71it/s] Train steps ... : 6%|▋ | 6488/100000 [1:52:28<15:09:32, 1.71it/s] Train steps ... : 6%|▋ | 6489/100000 [1:52:29<15:09:34, 1.71it/s] Train steps ... : 6%|▋ | 6490/100000 [1:52:29<15:10:30, 1.71it/s] Train steps ... : 6%|▋ | 6491/100000 [1:52:30<15:10:46, 1.71it/s] Train steps ... : 6%|▋ | 6492/100000 [1:52:31<15:10:22, 1.71it/s] Train steps ... : 6%|▋ | 6493/100000 [1:52:31<15:10:03, 1.71it/s] Train steps ... : 6%|▋ | 6494/100000 [1:52:32<15:10:49, 1.71it/s] Train steps ... : 6%|▋ | 6495/100000 [1:52:32<15:13:05, 1.71it/s] Train steps ... : 6%|▋ | 6496/100000 [1:52:33<15:14:57, 1.70it/s] Train steps ... : 6%|▋ | 6497/100000 [1:52:33<15:12:22, 1.71it/s] Train steps ... : 6%|▋ | 6498/100000 [1:52:34<15:11:33, 1.71it/s] Train steps ... : 6%|▋ | 6499/100000 [1:52:35<15:12:01, 1.71it/s] Train steps ... : 6%|▋ | 6500/100000 [1:52:35<15:11:42, 1.71it/s]Step... (6500 / 100000 | Loss: 1.2108147144317627, Learning Rate: 9.396984924623115e-05) Step... (6500 / 100000 | Loss: 1.1280534267425537, Learning Rate: 9.396984924623115e-05) Train steps ... : 6%|▋ | 6500/100000 [1:52:36<15:11:42, 1.71it/s] Train steps ... : 7%|▋ | 6501/100000 [1:52:36<15:12:19, 1.71it/s] Train steps ... : 7%|▋ | 6502/100000 [1:52:36<15:11:21, 1.71it/s] Train steps ... : 7%|▋ | 6503/100000 [1:52:37<15:11:22, 1.71it/s] Train steps ... : 7%|▋ | 6504/100000 [1:52:38<15:10:21, 1.71it/s] Train steps ... : 7%|▋ | 6505/100000 [1:52:38<15:11:24, 1.71it/s] Train steps ... : 7%|▋ | 6506/100000 [1:52:39<15:12:21, 1.71it/s] Train steps ... : 7%|▋ | 6507/100000 [1:52:39<15:11:54, 1.71it/s] Train steps ... : 7%|▋ | 6508/100000 [1:52:40<15:12:09, 1.71it/s] Train steps ... : 7%|▋ | 6509/100000 [1:52:41<15:13:46, 1.71it/s] Train steps ... : 7%|▋ | 6510/100000 [1:52:41<15:11:13, 1.71it/s] Train steps ... : 7%|▋ | 6511/100000 [1:52:42<15:12:25, 1.71it/s] Train steps ... : 7%|▋ | 6512/100000 [1:52:42<15:11:40, 1.71it/s] Train steps ... : 7%|▋ | 6513/100000 [1:52:43<15:11:57, 1.71it/s] Train steps ... : 7%|▋ | 6514/100000 [1:52:43<15:11:24, 1.71it/s] Train steps ... : 7%|▋ | 6515/100000 [1:52:44<15:12:32, 1.71it/s] Train steps ... : 7%|▋ | 6516/100000 [1:52:45<15:11:55, 1.71it/s] Train steps ... : 7%|▋ | 6517/100000 [1:52:45<15:11:05, 1.71it/s] Train steps ... : 7%|▋ | 6518/100000 [1:52:46<15:10:41, 1.71it/s] Train steps ... : 7%|▋ | 6519/100000 [1:52:46<15:10:57, 1.71it/s] Train steps ... : 7%|▋ | 6520/100000 [1:52:47<15:11:52, 1.71it/s] Train steps ... : 7%|▋ | 6521/100000 [1:52:48<15:11:05, 1.71it/s] Train steps ... : 7%|▋ | 6522/100000 [1:52:48<15:10:21, 1.71it/s] Train steps ... : 7%|▋ | 6523/100000 [1:52:49<15:11:17, 1.71it/s] Train steps ... : 7%|▋ | 6524/100000 [1:52:49<15:11:57, 1.71it/s] Train steps ... : 7%|▋ | 6525/100000 [1:52:50<15:13:52, 1.70it/s]Step... (6525 / 100000 | Loss: 1.7583601474761963, Learning Rate: 9.394472361809046e-05) Step... (6525 / 100000 | Loss: 1.7998219728469849, Learning Rate: 9.394472361809046e-05) Train steps ... : 7%|▋ | 6525/100000 [1:52:50<15:13:52, 1.70it/s] Train steps ... : 7%|▋ | 6526/100000 [1:52:50<15:13:00, 1.71it/s] Train steps ... : 7%|▋ | 6527/100000 [1:52:51<15:12:01, 1.71it/s] Train steps ... : 7%|▋ | 6528/100000 [1:52:52<15:11:46, 1.71it/s] Train steps ... : 7%|▋ | 6529/100000 [1:52:52<15:12:52, 1.71it/s] Train steps ... : 7%|▋ | 6530/100000 [1:52:53<15:13:55, 1.70it/s] Train steps ... : 7%|▋ | 6531/100000 [1:52:53<15:13:01, 1.71it/s] Train steps ... : 7%|▋ | 6532/100000 [1:52:54<15:12:27, 1.71it/s] Train steps ... : 7%|▋ | 6533/100000 [1:52:55<15:12:02, 1.71it/s] Train steps ... : 7%|▋ | 6534/100000 [1:52:55<15:10:31, 1.71it/s] Train steps ... : 7%|▋ | 6535/100000 [1:52:56<15:12:04, 1.71it/s] Train steps ... : 7%|▋ | 6536/100000 [1:52:56<15:10:57, 1.71it/s] Train steps ... : 7%|▋ | 6537/100000 [1:52:57<15:11:57, 1.71it/s] Train steps ... : 7%|▋ | 6538/100000 [1:52:57<15:11:12, 1.71it/s] Train steps ... : 7%|▋ | 6539/100000 [1:52:58<15:10:21, 1.71it/s] Train steps ... : 7%|▋ | 6540/100000 [1:52:59<15:10:52, 1.71it/s] Train steps ... : 7%|▋ | 6541/100000 [1:52:59<15:11:57, 1.71it/s] Train steps ... : 7%|▋ | 6542/100000 [1:53:00<15:11:37, 1.71it/s] Train steps ... : 7%|▋ | 6543/100000 [1:53:00<15:11:27, 1.71it/s] Train steps ... : 7%|▋ | 6544/100000 [1:53:01<15:10:40, 1.71it/s] Train steps ... : 7%|▋ | 6545/100000 [1:53:02<15:12:51, 1.71it/s] Train steps ... : 7%|▋ | 6546/100000 [1:53:02<15:11:21, 1.71it/s] Train steps ... : 7%|▋ | 6547/100000 [1:53:03<15:11:54, 1.71it/s] Train steps ... : 7%|▋ | 6548/100000 [1:53:03<15:12:20, 1.71it/s] Train steps ... : 7%|▋ | 6549/100000 [1:53:04<15:12:11, 1.71it/s] Train steps ... : 7%|▋ | 6550/100000 [1:53:05<15:11:53, 1.71it/s]Step... (6550 / 100000 | Loss: 1.2702817916870117, Learning Rate: 9.391959798994975e-05) Step... (6550 / 100000 | Loss: 1.230686902999878, Learning Rate: 9.391959798994975e-05) Train steps ... : 7%|▋ | 6550/100000 [1:53:05<15:11:53, 1.71it/s] Train steps ... : 7%|▋ | 6551/100000 [1:53:05<15:11:13, 1.71it/s] Train steps ... : 7%|▋ | 6552/100000 [1:53:06<15:11:53, 1.71it/s] Train steps ... : 7%|▋ | 6553/100000 [1:53:06<15:09:53, 1.71it/s] Train steps ... : 7%|▋ | 6554/100000 [1:53:07<15:11:49, 1.71it/s] Train steps ... : 7%|▋ | 6555/100000 [1:53:07<15:11:55, 1.71it/s] Train steps ... : 7%|▋ | 6556/100000 [1:53:08<15:12:18, 1.71it/s] Train steps ... : 7%|▋ | 6557/100000 [1:53:09<15:10:03, 1.71it/s] Train steps ... : 7%|▋ | 6558/100000 [1:53:09<15:10:21, 1.71it/s] Train steps ... : 7%|▋ | 6559/100000 [1:53:10<15:10:34, 1.71it/s] Train steps ... : 7%|▋ | 6560/100000 [1:53:10<15:11:10, 1.71it/s] Train steps ... : 7%|▋ | 6561/100000 [1:53:11<15:11:06, 1.71it/s] Train steps ... : 7%|▋ | 6562/100000 [1:53:12<15:11:34, 1.71it/s] Train steps ... : 7%|▋ | 6563/100000 [1:53:12<15:10:12, 1.71it/s] Train steps ... : 7%|▋ | 6564/100000 [1:53:13<15:10:12, 1.71it/s] Train steps ... : 7%|▋ | 6565/100000 [1:53:13<15:11:59, 1.71it/s] Train steps ... : 7%|▋ | 6566/100000 [1:53:14<15:11:15, 1.71it/s] Train steps ... : 7%|▋ | 6567/100000 [1:53:14<15:12:22, 1.71it/s] Train steps ... : 7%|▋ | 6568/100000 [1:53:15<15:10:25, 1.71it/s] Train steps ... : 7%|▋ | 6569/100000 [1:53:16<15:12:14, 1.71it/s] Train steps ... : 7%|▋ | 6570/100000 [1:53:16<15:11:41, 1.71it/s] Train steps ... : 7%|▋ | 6571/100000 [1:53:17<15:10:17, 1.71it/s] Train steps ... : 7%|▋ | 6572/100000 [1:53:17<15:10:39, 1.71it/s] Train steps ... : 7%|▋ | 6573/100000 [1:53:18<15:11:31, 1.71it/s] Train steps ... : 7%|▋ | 6574/100000 [1:53:19<15:11:33, 1.71it/s] Train steps ... : 7%|▋ | 6575/100000 [1:53:19<15:12:15, 1.71it/s]Step... (6575 / 100000 | Loss: 1.2867732048034668, Learning Rate: 9.389447236180904e-05) Step... (6575 / 100000 | Loss: 1.4133622646331787, Learning Rate: 9.389447236180904e-05) Train steps ... : 7%|▋ | 6575/100000 [1:53:19<15:12:15, 1.71it/s] Train steps ... : 7%|▋ | 6576/100000 [1:53:20<15:12:53, 1.71it/s] Train steps ... : 7%|▋ | 6577/100000 [1:53:20<15:11:34, 1.71it/s] Train steps ... : 7%|▋ | 6578/100000 [1:53:21<15:12:22, 1.71it/s] Train steps ... : 7%|▋ | 6579/100000 [1:53:21<15:11:37, 1.71it/s] Train steps ... : 7%|▋ | 6580/100000 [1:53:22<15:11:06, 1.71it/s] Train steps ... : 7%|▋ | 6581/100000 [1:53:23<15:11:10, 1.71it/s] Train steps ... : 7%|▋ | 6582/100000 [1:53:23<15:10:28, 1.71it/s] Train steps ... : 7%|▋ | 6583/100000 [1:53:24<15:10:09, 1.71it/s] Train steps ... : 7%|▋ | 6584/100000 [1:53:24<15:10:29, 1.71it/s] Train steps ... : 7%|▋ | 6585/100000 [1:53:25<15:11:08, 1.71it/s] Train steps ... : 7%|▋ | 6586/100000 [1:53:26<15:10:18, 1.71it/s] Train steps ... : 7%|▋ | 6587/100000 [1:53:26<15:11:18, 1.71it/s] Train steps ... : 7%|▋ | 6588/100000 [1:53:27<15:11:56, 1.71it/s] Train steps ... : 7%|▋ | 6589/100000 [1:53:27<15:10:58, 1.71it/s] Train steps ... : 7%|▋ | 6590/100000 [1:53:28<15:11:29, 1.71it/s] Train steps ... : 7%|▋ | 6591/100000 [1:53:28<15:11:33, 1.71it/s] Train steps ... : 7%|▋ | 6592/100000 [1:53:29<15:10:29, 1.71it/s] Train steps ... : 7%|▋ | 6593/100000 [1:53:30<15:10:09, 1.71it/s] Train steps ... : 7%|▋ | 6594/100000 [1:53:30<15:10:27, 1.71it/s] Train steps ... : 7%|▋ | 6595/100000 [1:53:31<15:09:17, 1.71it/s] Train steps ... : 7%|▋ | 6596/100000 [1:53:31<15:11:05, 1.71it/s] Train steps ... : 7%|▋ | 6597/100000 [1:53:32<15:11:30, 1.71it/s] Train steps ... : 7%|▋ | 6598/100000 [1:53:33<15:10:31, 1.71it/s] Train steps ... : 7%|▋ | 6599/100000 [1:53:33<15:10:23, 1.71it/s] Train steps ... : 7%|▋ | 6600/100000 [1:53:34<15:09:41, 1.71it/s]Step... (6600 / 100000 | Loss: 1.1542948484420776, Learning Rate: 9.386934673366835e-05) Step... (6600 / 100000 | Loss: 2.3480043411254883, Learning Rate: 9.386934673366835e-05) Train steps ... : 7%|▋ | 6600/100000 [1:53:34<15:09:41, 1.71it/s] Train steps ... : 7%|▋ | 6601/100000 [1:53:34<15:10:49, 1.71it/s] Train steps ... : 7%|▋ | 6602/100000 [1:53:35<15:11:24, 1.71it/s] Train steps ... : 7%|▋ | 6603/100000 [1:53:36<15:09:06, 1.71it/s] Train steps ... : 7%|▋ | 6604/100000 [1:53:36<15:10:45, 1.71it/s] Train steps ... : 7%|▋ | 6605/100000 [1:53:37<15:11:10, 1.71it/s] Train steps ... : 7%|▋ | 6606/100000 [1:53:37<15:11:27, 1.71it/s] Train steps ... : 7%|▋ | 6607/100000 [1:53:38<15:11:36, 1.71it/s] Train steps ... : 7%|▋ | 6608/100000 [1:53:38<15:11:09, 1.71it/s] Train steps ... : 7%|▋ | 6609/100000 [1:53:39<15:10:20, 1.71it/s] Train steps ... : 7%|▋ | 6610/100000 [1:53:40<15:11:21, 1.71it/s] Train steps ... : 7%|▋ | 6611/100000 [1:53:40<15:11:39, 1.71it/s] Train steps ... : 7%|▋ | 6612/100000 [1:53:41<15:11:02, 1.71it/s] Train steps ... : 7%|▋ | 6613/100000 [1:53:41<15:10:22, 1.71it/s] Train steps ... : 7%|▋ | 6614/100000 [1:53:42<15:09:56, 1.71it/s] Train steps ... : 7%|▋ | 6615/100000 [1:53:43<15:09:13, 1.71it/s] Train steps ... : 7%|▋ | 6616/100000 [1:53:43<15:12:17, 1.71it/s] Train steps ... : 7%|▋ | 6617/100000 [1:53:44<15:11:02, 1.71it/s] Train steps ... : 7%|▋ | 6618/100000 [1:53:44<15:10:14, 1.71it/s] Train steps ... : 7%|▋ | 6619/100000 [1:53:45<15:11:11, 1.71it/s] Train steps ... : 7%|▋ | 6620/100000 [1:53:45<15:10:53, 1.71it/s] Train steps ... : 7%|▋ | 6621/100000 [1:53:46<15:09:53, 1.71it/s] Train steps ... : 7%|▋ | 6622/100000 [1:53:47<15:09:19, 1.71it/s] Train steps ... : 7%|▋ | 6623/100000 [1:53:47<15:09:19, 1.71it/s] Train steps ... : 7%|▋ | 6624/100000 [1:53:48<15:09:38, 1.71it/s] Train steps ... : 7%|▋ | 6625/100000 [1:53:48<15:10:19, 1.71it/s]Step... (6625 / 100000 | Loss: 1.2257537841796875, Learning Rate: 9.384422110552764e-05) Step... (6625 / 100000 | Loss: 1.1455190181732178, Learning Rate: 9.384422110552764e-05) Train steps ... : 7%|▋ | 6625/100000 [1:53:49<15:10:19, 1.71it/s] Train steps ... : 7%|▋ | 6626/100000 [1:53:49<15:11:15, 1.71it/s] Train steps ... : 7%|▋ | 6627/100000 [1:53:50<15:11:52, 1.71it/s] Train steps ... : 7%|▋ | 6628/100000 [1:53:50<15:10:43, 1.71it/s] Train steps ... : 7%|▋ | 6629/100000 [1:53:51<15:09:43, 1.71it/s] Train steps ... : 7%|▋ | 6630/100000 [1:53:51<15:10:48, 1.71it/s] Train steps ... : 7%|▋ | 6631/100000 [1:53:52<15:09:19, 1.71it/s] Train steps ... : 7%|▋ | 6632/100000 [1:53:52<15:09:23, 1.71it/s] Train steps ... : 7%|▋ | 6633/100000 [1:53:53<15:09:23, 1.71it/s] Train steps ... : 7%|▋ | 6634/100000 [1:53:54<15:10:30, 1.71it/s] Train steps ... : 7%|▋ | 6635/100000 [1:53:54<15:10:31, 1.71it/s] Train steps ... : 7%|▋ | 6636/100000 [1:53:55<15:11:30, 1.71it/s] Train steps ... : 7%|▋ | 6637/100000 [1:53:55<15:10:12, 1.71it/s] Train steps ... : 7%|▋ | 6638/100000 [1:53:56<15:09:52, 1.71it/s] Train steps ... : 7%|▋ | 6639/100000 [1:53:57<15:09:19, 1.71it/s] Train steps ... : 7%|▋ | 6640/100000 [1:53:57<15:09:39, 1.71it/s] Train steps ... : 7%|▋ | 6641/100000 [1:53:58<15:10:48, 1.71it/s] Train steps ... : 7%|▋ | 6642/100000 [1:53:58<15:11:36, 1.71it/s] Train steps ... : 7%|▋ | 6643/100000 [1:53:59<15:11:19, 1.71it/s] Train steps ... : 7%|▋ | 6644/100000 [1:54:00<15:11:40, 1.71it/s] Train steps ... : 7%|▋ | 6645/100000 [1:54:00<15:10:06, 1.71it/s] Train steps ... : 7%|▋ | 6646/100000 [1:54:01<15:10:22, 1.71it/s] Train steps ... : 7%|▋ | 6647/100000 [1:54:01<15:11:03, 1.71it/s] Train steps ... : 7%|▋ | 6648/100000 [1:54:02<15:10:49, 1.71it/s] Train steps ... : 7%|▋ | 6649/100000 [1:54:02<15:10:21, 1.71it/s] Train steps ... : 7%|▋ | 6650/100000 [1:54:03<15:10:27, 1.71it/s]Step... (6650 / 100000 | Loss: 1.2050769329071045, Learning Rate: 9.381909547738695e-05) Step... (6650 / 100000 | Loss: 1.3405334949493408, Learning Rate: 9.381909547738695e-05) Train steps ... : 7%|▋ | 6650/100000 [1:54:03<15:10:27, 1.71it/s] Train steps ... : 7%|▋ | 6651/100000 [1:54:04<15:10:45, 1.71it/s] Train steps ... : 7%|▋ | 6652/100000 [1:54:04<15:11:57, 1.71it/s] Train steps ... : 7%|▋ | 6653/100000 [1:54:05<15:12:06, 1.71it/s] Train steps ... : 7%|▋ | 6654/100000 [1:54:05<15:10:06, 1.71it/s] Train steps ... : 7%|▋ | 6655/100000 [1:54:06<15:09:32, 1.71it/s] Train steps ... : 7%|▋ | 6656/100000 [1:54:07<15:09:30, 1.71it/s] Train steps ... : 7%|▋ | 6657/100000 [1:54:07<15:09:57, 1.71it/s] Train steps ... : 7%|▋ | 6658/100000 [1:54:08<15:10:14, 1.71it/s] Train steps ... : 7%|▋ | 6659/100000 [1:54:08<15:10:08, 1.71it/s] Train steps ... : 7%|▋ | 6660/100000 [1:54:09<15:10:08, 1.71it/s] Train steps ... : 7%|▋ | 6661/100000 [1:54:09<15:09:55, 1.71it/s] Train steps ... : 7%|▋ | 6662/100000 [1:54:10<15:09:03, 1.71it/s] Train steps ... : 7%|▋ | 6663/100000 [1:54:11<15:09:12, 1.71it/s] Train steps ... : 7%|▋ | 6664/100000 [1:54:11<15:10:05, 1.71it/s] Train steps ... : 7%|▋ | 6665/100000 [1:54:12<15:10:19, 1.71it/s] Train steps ... : 7%|▋ | 6666/100000 [1:54:12<15:10:27, 1.71it/s] Train steps ... : 7%|▋ | 6667/100000 [1:54:13<15:09:32, 1.71it/s] Train steps ... : 7%|▋ | 6668/100000 [1:54:14<15:09:49, 1.71it/s] Train steps ... : 7%|▋ | 6669/100000 [1:54:14<15:10:59, 1.71it/s] Train steps ... : 7%|▋ | 6670/100000 [1:54:15<15:11:25, 1.71it/s] Train steps ... : 7%|▋ | 6671/100000 [1:54:15<15:10:39, 1.71it/s] Train steps ... : 7%|▋ | 6672/100000 [1:54:16<15:10:17, 1.71it/s] Train steps ... : 7%|▋ | 6673/100000 [1:54:16<15:10:45, 1.71it/s] Train steps ... : 7%|▋ | 6674/100000 [1:54:17<15:10:57, 1.71it/s] Train steps ... : 7%|▋ | 6675/100000 [1:54:18<15:11:11, 1.71it/s]Step... (6675 / 100000 | Loss: 1.189208745956421, Learning Rate: 9.379396984924623e-05) Step... (6675 / 100000 | Loss: 1.5935989618301392, Learning Rate: 9.379396984924623e-05) Train steps ... : 7%|▋ | 6675/100000 [1:54:18<15:11:11, 1.71it/s] Train steps ... : 7%|▋ | 6676/100000 [1:54:18<15:12:22, 1.70it/s] Train steps ... : 7%|▋ | 6677/100000 [1:54:19<15:10:59, 1.71it/s] Train steps ... : 7%|▋ | 6678/100000 [1:54:19<15:10:01, 1.71it/s] Train steps ... : 7%|▋ | 6679/100000 [1:54:20<15:10:19, 1.71it/s] Train steps ... : 7%|▋ | 6680/100000 [1:54:21<15:10:39, 1.71it/s] Train steps ... : 7%|▋ | 6681/100000 [1:54:21<15:08:58, 1.71it/s] Train steps ... : 7%|▋ | 6682/100000 [1:54:22<15:08:37, 1.71it/s] Train steps ... : 7%|▋ | 6683/100000 [1:54:22<15:08:50, 1.71it/s] Train steps ... : 7%|▋ | 6684/100000 [1:54:23<15:09:06, 1.71it/s] Train steps ... : 7%|▋ | 6685/100000 [1:54:23<15:08:31, 1.71it/s] Train steps ... : 7%|▋ | 6686/100000 [1:54:24<15:09:51, 1.71it/s] Train steps ... : 7%|▋ | 6687/100000 [1:54:25<15:09:23, 1.71it/s] Train steps ... : 7%|▋ | 6688/100000 [1:54:25<15:09:48, 1.71it/s] Train steps ... : 7%|▋ | 6689/100000 [1:54:26<15:09:27, 1.71it/s] Train steps ... : 7%|▋ | 6690/100000 [1:54:26<15:10:02, 1.71it/s] Train steps ... : 7%|▋ | 6691/100000 [1:54:27<15:10:17, 1.71it/s] Train steps ... : 7%|▋ | 6692/100000 [1:54:28<15:09:45, 1.71it/s] Train steps ... : 7%|▋ | 6693/100000 [1:54:28<15:10:55, 1.71it/s] Train steps ... : 7%|▋ | 6694/100000 [1:54:29<15:09:51, 1.71it/s] Train steps ... : 7%|▋ | 6695/100000 [1:54:29<15:09:02, 1.71it/s] Train steps ... : 7%|▋ | 6696/100000 [1:54:30<15:08:41, 1.71it/s] Train steps ... : 7%|▋ | 6697/100000 [1:54:31<15:08:23, 1.71it/s] Train steps ... : 7%|▋ | 6698/100000 [1:54:31<15:08:34, 1.71it/s] Train steps ... : 7%|▋ | 6699/100000 [1:54:32<15:11:38, 1.71it/s] Train steps ... : 7%|▋ | 6700/100000 [1:54:32<15:10:41, 1.71it/s]Step... (6700 / 100000 | Loss: 2.0521926879882812, Learning Rate: 9.376884422110554e-05) Step... (6700 / 100000 | Loss: 1.3930243253707886, Learning Rate: 9.376884422110554e-05) Train steps ... : 7%|▋ | 6700/100000 [1:54:33<15:10:41, 1.71it/s] Train steps ... : 7%|▋ | 6701/100000 [1:54:33<15:09:32, 1.71it/s] Train steps ... : 7%|▋ | 6702/100000 [1:54:33<15:09:07, 1.71it/s] Train steps ... : 7%|▋ | 6703/100000 [1:54:34<15:08:29, 1.71it/s] Train steps ... : 7%|▋ | 6704/100000 [1:54:35<15:08:35, 1.71it/s] Train steps ... : 7%|▋ | 6705/100000 [1:54:35<15:09:51, 1.71it/s] Train steps ... : 7%|▋ | 6706/100000 [1:54:36<15:08:50, 1.71it/s] Train steps ... : 7%|▋ | 6707/100000 [1:54:36<15:08:38, 1.71it/s] Train steps ... : 7%|▋ | 6708/100000 [1:54:37<15:08:22, 1.71it/s] Train steps ... : 7%|▋ | 6709/100000 [1:54:38<15:07:39, 1.71it/s] Train steps ... : 7%|▋ | 6710/100000 [1:54:38<15:08:56, 1.71it/s] Train steps ... : 7%|▋ | 6711/100000 [1:54:39<15:08:12, 1.71it/s] Train steps ... : 7%|▋ | 6712/100000 [1:54:39<15:07:51, 1.71it/s] Train steps ... : 7%|▋ | 6713/100000 [1:54:40<15:08:26, 1.71it/s] Train steps ... : 7%|▋ | 6714/100000 [1:54:40<15:08:25, 1.71it/s] Train steps ... : 7%|▋ | 6715/100000 [1:54:41<15:09:08, 1.71it/s] Train steps ... : 7%|▋ | 6716/100000 [1:54:42<15:09:51, 1.71it/s] Train steps ... : 7%|▋ | 6717/100000 [1:54:42<15:07:50, 1.71it/s] Train steps ... : 7%|▋ | 6718/100000 [1:54:43<15:08:30, 1.71it/s] Train steps ... : 7%|▋ | 6719/100000 [1:54:43<15:09:32, 1.71it/s] Train steps ... : 7%|▋ | 6720/100000 [1:54:44<15:09:49, 1.71it/s] Train steps ... : 7%|▋ | 6721/100000 [1:54:45<15:10:49, 1.71it/s] Train steps ... : 7%|▋ | 6722/100000 [1:54:45<15:09:57, 1.71it/s] Train steps ... : 7%|▋ | 6723/100000 [1:54:46<15:10:21, 1.71it/s] Train steps ... : 7%|▋ | 6724/100000 [1:54:46<15:10:45, 1.71it/s] Train steps ... : 7%|▋ | 6725/100000 [1:54:47<15:11:12, 1.71it/s]Step... (6725 / 100000 | Loss: 1.743065595626831, Learning Rate: 9.374371859296482e-05) Step... (6725 / 100000 | Loss: 1.4698293209075928, Learning Rate: 9.374371859296482e-05) Train steps ... : 7%|▋ | 6725/100000 [1:54:47<15:11:12, 1.71it/s] Train steps ... : 7%|▋ | 6726/100000 [1:54:47<15:11:49, 1.70it/s] Train steps ... : 7%|▋ | 6727/100000 [1:54:48<15:10:21, 1.71it/s] Train steps ... : 7%|▋ | 6728/100000 [1:54:49<15:11:15, 1.71it/s] Train steps ... : 7%|▋ | 6729/100000 [1:54:49<15:11:34, 1.71it/s] Train steps ... : 7%|▋ | 6730/100000 [1:54:50<15:10:44, 1.71it/s] Train steps ... : 7%|▋ | 6731/100000 [1:54:50<15:10:39, 1.71it/s] Train steps ... : 7%|▋ | 6732/100000 [1:54:51<15:09:42, 1.71it/s] Train steps ... : 7%|▋ | 6733/100000 [1:54:52<15:09:09, 1.71it/s] Train steps ... : 7%|▋ | 6734/100000 [1:54:52<15:09:29, 1.71it/s] Train steps ... : 7%|▋ | 6735/100000 [1:54:53<15:08:51, 1.71it/s] Train steps ... : 7%|▋ | 6736/100000 [1:54:53<15:08:42, 1.71it/s] Train steps ... : 7%|▋ | 6737/100000 [1:54:54<15:08:43, 1.71it/s] Train steps ... : 7%|▋ | 6738/100000 [1:54:54<15:10:03, 1.71it/s] Train steps ... : 7%|▋ | 6739/100000 [1:54:55<15:09:54, 1.71it/s] Train steps ... : 7%|▋ | 6740/100000 [1:54:56<15:10:14, 1.71it/s] Train steps ... : 7%|▋ | 6741/100000 [1:54:56<15:11:41, 1.70it/s] Train steps ... : 7%|▋ | 6742/100000 [1:54:57<15:11:33, 1.71it/s] Train steps ... : 7%|▋ | 6743/100000 [1:54:57<15:12:01, 1.70it/s] Train steps ... : 7%|▋ | 6744/100000 [1:54:58<15:11:00, 1.71it/s] Train steps ... : 7%|▋ | 6745/100000 [1:54:59<15:10:19, 1.71it/s] Train steps ... : 7%|▋ | 6746/100000 [1:54:59<15:10:05, 1.71it/s] Train steps ... : 7%|▋ | 6747/100000 [1:55:00<15:10:40, 1.71it/s] Train steps ... : 7%|▋ | 6748/100000 [1:55:00<15:09:21, 1.71it/s] Train steps ... : 7%|▋ | 6749/100000 [1:55:01<15:09:25, 1.71it/s] Train steps ... : 7%|▋ | 6750/100000 [1:55:02<15:08:58, 1.71it/s]Step... (6750 / 100000 | Loss: 1.7047150135040283, Learning Rate: 9.371859296482412e-05) Step... (6750 / 100000 | Loss: 1.2154961824417114, Learning Rate: 9.371859296482412e-05) Train steps ... : 7%|▋ | 6750/100000 [1:55:02<15:08:58, 1.71it/s] Train steps ... : 7%|▋ | 6751/100000 [1:55:02<15:09:12, 1.71it/s] Train steps ... : 7%|▋ | 6752/100000 [1:55:03<15:09:40, 1.71it/s] Train steps ... : 7%|▋ | 6753/100000 [1:55:03<15:08:21, 1.71it/s] Train steps ... : 7%|▋ | 6754/100000 [1:55:04<15:08:45, 1.71it/s] Train steps ... : 7%|▋ | 6755/100000 [1:55:04<15:08:03, 1.71it/s] Train steps ... : 7%|▋ | 6756/100000 [1:55:05<15:08:27, 1.71it/s] Train steps ... : 7%|▋ | 6757/100000 [1:55:06<15:07:39, 1.71it/s] Train steps ... : 7%|▋ | 6758/100000 [1:55:06<15:08:05, 1.71it/s] Train steps ... : 7%|▋ | 6759/100000 [1:55:07<15:09:21, 1.71it/s] Train steps ... : 7%|▋ | 6760/100000 [1:55:07<15:10:11, 1.71it/s] Train steps ... : 7%|▋ | 6761/100000 [1:55:08<15:09:28, 1.71it/s] Train steps ... : 7%|▋ | 6762/100000 [1:55:09<15:10:15, 1.71it/s] Train steps ... : 7%|▋ | 6763/100000 [1:55:09<15:11:54, 1.70it/s] Train steps ... : 7%|▋ | 6764/100000 [1:55:10<15:09:24, 1.71it/s] Train steps ... : 7%|▋ | 6765/100000 [1:55:10<15:11:32, 1.70it/s] Train steps ... : 7%|▋ | 6766/100000 [1:55:11<15:10:57, 1.71it/s] Train steps ... : 7%|▋ | 6767/100000 [1:55:11<15:09:55, 1.71it/s] Train steps ... : 7%|▋ | 6768/100000 [1:55:12<15:08:53, 1.71it/s] Train steps ... : 7%|▋ | 6769/100000 [1:55:13<15:08:25, 1.71it/s] Train steps ... : 7%|▋ | 6770/100000 [1:55:13<15:08:24, 1.71it/s] Train steps ... : 7%|▋ | 6771/100000 [1:55:14<15:09:08, 1.71it/s] Train steps ... : 7%|▋ | 6772/100000 [1:55:14<15:08:52, 1.71it/s] Train steps ... : 7%|▋ | 6773/100000 [1:55:15<15:08:56, 1.71it/s] Train steps ... : 7%|▋ | 6774/100000 [1:55:16<15:08:38, 1.71it/s] Train steps ... : 7%|▋ | 6775/100000 [1:55:16<15:08:24, 1.71it/s]Step... (6775 / 100000 | Loss: 1.3800512552261353, Learning Rate: 9.369346733668343e-05) Step... (6775 / 100000 | Loss: 1.4078619480133057, Learning Rate: 9.369346733668343e-05) Train steps ... : 7%|▋ | 6775/100000 [1:55:16<15:08:24, 1.71it/s] Train steps ... : 7%|▋ | 6776/100000 [1:55:17<15:08:32, 1.71it/s] Train steps ... : 7%|▋ | 6777/100000 [1:55:17<15:07:59, 1.71it/s] Train steps ... : 7%|▋ | 6778/100000 [1:55:18<15:08:23, 1.71it/s] Train steps ... : 7%|▋ | 6779/100000 [1:55:18<15:09:14, 1.71it/s] Train steps ... : 7%|▋ | 6780/100000 [1:55:19<15:09:01, 1.71it/s] Train steps ... : 7%|▋ | 6781/100000 [1:55:20<15:08:31, 1.71it/s] Train steps ... : 7%|▋ | 6782/100000 [1:55:20<15:08:27, 1.71it/s] Train steps ... : 7%|▋ | 6783/100000 [1:55:21<15:08:04, 1.71it/s] Train steps ... : 7%|▋ | 6784/100000 [1:55:21<15:07:55, 1.71it/s] Train steps ... : 7%|▋ | 6785/100000 [1:55:22<15:08:33, 1.71it/s] Train steps ... : 7%|▋ | 6786/100000 [1:55:23<15:06:52, 1.71it/s] Train steps ... : 7%|▋ | 6787/100000 [1:55:23<15:09:12, 1.71it/s] Train steps ... : 7%|▋ | 6788/100000 [1:55:24<15:08:48, 1.71it/s] Train steps ... : 7%|▋ | 6789/100000 [1:55:24<15:10:17, 1.71it/s] Train steps ... : 7%|▋ | 6790/100000 [1:55:25<15:10:18, 1.71it/s] Train steps ... : 7%|▋ | 6791/100000 [1:55:26<15:12:14, 1.70it/s] Train steps ... : 7%|▋ | 6792/100000 [1:55:26<15:10:58, 1.71it/s] Train steps ... : 7%|▋ | 6793/100000 [1:55:27<15:11:30, 1.70it/s] Train steps ... : 7%|▋ | 6794/100000 [1:55:27<15:08:56, 1.71it/s] Train steps ... : 7%|▋ | 6795/100000 [1:55:28<15:09:17, 1.71it/s] Train steps ... : 7%|▋ | 6796/100000 [1:55:28<15:09:43, 1.71it/s] Train steps ... : 7%|▋ | 6797/100000 [1:55:29<15:09:44, 1.71it/s] Train steps ... : 7%|▋ | 6798/100000 [1:55:30<15:10:03, 1.71it/s] Train steps ... : 7%|▋ | 6799/100000 [1:55:30<15:08:41, 1.71it/s] Train steps ... : 7%|▋ | 6800/100000 [1:55:31<15:08:59, 1.71it/s]Step... (6800 / 100000 | Loss: 1.0681791305541992, Learning Rate: 9.366834170854271e-05) Step... (6800 / 100000 | Loss: 1.5944658517837524, Learning Rate: 9.366834170854271e-05) Train steps ... : 7%|▋ | 6800/100000 [1:55:31<15:08:59, 1.71it/s] Train steps ... : 7%|▋ | 6801/100000 [1:55:31<15:09:08, 1.71it/s] Train steps ... : 7%|▋ | 6802/100000 [1:55:32<15:08:22, 1.71it/s] Train steps ... : 7%|▋ | 6803/100000 [1:55:33<15:08:05, 1.71it/s] Train steps ... : 7%|▋ | 6804/100000 [1:55:33<15:07:52, 1.71it/s] Train steps ... : 7%|▋ | 6805/100000 [1:55:34<15:07:32, 1.71it/s] Train steps ... : 7%|▋ | 6806/100000 [1:55:34<15:06:47, 1.71it/s] Train steps ... : 7%|▋ | 6807/100000 [1:55:35<15:08:04, 1.71it/s] Train steps ... : 7%|▋ | 6808/100000 [1:55:35<15:08:44, 1.71it/s] Train steps ... : 7%|▋ | 6809/100000 [1:55:36<15:09:04, 1.71it/s] Train steps ... : 7%|▋ | 6810/100000 [1:55:37<15:09:19, 1.71it/s] Train steps ... : 7%|▋ | 6811/100000 [1:55:37<15:08:13, 1.71it/s] Train steps ... : 7%|▋ | 6812/100000 [1:55:38<15:07:57, 1.71it/s] Train steps ... : 7%|▋ | 6813/100000 [1:55:38<15:07:00, 1.71it/s] Train steps ... : 7%|▋ | 6814/100000 [1:55:39<15:08:38, 1.71it/s] Train steps ... : 7%|▋ | 6815/100000 [1:55:40<15:09:07, 1.71it/s] Train steps ... : 7%|▋ | 6816/100000 [1:55:40<15:09:05, 1.71it/s] Train steps ... : 7%|▋ | 6817/100000 [1:55:41<15:08:16, 1.71it/s] Train steps ... : 7%|▋ | 6818/100000 [1:55:41<15:08:36, 1.71it/s] Train steps ... : 7%|▋ | 6819/100000 [1:55:42<15:08:40, 1.71it/s] Train steps ... : 7%|▋ | 6820/100000 [1:55:42<15:07:44, 1.71it/s] Train steps ... : 7%|▋ | 6821/100000 [1:55:43<15:07:14, 1.71it/s] Train steps ... : 7%|▋ | 6822/100000 [1:55:44<15:07:12, 1.71it/s] Train steps ... : 7%|▋ | 6823/100000 [1:55:44<15:06:58, 1.71it/s] Train steps ... : 7%|▋ | 6824/100000 [1:55:45<15:07:40, 1.71it/s] Train steps ... : 7%|▋ | 6825/100000 [1:55:45<15:08:19, 1.71it/s]Step... (6825 / 100000 | Loss: 1.429560661315918, Learning Rate: 9.364321608040202e-05) Step... (6825 / 100000 | Loss: 1.5644149780273438, Learning Rate: 9.364321608040202e-05) Train steps ... : 7%|▋ | 6825/100000 [1:55:46<15:08:19, 1.71it/s] Train steps ... : 7%|▋ | 6826/100000 [1:55:46<15:07:36, 1.71it/s] Train steps ... : 7%|▋ | 6827/100000 [1:55:47<15:08:49, 1.71it/s] Train steps ... : 7%|▋ | 6828/100000 [1:55:47<15:08:26, 1.71it/s] Train steps ... : 7%|▋ | 6829/100000 [1:55:48<15:08:41, 1.71it/s] Train steps ... : 7%|▋ | 6830/100000 [1:55:48<15:08:16, 1.71it/s] Train steps ... : 7%|▋ | 6831/100000 [1:55:49<15:08:02, 1.71it/s] Train steps ... : 7%|▋ | 6832/100000 [1:55:49<15:07:53, 1.71it/s] Train steps ... : 7%|▋ | 6833/100000 [1:55:50<15:08:15, 1.71it/s] Train steps ... : 7%|▋ | 6834/100000 [1:55:51<15:08:00, 1.71it/s] Train steps ... : 7%|▋ | 6835/100000 [1:55:51<15:08:07, 1.71it/s] Train steps ... : 7%|▋ | 6836/100000 [1:55:52<15:08:36, 1.71it/s] Train steps ... : 7%|▋ | 6837/100000 [1:55:52<15:09:00, 1.71it/s] Train steps ... : 7%|▋ | 6838/100000 [1:55:53<15:07:43, 1.71it/s] Train steps ... : 7%|▋ | 6839/100000 [1:55:54<15:08:50, 1.71it/s] Train steps ... : 7%|▋ | 6840/100000 [1:55:54<15:09:02, 1.71it/s] Train steps ... : 7%|▋ | 6841/100000 [1:55:55<15:08:41, 1.71it/s] Train steps ... : 7%|▋ | 6842/100000 [1:55:55<15:08:39, 1.71it/s] Train steps ... : 7%|▋ | 6843/100000 [1:55:56<15:09:19, 1.71it/s] Train steps ... : 7%|▋ | 6844/100000 [1:55:57<15:08:39, 1.71it/s] Train steps ... : 7%|▋ | 6845/100000 [1:55:57<15:09:50, 1.71it/s] Train steps ... : 7%|▋ | 6846/100000 [1:55:58<15:09:22, 1.71it/s] Train steps ... : 7%|▋ | 6847/100000 [1:55:58<15:08:29, 1.71it/s] Train steps ... : 7%|▋ | 6848/100000 [1:55:59<15:09:25, 1.71it/s] Train steps ... : 7%|▋ | 6849/100000 [1:55:59<15:09:43, 1.71it/s] Train steps ... : 7%|▋ | 6850/100000 [1:56:00<15:09:41, 1.71it/s]Step... (6850 / 100000 | Loss: 1.3814430236816406, Learning Rate: 9.36180904522613e-05) Step... (6850 / 100000 | Loss: 1.4828702211380005, Learning Rate: 9.36180904522613e-05) Train steps ... : 7%|▋ | 6850/100000 [1:56:00<15:09:41, 1.71it/s] Train steps ... : 7%|▋ | 6851/100000 [1:56:01<15:08:36, 1.71it/s] Train steps ... : 7%|▋ | 6852/100000 [1:56:01<15:08:39, 1.71it/s] Train steps ... : 7%|▋ | 6853/100000 [1:56:02<15:09:14, 1.71it/s] Train steps ... : 7%|▋ | 6854/100000 [1:56:02<15:08:26, 1.71it/s] Train steps ... : 7%|▋ | 6855/100000 [1:56:03<15:08:59, 1.71it/s] Train steps ... : 7%|▋ | 6856/100000 [1:56:04<15:08:49, 1.71it/s] Train steps ... : 7%|▋ | 6857/100000 [1:56:04<15:09:01, 1.71it/s] Train steps ... : 7%|▋ | 6858/100000 [1:56:05<15:08:33, 1.71it/s] Train steps ... : 7%|▋ | 6859/100000 [1:56:05<15:08:22, 1.71it/s] Train steps ... : 7%|▋ | 6860/100000 [1:56:06<15:07:42, 1.71it/s] Train steps ... : 7%|▋ | 6861/100000 [1:56:06<15:07:50, 1.71it/s] Train steps ... : 7%|▋ | 6862/100000 [1:56:07<15:07:48, 1.71it/s] Train steps ... : 7%|▋ | 6863/100000 [1:56:08<15:08:38, 1.71it/s] Train steps ... : 7%|▋ | 6864/100000 [1:56:08<15:07:53, 1.71it/s] Train steps ... : 7%|▋ | 6865/100000 [1:56:09<15:07:07, 1.71it/s] Train steps ... : 7%|▋ | 6866/100000 [1:56:09<15:06:57, 1.71it/s] Train steps ... : 7%|▋ | 6867/100000 [1:56:10<15:07:33, 1.71it/s] Train steps ... : 7%|▋ | 6868/100000 [1:56:11<15:08:35, 1.71it/s] Train steps ... : 7%|▋ | 6869/100000 [1:56:11<15:07:00, 1.71it/s] Train steps ... : 7%|▋ | 6870/100000 [1:56:12<15:06:59, 1.71it/s] Train steps ... : 7%|▋ | 6871/100000 [1:56:12<15:07:13, 1.71it/s] Train steps ... : 7%|▋ | 6872/100000 [1:56:13<15:06:57, 1.71it/s] Train steps ... : 7%|▋ | 6873/100000 [1:56:13<15:07:04, 1.71it/s] Train steps ... : 7%|▋ | 6874/100000 [1:56:14<15:06:47, 1.71it/s] Train steps ... : 7%|▋ | 6875/100000 [1:56:15<15:08:18, 1.71it/s]Step... (6875 / 100000 | Loss: 1.4143364429473877, Learning Rate: 9.359296482412062e-05) Step... (6875 / 100000 | Loss: 1.2994065284729004, Learning Rate: 9.359296482412062e-05) Train steps ... : 7%|▋ | 6875/100000 [1:56:15<15:08:18, 1.71it/s] Train steps ... : 7%|▋ | 6876/100000 [1:56:15<15:08:40, 1.71it/s] Train steps ... : 7%|▋ | 6877/100000 [1:56:16<15:07:40, 1.71it/s] Train steps ... : 7%|▋ | 6878/100000 [1:56:16<15:09:12, 1.71it/s] Train steps ... : 7%|▋ | 6879/100000 [1:56:17<15:07:44, 1.71it/s] Train steps ... : 7%|▋ | 6880/100000 [1:56:18<15:07:22, 1.71it/s] Train steps ... : 7%|▋ | 6881/100000 [1:56:18<15:07:53, 1.71it/s] Train steps ... : 7%|▋ | 6882/100000 [1:56:19<15:06:49, 1.71it/s] Train steps ... : 7%|▋ | 6883/100000 [1:56:19<15:07:46, 1.71it/s] Train steps ... : 7%|▋ | 6884/100000 [1:56:20<15:07:35, 1.71it/s] Train steps ... : 7%|▋ | 6885/100000 [1:56:21<15:06:26, 1.71it/s] Train steps ... : 7%|▋ | 6886/100000 [1:56:21<15:07:26, 1.71it/s] Train steps ... : 7%|▋ | 6887/100000 [1:56:22<15:06:43, 1.71it/s] Train steps ... : 7%|▋ | 6888/100000 [1:56:22<15:07:44, 1.71it/s] Train steps ... : 7%|▋ | 6889/100000 [1:56:23<15:08:30, 1.71it/s] Train steps ... : 7%|▋ | 6890/100000 [1:56:23<15:09:47, 1.71it/s] Train steps ... : 7%|▋ | 6891/100000 [1:56:24<15:09:16, 1.71it/s] Train steps ... : 7%|▋ | 6892/100000 [1:56:25<15:09:11, 1.71it/s] Train steps ... : 7%|▋ | 6893/100000 [1:56:25<15:09:01, 1.71it/s] Train steps ... : 7%|▋ | 6894/100000 [1:56:26<15:09:49, 1.71it/s] Train steps ... : 7%|▋ | 6895/100000 [1:56:26<15:10:07, 1.70it/s] Train steps ... : 7%|▋ | 6896/100000 [1:56:27<15:10:21, 1.70it/s] Train steps ... : 7%|▋ | 6897/100000 [1:56:28<15:08:28, 1.71it/s] Train steps ... : 7%|▋ | 6898/100000 [1:56:28<15:09:05, 1.71it/s] Train steps ... : 7%|▋ | 6899/100000 [1:56:29<15:08:37, 1.71it/s] Train steps ... : 7%|▋ | 6900/100000 [1:56:29<15:08:36, 1.71it/s]Step... (6900 / 100000 | Loss: 1.760314702987671, Learning Rate: 9.35678391959799e-05) Step... (6900 / 100000 | Loss: 1.4244699478149414, Learning Rate: 9.35678391959799e-05) Train steps ... : 7%|▋ | 6900/100000 [1:56:30<15:08:36, 1.71it/s] Train steps ... : 7%|▋ | 6901/100000 [1:56:30<15:08:58, 1.71it/s] Train steps ... : 7%|▋ | 6902/100000 [1:56:30<15:08:56, 1.71it/s] Train steps ... : 7%|▋ | 6903/100000 [1:56:31<15:07:41, 1.71it/s] Train steps ... : 7%|▋ | 6904/100000 [1:56:32<15:07:21, 1.71it/s] Train steps ... : 7%|▋ | 6905/100000 [1:56:32<15:07:03, 1.71it/s] Train steps ... : 7%|▋ | 6906/100000 [1:56:33<15:07:38, 1.71it/s] Train steps ... : 7%|▋ | 6907/100000 [1:56:33<15:10:24, 1.70it/s] Train steps ... : 7%|▋ | 6908/100000 [1:56:34<15:07:34, 1.71it/s] Train steps ... : 7%|▋ | 6909/100000 [1:56:35<15:08:53, 1.71it/s] Train steps ... : 7%|▋ | 6910/100000 [1:56:35<15:08:26, 1.71it/s] Train steps ... : 7%|▋ | 6911/100000 [1:56:36<15:08:39, 1.71it/s] Train steps ... : 7%|▋ | 6912/100000 [1:56:36<15:08:17, 1.71it/s] Train steps ... : 7%|▋ | 6913/100000 [1:56:37<15:08:06, 1.71it/s] Train steps ... : 7%|▋ | 6914/100000 [1:56:37<15:09:48, 1.71it/s] Train steps ... : 7%|▋ | 6915/100000 [1:56:38<15:07:01, 1.71it/s] Train steps ... : 7%|▋ | 6916/100000 [1:56:39<15:07:18, 1.71it/s] Train steps ... : 7%|▋ | 6917/100000 [1:56:39<15:06:53, 1.71it/s] Train steps ... : 7%|▋ | 6918/100000 [1:56:40<15:08:02, 1.71it/s] Train steps ... : 7%|▋ | 6919/100000 [1:56:40<15:10:55, 1.70it/s] Train steps ... : 7%|▋ | 6920/100000 [1:56:41<15:08:23, 1.71it/s] Train steps ... : 7%|▋ | 6921/100000 [1:56:42<15:08:36, 1.71it/s] Train steps ... : 7%|▋ | 6922/100000 [1:56:42<15:07:36, 1.71it/s] Train steps ... : 7%|▋ | 6923/100000 [1:56:43<15:09:03, 1.71it/s] Train steps ... : 7%|▋ | 6924/100000 [1:56:43<15:07:22, 1.71it/s] Train steps ... : 7%|▋ | 6925/100000 [1:56:44<15:08:15, 1.71it/s]Step... (6925 / 100000 | Loss: 1.7841835021972656, Learning Rate: 9.35427135678392e-05) Step... (6925 / 100000 | Loss: 1.157274603843689, Learning Rate: 9.35427135678392e-05) Train steps ... : 7%|▋ | 6925/100000 [1:56:44<15:08:15, 1.71it/s] Train steps ... : 7%|▋ | 6926/100000 [1:56:45<15:08:00, 1.71it/s] Train steps ... : 7%|▋ | 6927/100000 [1:56:45<15:06:58, 1.71it/s] Train steps ... : 7%|▋ | 6928/100000 [1:56:46<15:07:03, 1.71it/s] Train steps ... : 7%|▋ | 6929/100000 [1:56:46<15:06:29, 1.71it/s] Train steps ... : 7%|▋ | 6930/100000 [1:56:47<15:05:46, 1.71it/s] Train steps ... : 7%|▋ | 6931/100000 [1:56:47<15:05:39, 1.71it/s] Train steps ... : 7%|▋ | 6932/100000 [1:56:48<15:07:04, 1.71it/s] Train steps ... : 7%|▋ | 6933/100000 [1:56:49<15:07:03, 1.71it/s] Train steps ... : 7%|▋ | 6934/100000 [1:56:49<15:08:02, 1.71it/s] Train steps ... : 7%|▋ | 6935/100000 [1:56:50<15:07:16, 1.71it/s] Train steps ... : 7%|▋ | 6936/100000 [1:56:50<15:07:22, 1.71it/s] Train steps ... : 7%|▋ | 6937/100000 [1:56:51<15:06:47, 1.71it/s] Train steps ... : 7%|▋ | 6938/100000 [1:56:52<15:06:15, 1.71it/s] Train steps ... : 7%|▋ | 6939/100000 [1:56:52<15:07:16, 1.71it/s] Train steps ... : 7%|▋ | 6940/100000 [1:56:53<15:07:07, 1.71it/s] Train steps ... : 7%|▋ | 6941/100000 [1:56:53<15:07:49, 1.71it/s] Train steps ... : 7%|▋ | 6942/100000 [1:56:54<15:07:13, 1.71it/s] Train steps ... : 7%|▋ | 6943/100000 [1:56:54<15:06:47, 1.71it/s] Train steps ... : 7%|▋ | 6944/100000 [1:56:55<15:06:03, 1.71it/s] Train steps ... : 7%|▋ | 6945/100000 [1:56:56<15:06:32, 1.71it/s] Train steps ... : 7%|▋ | 6946/100000 [1:56:56<15:07:21, 1.71it/s] Train steps ... : 7%|▋ | 6947/100000 [1:56:57<15:08:06, 1.71it/s] Train steps ... : 7%|▋ | 6948/100000 [1:56:57<15:07:17, 1.71it/s] Train steps ... : 7%|▋ | 6949/100000 [1:56:58<15:07:59, 1.71it/s] Train steps ... : 7%|▋ | 6950/100000 [1:56:59<15:07:22, 1.71it/s]Step... (6950 / 100000 | Loss: 1.6935583353042603, Learning Rate: 9.351758793969849e-05) Step... (6950 / 100000 | Loss: 1.3730818033218384, Learning Rate: 9.351758793969849e-05) Train steps ... : 7%|▋ | 6950/100000 [1:56:59<15:07:22, 1.71it/s] Train steps ... : 7%|▋ | 6951/100000 [1:56:59<15:08:07, 1.71it/s] Train steps ... : 7%|▋ | 6952/100000 [1:57:00<15:07:26, 1.71it/s] Train steps ... : 7%|▋ | 6953/100000 [1:57:00<15:07:06, 1.71it/s] Train steps ... : 7%|▋ | 6954/100000 [1:57:01<15:07:03, 1.71it/s] Train steps ... : 7%|▋ | 6955/100000 [1:57:01<15:06:56, 1.71it/s] Train steps ... : 7%|▋ | 6956/100000 [1:57:02<15:06:13, 1.71it/s] Train steps ... : 7%|▋ | 6957/100000 [1:57:03<15:05:58, 1.71it/s] Train steps ... : 7%|▋ | 6958/100000 [1:57:03<15:07:13, 1.71it/s] Train steps ... : 7%|▋ | 6959/100000 [1:57:04<15:06:51, 1.71it/s] Train steps ... : 7%|▋ | 6960/100000 [1:57:04<15:07:17, 1.71it/s] Train steps ... : 7%|▋ | 6961/100000 [1:57:05<15:06:00, 1.71it/s] Train steps ... : 7%|▋ | 6962/100000 [1:57:06<15:06:31, 1.71it/s] Train steps ... : 7%|▋ | 6963/100000 [1:57:06<15:07:16, 1.71it/s] Train steps ... : 7%|▋ | 6964/100000 [1:57:07<15:07:04, 1.71it/s] Train steps ... : 7%|▋ | 6965/100000 [1:57:07<15:06:47, 1.71it/s] Train steps ... : 7%|▋ | 6966/100000 [1:57:08<15:07:04, 1.71it/s] Train steps ... : 7%|▋ | 6967/100000 [1:57:08<15:06:49, 1.71it/s] Train steps ... : 7%|▋ | 6968/100000 [1:57:09<15:07:01, 1.71it/s] Train steps ... : 7%|▋ | 6969/100000 [1:57:10<15:06:31, 1.71it/s] Train steps ... : 7%|▋ | 6970/100000 [1:57:10<15:06:12, 1.71it/s] Train steps ... : 7%|▋ | 6971/100000 [1:57:11<15:07:23, 1.71it/s] Train steps ... : 7%|▋ | 6972/100000 [1:57:11<15:06:34, 1.71it/s] Train steps ... : 7%|▋ | 6973/100000 [1:57:12<15:06:52, 1.71it/s] Train steps ... : 7%|▋ | 6974/100000 [1:57:13<15:07:22, 1.71it/s] Train steps ... : 7%|▋ | 6975/100000 [1:57:13<15:06:17, 1.71it/s]Step... (6975 / 100000 | Loss: 1.4609103202819824, Learning Rate: 9.349246231155779e-05) Step... (6975 / 100000 | Loss: 1.4670696258544922, Learning Rate: 9.349246231155779e-05) Train steps ... : 7%|▋ | 6975/100000 [1:57:14<15:06:17, 1.71it/s] Train steps ... : 7%|▋ | 6976/100000 [1:57:14<15:06:59, 1.71it/s] Train steps ... : 7%|▋ | 6977/100000 [1:57:14<15:08:32, 1.71it/s] Train steps ... : 7%|▋ | 6978/100000 [1:57:15<15:07:59, 1.71it/s] Train steps ... : 7%|▋ | 6979/100000 [1:57:16<15:06:31, 1.71it/s] Train steps ... : 7%|▋ | 6980/100000 [1:57:16<15:06:50, 1.71it/s] Train steps ... : 7%|▋ | 6981/100000 [1:57:17<15:05:53, 1.71it/s] Train steps ... : 7%|▋ | 6982/100000 [1:57:17<15:05:41, 1.71it/s] Train steps ... : 7%|▋ | 6983/100000 [1:57:18<15:05:54, 1.71it/s] Train steps ... : 7%|▋ | 6984/100000 [1:57:18<15:05:40, 1.71it/s] Train steps ... : 7%|▋ | 6985/100000 [1:57:19<15:05:19, 1.71it/s] Train steps ... : 7%|▋ | 6986/100000 [1:57:20<15:05:45, 1.71it/s] Train steps ... : 7%|▋ | 6987/100000 [1:57:20<15:07:40, 1.71it/s] Train steps ... : 7%|▋ | 6988/100000 [1:57:21<15:07:35, 1.71it/s] Train steps ... : 7%|▋ | 6989/100000 [1:57:21<15:07:42, 1.71it/s] Train steps ... : 7%|▋ | 6990/100000 [1:57:22<15:06:53, 1.71it/s] Train steps ... : 7%|▋ | 6991/100000 [1:57:23<15:07:39, 1.71it/s] Train steps ... : 7%|▋ | 6992/100000 [1:57:23<15:06:36, 1.71it/s] Train steps ... : 7%|▋ | 6993/100000 [1:57:24<15:06:56, 1.71it/s] Train steps ... : 7%|▋ | 6994/100000 [1:57:24<15:07:33, 1.71it/s] Train steps ... : 7%|▋ | 6995/100000 [1:57:25<15:07:10, 1.71it/s] Train steps ... : 7%|▋ | 6996/100000 [1:57:25<15:06:41, 1.71it/s] Train steps ... : 7%|▋ | 6997/100000 [1:57:26<15:09:12, 1.70it/s] Train steps ... : 7%|▋ | 6998/100000 [1:57:27<15:06:12, 1.71it/s] Train steps ... : 7%|▋ | 6999/100000 [1:57:27<15:05:49, 1.71it/s] Train steps ... : 7%|▋ | 7000/100000 [1:57:28<15:06:51, 1.71it/s]Step... (7000 / 100000 | Loss: 1.4202003479003906, Learning Rate: 9.34673366834171e-05) Step... (7000 / 100000 | Loss: 1.7295417785644531, Learning Rate: 9.34673366834171e-05) Train steps ... : 7%|▋ | 7000/100000 [1:57:28<15:06:51, 1.71it/s] Train steps ... : 7%|▋ | 7001/100000 [1:57:28<15:05:58, 1.71it/s] Train steps ... : 7%|▋ | 7002/100000 [1:57:29<15:06:02, 1.71it/s] Train steps ... : 7%|▋ | 7003/100000 [1:57:30<15:05:18, 1.71it/s] Train steps ... : 7%|▋ | 7004/100000 [1:57:30<15:05:16, 1.71it/s] Train steps ... : 7%|▋ | 7005/100000 [1:57:31<15:05:58, 1.71it/s] Train steps ... : 7%|▋ | 7006/100000 [1:57:31<15:05:14, 1.71it/s] Train steps ... : 7%|▋ | 7007/100000 [1:57:32<15:05:29, 1.71it/s] Train steps ... : 7%|▋ | 7008/100000 [1:57:32<15:06:36, 1.71it/s] Train steps ... : 7%|▋ | 7009/100000 [1:57:33<15:06:50, 1.71it/s] Train steps ... : 7%|▋ | 7010/100000 [1:57:34<15:07:25, 1.71it/s] Train steps ... : 7%|▋ | 7011/100000 [1:57:34<15:07:02, 1.71it/s] Train steps ... : 7%|▋ | 7012/100000 [1:57:35<15:07:09, 1.71it/s] Train steps ... : 7%|▋ | 7013/100000 [1:57:35<15:06:16, 1.71it/s] Train steps ... : 7%|▋ | 7014/100000 [1:57:36<15:07:06, 1.71it/s] Train steps ... : 7%|▋ | 7015/100000 [1:57:37<15:06:38, 1.71it/s] Train steps ... : 7%|▋ | 7016/100000 [1:57:37<15:05:33, 1.71it/s] Train steps ... : 7%|▋ | 7017/100000 [1:57:38<15:04:52, 1.71it/s] Train steps ... : 7%|▋ | 7018/100000 [1:57:38<15:05:27, 1.71it/s] Train steps ... : 7%|▋ | 7019/100000 [1:57:39<15:06:15, 1.71it/s] Train steps ... : 7%|▋ | 7020/100000 [1:57:39<15:05:44, 1.71it/s] Train steps ... : 7%|▋ | 7021/100000 [1:57:40<15:06:14, 1.71it/s] Train steps ... : 7%|▋ | 7022/100000 [1:57:41<15:06:29, 1.71it/s] Train steps ... : 7%|▋ | 7023/100000 [1:57:41<15:06:41, 1.71it/s] Train steps ... : 7%|▋ | 7024/100000 [1:57:42<15:05:57, 1.71it/s] Train steps ... : 7%|▋ | 7025/100000 [1:57:42<15:06:48, 1.71it/s]Step... (7025 / 100000 | Loss: 1.0487277507781982, Learning Rate: 9.344221105527638e-05) Step... (7025 / 100000 | Loss: 1.2228320837020874, Learning Rate: 9.344221105527638e-05) Train steps ... : 7%|▋ | 7025/100000 [1:57:43<15:06:48, 1.71it/s] Train steps ... : 7%|▋ | 7026/100000 [1:57:43<15:09:09, 1.70it/s] Train steps ... : 7%|▋ | 7027/100000 [1:57:44<15:08:37, 1.71it/s] Train steps ... : 7%|▋ | 7028/100000 [1:57:44<15:06:45, 1.71it/s] Train steps ... : 7%|▋ | 7029/100000 [1:57:45<15:07:14, 1.71it/s] Train steps ... : 7%|▋ | 7030/100000 [1:57:45<15:06:29, 1.71it/s] Train steps ... : 7%|▋ | 7031/100000 [1:57:46<15:05:52, 1.71it/s] Train steps ... : 7%|▋ | 7032/100000 [1:57:47<15:05:46, 1.71it/s] Train steps ... : 7%|▋ | 7033/100000 [1:57:47<15:06:12, 1.71it/s] Train steps ... : 7%|▋ | 7034/100000 [1:57:48<15:05:17, 1.71it/s] Train steps ... : 7%|▋ | 7035/100000 [1:57:48<15:06:13, 1.71it/s] Train steps ... : 7%|▋ | 7036/100000 [1:57:49<15:06:26, 1.71it/s] Train steps ... : 7%|▋ | 7037/100000 [1:57:49<15:06:35, 1.71it/s] Train steps ... : 7%|▋ | 7038/100000 [1:57:50<15:05:56, 1.71it/s] Train steps ... : 7%|▋ | 7039/100000 [1:57:51<15:08:16, 1.71it/s] Train steps ... : 7%|▋ | 7040/100000 [1:57:51<15:07:29, 1.71it/s] Train steps ... : 7%|▋ | 7041/100000 [1:57:52<15:06:28, 1.71it/s] Train steps ... : 7%|▋ | 7042/100000 [1:57:52<15:05:44, 1.71it/s] Train steps ... : 7%|▋ | 7043/100000 [1:57:53<15:04:56, 1.71it/s] Train steps ... : 7%|▋ | 7044/100000 [1:57:54<15:05:13, 1.71it/s] Train steps ... : 7%|▋ | 7045/100000 [1:57:54<15:04:46, 1.71it/s] Train steps ... : 7%|▋ | 7046/100000 [1:57:55<15:04:46, 1.71it/s] Train steps ... : 7%|▋ | 7047/100000 [1:57:55<15:06:17, 1.71it/s] Train steps ... : 7%|▋ | 7048/100000 [1:57:56<15:06:57, 1.71it/s] Train steps ... : 7%|▋ | 7049/100000 [1:57:56<15:07:08, 1.71it/s] Train steps ... : 7%|▋ | 7050/100000 [1:57:57<15:07:09, 1.71it/s]Step... (7050 / 100000 | Loss: 1.4900038242340088, Learning Rate: 9.341708542713569e-05) Step... (7050 / 100000 | Loss: 1.8293150663375854, Learning Rate: 9.341708542713569e-05) Train steps ... : 7%|▋ | 7050/100000 [1:57:57<15:07:09, 1.71it/s] Train steps ... : 7%|▋ | 7051/100000 [1:57:58<15:06:19, 1.71it/s] Train steps ... : 7%|▋ | 7052/100000 [1:57:58<15:05:55, 1.71it/s] Train steps ... : 7%|▋ | 7053/100000 [1:57:59<15:06:02, 1.71it/s] Train steps ... : 7%|▋ | 7054/100000 [1:57:59<15:05:49, 1.71it/s] Train steps ... : 7%|▋ | 7055/100000 [1:58:00<15:06:35, 1.71it/s] Train steps ... : 7%|▋ | 7056/100000 [1:58:01<15:06:40, 1.71it/s] Train steps ... : 7%|▋ | 7057/100000 [1:58:01<15:06:23, 1.71it/s] Train steps ... : 7%|▋ | 7058/100000 [1:58:02<15:05:39, 1.71it/s] Train steps ... : 7%|▋ | 7059/100000 [1:58:02<15:05:33, 1.71it/s] Train steps ... : 7%|▋ | 7060/100000 [1:58:03<15:06:13, 1.71it/s] Train steps ... : 7%|▋ | 7061/100000 [1:58:03<15:05:15, 1.71it/s] Train steps ... : 7%|▋ | 7062/100000 [1:58:04<15:06:58, 1.71it/s] Train steps ... : 7%|▋ | 7063/100000 [1:58:05<15:06:11, 1.71it/s] Train steps ... : 7%|▋ | 7064/100000 [1:58:05<15:07:14, 1.71it/s] Train steps ... : 7%|▋ | 7065/100000 [1:58:06<15:07:19, 1.71it/s] Train steps ... : 7%|▋ | 7066/100000 [1:58:06<15:06:21, 1.71it/s] Train steps ... : 7%|▋ | 7067/100000 [1:58:07<15:06:15, 1.71it/s] Train steps ... : 7%|▋ | 7068/100000 [1:58:08<15:05:43, 1.71it/s] Train steps ... : 7%|▋ | 7069/100000 [1:58:08<15:06:18, 1.71it/s] Train steps ... : 7%|▋ | 7070/100000 [1:58:09<15:05:57, 1.71it/s] Train steps ... : 7%|▋ | 7071/100000 [1:58:09<15:05:40, 1.71it/s] Train steps ... : 7%|▋ | 7072/100000 [1:58:10<15:04:58, 1.71it/s] Train steps ... : 7%|▋ | 7073/100000 [1:58:10<15:04:46, 1.71it/s] Train steps ... : 7%|▋ | 7074/100000 [1:58:11<15:05:11, 1.71it/s] Train steps ... : 7%|▋ | 7075/100000 [1:58:12<15:05:43, 1.71it/s]Step... (7075 / 100000 | Loss: 1.1365162134170532, Learning Rate: 9.339195979899498e-05) Step... (7075 / 100000 | Loss: 1.5069639682769775, Learning Rate: 9.339195979899498e-05) Train steps ... : 7%|▋ | 7075/100000 [1:58:12<15:05:43, 1.71it/s] Train steps ... : 7%|▋ | 7076/100000 [1:58:12<15:06:11, 1.71it/s] Train steps ... : 7%|▋ | 7077/100000 [1:58:13<15:06:51, 1.71it/s] Train steps ... : 7%|▋ | 7078/100000 [1:58:13<15:05:20, 1.71it/s] Train steps ... : 7%|▋ | 7079/100000 [1:58:14<15:05:29, 1.71it/s] Train steps ... : 7%|▋ | 7080/100000 [1:58:15<15:05:13, 1.71it/s] Train steps ... : 7%|▋ | 7081/100000 [1:58:15<15:04:50, 1.71it/s] Train steps ... : 7%|▋ | 7082/100000 [1:58:16<15:04:49, 1.71it/s] Train steps ... : 7%|▋ | 7083/100000 [1:58:16<15:04:43, 1.71it/s] Train steps ... : 7%|▋ | 7084/100000 [1:58:17<15:05:31, 1.71it/s] Train steps ... : 7%|▋ | 7085/100000 [1:58:18<15:06:17, 1.71it/s] Train steps ... : 7%|▋ | 7086/100000 [1:58:18<15:06:26, 1.71it/s] Train steps ... : 7%|▋ | 7087/100000 [1:58:19<15:06:09, 1.71it/s] Train steps ... : 7%|▋ | 7088/100000 [1:58:19<15:04:59, 1.71it/s] Train steps ... : 7%|▋ | 7089/100000 [1:58:20<15:05:13, 1.71it/s] Train steps ... : 7%|▋ | 7090/100000 [1:58:20<15:04:25, 1.71it/s] Train steps ... : 7%|▋ | 7091/100000 [1:58:21<15:04:15, 1.71it/s] Train steps ... : 7%|▋ | 7092/100000 [1:58:22<15:05:00, 1.71it/s] Train steps ... : 7%|▋ | 7093/100000 [1:58:22<15:04:27, 1.71it/s] Train steps ... : 7%|▋ | 7094/100000 [1:58:23<15:04:45, 1.71it/s] Train steps ... : 7%|▋ | 7095/100000 [1:58:23<15:04:44, 1.71it/s] Train steps ... : 7%|▋ | 7096/100000 [1:58:24<15:04:49, 1.71it/s] Train steps ... : 7%|▋ | 7097/100000 [1:58:25<15:05:37, 1.71it/s] Train steps ... : 7%|▋ | 7098/100000 [1:58:25<15:04:58, 1.71it/s] Train steps ... : 7%|▋ | 7099/100000 [1:58:26<15:06:39, 1.71it/s] Train steps ... : 7%|▋ | 7100/100000 [1:58:26<15:06:52, 1.71it/s]Step... (7100 / 100000 | Loss: 1.3073086738586426, Learning Rate: 9.336683417085427e-05) Step... (7100 / 100000 | Loss: 1.3563408851623535, Learning Rate: 9.336683417085427e-05) Train steps ... : 7%|▋ | 7100/100000 [1:58:27<15:06:52, 1.71it/s] Train steps ... : 7%|▋ | 7101/100000 [1:58:27<15:06:22, 1.71it/s] Train steps ... : 7%|▋ | 7102/100000 [1:58:27<15:05:42, 1.71it/s] Train steps ... : 7%|▋ | 7103/100000 [1:58:28<15:05:25, 1.71it/s] Train steps ... : 7%|▋ | 7104/100000 [1:58:29<15:06:06, 1.71it/s] Train steps ... : 7%|▋ | 7105/100000 [1:58:29<15:05:17, 1.71it/s] Train steps ... : 7%|▋ | 7106/100000 [1:58:30<15:05:03, 1.71it/s] Train steps ... : 7%|▋ | 7107/100000 [1:58:30<15:05:39, 1.71it/s] Train steps ... : 7%|▋ | 7108/100000 [1:58:31<15:06:20, 1.71it/s] Train steps ... : 7%|▋ | 7109/100000 [1:58:32<15:06:13, 1.71it/s] Train steps ... : 7%|▋ | 7110/100000 [1:58:32<15:05:47, 1.71it/s] Train steps ... : 7%|▋ | 7111/100000 [1:58:33<15:05:26, 1.71it/s] Train steps ... : 7%|▋ | 7112/100000 [1:58:33<15:05:03, 1.71it/s] Train steps ... : 7%|▋ | 7113/100000 [1:58:34<15:04:45, 1.71it/s] Train steps ... : 7%|▋ | 7114/100000 [1:58:34<15:05:03, 1.71it/s] Train steps ... : 7%|▋ | 7115/100000 [1:58:35<15:05:00, 1.71it/s] Train steps ... : 7%|▋ | 7116/100000 [1:58:36<15:04:14, 1.71it/s] Train steps ... : 7%|▋ | 7117/100000 [1:58:36<15:04:01, 1.71it/s] Train steps ... : 7%|▋ | 7118/100000 [1:58:37<15:04:31, 1.71it/s] Train steps ... : 7%|▋ | 7119/100000 [1:58:37<15:05:10, 1.71it/s] Train steps ... : 7%|▋ | 7120/100000 [1:58:38<15:05:11, 1.71it/s] Train steps ... : 7%|▋ | 7121/100000 [1:58:39<15:06:04, 1.71it/s] Train steps ... : 7%|▋ | 7122/100000 [1:58:39<15:05:46, 1.71it/s] Train steps ... : 7%|▋ | 7123/100000 [1:58:40<15:05:49, 1.71it/s] Train steps ... : 7%|▋ | 7124/100000 [1:58:40<15:06:46, 1.71it/s] Train steps ... : 7%|▋ | 7125/100000 [1:58:41<15:06:56, 1.71it/s]Step... (7125 / 100000 | Loss: 0.9000083208084106, Learning Rate: 9.334170854271357e-05) Step... (7125 / 100000 | Loss: 0.9475829601287842, Learning Rate: 9.334170854271357e-05) Train steps ... : 7%|▋ | 7125/100000 [1:58:41<15:06:56, 1.71it/s] Train steps ... : 7%|▋ | 7126/100000 [1:58:41<15:07:00, 1.71it/s] Train steps ... : 7%|▋ | 7127/100000 [1:58:42<15:05:47, 1.71it/s] Train steps ... : 7%|▋ | 7128/100000 [1:58:43<15:04:52, 1.71it/s] Train steps ... : 7%|▋ | 7129/100000 [1:58:43<15:05:15, 1.71it/s] Train steps ... : 7%|▋ | 7130/100000 [1:58:44<15:05:52, 1.71it/s] Train steps ... : 7%|▋ | 7131/100000 [1:58:44<15:04:53, 1.71it/s] Train steps ... : 7%|▋ | 7132/100000 [1:58:45<15:07:19, 1.71it/s] Train steps ... : 7%|▋ | 7133/100000 [1:58:46<15:07:07, 1.71it/s] Train steps ... : 7%|▋ | 7134/100000 [1:58:46<15:05:45, 1.71it/s] Train steps ... : 7%|▋ | 7135/100000 [1:58:47<15:06:17, 1.71it/s] Train steps ... : 7%|▋ | 7136/100000 [1:58:47<15:05:45, 1.71it/s] Train steps ... : 7%|▋ | 7137/100000 [1:58:48<15:04:53, 1.71it/s] Train steps ... : 7%|▋ | 7138/100000 [1:58:49<15:05:12, 1.71it/s] Train steps ... : 7%|▋ | 7139/100000 [1:58:49<15:05:33, 1.71it/s] Train steps ... : 7%|▋ | 7140/100000 [1:58:50<15:05:25, 1.71it/s] Train steps ... : 7%|▋ | 7141/100000 [1:58:50<15:04:32, 1.71it/s] Train steps ... : 7%|▋ | 7142/100000 [1:58:51<15:05:36, 1.71it/s] Train steps ... : 7%|▋ | 7143/100000 [1:58:51<15:05:45, 1.71it/s] Train steps ... : 7%|▋ | 7144/100000 [1:58:52<15:05:13, 1.71it/s] Train steps ... : 7%|▋ | 7145/100000 [1:58:53<15:04:53, 1.71it/s] Train steps ... : 7%|▋ | 7146/100000 [1:58:53<15:04:20, 1.71it/s] Train steps ... : 7%|▋ | 7147/100000 [1:58:54<15:04:22, 1.71it/s] Train steps ... : 7%|▋ | 7148/100000 [1:58:54<15:03:57, 1.71it/s] Train steps ... : 7%|▋ | 7149/100000 [1:58:55<15:05:41, 1.71it/s] Train steps ... : 7%|▋ | 7150/100000 [1:58:56<15:05:26, 1.71it/s]Step... (7150 / 100000 | Loss: 1.770723819732666, Learning Rate: 9.331658291457287e-05) Step... (7150 / 100000 | Loss: 1.7121350765228271, Learning Rate: 9.331658291457287e-05) Train steps ... : 7%|▋ | 7150/100000 [1:58:56<15:05:26, 1.71it/s] Train steps ... : 7%|▋ | 7151/100000 [1:58:56<15:04:59, 1.71it/s] Train steps ... : 7%|▋ | 7152/100000 [1:58:57<15:05:32, 1.71it/s] Train steps ... : 7%|▋ | 7153/100000 [1:58:57<15:05:28, 1.71it/s] Train steps ... : 7%|▋ | 7154/100000 [1:58:58<15:04:43, 1.71it/s] Train steps ... : 7%|▋ | 7155/100000 [1:58:58<15:03:59, 1.71it/s] Train steps ... : 7%|▋ | 7156/100000 [1:58:59<15:04:43, 1.71it/s] Train steps ... : 7%|▋ | 7157/100000 [1:59:00<15:04:20, 1.71it/s] Train steps ... : 7%|▋ | 7158/100000 [1:59:00<15:05:00, 1.71it/s] Train steps ... : 7%|▋ | 7159/100000 [1:59:01<15:04:10, 1.71it/s] Train steps ... : 7%|▋ | 7160/100000 [1:59:01<15:04:23, 1.71it/s] Train steps ... : 7%|▋ | 7161/100000 [1:59:02<15:03:53, 1.71it/s] Train steps ... : 7%|▋ | 7162/100000 [1:59:03<15:03:30, 1.71it/s] Train steps ... : 7%|▋ | 7163/100000 [1:59:03<15:03:33, 1.71it/s] Train steps ... : 7%|▋ | 7164/100000 [1:59:04<15:04:04, 1.71it/s] Train steps ... : 7%|▋ | 7165/100000 [1:59:04<15:04:42, 1.71it/s] Train steps ... : 7%|▋ | 7166/100000 [1:59:05<15:04:55, 1.71it/s] Train steps ... : 7%|▋ | 7167/100000 [1:59:05<15:03:28, 1.71it/s] Train steps ... : 7%|▋ | 7168/100000 [1:59:06<15:04:06, 1.71it/s] Train steps ... : 7%|▋ | 7169/100000 [1:59:07<15:05:27, 1.71it/s] Train steps ... : 7%|▋ | 7170/100000 [1:59:07<15:04:21, 1.71it/s] Train steps ... : 7%|▋ | 7171/100000 [1:59:08<15:03:24, 1.71it/s] Train steps ... : 7%|▋ | 7172/100000 [1:59:08<15:04:53, 1.71it/s] Train steps ... : 7%|▋ | 7173/100000 [1:59:09<15:03:44, 1.71it/s] Train steps ... : 7%|▋ | 7174/100000 [1:59:10<15:03:41, 1.71it/s] Train steps ... : 7%|▋ | 7175/100000 [1:59:10<15:03:58, 1.71it/s]Step... (7175 / 100000 | Loss: 1.4564623832702637, Learning Rate: 9.329145728643216e-05) Step... (7175 / 100000 | Loss: 1.3369704484939575, Learning Rate: 9.329145728643216e-05) Train steps ... : 7%|▋ | 7175/100000 [1:59:10<15:03:58, 1.71it/s] Train steps ... : 7%|▋ | 7176/100000 [1:59:11<15:03:33, 1.71it/s] Train steps ... : 7%|▋ | 7177/100000 [1:59:11<15:05:55, 1.71it/s] Train steps ... : 7%|▋ | 7178/100000 [1:59:12<15:05:09, 1.71it/s] Train steps ... : 7%|▋ | 7179/100000 [1:59:12<15:04:20, 1.71it/s] Train steps ... : 7%|▋ | 7180/100000 [1:59:13<15:04:29, 1.71it/s] Train steps ... : 7%|▋ | 7181/100000 [1:59:14<15:03:52, 1.71it/s] Train steps ... : 7%|▋ | 7182/100000 [1:59:14<15:03:53, 1.71it/s] Train steps ... : 7%|▋ | 7183/100000 [1:59:15<15:03:51, 1.71it/s] Train steps ... : 7%|▋ | 7184/100000 [1:59:15<15:03:39, 1.71it/s] Train steps ... : 7%|▋ | 7185/100000 [1:59:16<15:03:07, 1.71it/s] Train steps ... : 7%|▋ | 7186/100000 [1:59:17<15:03:19, 1.71it/s] Train steps ... : 7%|▋ | 7187/100000 [1:59:17<15:03:07, 1.71it/s] Train steps ... : 7%|▋ | 7188/100000 [1:59:18<15:03:18, 1.71it/s] Train steps ... : 7%|▋ | 7189/100000 [1:59:18<15:03:49, 1.71it/s] Train steps ... : 7%|▋ | 7190/100000 [1:59:19<15:03:51, 1.71it/s] Train steps ... : 7%|▋ | 7191/100000 [1:59:19<15:03:41, 1.71it/s] Train steps ... : 7%|▋ | 7192/100000 [1:59:20<15:03:41, 1.71it/s] Train steps ... : 7%|▋ | 7193/100000 [1:59:21<15:04:25, 1.71it/s] Train steps ... : 7%|▋ | 7194/100000 [1:59:21<15:03:12, 1.71it/s] Train steps ... : 7%|▋ | 7195/100000 [1:59:22<15:04:09, 1.71it/s] Train steps ... : 7%|▋ | 7196/100000 [1:59:22<15:04:51, 1.71it/s] Train steps ... : 7%|▋ | 7197/100000 [1:59:23<15:05:05, 1.71it/s] Train steps ... : 7%|▋ | 7198/100000 [1:59:24<15:06:03, 1.71it/s] Train steps ... : 7%|▋ | 7199/100000 [1:59:24<15:05:35, 1.71it/s] Train steps ... : 7%|▋ | 7200/100000 [1:59:25<15:04:52, 1.71it/s]Step... (7200 / 100000 | Loss: 1.1545031070709229, Learning Rate: 9.326633165829146e-05) Step... (7200 / 100000 | Loss: 1.6303834915161133, Learning Rate: 9.326633165829146e-05) Train steps ... : 7%|▋ | 7200/100000 [1:59:25<15:04:52, 1.71it/s] Train steps ... : 7%|▋ | 7201/100000 [1:59:25<15:04:48, 1.71it/s] Train steps ... : 7%|▋ | 7202/100000 [1:59:26<15:04:30, 1.71it/s] Train steps ... : 7%|▋ | 7203/100000 [1:59:27<15:04:59, 1.71it/s] Train steps ... : 7%|▋ | 7204/100000 [1:59:27<15:04:19, 1.71it/s] Train steps ... : 7%|▋ | 7205/100000 [1:59:28<15:04:06, 1.71it/s] Train steps ... : 7%|▋ | 7206/100000 [1:59:28<15:03:18, 1.71it/s] Train steps ... : 7%|▋ | 7207/100000 [1:59:29<15:03:51, 1.71it/s] Train steps ... : 7%|▋ | 7208/100000 [1:59:29<15:05:17, 1.71it/s] Train steps ... : 7%|▋ | 7209/100000 [1:59:30<15:03:41, 1.71it/s] Train steps ... : 7%|▋ | 7210/100000 [1:59:31<15:04:37, 1.71it/s] Train steps ... : 7%|▋ | 7211/100000 [1:59:31<15:04:54, 1.71it/s] Train steps ... : 7%|▋ | 7212/100000 [1:59:32<15:04:07, 1.71it/s] Train steps ... : 7%|▋ | 7213/100000 [1:59:32<15:03:29, 1.71it/s] Train steps ... : 7%|▋ | 7214/100000 [1:59:33<15:03:34, 1.71it/s] Train steps ... : 7%|▋ | 7215/100000 [1:59:34<15:04:00, 1.71it/s] Train steps ... : 7%|▋ | 7216/100000 [1:59:34<15:03:31, 1.71it/s] Train steps ... : 7%|▋ | 7217/100000 [1:59:35<15:03:53, 1.71it/s] Train steps ... : 7%|▋ | 7218/100000 [1:59:35<15:04:30, 1.71it/s] Train steps ... : 7%|▋ | 7219/100000 [1:59:36<15:03:03, 1.71it/s] Train steps ... : 7%|▋ | 7220/100000 [1:59:36<15:03:37, 1.71it/s] Train steps ... : 7%|▋ | 7221/100000 [1:59:37<15:03:40, 1.71it/s] Train steps ... : 7%|▋ | 7222/100000 [1:59:38<15:04:19, 1.71it/s] Train steps ... : 7%|▋ | 7223/100000 [1:59:38<15:04:57, 1.71it/s] Train steps ... : 7%|▋ | 7224/100000 [1:59:39<15:04:36, 1.71it/s] Train steps ... : 7%|▋ | 7225/100000 [1:59:39<15:04:34, 1.71it/s]Step... (7225 / 100000 | Loss: 1.8033788204193115, Learning Rate: 9.324120603015077e-05) Step... (7225 / 100000 | Loss: 1.7695962190628052, Learning Rate: 9.324120603015077e-05) Train steps ... : 7%|▋ | 7225/100000 [1:59:40<15:04:34, 1.71it/s] Train steps ... : 7%|▋ | 7226/100000 [1:59:40<15:04:08, 1.71it/s] Train steps ... : 7%|▋ | 7227/100000 [1:59:41<15:03:52, 1.71it/s] Train steps ... : 7%|▋ | 7228/100000 [1:59:41<15:03:36, 1.71it/s] Train steps ... : 7%|▋ | 7229/100000 [1:59:42<15:03:52, 1.71it/s] Train steps ... : 7%|▋ | 7230/100000 [1:59:42<15:04:51, 1.71it/s] Train steps ... : 7%|▋ | 7231/100000 [1:59:43<15:06:26, 1.71it/s] Train steps ... : 7%|▋ | 7232/100000 [1:59:43<15:05:01, 1.71it/s] Train steps ... : 7%|▋ | 7233/100000 [1:59:44<15:04:34, 1.71it/s] Train steps ... : 7%|▋ | 7234/100000 [1:59:45<15:05:07, 1.71it/s] Train steps ... : 7%|▋ | 7235/100000 [1:59:45<15:05:27, 1.71it/s] Train steps ... : 7%|▋ | 7236/100000 [1:59:46<15:07:58, 1.70it/s] Train steps ... : 7%|▋ | 7237/100000 [1:59:46<15:06:29, 1.71it/s] Train steps ... : 7%|▋ | 7238/100000 [1:59:47<15:06:12, 1.71it/s] Train steps ... : 7%|▋ | 7239/100000 [1:59:48<15:07:21, 1.70it/s] Train steps ... : 7%|▋ | 7240/100000 [1:59:48<15:06:54, 1.70it/s] Train steps ... : 7%|▋ | 7241/100000 [1:59:49<15:06:06, 1.71it/s] Train steps ... : 7%|▋ | 7242/100000 [1:59:49<15:04:57, 1.71it/s] Train steps ... : 7%|▋ | 7243/100000 [1:59:50<15:04:45, 1.71it/s] Train steps ... : 7%|▋ | 7244/100000 [1:59:51<15:05:05, 1.71it/s] Train steps ... : 7%|▋ | 7245/100000 [1:59:51<15:04:07, 1.71it/s] Train steps ... : 7%|▋ | 7246/100000 [1:59:52<15:05:10, 1.71it/s] Train steps ... : 7%|▋ | 7247/100000 [1:59:52<15:04:35, 1.71it/s] Train steps ... : 7%|▋ | 7248/100000 [1:59:53<15:04:37, 1.71it/s] Train steps ... : 7%|▋ | 7249/100000 [1:59:53<15:04:40, 1.71it/s] Train steps ... : 7%|▋ | 7250/100000 [1:59:54<15:06:25, 1.71it/s]Step... (7250 / 100000 | Loss: 1.2488670349121094, Learning Rate: 9.321608040201005e-05) Step... (7250 / 100000 | Loss: 1.6009092330932617, Learning Rate: 9.321608040201005e-05) Train steps ... : 7%|▋ | 7250/100000 [1:59:54<15:06:25, 1.71it/s] Train steps ... : 7%|▋ | 7251/100000 [1:59:55<15:05:51, 1.71it/s] Train steps ... : 7%|▋ | 7252/100000 [1:59:55<15:04:51, 1.71it/s] Train steps ... : 7%|▋ | 7253/100000 [1:59:56<15:03:34, 1.71it/s] Train steps ... : 7%|▋ | 7254/100000 [1:59:56<15:04:04, 1.71it/s] Train steps ... : 7%|▋ | 7255/100000 [1:59:57<15:03:20, 1.71it/s] Train steps ... : 7%|▋ | 7256/100000 [1:59:58<15:03:12, 1.71it/s] Train steps ... : 7%|▋ | 7257/100000 [1:59:58<15:03:23, 1.71it/s] Train steps ... : 7%|▋ | 7258/100000 [1:59:59<15:03:07, 1.71it/s] Train steps ... : 7%|▋ | 7259/100000 [1:59:59<15:04:15, 1.71it/s] Train steps ... : 7%|▋ | 7260/100000 [2:00:00<15:04:32, 1.71it/s] Train steps ... : 7%|▋ | 7261/100000 [2:00:00<15:04:22, 1.71it/s] Train steps ... : 7%|▋ | 7262/100000 [2:00:01<15:04:59, 1.71it/s] Train steps ... : 7%|▋ | 7263/100000 [2:00:02<15:05:52, 1.71it/s] Train steps ... : 7%|▋ | 7264/100000 [2:00:02<15:05:03, 1.71it/s] Train steps ... : 7%|▋ | 7265/100000 [2:00:03<15:05:16, 1.71it/s] Train steps ... : 7%|▋ | 7266/100000 [2:00:03<15:06:08, 1.71it/s] Train steps ... : 7%|▋ | 7267/100000 [2:00:04<15:03:47, 1.71it/s] Train steps ... : 7%|▋ | 7268/100000 [2:00:05<15:04:46, 1.71it/s] Train steps ... : 7%|▋ | 7269/100000 [2:00:05<15:05:05, 1.71it/s] Train steps ... : 7%|▋ | 7270/100000 [2:00:06<15:04:30, 1.71it/s] Train steps ... : 7%|▋ | 7271/100000 [2:00:06<15:04:37, 1.71it/s] Train steps ... : 7%|▋ | 7272/100000 [2:00:07<15:03:26, 1.71it/s] Train steps ... : 7%|▋ | 7273/100000 [2:00:07<15:04:23, 1.71it/s] Train steps ... : 7%|▋ | 7274/100000 [2:00:08<15:02:44, 1.71it/s] Train steps ... : 7%|▋ | 7275/100000 [2:00:09<15:02:37, 1.71it/s]Step... (7275 / 100000 | Loss: 1.412576675415039, Learning Rate: 9.319095477386935e-05) Step... (7275 / 100000 | Loss: 1.0848308801651, Learning Rate: 9.319095477386935e-05) Train steps ... : 7%|▋ | 7275/100000 [2:00:09<15:02:37, 1.71it/s] Train steps ... : 7%|▋ | 7276/100000 [2:00:09<15:02:48, 1.71it/s] Train steps ... : 7%|▋ | 7277/100000 [2:00:10<15:03:10, 1.71it/s] Train steps ... : 7%|▋ | 7278/100000 [2:00:10<15:02:35, 1.71it/s] Train steps ... : 7%|▋ | 7279/100000 [2:00:11<15:03:51, 1.71it/s] Train steps ... : 7%|▋ | 7280/100000 [2:00:12<15:03:23, 1.71it/s] Train steps ... : 7%|▋ | 7281/100000 [2:00:12<15:03:21, 1.71it/s] Train steps ... : 7%|▋ | 7282/100000 [2:00:13<15:02:30, 1.71it/s] Train steps ... : 7%|▋ | 7283/100000 [2:00:13<15:03:07, 1.71it/s] Train steps ... : 7%|▋ | 7284/100000 [2:00:14<15:03:36, 1.71it/s] Train steps ... : 7%|▋ | 7285/100000 [2:00:14<15:03:15, 1.71it/s] Train steps ... : 7%|▋ | 7286/100000 [2:00:15<15:03:05, 1.71it/s] Train steps ... : 7%|▋ | 7287/100000 [2:00:16<15:03:03, 1.71it/s] Train steps ... : 7%|▋ | 7288/100000 [2:00:16<15:03:42, 1.71it/s] Train steps ... : 7%|▋ | 7289/100000 [2:00:17<15:03:01, 1.71it/s] Train steps ... : 7%|▋ | 7290/100000 [2:00:17<15:03:31, 1.71it/s] Train steps ... : 7%|▋ | 7291/100000 [2:00:18<15:02:55, 1.71it/s] Train steps ... : 7%|▋ | 7292/100000 [2:00:19<15:03:00, 1.71it/s] Train steps ... : 7%|▋ | 7293/100000 [2:00:19<15:02:26, 1.71it/s] Train steps ... : 7%|▋ | 7294/100000 [2:00:20<15:02:12, 1.71it/s] Train steps ... : 7%|▋ | 7295/100000 [2:00:20<15:02:15, 1.71it/s] Train steps ... : 7%|▋ | 7296/100000 [2:00:21<15:01:54, 1.71it/s] Train steps ... : 7%|▋ | 7297/100000 [2:00:21<15:04:25, 1.71it/s] Train steps ... : 7%|▋ | 7298/100000 [2:00:22<15:03:36, 1.71it/s] Train steps ... : 7%|▋ | 7299/100000 [2:00:23<15:04:39, 1.71it/s] Train steps ... : 7%|▋ | 7300/100000 [2:00:23<15:03:54, 1.71it/s]Step... (7300 / 100000 | Loss: 1.8146686553955078, Learning Rate: 9.316582914572864e-05) Step... (7300 / 100000 | Loss: 1.50980544090271, Learning Rate: 9.316582914572864e-05) Train steps ... : 7%|▋ | 7300/100000 [2:00:24<15:03:54, 1.71it/s] Train steps ... : 7%|▋ | 7301/100000 [2:00:24<15:03:15, 1.71it/s] Train steps ... : 7%|▋ | 7302/100000 [2:00:24<15:03:23, 1.71it/s] Train steps ... : 7%|▋ | 7303/100000 [2:00:25<15:02:59, 1.71it/s] Train steps ... : 7%|▋ | 7304/100000 [2:00:26<15:02:37, 1.71it/s] Train steps ... : 7%|▋ | 7305/100000 [2:00:26<15:02:09, 1.71it/s] Train steps ... : 7%|▋ | 7306/100000 [2:00:27<15:02:15, 1.71it/s] Train steps ... : 7%|▋ | 7307/100000 [2:00:27<15:02:08, 1.71it/s] Train steps ... : 7%|▋ | 7308/100000 [2:00:28<15:02:33, 1.71it/s] Train steps ... : 7%|▋ | 7309/100000 [2:00:29<15:02:18, 1.71it/s] Train steps ... : 7%|▋ | 7310/100000 [2:00:29<15:02:06, 1.71it/s] Train steps ... : 7%|▋ | 7311/100000 [2:00:30<15:03:24, 1.71it/s] Train steps ... : 7%|▋ | 7312/100000 [2:00:30<15:06:29, 1.70it/s] Train steps ... : 7%|▋ | 7313/100000 [2:00:31<15:04:02, 1.71it/s] Train steps ... : 7%|▋ | 7314/100000 [2:00:31<15:03:30, 1.71it/s] Train steps ... : 7%|▋ | 7315/100000 [2:00:32<15:03:22, 1.71it/s] Train steps ... : 7%|▋ | 7316/100000 [2:00:33<15:03:16, 1.71it/s] Train steps ... : 7%|▋ | 7317/100000 [2:00:33<15:04:36, 1.71it/s] Train steps ... : 7%|▋ | 7318/100000 [2:00:34<15:03:34, 1.71it/s] Train steps ... : 7%|▋ | 7319/100000 [2:00:34<15:03:16, 1.71it/s] Train steps ... : 7%|▋ | 7320/100000 [2:00:35<15:03:04, 1.71it/s] Train steps ... : 7%|▋ | 7321/100000 [2:00:36<15:05:30, 1.71it/s] Train steps ... : 7%|▋ | 7322/100000 [2:00:36<15:04:19, 1.71it/s] Train steps ... : 7%|▋ | 7323/100000 [2:00:37<15:05:40, 1.71it/s] Train steps ... : 7%|▋ | 7324/100000 [2:00:37<15:05:20, 1.71it/s] Train steps ... : 7%|▋ | 7325/100000 [2:00:38<15:04:32, 1.71it/s]Step... (7325 / 100000 | Loss: 1.5160036087036133, Learning Rate: 9.314070351758794e-05) Step... (7325 / 100000 | Loss: 1.5877294540405273, Learning Rate: 9.314070351758794e-05) Train steps ... : 7%|▋ | 7325/100000 [2:00:38<15:04:32, 1.71it/s] Train steps ... : 7%|▋ | 7326/100000 [2:00:38<15:03:47, 1.71it/s] Train steps ... : 7%|▋ | 7327/100000 [2:00:39<15:02:57, 1.71it/s] Train steps ... : 7%|▋ | 7328/100000 [2:00:40<15:03:02, 1.71it/s] Train steps ... : 7%|▋ | 7329/100000 [2:00:40<15:02:31, 1.71it/s] Train steps ... : 7%|▋ | 7330/100000 [2:00:41<15:03:51, 1.71it/s] Train steps ... : 7%|▋ | 7331/100000 [2:00:41<15:02:33, 1.71it/s] Train steps ... : 7%|▋ | 7332/100000 [2:00:42<15:02:23, 1.71it/s] Train steps ... : 7%|▋ | 7333/100000 [2:00:43<15:02:08, 1.71it/s] Train steps ... : 7%|▋ | 7334/100000 [2:00:43<15:03:27, 1.71it/s] Train steps ... : 7%|▋ | 7335/100000 [2:00:44<15:02:37, 1.71it/s] Train steps ... : 7%|▋ | 7336/100000 [2:00:44<15:03:12, 1.71it/s] Train steps ... : 7%|▋ | 7337/100000 [2:00:45<15:04:29, 1.71it/s] Train steps ... : 7%|▋ | 7338/100000 [2:00:45<15:04:51, 1.71it/s] Train steps ... : 7%|▋ | 7339/100000 [2:00:46<15:04:54, 1.71it/s] Train steps ... : 7%|▋ | 7340/100000 [2:00:47<15:03:39, 1.71it/s] Train steps ... : 7%|▋ | 7341/100000 [2:00:47<15:03:08, 1.71it/s] Train steps ... : 7%|▋ | 7342/100000 [2:00:48<15:04:03, 1.71it/s] Train steps ... : 7%|▋ | 7343/100000 [2:00:48<15:02:13, 1.71it/s] Train steps ... : 7%|▋ | 7344/100000 [2:00:49<15:03:27, 1.71it/s] Train steps ... : 7%|▋ | 7345/100000 [2:00:50<15:02:52, 1.71it/s] Train steps ... : 7%|▋ | 7346/100000 [2:00:50<15:03:07, 1.71it/s] Train steps ... : 7%|▋ | 7347/100000 [2:00:51<15:02:40, 1.71it/s] Train steps ... : 7%|▋ | 7348/100000 [2:00:51<15:03:36, 1.71it/s] Train steps ... : 7%|▋ | 7349/100000 [2:00:52<15:02:46, 1.71it/s] Train steps ... : 7%|▋ | 7350/100000 [2:00:52<15:02:26, 1.71it/s]Step... (7350 / 100000 | Loss: 1.0777372121810913, Learning Rate: 9.311557788944724e-05) Step... (7350 / 100000 | Loss: 1.419048547744751, Learning Rate: 9.311557788944724e-05) Train steps ... : 7%|▋ | 7350/100000 [2:00:53<15:02:26, 1.71it/s] Train steps ... : 7%|▋ | 7351/100000 [2:00:53<15:02:41, 1.71it/s] Train steps ... : 7%|▋ | 7352/100000 [2:00:54<15:02:29, 1.71it/s] Train steps ... : 7%|▋ | 7353/100000 [2:00:54<15:02:33, 1.71it/s] Train steps ... : 7%|▋ | 7354/100000 [2:00:55<15:02:49, 1.71it/s] Train steps ... : 7%|▋ | 7355/100000 [2:00:55<15:02:10, 1.71it/s] Train steps ... : 7%|▋ | 7356/100000 [2:00:56<15:05:16, 1.71it/s] Train steps ... : 7%|▋ | 7357/100000 [2:00:57<15:04:16, 1.71it/s] Train steps ... : 7%|▋ | 7358/100000 [2:00:57<15:03:37, 1.71it/s] Train steps ... : 7%|▋ | 7359/100000 [2:00:58<15:03:33, 1.71it/s] Train steps ... : 7%|▋ | 7360/100000 [2:00:58<15:02:28, 1.71it/s] Train steps ... : 7%|▋ | 7361/100000 [2:00:59<15:02:35, 1.71it/s] Train steps ... : 7%|▋ | 7362/100000 [2:01:00<15:02:30, 1.71it/s] Train steps ... : 7%|▋ | 7363/100000 [2:01:00<15:01:58, 1.71it/s] Train steps ... : 7%|▋ | 7364/100000 [2:01:01<15:03:52, 1.71it/s] Train steps ... : 7%|▋ | 7365/100000 [2:01:01<15:03:21, 1.71it/s] Train steps ... : 7%|▋ | 7366/100000 [2:01:02<15:03:14, 1.71it/s] Train steps ... : 7%|▋ | 7367/100000 [2:01:02<15:02:28, 1.71it/s] Train steps ... : 7%|▋ | 7368/100000 [2:01:03<15:02:07, 1.71it/s] Train steps ... : 7%|▋ | 7369/100000 [2:01:04<15:01:39, 1.71it/s] Train steps ... : 7%|▋ | 7370/100000 [2:01:04<15:02:14, 1.71it/s] Train steps ... : 7%|▋ | 7371/100000 [2:01:05<15:01:54, 1.71it/s] Train steps ... : 7%|▋ | 7372/100000 [2:01:05<15:01:45, 1.71it/s] Train steps ... : 7%|▋ | 7373/100000 [2:01:06<15:01:57, 1.71it/s] Train steps ... : 7%|▋ | 7374/100000 [2:01:07<15:03:53, 1.71it/s] Train steps ... : 7%|▋ | 7375/100000 [2:01:07<15:04:33, 1.71it/s]Step... (7375 / 100000 | Loss: 0.9624816179275513, Learning Rate: 9.309045226130653e-05) Step... (7375 / 100000 | Loss: 1.934003472328186, Learning Rate: 9.309045226130653e-05) Train steps ... : 7%|▋ | 7375/100000 [2:01:07<15:04:33, 1.71it/s] Train steps ... : 7%|▋ | 7376/100000 [2:01:08<15:03:34, 1.71it/s] Train steps ... : 7%|▋ | 7377/100000 [2:01:08<15:02:37, 1.71it/s] Train steps ... : 7%|▋ | 7378/100000 [2:01:09<15:03:25, 1.71it/s] Train steps ... : 7%|▋ | 7379/100000 [2:01:09<15:03:52, 1.71it/s] Train steps ... : 7%|▋ | 7380/100000 [2:01:10<15:04:07, 1.71it/s] Train steps ... : 7%|▋ | 7381/100000 [2:01:11<15:02:46, 1.71it/s] Train steps ... : 7%|▋ | 7382/100000 [2:01:11<15:02:30, 1.71it/s] Train steps ... : 7%|▋ | 7383/100000 [2:01:12<15:02:23, 1.71it/s] Train steps ... : 7%|▋ | 7384/100000 [2:01:12<15:02:06, 1.71it/s] Train steps ... : 7%|▋ | 7385/100000 [2:01:13<15:01:07, 1.71it/s] Train steps ... : 7%|▋ | 7386/100000 [2:01:14<15:01:34, 1.71it/s] Train steps ... : 7%|▋ | 7387/100000 [2:01:14<15:01:37, 1.71it/s] Train steps ... : 7%|▋ | 7388/100000 [2:01:15<15:01:16, 1.71it/s] Train steps ... : 7%|▋ | 7389/100000 [2:01:15<15:02:36, 1.71it/s] Train steps ... : 7%|▋ | 7390/100000 [2:01:16<15:01:45, 1.71it/s] Train steps ... : 7%|▋ | 7391/100000 [2:01:16<15:02:07, 1.71it/s] Train steps ... : 7%|▋ | 7392/100000 [2:01:17<15:02:55, 1.71it/s] Train steps ... : 7%|▋ | 7393/100000 [2:01:18<15:01:55, 1.71it/s] Train steps ... : 7%|▋ | 7394/100000 [2:01:18<15:02:58, 1.71it/s] Train steps ... : 7%|▋ | 7395/100000 [2:01:19<15:02:08, 1.71it/s] Train steps ... : 7%|▋ | 7396/100000 [2:01:19<15:01:31, 1.71it/s] Train steps ... : 7%|▋ | 7397/100000 [2:01:20<15:01:37, 1.71it/s] Train steps ... : 7%|▋ | 7398/100000 [2:01:21<15:01:29, 1.71it/s] Train steps ... : 7%|▋ | 7399/100000 [2:01:21<15:02:41, 1.71it/s] Train steps ... : 7%|▋ | 7400/100000 [2:01:22<15:01:55, 1.71it/s]Step... (7400 / 100000 | Loss: 1.151871919631958, Learning Rate: 9.306532663316585e-05) Step... (7400 / 100000 | Loss: 1.705987811088562, Learning Rate: 9.306532663316585e-05) Train steps ... : 7%|▋ | 7400/100000 [2:01:22<15:01:55, 1.71it/s] Train steps ... : 7%|▋ | 7401/100000 [2:01:22<15:02:09, 1.71it/s] Train steps ... : 7%|▋ | 7402/100000 [2:01:23<15:02:47, 1.71it/s] Train steps ... : 7%|▋ | 7403/100000 [2:01:23<15:02:22, 1.71it/s] Train steps ... : 7%|▋ | 7404/100000 [2:01:24<15:01:52, 1.71it/s] Train steps ... : 7%|▋ | 7405/100000 [2:01:25<15:01:52, 1.71it/s] Train steps ... : 7%|▋ | 7406/100000 [2:01:25<15:01:51, 1.71it/s] Train steps ... : 7%|▋ | 7407/100000 [2:01:26<15:02:25, 1.71it/s] Train steps ... : 7%|▋ | 7408/100000 [2:01:26<15:03:18, 1.71it/s] Train steps ... : 7%|▋ | 7409/100000 [2:01:27<15:02:36, 1.71it/s] Train steps ... : 7%|▋ | 7410/100000 [2:01:28<15:02:23, 1.71it/s] Train steps ... : 7%|▋ | 7411/100000 [2:01:28<15:01:26, 1.71it/s] Train steps ... : 7%|▋ | 7412/100000 [2:01:29<15:02:38, 1.71it/s] Train steps ... : 7%|▋ | 7413/100000 [2:01:29<15:02:13, 1.71it/s] Train steps ... : 7%|▋ | 7414/100000 [2:01:30<15:02:07, 1.71it/s] Train steps ... : 7%|▋ | 7415/100000 [2:01:31<15:02:16, 1.71it/s] Train steps ... : 7%|▋ | 7416/100000 [2:01:31<15:02:09, 1.71it/s] Train steps ... : 7%|▋ | 7417/100000 [2:01:32<15:03:04, 1.71it/s] Train steps ... : 7%|▋ | 7418/100000 [2:01:32<15:03:37, 1.71it/s] Train steps ... : 7%|▋ | 7419/100000 [2:01:33<15:02:50, 1.71it/s] Train steps ... : 7%|▋ | 7420/100000 [2:01:33<15:04:27, 1.71it/s] Train steps ... : 7%|▋ | 7421/100000 [2:01:34<15:02:24, 1.71it/s] Train steps ... : 7%|▋ | 7422/100000 [2:01:35<15:03:07, 1.71it/s] Train steps ... : 7%|▋ | 7423/100000 [2:01:35<15:02:02, 1.71it/s] Train steps ... : 7%|▋ | 7424/100000 [2:01:36<15:03:59, 1.71it/s] Train steps ... : 7%|▋ | 7425/100000 [2:01:36<15:03:08, 1.71it/s]Step... (7425 / 100000 | Loss: 1.5189051628112793, Learning Rate: 9.304020100502513e-05) Step... (7425 / 100000 | Loss: 1.4089796543121338, Learning Rate: 9.304020100502513e-05) Train steps ... : 7%|▋ | 7425/100000 [2:01:37<15:03:08, 1.71it/s] Train steps ... : 7%|▋ | 7426/100000 [2:01:37<15:03:03, 1.71it/s] Train steps ... : 7%|▋ | 7427/100000 [2:01:38<15:03:00, 1.71it/s] Train steps ... : 7%|▋ | 7428/100000 [2:01:38<15:01:57, 1.71it/s] Train steps ... : 7%|▋ | 7429/100000 [2:01:39<15:02:59, 1.71it/s] Train steps ... : 7%|▋ | 7430/100000 [2:01:39<15:03:11, 1.71it/s] Train steps ... : 7%|▋ | 7431/100000 [2:01:40<15:03:08, 1.71it/s] Train steps ... : 7%|▋ | 7432/100000 [2:01:40<15:02:45, 1.71it/s] Train steps ... : 7%|▋ | 7433/100000 [2:01:41<15:05:00, 1.70it/s] Train steps ... : 7%|▋ | 7434/100000 [2:01:42<15:01:19, 1.71it/s] Train steps ... : 7%|▋ | 7435/100000 [2:01:42<15:00:58, 1.71it/s] Train steps ... : 7%|▋ | 7436/100000 [2:01:43<15:02:41, 1.71it/s] Train steps ... : 7%|▋ | 7437/100000 [2:01:43<15:01:11, 1.71it/s] Train steps ... : 7%|▋ | 7438/100000 [2:01:44<15:01:50, 1.71it/s] Train steps ... : 7%|▋ | 7439/100000 [2:01:45<15:01:49, 1.71it/s] Train steps ... : 7%|▋ | 7440/100000 [2:01:45<15:01:35, 1.71it/s] Train steps ... : 7%|▋ | 7441/100000 [2:01:46<15:02:11, 1.71it/s] Train steps ... : 7%|▋ | 7442/100000 [2:01:46<15:02:13, 1.71it/s] Train steps ... : 7%|▋ | 7443/100000 [2:01:47<15:07:07, 1.70it/s] Train steps ... : 7%|▋ | 7444/100000 [2:01:47<15:06:15, 1.70it/s] Train steps ... : 7%|▋ | 7445/100000 [2:01:48<15:05:06, 1.70it/s] Train steps ... : 7%|▋ | 7446/100000 [2:01:49<15:03:44, 1.71it/s] Train steps ... : 7%|▋ | 7447/100000 [2:01:49<15:03:03, 1.71it/s] Train steps ... : 7%|▋ | 7448/100000 [2:01:50<15:04:04, 1.71it/s] Train steps ... : 7%|▋ | 7449/100000 [2:01:50<15:02:52, 1.71it/s] Train steps ... : 7%|▋ | 7450/100000 [2:01:51<15:01:40, 1.71it/s]Step... (7450 / 100000 | Loss: 1.0072510242462158, Learning Rate: 9.301507537688442e-05) Step... (7450 / 100000 | Loss: 1.0094835758209229, Learning Rate: 9.301507537688442e-05) Train steps ... : 7%|▋ | 7450/100000 [2:01:51<15:01:40, 1.71it/s] Train steps ... : 7%|▋ | 7451/100000 [2:01:52<15:02:39, 1.71it/s] Train steps ... : 7%|▋ | 7452/100000 [2:01:52<15:01:52, 1.71it/s] Train steps ... : 7%|▋ | 7453/100000 [2:01:53<15:01:41, 1.71it/s] Train steps ... : 7%|▋ | 7454/100000 [2:01:53<15:01:18, 1.71it/s] Train steps ... : 7%|▋ | 7455/100000 [2:01:54<15:01:39, 1.71it/s] Train steps ... : 7%|▋ | 7456/100000 [2:01:54<15:02:29, 1.71it/s] Train steps ... : 7%|▋ | 7457/100000 [2:01:55<15:01:43, 1.71it/s] Train steps ... : 7%|▋ | 7458/100000 [2:01:56<15:03:56, 1.71it/s] Train steps ... : 7%|▋ | 7459/100000 [2:01:56<15:03:23, 1.71it/s] Train steps ... : 7%|▋ | 7460/100000 [2:01:57<15:02:02, 1.71it/s] Train steps ... : 7%|▋ | 7461/100000 [2:01:57<15:01:20, 1.71it/s] Train steps ... : 7%|▋ | 7462/100000 [2:01:58<15:01:07, 1.71it/s] Train steps ... : 7%|▋ | 7463/100000 [2:01:59<15:00:38, 1.71it/s] Train steps ... : 7%|▋ | 7464/100000 [2:01:59<15:00:47, 1.71it/s] Train steps ... : 7%|▋ | 7465/100000 [2:02:00<15:02:14, 1.71it/s] Train steps ... : 7%|▋ | 7466/100000 [2:02:00<15:02:07, 1.71it/s] Train steps ... : 7%|▋ | 7467/100000 [2:02:01<15:01:31, 1.71it/s] Train steps ... : 7%|▋ | 7468/100000 [2:02:02<15:03:33, 1.71it/s] Train steps ... : 7%|▋ | 7469/100000 [2:02:02<15:01:20, 1.71it/s] Train steps ... : 7%|▋ | 7470/100000 [2:02:03<15:01:47, 1.71it/s] Train steps ... : 7%|▋ | 7471/100000 [2:02:03<15:02:41, 1.71it/s] Train steps ... : 7%|▋ | 7472/100000 [2:02:04<15:02:05, 1.71it/s] Train steps ... : 7%|▋ | 7473/100000 [2:02:04<15:01:44, 1.71it/s] Train steps ... : 7%|▋ | 7474/100000 [2:02:05<15:02:48, 1.71it/s] Train steps ... : 7%|▋ | 7475/100000 [2:02:06<15:02:28, 1.71it/s]Step... (7475 / 100000 | Loss: 1.4692091941833496, Learning Rate: 9.298994974874372e-05) Step... (7475 / 100000 | Loss: 1.7260900735855103, Learning Rate: 9.298994974874372e-05) Train steps ... : 7%|▋ | 7475/100000 [2:02:06<15:02:28, 1.71it/s] Train steps ... : 7%|▋ | 7476/100000 [2:02:06<15:02:30, 1.71it/s] Train steps ... : 7%|▋ | 7477/100000 [2:02:07<15:04:33, 1.70it/s] Train steps ... : 7%|▋ | 7478/100000 [2:02:07<15:01:27, 1.71it/s] Train steps ... : 7%|▋ | 7479/100000 [2:02:08<15:01:29, 1.71it/s] Train steps ... : 7%|▋ | 7480/100000 [2:02:09<15:00:47, 1.71it/s] Train steps ... : 7%|▋ | 7481/100000 [2:02:09<15:01:46, 1.71it/s] Train steps ... : 7%|▋ | 7482/100000 [2:02:10<15:01:00, 1.71it/s] Train steps ... : 7%|▋ | 7483/100000 [2:02:10<15:02:08, 1.71it/s] Train steps ... : 7%|▋ | 7484/100000 [2:02:11<15:02:01, 1.71it/s] Train steps ... : 7%|▋ | 7485/100000 [2:02:11<15:01:25, 1.71it/s] Train steps ... : 7%|▋ | 7486/100000 [2:02:12<15:02:17, 1.71it/s] Train steps ... : 7%|▋ | 7487/100000 [2:02:13<15:01:19, 1.71it/s] Train steps ... : 7%|▋ | 7488/100000 [2:02:13<15:01:45, 1.71it/s] Train steps ... : 7%|▋ | 7489/100000 [2:02:14<15:02:15, 1.71it/s] Train steps ... : 7%|▋ | 7490/100000 [2:02:14<15:05:43, 1.70it/s] Train steps ... : 7%|▋ | 7491/100000 [2:02:15<15:03:55, 1.71it/s] Train steps ... : 7%|▋ | 7492/100000 [2:02:16<15:03:23, 1.71it/s] Train steps ... : 7%|▋ | 7493/100000 [2:02:16<15:02:13, 1.71it/s] Train steps ... : 7%|▋ | 7494/100000 [2:02:17<15:01:31, 1.71it/s] Train steps ... : 7%|▋ | 7495/100000 [2:02:17<15:01:52, 1.71it/s] Train steps ... : 7%|▋ | 7496/100000 [2:02:18<15:01:50, 1.71it/s] Train steps ... : 7%|▋ | 7497/100000 [2:02:18<15:01:34, 1.71it/s] Train steps ... : 7%|▋ | 7498/100000 [2:02:19<15:00:40, 1.71it/s] Train steps ... : 7%|▋ | 7499/100000 [2:02:20<15:00:33, 1.71it/s] Train steps ... : 8%|▊ | 7500/100000 [2:02:20<15:00:23, 1.71it/s]Step... (7500 / 100000 | Loss: 1.2990715503692627, Learning Rate: 9.296482412060302e-05) Step... (7500 / 100000 | Loss: 1.2092543840408325, Learning Rate: 9.296482412060302e-05) Train steps ... : 8%|▊ | 7500/100000 [2:02:21<15:00:23, 1.71it/s] Train steps ... : 8%|▊ | 7501/100000 [2:02:21<15:00:48, 1.71it/s] Train steps ... : 8%|▊ | 7502/100000 [2:02:21<15:00:15, 1.71it/s] Train steps ... : 8%|▊ | 7503/100000 [2:02:22<15:01:41, 1.71it/s] Train steps ... : 8%|▊ | 7504/100000 [2:02:23<15:00:06, 1.71it/s] Train steps ... : 8%|▊ | 7505/100000 [2:02:23<15:01:08, 1.71it/s] Train steps ... : 8%|▊ | 7506/100000 [2:02:24<15:00:43, 1.71it/s] Train steps ... : 8%|▊ | 7507/100000 [2:02:24<15:01:37, 1.71it/s] Train steps ... : 8%|▊ | 7508/100000 [2:02:25<15:02:09, 1.71it/s] Train steps ... : 8%|▊ | 7509/100000 [2:02:25<15:02:57, 1.71it/s] Train steps ... : 8%|▊ | 7510/100000 [2:02:26<15:02:30, 1.71it/s] Train steps ... : 8%|▊ | 7511/100000 [2:02:27<15:06:00, 1.70it/s] Train steps ... : 8%|▊ | 7512/100000 [2:02:27<15:01:27, 1.71it/s] Train steps ... : 8%|▊ | 7513/100000 [2:02:28<15:01:35, 1.71it/s] Train steps ... : 8%|▊ | 7514/100000 [2:02:28<15:01:52, 1.71it/s] Train steps ... : 8%|▊ | 7515/100000 [2:02:29<15:01:22, 1.71it/s] Train steps ... : 8%|▊ | 7516/100000 [2:02:30<15:01:26, 1.71it/s] Train steps ... : 8%|▊ | 7517/100000 [2:02:30<15:01:18, 1.71it/s] Train steps ... : 8%|▊ | 7518/100000 [2:02:31<15:01:04, 1.71it/s] Train steps ... : 8%|▊ | 7519/100000 [2:02:31<15:00:51, 1.71it/s] Train steps ... : 8%|▊ | 7520/100000 [2:02:32<15:01:23, 1.71it/s] Train steps ... : 8%|▊ | 7521/100000 [2:02:33<15:02:09, 1.71it/s] Train steps ... : 8%|▊ | 7522/100000 [2:02:33<15:01:08, 1.71it/s] Train steps ... : 8%|▊ | 7523/100000 [2:02:34<15:02:41, 1.71it/s] Train steps ... : 8%|▊ | 7524/100000 [2:02:34<15:03:58, 1.70it/s] Train steps ... : 8%|▊ | 7525/100000 [2:02:35<15:03:27, 1.71it/s]Step... (7525 / 100000 | Loss: 1.687319040298462, Learning Rate: 9.293969849246231e-05) Step... (7525 / 100000 | Loss: 1.5347232818603516, Learning Rate: 9.293969849246231e-05) Train steps ... : 8%|▊ | 7525/100000 [2:02:35<15:03:27, 1.71it/s] Train steps ... : 8%|▊ | 7526/100000 [2:02:35<15:03:26, 1.71it/s] Train steps ... : 8%|▊ | 7527/100000 [2:02:36<15:02:51, 1.71it/s] Train steps ... : 8%|▊ | 7528/100000 [2:02:37<15:02:04, 1.71it/s] Train steps ... : 8%|▊ | 7529/100000 [2:02:37<15:02:10, 1.71it/s] Train steps ... : 8%|▊ | 7530/100000 [2:02:38<15:01:05, 1.71it/s] Train steps ... : 8%|▊ | 7531/100000 [2:02:38<15:02:46, 1.71it/s] Train steps ... : 8%|▊ | 7532/100000 [2:02:39<15:01:42, 1.71it/s] Train steps ... : 8%|▊ | 7533/100000 [2:02:40<15:01:15, 1.71it/s] Train steps ... : 8%|▊ | 7534/100000 [2:02:40<15:01:41, 1.71it/s] Train steps ... : 8%|▊ | 7535/100000 [2:02:41<15:02:16, 1.71it/s] Train steps ... : 8%|▊ | 7536/100000 [2:02:41<15:01:59, 1.71it/s] Train steps ... : 8%|▊ | 7537/100000 [2:02:42<15:02:24, 1.71it/s] Train steps ... : 8%|▊ | 7538/100000 [2:02:42<15:02:13, 1.71it/s] Train steps ... : 8%|▊ | 7539/100000 [2:02:43<15:02:01, 1.71it/s] Train steps ... : 8%|▊ | 7540/100000 [2:02:44<15:02:23, 1.71it/s] Train steps ... : 8%|▊ | 7541/100000 [2:02:44<14:59:51, 1.71it/s] Train steps ... : 8%|▊ | 7542/100000 [2:02:45<14:59:40, 1.71it/s] Train steps ... : 8%|▊ | 7543/100000 [2:02:45<14:59:57, 1.71it/s] Train steps ... : 8%|▊ | 7544/100000 [2:02:46<14:59:45, 1.71it/s] Train steps ... : 8%|▊ | 7545/100000 [2:02:47<15:00:13, 1.71it/s] Train steps ... : 8%|▊ | 7546/100000 [2:02:47<14:59:31, 1.71it/s] Train steps ... : 8%|▊ | 7547/100000 [2:02:48<15:00:58, 1.71it/s] Train steps ... : 8%|▊ | 7548/100000 [2:02:48<15:00:12, 1.71it/s] Train steps ... : 8%|▊ | 7549/100000 [2:02:49<15:00:16, 1.71it/s] Train steps ... : 8%|▊ | 7550/100000 [2:02:49<15:00:27, 1.71it/s]Step... (7550 / 100000 | Loss: 1.465956449508667, Learning Rate: 9.291457286432161e-05) Step... (7550 / 100000 | Loss: 1.4158415794372559, Learning Rate: 9.291457286432161e-05) Train steps ... : 8%|▊ | 7550/100000 [2:02:50<15:00:27, 1.71it/s] Train steps ... : 8%|▊ | 7551/100000 [2:02:50<15:01:13, 1.71it/s] Train steps ... : 8%|▊ | 7552/100000 [2:02:51<15:00:28, 1.71it/s] Train steps ... : 8%|▊ | 7553/100000 [2:02:51<15:01:56, 1.71it/s] Train steps ... : 8%|▊ | 7554/100000 [2:02:52<15:00:41, 1.71it/s] Train steps ... : 8%|▊ | 7555/100000 [2:02:52<15:00:54, 1.71it/s] Train steps ... : 8%|▊ | 7556/100000 [2:02:53<15:01:59, 1.71it/s] Train steps ... : 8%|▊ | 7557/100000 [2:02:54<15:02:44, 1.71it/s] Train steps ... : 8%|▊ | 7558/100000 [2:02:54<15:03:38, 1.70it/s] Train steps ... : 8%|▊ | 7559/100000 [2:02:55<15:02:47, 1.71it/s] Train steps ... : 8%|▊ | 7560/100000 [2:02:55<15:02:13, 1.71it/s] Train steps ... : 8%|▊ | 7561/100000 [2:02:56<15:02:04, 1.71it/s] Train steps ... : 8%|▊ | 7562/100000 [2:02:57<15:00:45, 1.71it/s] Train steps ... : 8%|▊ | 7563/100000 [2:02:57<15:01:15, 1.71it/s] Train steps ... : 8%|▊ | 7564/100000 [2:02:58<15:00:22, 1.71it/s] Train steps ... : 8%|▊ | 7565/100000 [2:02:58<15:01:13, 1.71it/s] Train steps ... : 8%|▊ | 7566/100000 [2:02:59<15:01:00, 1.71it/s] Train steps ... : 8%|▊ | 7567/100000 [2:02:59<15:00:30, 1.71it/s] Train steps ... : 8%|▊ | 7568/100000 [2:03:00<15:00:39, 1.71it/s] Train steps ... : 8%|▊ | 7569/100000 [2:03:01<15:00:16, 1.71it/s] Train steps ... : 8%|▊ | 7570/100000 [2:03:01<15:00:32, 1.71it/s] Train steps ... : 8%|▊ | 7571/100000 [2:03:02<15:01:43, 1.71it/s] Train steps ... : 8%|▊ | 7572/100000 [2:03:02<15:01:56, 1.71it/s] Train steps ... : 8%|▊ | 7573/100000 [2:03:03<15:00:59, 1.71it/s] Train steps ... : 8%|▊ | 7574/100000 [2:03:04<15:01:59, 1.71it/s] Train steps ... : 8%|▊ | 7575/100000 [2:03:04<15:00:01, 1.71it/s]Step... (7575 / 100000 | Loss: 1.432108998298645, Learning Rate: 9.288944723618091e-05) Step... (7575 / 100000 | Loss: 1.0413819551467896, Learning Rate: 9.288944723618091e-05) Train steps ... : 8%|▊ | 7575/100000 [2:03:04<15:00:01, 1.71it/s] Train steps ... : 8%|▊ | 7576/100000 [2:03:05<15:01:02, 1.71it/s] Train steps ... : 8%|▊ | 7577/100000 [2:03:05<15:02:22, 1.71it/s] Train steps ... : 8%|▊ | 7578/100000 [2:03:06<15:01:29, 1.71it/s] Train steps ... : 8%|▊ | 7579/100000 [2:03:06<15:00:52, 1.71it/s] Train steps ... : 8%|▊ | 7580/100000 [2:03:07<15:00:13, 1.71it/s] Train steps ... : 8%|▊ | 7581/100000 [2:03:08<15:01:51, 1.71it/s] Train steps ... : 8%|▊ | 7582/100000 [2:03:08<15:01:55, 1.71it/s] Train steps ... : 8%|▊ | 7583/100000 [2:03:09<15:02:12, 1.71it/s] Train steps ... : 8%|▊ | 7584/100000 [2:03:09<15:02:27, 1.71it/s] Train steps ... : 8%|▊ | 7585/100000 [2:03:10<15:01:37, 1.71it/s] Train steps ... : 8%|▊ | 7586/100000 [2:03:11<15:02:10, 1.71it/s] Train steps ... : 8%|▊ | 7587/100000 [2:03:11<15:01:29, 1.71it/s] Train steps ... : 8%|▊ | 7588/100000 [2:03:12<15:01:22, 1.71it/s] Train steps ... : 8%|▊ | 7589/100000 [2:03:12<15:01:02, 1.71it/s] Train steps ... : 8%|▊ | 7590/100000 [2:03:13<15:02:50, 1.71it/s] Train steps ... : 8%|▊ | 7591/100000 [2:03:13<15:00:50, 1.71it/s] Train steps ... : 8%|▊ | 7592/100000 [2:03:14<15:00:32, 1.71it/s] Train steps ... : 8%|▊ | 7593/100000 [2:03:15<15:00:53, 1.71it/s] Train steps ... : 8%|▊ | 7594/100000 [2:03:15<15:02:26, 1.71it/s] Train steps ... : 8%|▊ | 7595/100000 [2:03:16<15:01:40, 1.71it/s] Train steps ... : 8%|▊ | 7596/100000 [2:03:16<15:01:04, 1.71it/s] Train steps ... : 8%|▊ | 7597/100000 [2:03:17<15:02:27, 1.71it/s] Train steps ... : 8%|▊ | 7598/100000 [2:03:18<15:02:18, 1.71it/s] Train steps ... : 8%|▊ | 7599/100000 [2:03:18<15:01:06, 1.71it/s] Train steps ... : 8%|▊ | 7600/100000 [2:03:19<15:01:14, 1.71it/s]Step... (7600 / 100000 | Loss: 1.2420250177383423, Learning Rate: 9.28643216080402e-05) Step... (7600 / 100000 | Loss: 1.2371224164962769, Learning Rate: 9.28643216080402e-05) Train steps ... : 8%|▊ | 7600/100000 [2:03:19<15:01:14, 1.71it/s] Train steps ... : 8%|▊ | 7601/100000 [2:03:19<15:01:29, 1.71it/s] Train steps ... : 8%|▊ | 7602/100000 [2:03:20<15:00:47, 1.71it/s] Train steps ... : 8%|▊ | 7603/100000 [2:03:20<15:00:12, 1.71it/s] Train steps ... : 8%|▊ | 7604/100000 [2:03:21<15:00:31, 1.71it/s] Train steps ... : 8%|▊ | 7605/100000 [2:03:22<15:00:49, 1.71it/s] Train steps ... : 8%|▊ | 7606/100000 [2:03:22<15:01:37, 1.71it/s] Train steps ... : 8%|▊ | 7607/100000 [2:03:23<15:00:23, 1.71it/s] Train steps ... : 8%|▊ | 7608/100000 [2:03:23<15:00:05, 1.71it/s] Train steps ... : 8%|▊ | 7609/100000 [2:03:24<14:59:32, 1.71it/s] Train steps ... : 8%|▊ | 7610/100000 [2:03:25<15:00:13, 1.71it/s] Train steps ... : 8%|▊ | 7611/100000 [2:03:25<15:00:27, 1.71it/s] Train steps ... : 8%|▊ | 7612/100000 [2:03:26<15:00:25, 1.71it/s] Train steps ... : 8%|▊ | 7613/100000 [2:03:26<15:00:32, 1.71it/s] Train steps ... : 8%|▊ | 7614/100000 [2:03:27<15:00:01, 1.71it/s] Train steps ... : 8%|▊ | 7615/100000 [2:03:28<14:59:58, 1.71it/s] Train steps ... : 8%|▊ | 7616/100000 [2:03:28<15:00:27, 1.71it/s] Train steps ... : 8%|▊ | 7617/100000 [2:03:29<14:59:55, 1.71it/s] Train steps ... : 8%|▊ | 7618/100000 [2:03:29<15:00:18, 1.71it/s] Train steps ... : 8%|▊ | 7619/100000 [2:03:30<14:59:38, 1.71it/s] Train steps ... : 8%|▊ | 7620/100000 [2:03:30<15:00:18, 1.71it/s] Train steps ... : 8%|▊ | 7621/100000 [2:03:31<15:01:02, 1.71it/s] Train steps ... : 8%|▊ | 7622/100000 [2:03:32<15:00:27, 1.71it/s] Train steps ... : 8%|▊ | 7623/100000 [2:03:32<15:00:49, 1.71it/s] Train steps ... : 8%|▊ | 7624/100000 [2:03:33<14:59:40, 1.71it/s] Train steps ... : 8%|▊ | 7625/100000 [2:03:33<14:59:42, 1.71it/s]Step... (7625 / 100000 | Loss: 1.3230059146881104, Learning Rate: 9.28391959798995e-05) Step... (7625 / 100000 | Loss: 1.9822694063186646, Learning Rate: 9.28391959798995e-05) Train steps ... : 8%|▊ | 7625/100000 [2:03:34<14:59:42, 1.71it/s] Train steps ... : 8%|▊ | 7626/100000 [2:03:34<14:59:53, 1.71it/s] Train steps ... : 8%|▊ | 7627/100000 [2:03:35<15:00:05, 1.71it/s] Train steps ... : 8%|▊ | 7628/100000 [2:03:35<14:59:56, 1.71it/s] Train steps ... : 8%|▊ | 7629/100000 [2:03:36<14:59:37, 1.71it/s] Train steps ... : 8%|▊ | 7630/100000 [2:03:36<14:58:52, 1.71it/s] Train steps ... : 8%|▊ | 7631/100000 [2:03:37<14:59:34, 1.71it/s] Train steps ... : 8%|▊ | 7632/100000 [2:03:37<15:00:27, 1.71it/s] Train steps ... : 8%|▊ | 7633/100000 [2:03:38<15:00:01, 1.71it/s] Train steps ... : 8%|▊ | 7634/100000 [2:03:39<14:59:38, 1.71it/s] Train steps ... : 8%|▊ | 7635/100000 [2:03:39<15:00:24, 1.71it/s] Train steps ... : 8%|▊ | 7636/100000 [2:03:40<15:00:08, 1.71it/s] Train steps ... : 8%|▊ | 7637/100000 [2:03:40<15:00:17, 1.71it/s] Train steps ... : 8%|▊ | 7638/100000 [2:03:41<14:59:35, 1.71it/s] Train steps ... : 8%|▊ | 7639/100000 [2:03:42<14:59:57, 1.71it/s] Train steps ... : 8%|▊ | 7640/100000 [2:03:42<15:00:07, 1.71it/s] Train steps ... : 8%|▊ | 7641/100000 [2:03:43<14:59:42, 1.71it/s] Train steps ... : 8%|▊ | 7642/100000 [2:03:43<14:58:52, 1.71it/s] Train steps ... : 8%|▊ | 7643/100000 [2:03:44<14:59:25, 1.71it/s] Train steps ... : 8%|▊ | 7644/100000 [2:03:44<14:59:40, 1.71it/s] Train steps ... : 8%|▊ | 7645/100000 [2:03:45<14:59:48, 1.71it/s] Train steps ... : 8%|▊ | 7646/100000 [2:03:46<15:00:11, 1.71it/s] Train steps ... : 8%|▊ | 7647/100000 [2:03:46<14:59:45, 1.71it/s] Train steps ... : 8%|▊ | 7648/100000 [2:03:47<14:59:52, 1.71it/s] Train steps ... : 8%|▊ | 7649/100000 [2:03:47<14:59:44, 1.71it/s] Train steps ... : 8%|▊ | 7650/100000 [2:03:48<14:59:30, 1.71it/s]Step... (7650 / 100000 | Loss: 1.0052478313446045, Learning Rate: 9.28140703517588e-05) Step... (7650 / 100000 | Loss: 1.3228888511657715, Learning Rate: 9.28140703517588e-05) Train steps ... : 8%|▊ | 7650/100000 [2:03:48<14:59:30, 1.71it/s] Train steps ... : 8%|▊ | 7651/100000 [2:03:49<15:00:29, 1.71it/s] Train steps ... : 8%|▊ | 7652/100000 [2:03:49<15:01:05, 1.71it/s] Train steps ... : 8%|▊ | 7653/100000 [2:03:50<15:00:59, 1.71it/s] Train steps ... : 8%|▊ | 7654/100000 [2:03:50<15:00:27, 1.71it/s] Train steps ... : 8%|▊ | 7655/100000 [2:03:51<15:00:12, 1.71it/s] Train steps ... : 8%|▊ | 7656/100000 [2:03:51<15:00:02, 1.71it/s] Train steps ... : 8%|▊ | 7657/100000 [2:03:52<14:59:27, 1.71it/s] Train steps ... : 8%|▊ | 7658/100000 [2:03:53<14:59:54, 1.71it/s] Train steps ... : 8%|▊ | 7659/100000 [2:03:53<14:59:26, 1.71it/s] Train steps ... : 8%|▊ | 7660/100000 [2:03:54<14:59:23, 1.71it/s] Train steps ... : 8%|▊ | 7661/100000 [2:03:54<15:02:24, 1.71it/s] Train steps ... : 8%|▊ | 7662/100000 [2:03:55<14:59:43, 1.71it/s] Train steps ... : 8%|▊ | 7663/100000 [2:03:56<15:02:12, 1.71it/s] Train steps ... : 8%|▊ | 7664/100000 [2:03:56<15:00:15, 1.71it/s] Train steps ... : 8%|▊ | 7665/100000 [2:03:57<14:59:57, 1.71it/s] Train steps ... : 8%|▊ | 7666/100000 [2:03:57<15:00:54, 1.71it/s] Train steps ... : 8%|▊ | 7667/100000 [2:03:58<15:00:42, 1.71it/s] Train steps ... : 8%|▊ | 7668/100000 [2:03:59<14:59:54, 1.71it/s] Train steps ... : 8%|▊ | 7669/100000 [2:03:59<15:00:08, 1.71it/s] Train steps ... : 8%|▊ | 7670/100000 [2:04:00<15:00:48, 1.71it/s] Train steps ... : 8%|▊ | 7671/100000 [2:04:00<15:00:08, 1.71it/s] Train steps ... : 8%|▊ | 7672/100000 [2:04:01<14:59:55, 1.71it/s] Train steps ... : 8%|▊ | 7673/100000 [2:04:01<14:59:03, 1.71it/s] Train steps ... : 8%|▊ | 7674/100000 [2:04:02<14:59:38, 1.71it/s] Train steps ... : 8%|▊ | 7675/100000 [2:04:03<14:59:28, 1.71it/s]Step... (7675 / 100000 | Loss: 1.1947462558746338, Learning Rate: 9.27889447236181e-05) Step... (7675 / 100000 | Loss: 1.5263198614120483, Learning Rate: 9.27889447236181e-05) Train steps ... : 8%|▊ | 7675/100000 [2:04:03<14:59:28, 1.71it/s] Train steps ... : 8%|▊ | 7676/100000 [2:04:03<15:00:04, 1.71it/s] Train steps ... : 8%|▊ | 7677/100000 [2:04:04<15:01:00, 1.71it/s] Train steps ... : 8%|▊ | 7678/100000 [2:04:04<15:03:05, 1.70it/s] Train steps ... : 8%|▊ | 7679/100000 [2:04:05<15:00:58, 1.71it/s] Train steps ... : 8%|▊ | 7680/100000 [2:04:06<15:00:12, 1.71it/s] Train steps ... : 8%|▊ | 7681/100000 [2:04:06<14:59:43, 1.71it/s] Train steps ... : 8%|▊ | 7682/100000 [2:04:07<14:59:52, 1.71it/s] Train steps ... : 8%|▊ | 7683/100000 [2:04:07<14:59:14, 1.71it/s] Train steps ... : 8%|▊ | 7684/100000 [2:04:08<14:59:57, 1.71it/s] Train steps ... : 8%|▊ | 7685/100000 [2:04:08<15:00:18, 1.71it/s] Train steps ... : 8%|▊ | 7686/100000 [2:04:09<15:00:05, 1.71it/s] Train steps ... : 8%|▊ | 7687/100000 [2:04:10<14:59:21, 1.71it/s] Train steps ... : 8%|▊ | 7688/100000 [2:04:10<14:59:06, 1.71it/s] Train steps ... : 8%|▊ | 7689/100000 [2:04:11<14:59:12, 1.71it/s] Train steps ... : 8%|▊ | 7690/100000 [2:04:11<14:59:14, 1.71it/s] Train steps ... : 8%|▊ | 7691/100000 [2:04:12<15:00:19, 1.71it/s] Train steps ... : 8%|▊ | 7692/100000 [2:04:13<15:02:44, 1.70it/s] Train steps ... : 8%|▊ | 7693/100000 [2:04:13<15:01:56, 1.71it/s] Train steps ... : 8%|▊ | 7694/100000 [2:04:14<15:02:05, 1.71it/s] Train steps ... : 8%|▊ | 7695/100000 [2:04:14<15:00:23, 1.71it/s] Train steps ... : 8%|▊ | 7696/100000 [2:04:15<14:59:58, 1.71it/s] Train steps ... : 8%|▊ | 7697/100000 [2:04:15<15:00:22, 1.71it/s] Train steps ... : 8%|▊ | 7698/100000 [2:04:16<14:59:16, 1.71it/s] Train steps ... : 8%|▊ | 7699/100000 [2:04:17<14:59:28, 1.71it/s] Train steps ... : 8%|▊ | 7700/100000 [2:04:17<14:59:22, 1.71it/s]Step... (7700 / 100000 | Loss: 1.4722825288772583, Learning Rate: 9.276381909547739e-05) Step... (7700 / 100000 | Loss: 1.9252409934997559, Learning Rate: 9.276381909547739e-05) Train steps ... : 8%|▊ | 7700/100000 [2:04:18<14:59:22, 1.71it/s] Train steps ... : 8%|▊ | 7701/100000 [2:04:18<14:59:12, 1.71it/s] Train steps ... : 8%|▊ | 7702/100000 [2:04:18<14:59:16, 1.71it/s] Train steps ... : 8%|▊ | 7703/100000 [2:04:19<14:58:25, 1.71it/s] Train steps ... : 8%|▊ | 7704/100000 [2:04:20<14:58:26, 1.71it/s] Train steps ... : 8%|▊ | 7705/100000 [2:04:20<14:57:59, 1.71it/s] Train steps ... : 8%|▊ | 7706/100000 [2:04:21<14:59:04, 1.71it/s] Train steps ... : 8%|▊ | 7707/100000 [2:04:21<14:59:59, 1.71it/s] Train steps ... : 8%|▊ | 7708/100000 [2:04:22<15:00:34, 1.71it/s] Train steps ... : 8%|▊ | 7709/100000 [2:04:22<14:59:27, 1.71it/s] Train steps ... : 8%|▊ | 7710/100000 [2:04:23<15:00:32, 1.71it/s] Train steps ... : 8%|▊ | 7711/100000 [2:04:24<15:00:33, 1.71it/s] Train steps ... : 8%|▊ | 7712/100000 [2:04:24<15:01:05, 1.71it/s] Train steps ... : 8%|▊ | 7713/100000 [2:04:25<14:59:48, 1.71it/s] Train steps ... : 8%|▊ | 7714/100000 [2:04:25<15:00:12, 1.71it/s] Train steps ... : 8%|▊ | 7715/100000 [2:04:26<15:00:18, 1.71it/s] Train steps ... : 8%|▊ | 7716/100000 [2:04:27<14:59:15, 1.71it/s] Train steps ... : 8%|▊ | 7717/100000 [2:04:27<15:00:10, 1.71it/s] Train steps ... : 8%|▊ | 7718/100000 [2:04:28<15:01:13, 1.71it/s] Train steps ... : 8%|▊ | 7719/100000 [2:04:28<15:00:31, 1.71it/s] Train steps ... : 8%|▊ | 7720/100000 [2:04:29<14:59:45, 1.71it/s] Train steps ... : 8%|▊ | 7721/100000 [2:04:30<15:01:31, 1.71it/s] Train steps ... : 8%|▊ | 7722/100000 [2:04:30<15:00:11, 1.71it/s] Train steps ... : 8%|▊ | 7723/100000 [2:04:31<14:59:45, 1.71it/s] Train steps ... : 8%|▊ | 7724/100000 [2:04:31<14:59:10, 1.71it/s] Train steps ... : 8%|▊ | 7725/100000 [2:04:32<14:59:04, 1.71it/s]Step... (7725 / 100000 | Loss: 1.4318516254425049, Learning Rate: 9.273869346733669e-05) Step... (7725 / 100000 | Loss: 1.2045918703079224, Learning Rate: 9.273869346733669e-05) Train steps ... : 8%|▊ | 7725/100000 [2:04:32<14:59:04, 1.71it/s] Train steps ... : 8%|▊ | 7726/100000 [2:04:32<14:59:30, 1.71it/s] Train steps ... : 8%|▊ | 7727/100000 [2:04:33<14:59:00, 1.71it/s] Train steps ... : 8%|▊ | 7728/100000 [2:04:34<14:58:46, 1.71it/s] Train steps ... : 8%|▊ | 7729/100000 [2:04:34<14:58:35, 1.71it/s] Train steps ... : 8%|▊ | 7730/100000 [2:04:35<14:58:27, 1.71it/s] Train steps ... : 8%|▊ | 7731/100000 [2:04:35<14:59:30, 1.71it/s] Train steps ... : 8%|▊ | 7732/100000 [2:04:36<14:58:58, 1.71it/s] Train steps ... : 8%|▊ | 7733/100000 [2:04:37<14:58:13, 1.71it/s] Train steps ... : 8%|▊ | 7734/100000 [2:04:37<14:58:25, 1.71it/s] Train steps ... : 8%|▊ | 7735/100000 [2:04:38<14:58:26, 1.71it/s] Train steps ... : 8%|▊ | 7736/100000 [2:04:38<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 7737/100000 [2:04:39<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 7738/100000 [2:04:39<14:58:06, 1.71it/s] Train steps ... : 8%|▊ | 7739/100000 [2:04:40<14:58:17, 1.71it/s] Train steps ... : 8%|▊ | 7740/100000 [2:04:41<14:59:49, 1.71it/s] Train steps ... : 8%|▊ | 7741/100000 [2:04:41<15:00:19, 1.71it/s] Train steps ... : 8%|▊ | 7742/100000 [2:04:42<14:59:43, 1.71it/s] Train steps ... : 8%|▊ | 7743/100000 [2:04:42<15:00:30, 1.71it/s] Train steps ... : 8%|▊ | 7744/100000 [2:04:43<14:59:33, 1.71it/s] Train steps ... : 8%|▊ | 7745/100000 [2:04:44<14:59:21, 1.71it/s] Train steps ... : 8%|▊ | 7746/100000 [2:04:44<14:58:25, 1.71it/s] Train steps ... : 8%|▊ | 7747/100000 [2:04:45<14:59:14, 1.71it/s] Train steps ... : 8%|▊ | 7748/100000 [2:04:45<14:59:34, 1.71it/s] Train steps ... : 8%|▊ | 7749/100000 [2:04:46<14:58:19, 1.71it/s] Train steps ... : 8%|▊ | 7750/100000 [2:04:46<14:58:50, 1.71it/s]Step... (7750 / 100000 | Loss: 1.1318047046661377, Learning Rate: 9.271356783919598e-05) Step... (7750 / 100000 | Loss: 1.6079678535461426, Learning Rate: 9.271356783919598e-05) Train steps ... : 8%|▊ | 7750/100000 [2:04:47<14:58:50, 1.71it/s] Train steps ... : 8%|▊ | 7751/100000 [2:04:47<15:00:26, 1.71it/s] Train steps ... : 8%|▊ | 7752/100000 [2:04:48<14:59:19, 1.71it/s] Train steps ... : 8%|▊ | 7753/100000 [2:04:48<14:58:36, 1.71it/s] Train steps ... : 8%|▊ | 7754/100000 [2:04:49<14:58:42, 1.71it/s] Train steps ... : 8%|▊ | 7755/100000 [2:04:49<14:58:44, 1.71it/s] Train steps ... : 8%|▊ | 7756/100000 [2:04:50<15:00:09, 1.71it/s] Train steps ... : 8%|▊ | 7757/100000 [2:04:51<14:59:05, 1.71it/s] Train steps ... : 8%|▊ | 7758/100000 [2:04:51<14:58:57, 1.71it/s] Train steps ... : 8%|▊ | 7759/100000 [2:04:52<14:58:20, 1.71it/s] Train steps ... : 8%|▊ | 7760/100000 [2:04:52<14:58:06, 1.71it/s] Train steps ... : 8%|▊ | 7761/100000 [2:04:53<14:57:56, 1.71it/s] Train steps ... : 8%|▊ | 7762/100000 [2:04:53<14:58:38, 1.71it/s] Train steps ... : 8%|▊ | 7763/100000 [2:04:54<14:59:20, 1.71it/s] Train steps ... : 8%|▊ | 7764/100000 [2:04:55<15:01:27, 1.71it/s] Train steps ... : 8%|▊ | 7765/100000 [2:04:55<15:01:24, 1.71it/s] Train steps ... : 8%|▊ | 7766/100000 [2:04:56<15:00:38, 1.71it/s] Train steps ... : 8%|▊ | 7767/100000 [2:04:56<14:59:05, 1.71it/s] Train steps ... : 8%|▊ | 7768/100000 [2:04:57<14:58:59, 1.71it/s] Train steps ... : 8%|▊ | 7769/100000 [2:04:58<14:58:24, 1.71it/s] Train steps ... : 8%|▊ | 7770/100000 [2:04:58<14:59:49, 1.71it/s] Train steps ... : 8%|▊ | 7771/100000 [2:04:59<14:58:45, 1.71it/s] Train steps ... : 8%|▊ | 7772/100000 [2:04:59<14:58:20, 1.71it/s] Train steps ... : 8%|▊ | 7773/100000 [2:05:00<14:58:39, 1.71it/s] Train steps ... : 8%|▊ | 7774/100000 [2:05:01<14:58:12, 1.71it/s] Train steps ... : 8%|▊ | 7775/100000 [2:05:01<14:57:47, 1.71it/s]Step... (7775 / 100000 | Loss: 1.2935298681259155, Learning Rate: 9.268844221105528e-05) Step... (7775 / 100000 | Loss: 1.6063528060913086, Learning Rate: 9.268844221105528e-05) Train steps ... : 8%|▊ | 7775/100000 [2:05:01<14:57:47, 1.71it/s] Train steps ... : 8%|▊ | 7776/100000 [2:05:02<14:58:39, 1.71it/s] Train steps ... : 8%|▊ | 7777/100000 [2:05:02<14:58:13, 1.71it/s] Train steps ... : 8%|▊ | 7778/100000 [2:05:03<14:58:47, 1.71it/s] Train steps ... : 8%|▊ | 7779/100000 [2:05:03<14:58:10, 1.71it/s] Train steps ... : 8%|▊ | 7780/100000 [2:05:04<14:58:54, 1.71it/s] Train steps ... : 8%|▊ | 7781/100000 [2:05:05<14:59:54, 1.71it/s] Train steps ... : 8%|▊ | 7782/100000 [2:05:05<14:58:52, 1.71it/s] Train steps ... : 8%|▊ | 7783/100000 [2:05:06<14:58:26, 1.71it/s] Train steps ... : 8%|▊ | 7784/100000 [2:05:06<14:59:15, 1.71it/s] Train steps ... : 8%|▊ | 7785/100000 [2:05:07<14:58:11, 1.71it/s] Train steps ... : 8%|▊ | 7786/100000 [2:05:08<14:57:30, 1.71it/s] Train steps ... : 8%|▊ | 7787/100000 [2:05:08<14:57:16, 1.71it/s] Train steps ... : 8%|▊ | 7788/100000 [2:05:09<14:58:20, 1.71it/s] Train steps ... : 8%|▊ | 7789/100000 [2:05:09<14:59:41, 1.71it/s] Train steps ... : 8%|▊ | 7790/100000 [2:05:10<14:58:49, 1.71it/s] Train steps ... : 8%|▊ | 7791/100000 [2:05:10<14:58:44, 1.71it/s] Train steps ... : 8%|▊ | 7792/100000 [2:05:11<14:58:09, 1.71it/s] Train steps ... : 8%|▊ | 7793/100000 [2:05:12<14:57:06, 1.71it/s] Train steps ... : 8%|▊ | 7794/100000 [2:05:12<14:57:02, 1.71it/s] Train steps ... : 8%|▊ | 7795/100000 [2:05:13<14:58:08, 1.71it/s] Train steps ... : 8%|▊ | 7796/100000 [2:05:13<14:59:11, 1.71it/s] Train steps ... : 8%|▊ | 7797/100000 [2:05:14<14:58:06, 1.71it/s] Train steps ... : 8%|▊ | 7798/100000 [2:05:15<14:59:11, 1.71it/s] Train steps ... : 8%|▊ | 7799/100000 [2:05:15<14:58:38, 1.71it/s] Train steps ... : 8%|▊ | 7800/100000 [2:05:16<14:59:11, 1.71it/s]Step... (7800 / 100000 | Loss: 1.0301849842071533, Learning Rate: 9.266331658291458e-05) Step... (7800 / 100000 | Loss: 1.484176754951477, Learning Rate: 9.266331658291458e-05) Train steps ... : 8%|▊ | 7800/100000 [2:05:16<14:59:11, 1.71it/s] Train steps ... : 8%|▊ | 7801/100000 [2:05:16<14:59:03, 1.71it/s] Train steps ... : 8%|▊ | 7802/100000 [2:05:17<15:00:08, 1.71it/s] Train steps ... : 8%|▊ | 7803/100000 [2:05:17<14:59:08, 1.71it/s] Train steps ... : 8%|▊ | 7804/100000 [2:05:18<14:58:41, 1.71it/s] Train steps ... : 8%|▊ | 7805/100000 [2:05:19<14:57:50, 1.71it/s] Train steps ... : 8%|▊ | 7806/100000 [2:05:19<14:58:14, 1.71it/s] Train steps ... : 8%|▊ | 7807/100000 [2:05:20<14:57:32, 1.71it/s] Train steps ... : 8%|▊ | 7808/100000 [2:05:20<14:58:00, 1.71it/s] Train steps ... : 8%|▊ | 7809/100000 [2:05:21<14:57:11, 1.71it/s] Train steps ... : 8%|▊ | 7810/100000 [2:05:22<14:58:26, 1.71it/s] Train steps ... : 8%|▊ | 7811/100000 [2:05:22<14:57:58, 1.71it/s] Train steps ... : 8%|▊ | 7812/100000 [2:05:23<14:58:07, 1.71it/s] Train steps ... : 8%|▊ | 7813/100000 [2:05:23<14:58:11, 1.71it/s] Train steps ... : 8%|▊ | 7814/100000 [2:05:24<14:58:59, 1.71it/s] Train steps ... : 8%|▊ | 7815/100000 [2:05:24<14:58:34, 1.71it/s] Train steps ... : 8%|▊ | 7816/100000 [2:05:25<14:58:13, 1.71it/s] Train steps ... : 8%|▊ | 7817/100000 [2:05:26<14:59:10, 1.71it/s] Train steps ... : 8%|▊ | 7818/100000 [2:05:26<14:58:07, 1.71it/s] Train steps ... : 8%|▊ | 7819/100000 [2:05:27<14:59:08, 1.71it/s] Train steps ... : 8%|▊ | 7820/100000 [2:05:27<14:58:18, 1.71it/s] Train steps ... : 8%|▊ | 7821/100000 [2:05:28<14:57:42, 1.71it/s] Train steps ... : 8%|▊ | 7822/100000 [2:05:29<14:58:56, 1.71it/s] Train steps ... : 8%|▊ | 7823/100000 [2:05:29<14:57:59, 1.71it/s] Train steps ... : 8%|▊ | 7824/100000 [2:05:30<14:57:21, 1.71it/s] Train steps ... : 8%|▊ | 7825/100000 [2:05:30<14:56:27, 1.71it/s]Step... (7825 / 100000 | Loss: 1.5746427774429321, Learning Rate: 9.263819095477387e-05) Step... (7825 / 100000 | Loss: 1.0741848945617676, Learning Rate: 9.263819095477387e-05) Train steps ... : 8%|▊ | 7825/100000 [2:05:31<14:56:27, 1.71it/s] Train steps ... : 8%|▊ | 7826/100000 [2:05:31<14:57:01, 1.71it/s] Train steps ... : 8%|▊ | 7827/100000 [2:05:31<14:56:36, 1.71it/s] Train steps ... : 8%|▊ | 7828/100000 [2:05:32<14:56:37, 1.71it/s] Train steps ... : 8%|▊ | 7829/100000 [2:05:33<14:58:27, 1.71it/s] Train steps ... : 8%|▊ | 7830/100000 [2:05:33<14:57:55, 1.71it/s] Train steps ... : 8%|▊ | 7831/100000 [2:05:34<14:58:00, 1.71it/s] Train steps ... : 8%|▊ | 7832/100000 [2:05:34<14:57:44, 1.71it/s] Train steps ... : 8%|▊ | 7833/100000 [2:05:35<14:57:19, 1.71it/s] Train steps ... : 8%|▊ | 7834/100000 [2:05:36<14:59:29, 1.71it/s] Train steps ... : 8%|▊ | 7835/100000 [2:05:36<14:58:52, 1.71it/s] Train steps ... : 8%|▊ | 7836/100000 [2:05:37<14:57:19, 1.71it/s] Train steps ... : 8%|▊ | 7837/100000 [2:05:37<14:56:47, 1.71it/s] Train steps ... : 8%|▊ | 7838/100000 [2:05:38<14:59:24, 1.71it/s] Train steps ... : 8%|▊ | 7839/100000 [2:05:39<14:56:31, 1.71it/s] Train steps ... : 8%|▊ | 7840/100000 [2:05:39<14:56:45, 1.71it/s] Train steps ... : 8%|▊ | 7841/100000 [2:05:40<14:56:14, 1.71it/s] Train steps ... : 8%|▊ | 7842/100000 [2:05:40<14:56:50, 1.71it/s] Train steps ... : 8%|▊ | 7843/100000 [2:05:41<14:55:53, 1.71it/s] Train steps ... : 8%|▊ | 7844/100000 [2:05:41<14:56:08, 1.71it/s] Train steps ... : 8%|▊ | 7845/100000 [2:05:42<14:57:50, 1.71it/s] Train steps ... : 8%|▊ | 7846/100000 [2:05:43<14:56:04, 1.71it/s] Train steps ... : 8%|▊ | 7847/100000 [2:05:43<14:56:10, 1.71it/s] Train steps ... : 8%|▊ | 7848/100000 [2:05:44<14:56:19, 1.71it/s] Train steps ... : 8%|▊ | 7849/100000 [2:05:44<14:56:50, 1.71it/s] Train steps ... : 8%|▊ | 7850/100000 [2:05:45<14:56:52, 1.71it/s]Step... (7850 / 100000 | Loss: 0.822547435760498, Learning Rate: 9.261306532663317e-05) Step... (7850 / 100000 | Loss: 1.2285606861114502, Learning Rate: 9.261306532663317e-05) Train steps ... : 8%|▊ | 7850/100000 [2:05:45<14:56:52, 1.71it/s] Train steps ... : 8%|▊ | 7851/100000 [2:05:46<14:57:04, 1.71it/s] Train steps ... : 8%|▊ | 7852/100000 [2:05:46<14:58:23, 1.71it/s] Train steps ... : 8%|▊ | 7853/100000 [2:05:47<14:57:52, 1.71it/s] Train steps ... : 8%|▊ | 7854/100000 [2:05:47<14:57:39, 1.71it/s] Train steps ... : 8%|▊ | 7855/100000 [2:05:48<14:57:45, 1.71it/s] Train steps ... : 8%|▊ | 7856/100000 [2:05:48<14:57:40, 1.71it/s] Train steps ... : 8%|▊ | 7857/100000 [2:05:49<14:56:38, 1.71it/s] Train steps ... : 8%|▊ | 7858/100000 [2:05:50<14:56:39, 1.71it/s] Train steps ... : 8%|▊ | 7859/100000 [2:05:50<14:56:18, 1.71it/s] Train steps ... : 8%|▊ | 7860/100000 [2:05:51<14:56:06, 1.71it/s] Train steps ... : 8%|▊ | 7861/100000 [2:05:51<14:55:40, 1.71it/s] Train steps ... : 8%|▊ | 7862/100000 [2:05:52<14:55:32, 1.71it/s] Train steps ... : 8%|▊ | 7863/100000 [2:05:53<14:55:48, 1.71it/s] Train steps ... : 8%|▊ | 7864/100000 [2:05:53<14:57:00, 1.71it/s] Train steps ... : 8%|▊ | 7865/100000 [2:05:54<14:57:01, 1.71it/s] Train steps ... : 8%|▊ | 7866/100000 [2:05:54<14:57:30, 1.71it/s] Train steps ... : 8%|▊ | 7867/100000 [2:05:55<14:58:13, 1.71it/s] Train steps ... : 8%|▊ | 7868/100000 [2:05:55<14:58:04, 1.71it/s] Train steps ... : 8%|▊ | 7869/100000 [2:05:56<14:59:42, 1.71it/s] Train steps ... : 8%|▊ | 7870/100000 [2:05:57<14:59:39, 1.71it/s] Train steps ... : 8%|▊ | 7871/100000 [2:05:57<14:59:58, 1.71it/s] Train steps ... : 8%|▊ | 7872/100000 [2:05:58<14:58:47, 1.71it/s] Train steps ... : 8%|▊ | 7873/100000 [2:05:58<14:59:01, 1.71it/s] Train steps ... : 8%|▊ | 7874/100000 [2:05:59<14:58:13, 1.71it/s] Train steps ... : 8%|▊ | 7875/100000 [2:06:00<14:57:41, 1.71it/s]Step... (7875 / 100000 | Loss: 1.2470015287399292, Learning Rate: 9.258793969849247e-05) Step... (7875 / 100000 | Loss: 1.6107096672058105, Learning Rate: 9.258793969849247e-05) Train steps ... : 8%|▊ | 7875/100000 [2:06:00<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 7876/100000 [2:06:00<14:57:05, 1.71it/s] Train steps ... : 8%|▊ | 7877/100000 [2:06:01<14:59:05, 1.71it/s] Train steps ... : 8%|▊ | 7878/100000 [2:06:01<14:56:13, 1.71it/s] Train steps ... : 8%|▊ | 7879/100000 [2:06:02<14:56:53, 1.71it/s] Train steps ... : 8%|▊ | 7880/100000 [2:06:02<14:56:55, 1.71it/s] Train steps ... : 8%|▊ | 7881/100000 [2:06:03<14:59:13, 1.71it/s] Train steps ... : 8%|▊ | 7882/100000 [2:06:04<15:00:23, 1.71it/s] Train steps ... : 8%|▊ | 7883/100000 [2:06:04<15:01:46, 1.70it/s] Train steps ... : 8%|▊ | 7884/100000 [2:06:05<14:59:24, 1.71it/s] Train steps ... : 8%|▊ | 7885/100000 [2:06:05<15:01:10, 1.70it/s] Train steps ... : 8%|▊ | 7886/100000 [2:06:06<14:59:51, 1.71it/s] Train steps ... : 8%|▊ | 7887/100000 [2:06:07<14:58:55, 1.71it/s] Train steps ... : 8%|▊ | 7888/100000 [2:06:07<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 7889/100000 [2:06:08<14:58:10, 1.71it/s] Train steps ... : 8%|▊ | 7890/100000 [2:06:08<15:00:00, 1.71it/s] Train steps ... : 8%|▊ | 7891/100000 [2:06:09<14:57:28, 1.71it/s] Train steps ... : 8%|▊ | 7892/100000 [2:06:09<14:59:04, 1.71it/s] Train steps ... : 8%|▊ | 7893/100000 [2:06:10<14:58:10, 1.71it/s] Train steps ... : 8%|▊ | 7894/100000 [2:06:11<14:57:19, 1.71it/s] Train steps ... : 8%|▊ | 7895/100000 [2:06:11<14:58:39, 1.71it/s] Train steps ... : 8%|▊ | 7896/100000 [2:06:12<14:59:20, 1.71it/s] Train steps ... : 8%|▊ | 7897/100000 [2:06:12<14:57:55, 1.71it/s] Train steps ... : 8%|▊ | 7898/100000 [2:06:13<14:58:39, 1.71it/s] Train steps ... : 8%|▊ | 7899/100000 [2:06:14<14:59:07, 1.71it/s] Train steps ... : 8%|▊ | 7900/100000 [2:06:14<14:58:20, 1.71it/s]Step... (7900 / 100000 | Loss: 1.5651988983154297, Learning Rate: 9.256281407035176e-05) Step... (7900 / 100000 | Loss: 1.8198909759521484, Learning Rate: 9.256281407035176e-05) Train steps ... : 8%|▊ | 7900/100000 [2:06:15<14:58:20, 1.71it/s] Train steps ... : 8%|▊ | 7901/100000 [2:06:15<14:59:10, 1.71it/s] Train steps ... : 8%|▊ | 7902/100000 [2:06:15<14:59:21, 1.71it/s] Train steps ... : 8%|▊ | 7903/100000 [2:06:16<14:58:59, 1.71it/s] Train steps ... : 8%|▊ | 7904/100000 [2:06:17<14:58:46, 1.71it/s] Train steps ... : 8%|▊ | 7905/100000 [2:06:17<14:59:08, 1.71it/s] Train steps ... : 8%|▊ | 7906/100000 [2:06:18<14:58:14, 1.71it/s] Train steps ... : 8%|▊ | 7907/100000 [2:06:18<14:57:55, 1.71it/s] Train steps ... : 8%|▊ | 7908/100000 [2:06:19<14:57:50, 1.71it/s] Train steps ... : 8%|▊ | 7909/100000 [2:06:19<14:59:25, 1.71it/s] Train steps ... : 8%|▊ | 7910/100000 [2:06:20<14:59:08, 1.71it/s] Train steps ... : 8%|▊ | 7911/100000 [2:06:21<14:58:38, 1.71it/s] Train steps ... : 8%|▊ | 7912/100000 [2:06:21<14:58:33, 1.71it/s] Train steps ... : 8%|▊ | 7913/100000 [2:06:22<14:58:00, 1.71it/s] Train steps ... : 8%|▊ | 7914/100000 [2:06:22<15:00:10, 1.70it/s] Train steps ... : 8%|▊ | 7915/100000 [2:06:23<14:58:12, 1.71it/s] Train steps ... : 8%|▊ | 7916/100000 [2:06:24<14:59:27, 1.71it/s] Train steps ... : 8%|▊ | 7917/100000 [2:06:24<14:57:19, 1.71it/s] Train steps ... : 8%|▊ | 7918/100000 [2:06:25<14:58:06, 1.71it/s] Train steps ... : 8%|▊ | 7919/100000 [2:06:25<14:57:47, 1.71it/s] Train steps ... : 8%|▊ | 7920/100000 [2:06:26<14:57:36, 1.71it/s] Train steps ... : 8%|▊ | 7921/100000 [2:06:26<14:56:29, 1.71it/s] Train steps ... : 8%|▊ | 7922/100000 [2:06:27<14:57:27, 1.71it/s] Train steps ... : 8%|▊ | 7923/100000 [2:06:28<14:57:35, 1.71it/s] Train steps ... : 8%|▊ | 7924/100000 [2:06:28<14:58:11, 1.71it/s] Train steps ... : 8%|▊ | 7925/100000 [2:06:29<14:58:22, 1.71it/s]Step... (7925 / 100000 | Loss: 1.098860263824463, Learning Rate: 9.253768844221106e-05) Step... (7925 / 100000 | Loss: 1.2017099857330322, Learning Rate: 9.253768844221106e-05) Train steps ... : 8%|▊ | 7925/100000 [2:06:29<14:58:22, 1.71it/s] Train steps ... : 8%|▊ | 7926/100000 [2:06:29<14:59:11, 1.71it/s] Train steps ... : 8%|▊ | 7927/100000 [2:06:30<14:58:07, 1.71it/s] Train steps ... : 8%|▊ | 7928/100000 [2:06:31<14:56:57, 1.71it/s] Train steps ... : 8%|▊ | 7929/100000 [2:06:31<14:56:50, 1.71it/s] Train steps ... : 8%|▊ | 7930/100000 [2:06:32<14:57:10, 1.71it/s] Train steps ... : 8%|▊ | 7931/100000 [2:06:32<14:56:20, 1.71it/s] Train steps ... : 8%|▊ | 7932/100000 [2:06:33<14:57:02, 1.71it/s] Train steps ... : 8%|▊ | 7933/100000 [2:06:33<14:56:31, 1.71it/s] Train steps ... : 8%|▊ | 7934/100000 [2:06:34<14:57:33, 1.71it/s] Train steps ... : 8%|▊ | 7935/100000 [2:06:35<14:57:17, 1.71it/s] Train steps ... : 8%|▊ | 7936/100000 [2:06:35<14:57:36, 1.71it/s] Train steps ... : 8%|▊ | 7937/100000 [2:06:36<14:56:36, 1.71it/s] Train steps ... : 8%|▊ | 7938/100000 [2:06:36<14:57:26, 1.71it/s] Train steps ... : 8%|▊ | 7939/100000 [2:06:37<14:58:13, 1.71it/s] Train steps ... : 8%|▊ | 7940/100000 [2:06:38<14:58:36, 1.71it/s] Train steps ... : 8%|▊ | 7941/100000 [2:06:38<14:59:01, 1.71it/s] Train steps ... : 8%|▊ | 7942/100000 [2:06:39<14:57:38, 1.71it/s] Train steps ... : 8%|▊ | 7943/100000 [2:06:39<14:56:53, 1.71it/s] Train steps ... : 8%|▊ | 7944/100000 [2:06:40<14:57:12, 1.71it/s] Train steps ... : 8%|▊ | 7945/100000 [2:06:41<14:57:48, 1.71it/s] Train steps ... : 8%|▊ | 7946/100000 [2:06:41<14:57:13, 1.71it/s] Train steps ... : 8%|▊ | 7947/100000 [2:06:42<14:57:22, 1.71it/s] Train steps ... : 8%|▊ | 7948/100000 [2:06:42<14:56:17, 1.71it/s] Train steps ... : 8%|▊ | 7949/100000 [2:06:43<14:56:43, 1.71it/s] Train steps ... : 8%|▊ | 7950/100000 [2:06:43<14:56:08, 1.71it/s]Step... (7950 / 100000 | Loss: 1.2596453428268433, Learning Rate: 9.251256281407036e-05) Step... (7950 / 100000 | Loss: 1.489304542541504, Learning Rate: 9.251256281407036e-05) Train steps ... : 8%|▊ | 7950/100000 [2:06:44<14:56:08, 1.71it/s] Train steps ... : 8%|▊ | 7951/100000 [2:06:44<14:57:53, 1.71it/s] Train steps ... : 8%|▊ | 7952/100000 [2:06:45<14:56:47, 1.71it/s] Train steps ... : 8%|▊ | 7953/100000 [2:06:45<14:59:14, 1.71it/s] Train steps ... : 8%|▊ | 7954/100000 [2:06:46<14:58:36, 1.71it/s] Train steps ... : 8%|▊ | 7955/100000 [2:06:46<14:58:18, 1.71it/s] Train steps ... : 8%|▊ | 7956/100000 [2:06:47<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 7957/100000 [2:06:48<14:57:48, 1.71it/s] Train steps ... : 8%|▊ | 7958/100000 [2:06:48<14:57:25, 1.71it/s] Train steps ... : 8%|▊ | 7959/100000 [2:06:49<14:56:44, 1.71it/s] Train steps ... : 8%|▊ | 7960/100000 [2:06:49<14:57:33, 1.71it/s] Train steps ... : 8%|▊ | 7961/100000 [2:06:50<14:56:57, 1.71it/s] Train steps ... : 8%|▊ | 7962/100000 [2:06:50<14:56:36, 1.71it/s] Train steps ... : 8%|▊ | 7963/100000 [2:06:51<14:57:11, 1.71it/s] Train steps ... : 8%|▊ | 7964/100000 [2:06:52<14:57:40, 1.71it/s] Train steps ... : 8%|▊ | 7965/100000 [2:06:52<14:57:00, 1.71it/s] Train steps ... : 8%|▊ | 7966/100000 [2:06:53<14:56:36, 1.71it/s] Train steps ... : 8%|▊ | 7967/100000 [2:06:53<14:57:52, 1.71it/s] Train steps ... : 8%|▊ | 7968/100000 [2:06:54<14:58:01, 1.71it/s] Train steps ... : 8%|▊ | 7969/100000 [2:06:55<14:58:03, 1.71it/s] Train steps ... : 8%|▊ | 7970/100000 [2:06:55<14:59:47, 1.70it/s] Train steps ... : 8%|▊ | 7971/100000 [2:06:56<14:59:10, 1.71it/s] Train steps ... : 8%|▊ | 7972/100000 [2:06:56<14:57:58, 1.71it/s] Train steps ... : 8%|▊ | 7973/100000 [2:06:57<14:58:25, 1.71it/s] Train steps ... : 8%|▊ | 7974/100000 [2:06:57<14:57:27, 1.71it/s] Train steps ... : 8%|▊ | 7975/100000 [2:06:58<14:56:41, 1.71it/s]Step... (7975 / 100000 | Loss: 1.6690443754196167, Learning Rate: 9.248743718592965e-05) Step... (7975 / 100000 | Loss: 1.5940662622451782, Learning Rate: 9.248743718592965e-05) Train steps ... : 8%|▊ | 7975/100000 [2:06:58<14:56:41, 1.71it/s] Train steps ... : 8%|▊ | 7976/100000 [2:06:59<14:57:49, 1.71it/s] Train steps ... : 8%|▊ | 7977/100000 [2:06:59<14:56:48, 1.71it/s] Train steps ... : 8%|▊ | 7978/100000 [2:07:00<14:56:21, 1.71it/s] Train steps ... : 8%|▊ | 7979/100000 [2:07:00<14:56:29, 1.71it/s] Train steps ... : 8%|▊ | 7980/100000 [2:07:01<14:56:07, 1.71it/s] Train steps ... : 8%|▊ | 7981/100000 [2:07:02<14:56:06, 1.71it/s] Train steps ... : 8%|▊ | 7982/100000 [2:07:02<14:55:46, 1.71it/s] Train steps ... : 8%|▊ | 7983/100000 [2:07:03<14:56:22, 1.71it/s] Train steps ... : 8%|▊ | 7984/100000 [2:07:03<14:56:09, 1.71it/s] Train steps ... : 8%|▊ | 7985/100000 [2:07:04<14:55:18, 1.71it/s] Train steps ... : 8%|▊ | 7986/100000 [2:07:04<14:56:10, 1.71it/s] Train steps ... : 8%|▊ | 7987/100000 [2:07:05<14:56:03, 1.71it/s] Train steps ... : 8%|▊ | 7988/100000 [2:07:06<14:57:23, 1.71it/s] Train steps ... : 8%|▊ | 7989/100000 [2:07:06<14:57:38, 1.71it/s] Train steps ... : 8%|▊ | 7990/100000 [2:07:07<14:56:57, 1.71it/s] Train steps ... : 8%|▊ | 7991/100000 [2:07:07<14:56:53, 1.71it/s] Train steps ... : 8%|▊ | 7992/100000 [2:07:08<14:56:33, 1.71it/s] Train steps ... : 8%|▊ | 7993/100000 [2:07:09<14:56:13, 1.71it/s] Train steps ... : 8%|▊ | 7994/100000 [2:07:09<14:56:17, 1.71it/s] Train steps ... : 8%|▊ | 7995/100000 [2:07:10<14:57:40, 1.71it/s] Train steps ... : 8%|▊ | 7996/100000 [2:07:10<14:58:32, 1.71it/s] Train steps ... : 8%|▊ | 7997/100000 [2:07:11<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 7998/100000 [2:07:12<14:56:50, 1.71it/s] Train steps ... : 8%|▊ | 7999/100000 [2:07:12<14:57:24, 1.71it/s] Train steps ... : 8%|▊ | 8000/100000 [2:07:13<14:57:31, 1.71it/s]Step... (8000 / 100000 | Loss: 1.4011642932891846, Learning Rate: 9.246231155778895e-05) Step... (8000 / 100000 | Loss: 1.1194164752960205, Learning Rate: 9.246231155778895e-05) Train steps ... : 8%|▊ | 8000/100000 [2:07:13<14:57:31, 1.71it/s] Train steps ... : 8%|▊ | 8001/100000 [2:07:13<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 8002/100000 [2:07:14<14:57:11, 1.71it/s] Train steps ... : 8%|▊ | 8003/100000 [2:07:14<14:56:40, 1.71it/s] Train steps ... : 8%|▊ | 8004/100000 [2:07:15<14:59:35, 1.70it/s] Train steps ... : 8%|▊ | 8005/100000 [2:07:16<14:57:27, 1.71it/s] Train steps ... : 8%|▊ | 8006/100000 [2:07:16<14:59:42, 1.70it/s] Train steps ... : 8%|▊ | 8007/100000 [2:07:17<14:58:50, 1.71it/s] Train steps ... : 8%|▊ | 8008/100000 [2:07:17<14:57:46, 1.71it/s] Train steps ... : 8%|▊ | 8009/100000 [2:07:18<14:57:55, 1.71it/s] Train steps ... : 8%|▊ | 8010/100000 [2:07:19<14:58:08, 1.71it/s] Train steps ... : 8%|▊ | 8011/100000 [2:07:19<14:57:07, 1.71it/s] Train steps ... : 8%|▊ | 8012/100000 [2:07:20<14:57:01, 1.71it/s] Train steps ... : 8%|▊ | 8013/100000 [2:07:20<14:57:34, 1.71it/s] Train steps ... : 8%|▊ | 8014/100000 [2:07:21<14:56:46, 1.71it/s] Train steps ... : 8%|▊ | 8015/100000 [2:07:21<14:56:10, 1.71it/s] Train steps ... : 8%|▊ | 8016/100000 [2:07:22<14:56:10, 1.71it/s] Train steps ... : 8%|▊ | 8017/100000 [2:07:23<14:56:15, 1.71it/s] Train steps ... : 8%|▊ | 8018/100000 [2:07:23<14:56:41, 1.71it/s] Train steps ... : 8%|▊ | 8019/100000 [2:07:24<14:56:15, 1.71it/s] Train steps ... : 8%|▊ | 8020/100000 [2:07:24<14:57:36, 1.71it/s] Train steps ... : 8%|▊ | 8021/100000 [2:07:25<14:55:48, 1.71it/s] Train steps ... : 8%|▊ | 8022/100000 [2:07:26<14:57:33, 1.71it/s] Train steps ... : 8%|▊ | 8023/100000 [2:07:26<14:58:01, 1.71it/s] Train steps ... : 8%|▊ | 8024/100000 [2:07:27<14:57:49, 1.71it/s] Train steps ... : 8%|▊ | 8025/100000 [2:07:27<14:59:10, 1.70it/s]Step... (8025 / 100000 | Loss: 0.9397433996200562, Learning Rate: 9.243718592964823e-05) Step... (8025 / 100000 | Loss: 1.2854121923446655, Learning Rate: 9.243718592964823e-05) Train steps ... : 8%|▊ | 8025/100000 [2:07:28<14:59:10, 1.70it/s] Train steps ... : 8%|▊ | 8026/100000 [2:07:28<14:59:30, 1.70it/s] Train steps ... : 8%|▊ | 8027/100000 [2:07:28<14:58:24, 1.71it/s] Train steps ... : 8%|▊ | 8028/100000 [2:07:29<14:57:11, 1.71it/s] Train steps ... : 8%|▊ | 8029/100000 [2:07:30<14:58:08, 1.71it/s] Train steps ... : 8%|▊ | 8030/100000 [2:07:30<14:56:59, 1.71it/s] Train steps ... : 8%|▊ | 8031/100000 [2:07:31<14:56:56, 1.71it/s] Train steps ... : 8%|▊ | 8032/100000 [2:07:31<14:56:35, 1.71it/s] Train steps ... : 8%|▊ | 8033/100000 [2:07:32<14:56:22, 1.71it/s] Train steps ... : 8%|▊ | 8034/100000 [2:07:33<14:56:53, 1.71it/s] Train steps ... : 8%|▊ | 8035/100000 [2:07:33<14:56:21, 1.71it/s] Train steps ... : 8%|▊ | 8036/100000 [2:07:34<14:57:19, 1.71it/s] Train steps ... : 8%|▊ | 8037/100000 [2:07:34<14:57:49, 1.71it/s] Train steps ... : 8%|▊ | 8038/100000 [2:07:35<14:59:54, 1.70it/s] Train steps ... : 8%|▊ | 8039/100000 [2:07:36<14:57:20, 1.71it/s] Train steps ... : 8%|▊ | 8040/100000 [2:07:36<14:57:30, 1.71it/s] Train steps ... : 8%|▊ | 8041/100000 [2:07:37<14:58:36, 1.71it/s] Train steps ... : 8%|▊ | 8042/100000 [2:07:37<14:59:38, 1.70it/s] Train steps ... : 8%|▊ | 8043/100000 [2:07:38<15:00:08, 1.70it/s] Train steps ... : 8%|▊ | 8044/100000 [2:07:38<14:59:49, 1.70it/s] Train steps ... : 8%|▊ | 8045/100000 [2:07:39<14:59:16, 1.70it/s] Train steps ... : 8%|▊ | 8046/100000 [2:07:40<14:59:18, 1.70it/s] Train steps ... : 8%|▊ | 8047/100000 [2:07:40<14:56:47, 1.71it/s] Train steps ... : 8%|▊ | 8048/100000 [2:07:41<14:56:55, 1.71it/s] Train steps ... : 8%|▊ | 8049/100000 [2:07:41<15:00:12, 1.70it/s] Train steps ... : 8%|▊ | 8050/100000 [2:07:42<14:57:55, 1.71it/s]Step... (8050 / 100000 | Loss: 2.0310258865356445, Learning Rate: 9.241206030150754e-05) Step... (8050 / 100000 | Loss: 1.2135403156280518, Learning Rate: 9.241206030150754e-05) Train steps ... : 8%|▊ | 8050/100000 [2:07:42<14:57:55, 1.71it/s] Train steps ... : 8%|▊ | 8051/100000 [2:07:43<14:58:46, 1.71it/s] Train steps ... : 8%|▊ | 8052/100000 [2:07:43<14:58:28, 1.71it/s] Train steps ... : 8%|▊ | 8053/100000 [2:07:44<14:56:01, 1.71it/s] Train steps ... : 8%|▊ | 8054/100000 [2:07:44<14:57:25, 1.71it/s] Train steps ... : 8%|▊ | 8055/100000 [2:07:45<14:57:17, 1.71it/s] Train steps ... : 8%|▊ | 8056/100000 [2:07:45<14:57:38, 1.71it/s] Train steps ... : 8%|▊ | 8057/100000 [2:07:46<14:56:39, 1.71it/s] Train steps ... : 8%|▊ | 8058/100000 [2:07:47<14:55:50, 1.71it/s] Train steps ... : 8%|▊ | 8059/100000 [2:07:47<14:57:42, 1.71it/s] Train steps ... : 8%|▊ | 8060/100000 [2:07:48<14:57:32, 1.71it/s] Train steps ... : 8%|▊ | 8061/100000 [2:07:48<14:56:09, 1.71it/s] Train steps ... : 8%|▊ | 8062/100000 [2:07:49<14:55:41, 1.71it/s] Train steps ... : 8%|▊ | 8063/100000 [2:07:50<14:55:28, 1.71it/s] Train steps ... : 8%|▊ | 8064/100000 [2:07:50<14:55:21, 1.71it/s] Train steps ... : 8%|▊ | 8065/100000 [2:07:51<14:56:22, 1.71it/s] Train steps ... : 8%|▊ | 8066/100000 [2:07:51<14:55:52, 1.71it/s] Train steps ... : 8%|▊ | 8067/100000 [2:07:52<14:57:18, 1.71it/s] Train steps ... : 8%|▊ | 8068/100000 [2:07:53<14:56:45, 1.71it/s] Train steps ... : 8%|▊ | 8069/100000 [2:07:53<14:56:56, 1.71it/s] Train steps ... : 8%|▊ | 8070/100000 [2:07:54<14:59:36, 1.70it/s] Train steps ... : 8%|▊ | 8071/100000 [2:07:54<14:56:57, 1.71it/s] Train steps ... : 8%|▊ | 8072/100000 [2:07:55<14:59:02, 1.70it/s] Train steps ... : 8%|▊ | 8073/100000 [2:07:55<14:58:25, 1.71it/s] Train steps ... : 8%|▊ | 8074/100000 [2:07:56<14:58:36, 1.70it/s] Train steps ... : 8%|▊ | 8075/100000 [2:07:57<14:57:42, 1.71it/s]Step... (8075 / 100000 | Loss: 1.1465611457824707, Learning Rate: 9.238693467336684e-05) Step... (8075 / 100000 | Loss: 1.0934284925460815, Learning Rate: 9.238693467336684e-05) Train steps ... : 8%|▊ | 8075/100000 [2:07:57<14:57:42, 1.71it/s] Train steps ... : 8%|▊ | 8076/100000 [2:07:57<14:57:41, 1.71it/s] Train steps ... : 8%|▊ | 8077/100000 [2:07:58<14:59:10, 1.70it/s] Train steps ... : 8%|▊ | 8078/100000 [2:07:58<14:58:45, 1.70it/s] Train steps ... : 8%|▊ | 8079/100000 [2:07:59<14:58:12, 1.71it/s] Train steps ... : 8%|▊ | 8080/100000 [2:08:00<14:56:41, 1.71it/s] Train steps ... : 8%|▊ | 8081/100000 [2:08:00<14:58:41, 1.70it/s] Train steps ... : 8%|▊ | 8082/100000 [2:08:01<14:56:41, 1.71it/s] Train steps ... : 8%|▊ | 8083/100000 [2:08:01<14:57:02, 1.71it/s] Train steps ... : 8%|▊ | 8084/100000 [2:08:02<14:59:07, 1.70it/s] Train steps ... : 8%|▊ | 8085/100000 [2:08:02<14:58:57, 1.70it/s] Train steps ... : 8%|▊ | 8086/100000 [2:08:03<14:58:24, 1.71it/s] Train steps ... : 8%|▊ | 8087/100000 [2:08:04<14:58:39, 1.70it/s] Train steps ... : 8%|▊ | 8088/100000 [2:08:04<14:58:15, 1.71it/s] Train steps ... : 8%|▊ | 8089/100000 [2:08:05<14:56:39, 1.71it/s] Train steps ... : 8%|▊ | 8090/100000 [2:08:05<14:57:38, 1.71it/s] Train steps ... : 8%|▊ | 8091/100000 [2:08:06<14:57:20, 1.71it/s] Train steps ... : 8%|▊ | 8092/100000 [2:08:07<14:56:50, 1.71it/s] Train steps ... : 8%|▊ | 8093/100000 [2:08:07<14:57:07, 1.71it/s] Train steps ... : 8%|▊ | 8094/100000 [2:08:08<14:56:49, 1.71it/s] Train steps ... : 8%|▊ | 8095/100000 [2:08:08<14:56:08, 1.71it/s] Train steps ... : 8%|▊ | 8096/100000 [2:08:09<14:55:33, 1.71it/s] Train steps ... : 8%|▊ | 8097/100000 [2:08:09<14:56:58, 1.71it/s] Train steps ... : 8%|▊ | 8098/100000 [2:08:10<14:55:45, 1.71it/s] Train steps ... : 8%|▊ | 8099/100000 [2:08:11<14:55:20, 1.71it/s] Train steps ... : 8%|▊ | 8100/100000 [2:08:11<14:57:40, 1.71it/s]Step... (8100 / 100000 | Loss: 1.2269299030303955, Learning Rate: 9.236180904522614e-05) Step... (8100 / 100000 | Loss: 1.635135531425476, Learning Rate: 9.236180904522614e-05) Train steps ... : 8%|▊ | 8100/100000 [2:08:12<14:57:40, 1.71it/s] Train steps ... : 8%|▊ | 8101/100000 [2:08:12<14:57:27, 1.71it/s] Train steps ... : 8%|▊ | 8102/100000 [2:08:12<14:56:10, 1.71it/s] Train steps ... : 8%|▊ | 8103/100000 [2:08:13<14:55:24, 1.71it/s] Train steps ... : 8%|▊ | 8104/100000 [2:08:14<14:57:35, 1.71it/s] Train steps ... : 8%|▊ | 8105/100000 [2:08:14<14:56:00, 1.71it/s] Train steps ... : 8%|▊ | 8106/100000 [2:08:15<14:57:33, 1.71it/s] Train steps ... : 8%|▊ | 8107/100000 [2:08:15<14:55:45, 1.71it/s] Train steps ... : 8%|▊ | 8108/100000 [2:08:16<14:55:35, 1.71it/s] Train steps ... : 8%|▊ | 8109/100000 [2:08:17<14:56:43, 1.71it/s] Train steps ... : 8%|▊ | 8110/100000 [2:08:17<14:55:25, 1.71it/s] Train steps ... : 8%|▊ | 8111/100000 [2:08:18<14:54:59, 1.71it/s] Train steps ... : 8%|▊ | 8112/100000 [2:08:18<14:55:57, 1.71it/s] Train steps ... : 8%|▊ | 8113/100000 [2:08:19<14:54:09, 1.71it/s] Train steps ... : 8%|▊ | 8114/100000 [2:08:19<14:54:10, 1.71it/s] Train steps ... : 8%|▊ | 8115/100000 [2:08:20<14:54:00, 1.71it/s] Train steps ... : 8%|▊ | 8116/100000 [2:08:21<14:55:28, 1.71it/s] Train steps ... : 8%|▊ | 8117/100000 [2:08:21<14:56:44, 1.71it/s] Train steps ... : 8%|▊ | 8118/100000 [2:08:22<14:54:29, 1.71it/s] Train steps ... : 8%|▊ | 8119/100000 [2:08:22<14:55:10, 1.71it/s] Train steps ... : 8%|▊ | 8120/100000 [2:08:23<14:55:02, 1.71it/s] Train steps ... : 8%|▊ | 8121/100000 [2:08:24<14:54:04, 1.71it/s] Train steps ... : 8%|▊ | 8122/100000 [2:08:24<14:55:04, 1.71it/s] Train steps ... : 8%|▊ | 8123/100000 [2:08:25<14:55:17, 1.71it/s] Train steps ... : 8%|▊ | 8124/100000 [2:08:25<14:56:56, 1.71it/s] Train steps ... : 8%|▊ | 8125/100000 [2:08:26<14:55:08, 1.71it/s]Step... (8125 / 100000 | Loss: 1.26450514793396, Learning Rate: 9.233668341708543e-05) Step... (8125 / 100000 | Loss: 1.7787775993347168, Learning Rate: 9.233668341708543e-05) Train steps ... : 8%|▊ | 8125/100000 [2:08:26<14:55:08, 1.71it/s] Train steps ... : 8%|▊ | 8126/100000 [2:08:26<14:55:07, 1.71it/s] Train steps ... : 8%|▊ | 8127/100000 [2:08:27<14:59:24, 1.70it/s] Train steps ... : 8%|▊ | 8128/100000 [2:08:28<14:57:36, 1.71it/s] Train steps ... : 8%|▊ | 8129/100000 [2:08:28<14:56:50, 1.71it/s] Train steps ... : 8%|▊ | 8130/100000 [2:08:29<14:59:46, 1.70it/s] Train steps ... : 8%|▊ | 8131/100000 [2:08:29<14:58:21, 1.70it/s] Train steps ... : 8%|▊ | 8132/100000 [2:08:30<14:58:15, 1.70it/s] Train steps ... : 8%|▊ | 8133/100000 [2:08:31<14:58:44, 1.70it/s] Train steps ... : 8%|▊ | 8134/100000 [2:08:31<14:57:44, 1.71it/s] Train steps ... : 8%|▊ | 8135/100000 [2:08:32<14:57:25, 1.71it/s] Train steps ... : 8%|▊ | 8136/100000 [2:08:32<14:57:01, 1.71it/s] Train steps ... : 8%|▊ | 8137/100000 [2:08:33<14:57:31, 1.71it/s] Train steps ... : 8%|▊ | 8138/100000 [2:08:33<14:59:23, 1.70it/s] Train steps ... : 8%|▊ | 8139/100000 [2:08:34<14:55:34, 1.71it/s] Train steps ... : 8%|▊ | 8140/100000 [2:08:35<14:57:55, 1.71it/s] Train steps ... : 8%|▊ | 8141/100000 [2:08:35<14:57:58, 1.70it/s] Train steps ... : 8%|▊ | 8142/100000 [2:08:36<14:59:09, 1.70it/s] Train steps ... : 8%|▊ | 8143/100000 [2:08:36<14:58:23, 1.70it/s] Train steps ... : 8%|▊ | 8144/100000 [2:08:37<14:57:12, 1.71it/s] Train steps ... : 8%|▊ | 8145/100000 [2:08:38<14:57:02, 1.71it/s] Train steps ... : 8%|▊ | 8146/100000 [2:08:38<14:56:03, 1.71it/s] Train steps ... : 8%|▊ | 8147/100000 [2:08:39<14:58:13, 1.70it/s] Train steps ... : 8%|▊ | 8148/100000 [2:08:39<14:55:00, 1.71it/s] Train steps ... : 8%|▊ | 8149/100000 [2:08:40<14:54:45, 1.71it/s] Train steps ... : 8%|▊ | 8150/100000 [2:08:41<14:57:44, 1.71it/s]Step... (8150 / 100000 | Loss: 0.95233154296875, Learning Rate: 9.231155778894473e-05) Step... (8150 / 100000 | Loss: 1.3947328329086304, Learning Rate: 9.231155778894473e-05) Train steps ... : 8%|▊ | 8150/100000 [2:08:41<14:57:44, 1.71it/s] Train steps ... : 8%|▊ | 8151/100000 [2:08:41<14:56:42, 1.71it/s] Train steps ... : 8%|▊ | 8152/100000 [2:08:42<14:56:19, 1.71it/s] Train steps ... : 8%|▊ | 8153/100000 [2:08:42<14:55:45, 1.71it/s] Train steps ... : 8%|▊ | 8154/100000 [2:08:43<15:01:08, 1.70it/s] Train steps ... : 8%|▊ | 8155/100000 [2:08:43<15:00:00, 1.70it/s] Train steps ... : 8%|▊ | 8156/100000 [2:08:44<14:59:52, 1.70it/s] Train steps ... : 8%|▊ | 8157/100000 [2:08:45<14:59:13, 1.70it/s] Train steps ... : 8%|▊ | 8158/100000 [2:08:45<14:58:24, 1.70it/s] Train steps ... : 8%|▊ | 8159/100000 [2:08:46<14:56:50, 1.71it/s] Train steps ... : 8%|▊ | 8160/100000 [2:08:46<14:59:09, 1.70it/s] Train steps ... : 8%|▊ | 8161/100000 [2:08:47<14:56:10, 1.71it/s] Train steps ... : 8%|▊ | 8162/100000 [2:08:48<14:56:33, 1.71it/s] Train steps ... : 8%|▊ | 8163/100000 [2:08:48<14:56:55, 1.71it/s] Train steps ... : 8%|▊ | 8164/100000 [2:08:49<14:57:35, 1.71it/s] Train steps ... : 8%|▊ | 8165/100000 [2:08:49<14:57:50, 1.70it/s] Train steps ... : 8%|▊ | 8166/100000 [2:08:50<14:56:13, 1.71it/s] Train steps ... : 8%|▊ | 8167/100000 [2:08:51<14:57:37, 1.71it/s] Train steps ... : 8%|▊ | 8168/100000 [2:08:51<14:57:09, 1.71it/s] Train steps ... : 8%|▊ | 8169/100000 [2:08:52<14:56:13, 1.71it/s] Train steps ... : 8%|▊ | 8170/100000 [2:08:52<14:59:43, 1.70it/s] Train steps ... : 8%|▊ | 8171/100000 [2:08:53<14:57:52, 1.70it/s] Train steps ... : 8%|▊ | 8172/100000 [2:08:53<14:57:57, 1.70it/s] Train steps ... : 8%|▊ | 8173/100000 [2:08:54<14:59:46, 1.70it/s] Train steps ... : 8%|▊ | 8174/100000 [2:08:55<14:59:56, 1.70it/s] Train steps ... : 8%|▊ | 8175/100000 [2:08:55<14:58:30, 1.70it/s]Step... (8175 / 100000 | Loss: 1.5207372903823853, Learning Rate: 9.228643216080403e-05) Step... (8175 / 100000 | Loss: 0.8919270038604736, Learning Rate: 9.228643216080403e-05) Train steps ... : 8%|▊ | 8175/100000 [2:08:56<14:58:30, 1.70it/s] Train steps ... : 8%|▊ | 8176/100000 [2:08:56<14:57:18, 1.71it/s] Train steps ... : 8%|▊ | 8177/100000 [2:08:56<14:57:07, 1.71it/s] Train steps ... : 8%|▊ | 8178/100000 [2:08:57<14:56:28, 1.71it/s] Train steps ... : 8%|▊ | 8179/100000 [2:08:58<14:57:08, 1.71it/s] Train steps ... : 8%|▊ | 8180/100000 [2:08:58<14:56:35, 1.71it/s] Train steps ... : 8%|▊ | 8181/100000 [2:08:59<14:56:20, 1.71it/s] Train steps ... : 8%|▊ | 8182/100000 [2:08:59<14:56:25, 1.71it/s] Train steps ... : 8%|▊ | 8183/100000 [2:09:00<14:58:53, 1.70it/s] Train steps ... : 8%|▊ | 8184/100000 [2:09:00<14:57:11, 1.71it/s] Train steps ... : 8%|▊ | 8185/100000 [2:09:01<14:56:30, 1.71it/s] Train steps ... : 8%|▊ | 8186/100000 [2:09:02<14:56:36, 1.71it/s] Train steps ... : 8%|▊ | 8187/100000 [2:09:02<14:56:48, 1.71it/s] Train steps ... : 8%|▊ | 8188/100000 [2:09:03<15:00:53, 1.70it/s] Train steps ... : 8%|▊ | 8189/100000 [2:09:03<15:00:23, 1.70it/s] Train steps ... : 8%|▊ | 8190/100000 [2:09:04<14:59:28, 1.70it/s] Train steps ... : 8%|▊ | 8191/100000 [2:09:05<15:00:05, 1.70it/s] Train steps ... : 8%|▊ | 8192/100000 [2:09:05<14:57:05, 1.71it/s] Train steps ... : 8%|▊ | 8193/100000 [2:09:06<14:56:52, 1.71it/s] Train steps ... : 8%|▊ | 8194/100000 [2:09:06<14:58:02, 1.70it/s] Train steps ... : 8%|▊ | 8195/100000 [2:09:07<14:59:10, 1.70it/s] Train steps ... : 8%|▊ | 8196/100000 [2:09:08<14:57:25, 1.70it/s] Train steps ... : 8%|▊ | 8197/100000 [2:09:08<14:58:25, 1.70it/s] Train steps ... : 8%|▊ | 8198/100000 [2:09:09<14:56:03, 1.71it/s] Train steps ... : 8%|▊ | 8199/100000 [2:09:09<14:59:13, 1.70it/s] Train steps ... : 8%|▊ | 8200/100000 [2:09:10<14:56:19, 1.71it/s]Step... (8200 / 100000 | Loss: 1.0897027254104614, Learning Rate: 9.226130653266331e-05) Step... (8200 / 100000 | Loss: 1.609718918800354, Learning Rate: 9.226130653266331e-05) Train steps ... : 8%|▊ | 8200/100000 [2:09:10<14:56:19, 1.71it/s] Train steps ... : 8%|▊ | 8201/100000 [2:09:10<14:55:31, 1.71it/s] Train steps ... : 8%|▊ | 8202/100000 [2:09:11<14:57:18, 1.71it/s] Train steps ... : 8%|▊ | 8203/100000 [2:09:12<15:00:45, 1.70it/s] Train steps ... : 8%|▊ | 8204/100000 [2:09:12<15:00:05, 1.70it/s] Train steps ... : 8%|▊ | 8205/100000 [2:09:13<14:59:18, 1.70it/s] Train steps ... : 8%|▊ | 8206/100000 [2:09:13<14:59:11, 1.70it/s] Train steps ... : 8%|▊ | 8207/100000 [2:09:14<14:59:49, 1.70it/s] Train steps ... : 8%|▊ | 8208/100000 [2:09:15<15:00:47, 1.70it/s] Train steps ... : 8%|▊ | 8209/100000 [2:09:15<14:57:08, 1.71it/s] Train steps ... : 8%|▊ | 8210/100000 [2:09:16<14:56:28, 1.71it/s] Train steps ... : 8%|▊ | 8211/100000 [2:09:16<14:55:41, 1.71it/s] Train steps ... : 8%|▊ | 8212/100000 [2:09:17<14:55:56, 1.71it/s] Train steps ... : 8%|▊ | 8213/100000 [2:09:17<14:56:59, 1.71it/s] Train steps ... : 8%|▊ | 8214/100000 [2:09:18<14:55:55, 1.71it/s] Train steps ... : 8%|▊ | 8215/100000 [2:09:19<14:56:09, 1.71it/s] Train steps ... : 8%|▊ | 8216/100000 [2:09:19<14:56:30, 1.71it/s] Train steps ... : 8%|▊ | 8217/100000 [2:09:20<14:54:45, 1.71it/s] Train steps ... : 8%|▊ | 8218/100000 [2:09:20<14:55:08, 1.71it/s] Train steps ... : 8%|▊ | 8219/100000 [2:09:21<14:54:36, 1.71it/s] Train steps ... : 8%|▊ | 8220/100000 [2:09:22<14:54:54, 1.71it/s] Train steps ... : 8%|▊ | 8221/100000 [2:09:22<14:54:14, 1.71it/s] Train steps ... : 8%|▊ | 8222/100000 [2:09:23<14:54:43, 1.71it/s] Train steps ... : 8%|▊ | 8223/100000 [2:09:23<14:54:56, 1.71it/s] Train steps ... : 8%|▊ | 8224/100000 [2:09:24<14:55:04, 1.71it/s] Train steps ... : 8%|▊ | 8225/100000 [2:09:25<14:54:10, 1.71it/s]Step... (8225 / 100000 | Loss: 1.3821749687194824, Learning Rate: 9.223618090452262e-05) Step... (8225 / 100000 | Loss: 1.4446001052856445, Learning Rate: 9.223618090452262e-05) Train steps ... : 8%|▊ | 8225/100000 [2:09:25<14:54:10, 1.71it/s] Train steps ... : 8%|▊ | 8226/100000 [2:09:25<14:58:25, 1.70it/s] Train steps ... : 8%|▊ | 8227/100000 [2:09:26<14:56:37, 1.71it/s] Train steps ... : 8%|▊ | 8228/100000 [2:09:26<14:55:05, 1.71it/s] Train steps ... : 8%|▊ | 8229/100000 [2:09:27<14:55:59, 1.71it/s] Train steps ... : 8%|▊ | 8230/100000 [2:09:27<14:56:48, 1.71it/s] Train steps ... : 8%|▊ | 8231/100000 [2:09:28<14:56:34, 1.71it/s] Train steps ... : 8%|▊ | 8232/100000 [2:09:29<14:56:03, 1.71it/s] Train steps ... : 8%|▊ | 8233/100000 [2:09:29<14:56:54, 1.71it/s] Train steps ... : 8%|▊ | 8234/100000 [2:09:30<14:57:54, 1.70it/s] Train steps ... : 8%|▊ | 8235/100000 [2:09:30<14:56:13, 1.71it/s] Train steps ... : 8%|▊ | 8236/100000 [2:09:31<14:58:04, 1.70it/s] Train steps ... : 8%|▊ | 8237/100000 [2:09:32<14:58:37, 1.70it/s] Train steps ... : 8%|▊ | 8238/100000 [2:09:32<14:57:47, 1.70it/s] Train steps ... : 8%|▊ | 8239/100000 [2:09:33<14:58:35, 1.70it/s] Train steps ... : 8%|▊ | 8240/100000 [2:09:33<14:56:03, 1.71it/s] Train steps ... : 8%|▊ | 8241/100000 [2:09:34<14:55:15, 1.71it/s] Train steps ... : 8%|▊ | 8242/100000 [2:09:34<14:55:23, 1.71it/s] Train steps ... : 8%|▊ | 8243/100000 [2:09:35<14:57:56, 1.70it/s] Train steps ... : 8%|▊ | 8244/100000 [2:09:36<14:56:31, 1.71it/s] Train steps ... : 8%|▊ | 8245/100000 [2:09:36<14:56:09, 1.71it/s] Train steps ... : 8%|▊ | 8246/100000 [2:09:37<14:56:48, 1.71it/s] Train steps ... : 8%|▊ | 8247/100000 [2:09:37<14:57:05, 1.70it/s] Train steps ... : 8%|▊ | 8248/100000 [2:09:38<14:56:10, 1.71it/s] Train steps ... : 8%|▊ | 8249/100000 [2:09:39<14:58:43, 1.70it/s] Train steps ... : 8%|▊ | 8250/100000 [2:09:39<14:57:54, 1.70it/s]Step... (8250 / 100000 | Loss: 1.1733897924423218, Learning Rate: 9.221105527638192e-05) Step... (8250 / 100000 | Loss: 1.0571606159210205, Learning Rate: 9.221105527638192e-05) Train steps ... : 8%|▊ | 8250/100000 [2:09:40<14:57:54, 1.70it/s] Train steps ... : 8%|▊ | 8251/100000 [2:09:40<15:00:05, 1.70it/s] Train steps ... : 8%|▊ | 8252/100000 [2:09:40<14:59:28, 1.70it/s] Train steps ... : 8%|▊ | 8253/100000 [2:09:41<14:59:20, 1.70it/s] Train steps ... : 8%|▊ | 8254/100000 [2:09:42<14:58:34, 1.70it/s] Train steps ... : 8%|▊ | 8255/100000 [2:09:42<14:58:11, 1.70it/s] Train steps ... : 8%|▊ | 8256/100000 [2:09:43<14:59:17, 1.70it/s] Train steps ... : 8%|▊ | 8257/100000 [2:09:43<14:56:57, 1.70it/s] Train steps ... : 8%|▊ | 8258/100000 [2:09:44<14:57:56, 1.70it/s] Train steps ... : 8%|▊ | 8259/100000 [2:09:44<14:56:49, 1.70it/s] Train steps ... : 8%|▊ | 8260/100000 [2:09:45<14:57:09, 1.70it/s] Train steps ... : 8%|▊ | 8261/100000 [2:09:46<14:56:56, 1.70it/s] Train steps ... : 8%|▊ | 8262/100000 [2:09:46<14:55:59, 1.71it/s] Train steps ... : 8%|▊ | 8263/100000 [2:09:47<14:55:24, 1.71it/s] Train steps ... : 8%|▊ | 8264/100000 [2:09:47<14:56:54, 1.70it/s] Train steps ... : 8%|▊ | 8265/100000 [2:09:48<14:58:14, 1.70it/s] Train steps ... : 8%|▊ | 8266/100000 [2:09:49<14:57:34, 1.70it/s] Train steps ... : 8%|▊ | 8267/100000 [2:09:49<14:55:37, 1.71it/s] Train steps ... : 8%|▊ | 8268/100000 [2:09:50<14:56:18, 1.71it/s] Train steps ... : 8%|▊ | 8269/100000 [2:09:50<14:57:00, 1.70it/s] Train steps ... : 8%|▊ | 8270/100000 [2:09:51<14:55:48, 1.71it/s] Train steps ... : 8%|▊ | 8271/100000 [2:09:52<14:56:01, 1.71it/s] Train steps ... : 8%|▊ | 8272/100000 [2:09:52<14:56:43, 1.70it/s] Train steps ... : 8%|▊ | 8273/100000 [2:09:53<14:56:27, 1.71it/s] Train steps ... : 8%|▊ | 8274/100000 [2:09:53<14:58:20, 1.70it/s] Train steps ... : 8%|▊ | 8275/100000 [2:09:54<14:55:54, 1.71it/s]Step... (8275 / 100000 | Loss: 1.209798812866211, Learning Rate: 9.218592964824121e-05) Step... (8275 / 100000 | Loss: 1.0771301984786987, Learning Rate: 9.218592964824121e-05) Train steps ... : 8%|▊ | 8275/100000 [2:09:54<14:55:54, 1.71it/s] Train steps ... : 8%|▊ | 8276/100000 [2:09:54<14:56:43, 1.70it/s] Train steps ... : 8%|▊ | 8277/100000 [2:09:55<14:56:01, 1.71it/s] Train steps ... : 8%|▊ | 8278/100000 [2:09:56<14:55:45, 1.71it/s] Train steps ... : 8%|▊ | 8279/100000 [2:09:56<14:56:59, 1.70it/s] Train steps ... : 8%|▊ | 8280/100000 [2:09:57<14:57:03, 1.70it/s] Train steps ... : 8%|▊ | 8281/100000 [2:09:57<14:55:41, 1.71it/s] Train steps ... : 8%|▊ | 8282/100000 [2:09:58<14:59:17, 1.70it/s] Train steps ... : 8%|▊ | 8283/100000 [2:09:59<14:57:15, 1.70it/s] Train steps ... : 8%|▊ | 8284/100000 [2:09:59<14:57:53, 1.70it/s] Train steps ... : 8%|▊ | 8285/100000 [2:10:00<14:56:06, 1.71it/s] Train steps ... : 8%|▊ | 8286/100000 [2:10:00<14:57:56, 1.70it/s] Train steps ... : 8%|▊ | 8287/100000 [2:10:01<14:56:46, 1.70it/s] Train steps ... : 8%|▊ | 8288/100000 [2:10:01<14:55:04, 1.71it/s] Train steps ... : 8%|▊ | 8289/100000 [2:10:02<14:55:30, 1.71it/s] Train steps ... : 8%|▊ | 8290/100000 [2:10:03<14:55:34, 1.71it/s] Train steps ... : 8%|▊ | 8291/100000 [2:10:03<14:56:59, 1.70it/s] Train steps ... : 8%|▊ | 8292/100000 [2:10:04<14:58:42, 1.70it/s] Train steps ... : 8%|▊ | 8293/100000 [2:10:04<14:57:20, 1.70it/s] Train steps ... : 8%|▊ | 8294/100000 [2:10:05<14:56:30, 1.70it/s] Train steps ... : 8%|▊ | 8295/100000 [2:10:06<14:56:27, 1.70it/s] Train steps ... : 8%|▊ | 8296/100000 [2:10:06<14:56:02, 1.71it/s] Train steps ... : 8%|▊ | 8297/100000 [2:10:07<14:56:02, 1.71it/s] Train steps ... : 8%|▊ | 8298/100000 [2:10:07<14:55:30, 1.71it/s] Train steps ... : 8%|▊ | 8299/100000 [2:10:08<14:54:20, 1.71it/s] Train steps ... : 8%|▊ | 8300/100000 [2:10:09<14:56:03, 1.71it/s]Step... (8300 / 100000 | Loss: 1.2549796104431152, Learning Rate: 9.216080402010051e-05) Step... (8300 / 100000 | Loss: 1.1676994562149048, Learning Rate: 9.216080402010051e-05) Train steps ... : 8%|▊ | 8300/100000 [2:10:09<14:56:03, 1.71it/s] Train steps ... : 8%|▊ | 8301/100000 [2:10:09<14:57:24, 1.70it/s] Train steps ... : 8%|▊ | 8302/100000 [2:10:10<14:56:58, 1.70it/s] Train steps ... : 8%|▊ | 8303/100000 [2:10:10<14:55:23, 1.71it/s] Train steps ... : 8%|▊ | 8304/100000 [2:10:11<14:55:26, 1.71it/s] Train steps ... : 8%|▊ | 8305/100000 [2:10:11<14:57:06, 1.70it/s] Train steps ... : 8%|▊ | 8306/100000 [2:10:12<14:55:31, 1.71it/s] Train steps ... : 8%|▊ | 8307/100000 [2:10:13<14:53:30, 1.71it/s] Train steps ... : 8%|▊ | 8308/100000 [2:10:13<14:54:33, 1.71it/s] Train steps ... : 8%|▊ | 8309/100000 [2:10:14<14:55:40, 1.71it/s] Train steps ... : 8%|▊ | 8310/100000 [2:10:14<14:57:35, 1.70it/s] Train steps ... : 8%|▊ | 8311/100000 [2:10:15<14:53:56, 1.71it/s] Train steps ... : 8%|▊ | 8312/100000 [2:10:16<14:53:51, 1.71it/s] Train steps ... : 8%|▊ | 8313/100000 [2:10:16<14:53:21, 1.71it/s] Train steps ... : 8%|▊ | 8314/100000 [2:10:17<14:54:49, 1.71it/s] Train steps ... : 8%|▊ | 8315/100000 [2:10:17<14:53:59, 1.71it/s] Train steps ... : 8%|▊ | 8316/100000 [2:10:18<14:54:41, 1.71it/s] Train steps ... : 8%|▊ | 8317/100000 [2:10:18<14:54:11, 1.71it/s] Train steps ... : 8%|▊ | 8318/100000 [2:10:19<14:53:10, 1.71it/s] Train steps ... : 8%|▊ | 8319/100000 [2:10:20<14:52:55, 1.71it/s] Train steps ... : 8%|▊ | 8320/100000 [2:10:20<14:52:52, 1.71it/s] Train steps ... : 8%|▊ | 8321/100000 [2:10:21<14:53:30, 1.71it/s] Train steps ... : 8%|▊ | 8322/100000 [2:10:21<14:53:36, 1.71it/s] Train steps ... : 8%|▊ | 8323/100000 [2:10:22<14:54:20, 1.71it/s] Train steps ... : 8%|▊ | 8324/100000 [2:10:23<14:53:42, 1.71it/s] Train steps ... : 8%|▊ | 8325/100000 [2:10:23<14:53:08, 1.71it/s]Step... (8325 / 100000 | Loss: 1.5434311628341675, Learning Rate: 9.21356783919598e-05) Step... (8325 / 100000 | Loss: 1.1750093698501587, Learning Rate: 9.21356783919598e-05) Train steps ... : 8%|▊ | 8325/100000 [2:10:23<14:53:08, 1.71it/s] Train steps ... : 8%|▊ | 8326/100000 [2:10:24<14:53:37, 1.71it/s] Train steps ... : 8%|▊ | 8327/100000 [2:10:24<14:53:14, 1.71it/s] Train steps ... : 8%|▊ | 8328/100000 [2:10:25<14:52:38, 1.71it/s] Train steps ... : 8%|▊ | 8329/100000 [2:10:25<14:53:13, 1.71it/s] Train steps ... : 8%|▊ | 8330/100000 [2:10:26<14:54:06, 1.71it/s] Train steps ... : 8%|▊ | 8331/100000 [2:10:27<14:54:12, 1.71it/s] Train steps ... : 8%|▊ | 8332/100000 [2:10:27<14:54:24, 1.71it/s] Train steps ... : 8%|▊ | 8333/100000 [2:10:28<14:54:35, 1.71it/s] Train steps ... : 8%|▊ | 8334/100000 [2:10:28<14:55:00, 1.71it/s] Train steps ... : 8%|▊ | 8335/100000 [2:10:29<14:56:56, 1.70it/s] Train steps ... : 8%|▊ | 8336/100000 [2:10:30<14:55:26, 1.71it/s] Train steps ... : 8%|▊ | 8337/100000 [2:10:30<14:57:07, 1.70it/s] Train steps ... : 8%|▊ | 8338/100000 [2:10:31<14:56:06, 1.70it/s] Train steps ... : 8%|▊ | 8339/100000 [2:10:31<14:55:26, 1.71it/s] Train steps ... : 8%|▊ | 8340/100000 [2:10:32<14:54:57, 1.71it/s] Train steps ... : 8%|▊ | 8341/100000 [2:10:33<14:54:42, 1.71it/s] Train steps ... : 8%|▊ | 8342/100000 [2:10:33<14:55:10, 1.71it/s] Train steps ... : 8%|▊ | 8343/100000 [2:10:34<14:54:29, 1.71it/s] Train steps ... : 8%|▊ | 8344/100000 [2:10:34<14:54:09, 1.71it/s] Train steps ... : 8%|▊ | 8345/100000 [2:10:35<14:55:25, 1.71it/s] Train steps ... : 8%|▊ | 8346/100000 [2:10:35<14:56:21, 1.70it/s] Train steps ... : 8%|▊ | 8347/100000 [2:10:36<14:55:32, 1.71it/s] Train steps ... : 8%|▊ | 8348/100000 [2:10:37<14:55:16, 1.71it/s] Train steps ... : 8%|▊ | 8349/100000 [2:10:37<14:55:48, 1.71it/s] Train steps ... : 8%|▊ | 8350/100000 [2:10:38<14:57:24, 1.70it/s]Step... (8350 / 100000 | Loss: 1.4770877361297607, Learning Rate: 9.21105527638191e-05) Step... (8350 / 100000 | Loss: 1.7111707925796509, Learning Rate: 9.21105527638191e-05) Train steps ... : 8%|▊ | 8350/100000 [2:10:38<14:57:24, 1.70it/s] Train steps ... : 8%|▊ | 8351/100000 [2:10:38<14:58:21, 1.70it/s] Train steps ... : 8%|▊ | 8352/100000 [2:10:39<14:54:49, 1.71it/s] Train steps ... : 8%|▊ | 8353/100000 [2:10:40<14:53:55, 1.71it/s] Train steps ... : 8%|▊ | 8354/100000 [2:10:40<14:53:50, 1.71it/s] Train steps ... : 8%|▊ | 8355/100000 [2:10:41<14:56:36, 1.70it/s] Train steps ... : 8%|▊ | 8356/100000 [2:10:41<14:56:15, 1.70it/s] Train steps ... : 8%|▊ | 8357/100000 [2:10:42<14:57:09, 1.70it/s] Train steps ... : 8%|▊ | 8358/100000 [2:10:42<14:55:11, 1.71it/s] Train steps ... : 8%|▊ | 8359/100000 [2:10:43<14:55:22, 1.71it/s] Train steps ... : 8%|▊ | 8360/100000 [2:10:44<14:58:31, 1.70it/s] Train steps ... : 8%|▊ | 8361/100000 [2:10:44<14:56:44, 1.70it/s] Train steps ... : 8%|▊ | 8362/100000 [2:10:45<14:57:27, 1.70it/s] Train steps ... : 8%|▊ | 8363/100000 [2:10:45<14:57:35, 1.70it/s] Train steps ... : 8%|▊ | 8364/100000 [2:10:46<14:58:50, 1.70it/s] Train steps ... : 8%|▊ | 8365/100000 [2:10:47<14:59:09, 1.70it/s] Train steps ... : 8%|▊ | 8366/100000 [2:10:47<14:57:10, 1.70it/s] Train steps ... : 8%|▊ | 8367/100000 [2:10:48<14:57:23, 1.70it/s] Train steps ... : 8%|▊ | 8368/100000 [2:10:48<14:56:27, 1.70it/s] Train steps ... : 8%|▊ | 8369/100000 [2:10:49<14:56:49, 1.70it/s] Train steps ... : 8%|▊ | 8370/100000 [2:10:50<14:55:36, 1.71it/s] Train steps ... : 8%|▊ | 8371/100000 [2:10:50<14:58:04, 1.70it/s] Train steps ... : 8%|▊ | 8372/100000 [2:10:51<14:56:54, 1.70it/s] Train steps ... : 8%|▊ | 8373/100000 [2:10:51<14:53:35, 1.71it/s] Train steps ... : 8%|▊ | 8374/100000 [2:10:52<14:55:20, 1.71it/s] Train steps ... : 8%|▊ | 8375/100000 [2:10:52<14:54:09, 1.71it/s]Step... (8375 / 100000 | Loss: 1.3072617053985596, Learning Rate: 9.208542713567839e-05) Step... (8375 / 100000 | Loss: 1.0278468132019043, Learning Rate: 9.208542713567839e-05) Train steps ... : 8%|▊ | 8375/100000 [2:10:53<14:54:09, 1.71it/s] Train steps ... : 8%|▊ | 8376/100000 [2:10:53<14:53:52, 1.71it/s] Train steps ... : 8%|▊ | 8377/100000 [2:10:54<14:55:56, 1.70it/s] Train steps ... : 8%|▊ | 8378/100000 [2:10:54<14:54:48, 1.71it/s] Train steps ... : 8%|▊ | 8379/100000 [2:10:55<14:56:09, 1.70it/s] Train steps ... : 8%|▊ | 8380/100000 [2:10:55<14:57:06, 1.70it/s] Train steps ... : 8%|▊ | 8381/100000 [2:10:56<14:58:47, 1.70it/s] Train steps ... : 8%|▊ | 8382/100000 [2:10:57<14:58:45, 1.70it/s] Train steps ... : 8%|▊ | 8383/100000 [2:10:57<14:55:47, 1.70it/s] Train steps ... : 8%|▊ | 8384/100000 [2:10:58<14:55:07, 1.71it/s] Train steps ... : 8%|▊ | 8385/100000 [2:10:58<14:56:50, 1.70it/s] Train steps ... : 8%|▊ | 8386/100000 [2:10:59<14:56:06, 1.70it/s] Train steps ... : 8%|▊ | 8387/100000 [2:11:00<14:55:37, 1.70it/s] Train steps ... : 8%|▊ | 8388/100000 [2:11:00<14:55:53, 1.70it/s] Train steps ... : 8%|▊ | 8389/100000 [2:11:01<14:59:23, 1.70it/s] Train steps ... : 8%|▊ | 8390/100000 [2:11:01<14:58:23, 1.70it/s] Train steps ... : 8%|▊ | 8391/100000 [2:11:02<14:57:05, 1.70it/s] Train steps ... : 8%|▊ | 8392/100000 [2:11:02<14:54:18, 1.71it/s] Train steps ... : 8%|▊ | 8393/100000 [2:11:03<14:54:45, 1.71it/s] Train steps ... : 8%|▊ | 8394/100000 [2:11:04<14:54:14, 1.71it/s] Train steps ... : 8%|▊ | 8395/100000 [2:11:04<14:53:34, 1.71it/s] Train steps ... : 8%|▊ | 8396/100000 [2:11:05<14:54:36, 1.71it/s] Train steps ... : 8%|▊ | 8397/100000 [2:11:05<14:54:44, 1.71it/s] Train steps ... : 8%|▊ | 8398/100000 [2:11:06<14:53:36, 1.71it/s] Train steps ... : 8%|▊ | 8399/100000 [2:11:07<14:53:05, 1.71it/s] Train steps ... : 8%|▊ | 8400/100000 [2:11:07<14:52:38, 1.71it/s]Step... (8400 / 100000 | Loss: 1.204118013381958, Learning Rate: 9.20603015075377e-05) Step... (8400 / 100000 | Loss: 1.3729712963104248, Learning Rate: 9.20603015075377e-05) Train steps ... : 8%|▊ | 8400/100000 [2:11:07<14:52:38, 1.71it/s] Train steps ... : 8%|▊ | 8401/100000 [2:11:08<14:52:10, 1.71it/s] Train steps ... : 8%|▊ | 8402/100000 [2:11:08<14:51:58, 1.71it/s] Train steps ... : 8%|▊ | 8403/100000 [2:11:09<14:52:57, 1.71it/s] Train steps ... : 8%|▊ | 8404/100000 [2:11:09<14:52:44, 1.71it/s] Train steps ... : 8%|▊ | 8405/100000 [2:11:10<14:53:54, 1.71it/s] Train steps ... : 8%|▊ | 8406/100000 [2:11:11<14:54:46, 1.71it/s] Train steps ... : 8%|▊ | 8407/100000 [2:11:11<14:55:08, 1.71it/s] Train steps ... : 8%|▊ | 8408/100000 [2:11:12<14:53:24, 1.71it/s] Train steps ... : 8%|▊ | 8409/100000 [2:11:12<14:55:17, 1.71it/s] Train steps ... : 8%|▊ | 8410/100000 [2:11:13<14:58:14, 1.70it/s] Train steps ... : 8%|▊ | 8411/100000 [2:11:14<14:53:46, 1.71it/s] Train steps ... : 8%|▊ | 8412/100000 [2:11:14<14:53:39, 1.71it/s] Train steps ... : 8%|▊ | 8413/100000 [2:11:15<14:53:38, 1.71it/s] Train steps ... : 8%|▊ | 8414/100000 [2:11:15<14:53:21, 1.71it/s] Train steps ... : 8%|▊ | 8415/100000 [2:11:16<14:52:53, 1.71it/s] Train steps ... : 8%|▊ | 8416/100000 [2:11:17<14:53:00, 1.71it/s] Train steps ... : 8%|▊ | 8417/100000 [2:11:17<14:52:52, 1.71it/s] Train steps ... : 8%|▊ | 8418/100000 [2:11:18<14:55:08, 1.71it/s] Train steps ... : 8%|▊ | 8419/100000 [2:11:18<14:54:08, 1.71it/s] Train steps ... : 8%|▊ | 8420/100000 [2:11:19<14:55:36, 1.70it/s] Train steps ... : 8%|▊ | 8421/100000 [2:11:19<14:54:16, 1.71it/s] Train steps ... : 8%|▊ | 8422/100000 [2:11:20<14:55:19, 1.70it/s] Train steps ... : 8%|▊ | 8423/100000 [2:11:21<14:54:18, 1.71it/s] Train steps ... : 8%|▊ | 8424/100000 [2:11:21<14:53:31, 1.71it/s] Train steps ... : 8%|▊ | 8425/100000 [2:11:22<14:53:24, 1.71it/s]Step... (8425 / 100000 | Loss: 1.5033388137817383, Learning Rate: 9.203517587939698e-05) Step... (8425 / 100000 | Loss: 1.5469788312911987, Learning Rate: 9.203517587939698e-05) Train steps ... : 8%|▊ | 8425/100000 [2:11:22<14:53:24, 1.71it/s] Train steps ... : 8%|▊ | 8426/100000 [2:11:22<14:54:05, 1.71it/s] Train steps ... : 8%|▊ | 8427/100000 [2:11:23<14:56:52, 1.70it/s] Train steps ... : 8%|▊ | 8428/100000 [2:11:24<14:55:06, 1.71it/s] Train steps ... : 8%|▊ | 8429/100000 [2:11:24<14:54:45, 1.71it/s] Train steps ... : 8%|▊ | 8430/100000 [2:11:25<14:54:04, 1.71it/s] Train steps ... : 8%|▊ | 8431/100000 [2:11:25<14:53:29, 1.71it/s] Train steps ... : 8%|▊ | 8432/100000 [2:11:26<14:53:28, 1.71it/s] Train steps ... : 8%|▊ | 8433/100000 [2:11:26<14:54:10, 1.71it/s] Train steps ... : 8%|▊ | 8434/100000 [2:11:27<14:53:05, 1.71it/s] Train steps ... : 8%|▊ | 8435/100000 [2:11:28<14:54:15, 1.71it/s] Train steps ... : 8%|▊ | 8436/100000 [2:11:28<14:54:01, 1.71it/s] Train steps ... : 8%|▊ | 8437/100000 [2:11:29<14:56:20, 1.70it/s] Train steps ... : 8%|▊ | 8438/100000 [2:11:29<14:54:15, 1.71it/s] Train steps ... : 8%|▊ | 8439/100000 [2:11:30<14:53:42, 1.71it/s] Train steps ... : 8%|▊ | 8440/100000 [2:11:31<14:54:49, 1.71it/s] Train steps ... : 8%|▊ | 8441/100000 [2:11:31<14:54:44, 1.71it/s] Train steps ... : 8%|▊ | 8442/100000 [2:11:32<14:56:15, 1.70it/s] Train steps ... : 8%|▊ | 8443/100000 [2:11:32<14:54:28, 1.71it/s] Train steps ... : 8%|▊ | 8444/100000 [2:11:33<14:55:29, 1.70it/s] Train steps ... : 8%|▊ | 8445/100000 [2:11:33<14:52:46, 1.71it/s] Train steps ... : 8%|▊ | 8446/100000 [2:11:34<14:53:11, 1.71it/s] Train steps ... : 8%|▊ | 8447/100000 [2:11:35<14:52:59, 1.71it/s] Train steps ... : 8%|▊ | 8448/100000 [2:11:35<14:52:51, 1.71it/s] Train steps ... : 8%|▊ | 8449/100000 [2:11:36<14:52:55, 1.71it/s] Train steps ... : 8%|▊ | 8450/100000 [2:11:36<14:57:30, 1.70it/s]Step... (8450 / 100000 | Loss: 1.5914547443389893, Learning Rate: 9.201005025125629e-05) Step... (8450 / 100000 | Loss: 1.0675525665283203, Learning Rate: 9.201005025125629e-05) Train steps ... : 8%|▊ | 8450/100000 [2:11:37<14:57:30, 1.70it/s] Train steps ... : 8%|▊ | 8451/100000 [2:11:37<14:56:25, 1.70it/s] Train steps ... : 8%|▊ | 8452/100000 [2:11:38<14:55:20, 1.70it/s] Train steps ... : 8%|▊ | 8453/100000 [2:11:38<14:53:44, 1.71it/s] Train steps ... : 8%|▊ | 8454/100000 [2:11:39<14:54:58, 1.70it/s] Train steps ... : 8%|▊ | 8455/100000 [2:11:39<14:55:24, 1.70it/s] Train steps ... : 8%|▊ | 8456/100000 [2:11:40<14:54:53, 1.70it/s] Train steps ... : 8%|▊ | 8457/100000 [2:11:41<14:53:15, 1.71it/s] Train steps ... : 8%|▊ | 8458/100000 [2:11:41<14:54:59, 1.70it/s] Train steps ... : 8%|▊ | 8459/100000 [2:11:42<14:53:41, 1.71it/s] Train steps ... : 8%|▊ | 8460/100000 [2:11:42<14:52:51, 1.71it/s] Train steps ... : 8%|▊ | 8461/100000 [2:11:43<14:53:26, 1.71it/s] Train steps ... : 8%|▊ | 8462/100000 [2:11:43<14:54:41, 1.71it/s] Train steps ... : 8%|▊ | 8463/100000 [2:11:44<14:54:22, 1.71it/s] Train steps ... : 8%|▊ | 8464/100000 [2:11:45<14:53:41, 1.71it/s] Train steps ... : 8%|▊ | 8465/100000 [2:11:45<14:53:39, 1.71it/s] Train steps ... : 8%|▊ | 8466/100000 [2:11:46<14:53:55, 1.71it/s] Train steps ... : 8%|▊ | 8467/100000 [2:11:46<14:53:58, 1.71it/s] Train steps ... : 8%|▊ | 8468/100000 [2:11:47<14:52:41, 1.71it/s] Train steps ... : 8%|▊ | 8469/100000 [2:11:48<14:52:42, 1.71it/s] Train steps ... : 8%|▊ | 8470/100000 [2:11:48<14:52:39, 1.71it/s] Train steps ... : 8%|▊ | 8471/100000 [2:11:49<14:56:48, 1.70it/s] Train steps ... : 8%|▊ | 8472/100000 [2:11:49<14:55:03, 1.70it/s] Train steps ... : 8%|▊ | 8473/100000 [2:11:50<14:55:29, 1.70it/s] Train steps ... : 8%|▊ | 8474/100000 [2:11:51<14:57:19, 1.70it/s] Train steps ... : 8%|▊ | 8475/100000 [2:11:51<14:55:28, 1.70it/s]Step... (8475 / 100000 | Loss: 1.8075342178344727, Learning Rate: 9.198492462311559e-05) Step... (8475 / 100000 | Loss: 1.6880946159362793, Learning Rate: 9.198492462311559e-05) Train steps ... : 8%|▊ | 8475/100000 [2:11:51<14:55:28, 1.70it/s] Train steps ... : 8%|▊ | 8476/100000 [2:11:52<14:59:10, 1.70it/s] Train steps ... : 8%|▊ | 8477/100000 [2:11:52<14:57:32, 1.70it/s] Train steps ... : 8%|▊ | 8478/100000 [2:11:53<14:59:59, 1.69it/s] Train steps ... : 8%|▊ | 8479/100000 [2:11:53<14:57:04, 1.70it/s] Train steps ... : 8%|▊ | 8480/100000 [2:11:54<14:54:10, 1.71it/s] Train steps ... : 8%|▊ | 8481/100000 [2:11:55<14:56:11, 1.70it/s] Train steps ... : 8%|▊ | 8482/100000 [2:11:55<14:55:48, 1.70it/s] Train steps ... : 8%|▊ | 8483/100000 [2:11:56<14:57:14, 1.70it/s] Train steps ... : 8%|▊ | 8484/100000 [2:11:56<14:56:06, 1.70it/s] Train steps ... : 8%|▊ | 8485/100000 [2:11:57<15:01:14, 1.69it/s] Train steps ... : 8%|▊ | 8486/100000 [2:11:58<14:58:54, 1.70it/s] Train steps ... : 8%|▊ | 8487/100000 [2:11:58<14:59:58, 1.69it/s] Train steps ... : 8%|▊ | 8488/100000 [2:11:59<15:00:36, 1.69it/s] Train steps ... : 8%|▊ | 8489/100000 [2:11:59<14:55:54, 1.70it/s] Train steps ... : 8%|▊ | 8490/100000 [2:12:00<14:56:20, 1.70it/s] Train steps ... : 8%|▊ | 8491/100000 [2:12:01<14:57:56, 1.70it/s] Train steps ... : 8%|▊ | 8492/100000 [2:12:01<14:58:15, 1.70it/s] Train steps ... : 8%|▊ | 8493/100000 [2:12:02<14:57:49, 1.70it/s] Train steps ... : 8%|▊ | 8494/100000 [2:12:02<14:57:22, 1.70it/s] Train steps ... : 8%|▊ | 8495/100000 [2:12:03<14:56:55, 1.70it/s] Train steps ... : 8%|▊ | 8496/100000 [2:12:03<14:55:29, 1.70it/s] Train steps ... : 8%|▊ | 8497/100000 [2:12:04<14:55:37, 1.70it/s] Train steps ... : 8%|▊ | 8498/100000 [2:12:05<14:54:13, 1.71it/s] Train steps ... : 8%|▊ | 8499/100000 [2:12:05<14:54:03, 1.71it/s] Train steps ... : 8%|▊ | 8500/100000 [2:12:06<14:54:18, 1.71it/s]Step... (8500 / 100000 | Loss: 1.2257150411605835, Learning Rate: 9.195979899497488e-05) Step... (8500 / 100000 | Loss: 1.519235610961914, Learning Rate: 9.195979899497488e-05) Train steps ... : 8%|▊ | 8500/100000 [2:12:06<14:54:18, 1.71it/s] Train steps ... : 9%|▊ | 8501/100000 [2:12:06<14:52:49, 1.71it/s] Train steps ... : 9%|▊ | 8502/100000 [2:12:07<14:53:13, 1.71it/s] Train steps ... : 9%|▊ | 8503/100000 [2:12:08<14:52:06, 1.71it/s] Train steps ... : 9%|▊ | 8504/100000 [2:12:08<14:54:30, 1.70it/s] Train steps ... : 9%|▊ | 8505/100000 [2:12:09<14:54:02, 1.71it/s] Train steps ... : 9%|▊ | 8506/100000 [2:12:09<14:52:58, 1.71it/s] Train steps ... : 9%|▊ | 8507/100000 [2:12:10<14:51:52, 1.71it/s] Train steps ... : 9%|▊ | 8508/100000 [2:12:10<14:52:31, 1.71it/s] Train steps ... : 9%|▊ | 8509/100000 [2:12:11<14:52:36, 1.71it/s] Train steps ... : 9%|▊ | 8510/100000 [2:12:12<14:52:43, 1.71it/s] Train steps ... : 9%|▊ | 8511/100000 [2:12:12<14:52:50, 1.71it/s] Train steps ... : 9%|▊ | 8512/100000 [2:12:13<14:53:32, 1.71it/s] Train steps ... : 9%|▊ | 8513/100000 [2:12:13<14:52:59, 1.71it/s] Train steps ... : 9%|▊ | 8514/100000 [2:12:14<14:54:14, 1.71it/s] Train steps ... : 9%|▊ | 8515/100000 [2:12:15<14:55:34, 1.70it/s] Train steps ... : 9%|▊ | 8516/100000 [2:12:15<14:56:34, 1.70it/s] Train steps ... : 9%|▊ | 8517/100000 [2:12:16<14:57:46, 1.70it/s] Train steps ... : 9%|▊ | 8518/100000 [2:12:16<14:55:30, 1.70it/s] Train steps ... : 9%|▊ | 8519/100000 [2:12:17<14:55:39, 1.70it/s] Train steps ... : 9%|▊ | 8520/100000 [2:12:18<14:55:29, 1.70it/s] Train steps ... : 9%|▊ | 8521/100000 [2:12:18<14:54:17, 1.70it/s] Train steps ... : 9%|▊ | 8522/100000 [2:12:19<14:54:03, 1.71it/s] Train steps ... : 9%|▊ | 8523/100000 [2:12:19<14:54:33, 1.70it/s] Train steps ... : 9%|▊ | 8524/100000 [2:12:20<14:54:09, 1.71it/s] Train steps ... : 9%|▊ | 8525/100000 [2:12:20<14:53:43, 1.71it/s]Step... (8525 / 100000 | Loss: 1.8863849639892578, Learning Rate: 9.193467336683418e-05) Step... (8525 / 100000 | Loss: 1.637603759765625, Learning Rate: 9.193467336683418e-05) Train steps ... : 9%|▊ | 8525/100000 [2:12:21<14:53:43, 1.71it/s] Train steps ... : 9%|▊ | 8526/100000 [2:12:21<14:55:08, 1.70it/s] Train steps ... : 9%|▊ | 8527/100000 [2:12:22<14:54:06, 1.71it/s] Train steps ... : 9%|▊ | 8528/100000 [2:12:22<14:52:30, 1.71it/s] Train steps ... : 9%|▊ | 8529/100000 [2:12:23<14:53:02, 1.71it/s] Train steps ... : 9%|▊ | 8530/100000 [2:12:23<14:53:24, 1.71it/s] Train steps ... : 9%|▊ | 8531/100000 [2:12:24<14:54:46, 1.70it/s] Train steps ... : 9%|▊ | 8532/100000 [2:12:25<14:52:18, 1.71it/s] Train steps ... : 9%|▊ | 8533/100000 [2:12:25<14:54:59, 1.70it/s] Train steps ... : 9%|▊ | 8534/100000 [2:12:26<14:54:56, 1.70it/s] Train steps ... : 9%|▊ | 8535/100000 [2:12:26<14:55:07, 1.70it/s] Train steps ... : 9%|▊ | 8536/100000 [2:12:27<14:54:39, 1.70it/s] Train steps ... : 9%|▊ | 8537/100000 [2:12:27<14:54:01, 1.71it/s] Train steps ... : 9%|▊ | 8538/100000 [2:12:28<14:54:58, 1.70it/s] Train steps ... : 9%|▊ | 8539/100000 [2:12:29<14:54:44, 1.70it/s] Train steps ... : 9%|▊ | 8540/100000 [2:12:29<14:54:15, 1.70it/s] Train steps ... : 9%|▊ | 8541/100000 [2:12:30<14:54:31, 1.70it/s] Train steps ... : 9%|▊ | 8542/100000 [2:12:30<14:52:42, 1.71it/s] Train steps ... : 9%|▊ | 8543/100000 [2:12:31<14:52:28, 1.71it/s] Train steps ... : 9%|▊ | 8544/100000 [2:12:32<14:51:06, 1.71it/s] Train steps ... : 9%|▊ | 8545/100000 [2:12:32<14:50:45, 1.71it/s] Train steps ... : 9%|▊ | 8546/100000 [2:12:33<14:49:48, 1.71it/s] Train steps ... : 9%|▊ | 8547/100000 [2:12:33<14:51:55, 1.71it/s] Train steps ... : 9%|▊ | 8548/100000 [2:12:34<14:49:24, 1.71it/s] Train steps ... : 9%|▊ | 8549/100000 [2:12:35<14:49:58, 1.71it/s] Train steps ... : 9%|▊ | 8550/100000 [2:12:35<14:51:14, 1.71it/s]Step... (8550 / 100000 | Loss: 1.024999737739563, Learning Rate: 9.190954773869346e-05) Step... (8550 / 100000 | Loss: 1.324230670928955, Learning Rate: 9.190954773869346e-05) Train steps ... : 9%|▊ | 8550/100000 [2:12:35<14:51:14, 1.71it/s] Train steps ... : 9%|▊ | 8551/100000 [2:12:36<14:50:59, 1.71it/s] Train steps ... : 9%|▊ | 8552/100000 [2:12:36<14:51:31, 1.71it/s] Train steps ... : 9%|▊ | 8553/100000 [2:12:37<14:51:07, 1.71it/s] Train steps ... : 9%|▊ | 8554/100000 [2:12:37<14:51:07, 1.71it/s] Train steps ... : 9%|▊ | 8555/100000 [2:12:38<14:51:34, 1.71it/s] Train steps ... : 9%|▊ | 8556/100000 [2:12:39<14:52:24, 1.71it/s] Train steps ... : 9%|▊ | 8557/100000 [2:12:39<14:54:34, 1.70it/s] Train steps ... : 9%|▊ | 8558/100000 [2:12:40<14:53:55, 1.70it/s] Train steps ... : 9%|▊ | 8559/100000 [2:12:40<14:53:52, 1.70it/s] Train steps ... : 9%|▊ | 8560/100000 [2:12:41<14:51:53, 1.71it/s] Train steps ... : 9%|▊ | 8561/100000 [2:12:42<14:52:03, 1.71it/s] Train steps ... : 9%|▊ | 8562/100000 [2:12:42<14:52:38, 1.71it/s] Train steps ... : 9%|▊ | 8563/100000 [2:12:43<14:53:52, 1.70it/s] Train steps ... : 9%|▊ | 8564/100000 [2:12:43<14:53:23, 1.71it/s] Train steps ... : 9%|▊ | 8565/100000 [2:12:44<14:56:16, 1.70it/s] Train steps ... : 9%|▊ | 8566/100000 [2:12:44<14:54:38, 1.70it/s] Train steps ... : 9%|▊ | 8567/100000 [2:12:45<14:58:53, 1.70it/s] Train steps ... : 9%|▊ | 8568/100000 [2:12:46<14:54:17, 1.70it/s] Train steps ... : 9%|▊ | 8569/100000 [2:12:46<14:55:36, 1.70it/s] Train steps ... : 9%|▊ | 8570/100000 [2:12:47<14:56:46, 1.70it/s] Train steps ... : 9%|▊ | 8571/100000 [2:12:47<14:55:57, 1.70it/s] Train steps ... : 9%|▊ | 8572/100000 [2:12:48<14:54:45, 1.70it/s] Train steps ... : 9%|▊ | 8573/100000 [2:12:49<14:55:03, 1.70it/s] Train steps ... : 9%|▊ | 8574/100000 [2:12:49<14:55:18, 1.70it/s] Train steps ... : 9%|▊ | 8575/100000 [2:12:50<14:56:13, 1.70it/s]Step... (8575 / 100000 | Loss: 1.2231327295303345, Learning Rate: 9.188442211055277e-05) Step... (8575 / 100000 | Loss: 1.5331041812896729, Learning Rate: 9.188442211055277e-05) Train steps ... : 9%|▊ | 8575/100000 [2:12:50<14:56:13, 1.70it/s] Train steps ... : 9%|▊ | 8576/100000 [2:12:50<14:53:57, 1.70it/s] Train steps ... : 9%|▊ | 8577/100000 [2:12:51<14:54:15, 1.70it/s] Train steps ... : 9%|▊ | 8578/100000 [2:12:52<14:54:17, 1.70it/s] Train steps ... : 9%|▊ | 8579/100000 [2:12:52<14:53:20, 1.71it/s] Train steps ... : 9%|▊ | 8580/100000 [2:12:53<14:52:14, 1.71it/s] Train steps ... : 9%|▊ | 8581/100000 [2:12:53<14:51:11, 1.71it/s] Train steps ... : 9%|▊ | 8582/100000 [2:12:54<14:52:05, 1.71it/s] Train steps ... : 9%|▊ | 8583/100000 [2:12:54<14:53:17, 1.71it/s] Train steps ... : 9%|▊ | 8584/100000 [2:12:55<14:52:04, 1.71it/s] Train steps ... : 9%|▊ | 8585/100000 [2:12:56<14:53:53, 1.70it/s] Train steps ... : 9%|▊ | 8586/100000 [2:12:56<14:53:11, 1.71it/s] Train steps ... : 9%|▊ | 8587/100000 [2:12:57<14:54:37, 1.70it/s] Train steps ... : 9%|▊ | 8588/100000 [2:12:57<15:00:29, 1.69it/s] Train steps ... : 9%|▊ | 8589/100000 [2:12:58<14:56:13, 1.70it/s] Train steps ... : 9%|▊ | 8590/100000 [2:12:59<14:56:35, 1.70it/s] Train steps ... : 9%|▊ | 8591/100000 [2:12:59<14:58:12, 1.70it/s] Train steps ... : 9%|▊ | 8592/100000 [2:13:00<14:53:43, 1.70it/s] Train steps ... : 9%|▊ | 8593/100000 [2:13:00<14:52:44, 1.71it/s] Train steps ... : 9%|▊ | 8594/100000 [2:13:01<14:52:36, 1.71it/s] Train steps ... : 9%|▊ | 8595/100000 [2:13:02<14:55:43, 1.70it/s] Train steps ... : 9%|▊ | 8596/100000 [2:13:02<14:56:46, 1.70it/s] Train steps ... : 9%|▊ | 8597/100000 [2:13:03<14:55:10, 1.70it/s] Train steps ... : 9%|▊ | 8598/100000 [2:13:03<14:52:55, 1.71it/s] Train steps ... : 9%|▊ | 8599/100000 [2:13:04<14:51:48, 1.71it/s] Train steps ... : 9%|▊ | 8600/100000 [2:13:04<14:53:51, 1.70it/s]Step... (8600 / 100000 | Loss: 1.077612280845642, Learning Rate: 9.185929648241206e-05) Step... (8600 / 100000 | Loss: 1.4773972034454346, Learning Rate: 9.185929648241206e-05) Train steps ... : 9%|▊ | 8600/100000 [2:13:05<14:53:51, 1.70it/s] Train steps ... : 9%|▊ | 8601/100000 [2:13:05<14:52:31, 1.71it/s] Train steps ... : 9%|▊ | 8602/100000 [2:13:06<14:52:26, 1.71it/s] Train steps ... : 9%|▊ | 8603/100000 [2:13:06<14:50:44, 1.71it/s] Train steps ... : 9%|▊ | 8604/100000 [2:13:07<14:51:17, 1.71it/s] Train steps ... : 9%|▊ | 8605/100000 [2:13:07<14:50:18, 1.71it/s] Train steps ... : 9%|▊ | 8606/100000 [2:13:08<14:50:05, 1.71it/s] Train steps ... : 9%|▊ | 8607/100000 [2:13:09<14:50:45, 1.71it/s] Train steps ... : 9%|▊ | 8608/100000 [2:13:09<14:54:03, 1.70it/s] Train steps ... : 9%|▊ | 8609/100000 [2:13:10<14:51:14, 1.71it/s] Train steps ... : 9%|▊ | 8610/100000 [2:13:10<14:51:24, 1.71it/s] Train steps ... : 9%|▊ | 8611/100000 [2:13:11<14:53:49, 1.70it/s] Train steps ... : 9%|▊ | 8612/100000 [2:13:11<14:53:46, 1.70it/s] Train steps ... : 9%|▊ | 8613/100000 [2:13:12<14:53:48, 1.70it/s] Train steps ... : 9%|▊ | 8614/100000 [2:13:13<14:53:33, 1.70it/s] Train steps ... : 9%|▊ | 8615/100000 [2:13:13<14:52:36, 1.71it/s] Train steps ... : 9%|▊ | 8616/100000 [2:13:14<14:52:28, 1.71it/s] Train steps ... : 9%|▊ | 8617/100000 [2:13:14<14:51:19, 1.71it/s] Train steps ... : 9%|▊ | 8618/100000 [2:13:15<14:52:47, 1.71it/s] Train steps ... : 9%|▊ | 8619/100000 [2:13:16<14:51:49, 1.71it/s] Train steps ... : 9%|▊ | 8620/100000 [2:13:16<14:51:58, 1.71it/s] Train steps ... : 9%|▊ | 8621/100000 [2:13:17<14:52:06, 1.71it/s] Train steps ... : 9%|▊ | 8622/100000 [2:13:17<14:51:43, 1.71it/s] Train steps ... : 9%|▊ | 8623/100000 [2:13:18<14:51:17, 1.71it/s] Train steps ... : 9%|▊ | 8624/100000 [2:13:18<14:51:17, 1.71it/s] Train steps ... : 9%|▊ | 8625/100000 [2:13:19<14:51:22, 1.71it/s]Step... (8625 / 100000 | Loss: 1.3776044845581055, Learning Rate: 9.183417085427137e-05) Step... (8625 / 100000 | Loss: 1.5301601886749268, Learning Rate: 9.183417085427137e-05) Train steps ... : 9%|▊ | 8625/100000 [2:13:19<14:51:22, 1.71it/s] Train steps ... : 9%|▊ | 8626/100000 [2:13:20<14:51:10, 1.71it/s] Train steps ... : 9%|▊ | 8627/100000 [2:13:20<14:51:05, 1.71it/s] Train steps ... : 9%|▊ | 8628/100000 [2:13:21<14:52:48, 1.71it/s] Train steps ... : 9%|▊ | 8629/100000 [2:13:21<14:53:16, 1.70it/s] Train steps ... : 9%|▊ | 8630/100000 [2:13:22<14:52:27, 1.71it/s] Train steps ... : 9%|▊ | 8631/100000 [2:13:23<14:53:32, 1.70it/s] Train steps ... : 9%|▊ | 8632/100000 [2:13:23<14:53:47, 1.70it/s] Train steps ... : 9%|▊ | 8633/100000 [2:13:24<14:54:37, 1.70it/s] Train steps ... : 9%|▊ | 8634/100000 [2:13:24<14:52:28, 1.71it/s] Train steps ... : 9%|▊ | 8635/100000 [2:13:25<14:52:21, 1.71it/s] Train steps ... : 9%|▊ | 8636/100000 [2:13:26<14:51:26, 1.71it/s] Train steps ... : 9%|▊ | 8637/100000 [2:13:26<14:51:52, 1.71it/s] Train steps ... : 9%|▊ | 8638/100000 [2:13:27<14:53:25, 1.70it/s] Train steps ... : 9%|▊ | 8639/100000 [2:13:27<14:56:37, 1.70it/s] Train steps ... : 9%|▊ | 8640/100000 [2:13:28<14:51:27, 1.71it/s] Train steps ... : 9%|▊ | 8641/100000 [2:13:28<14:52:16, 1.71it/s] Train steps ... : 9%|▊ | 8642/100000 [2:13:29<14:51:36, 1.71it/s] Train steps ... : 9%|▊ | 8643/100000 [2:13:30<14:50:55, 1.71it/s] Train steps ... : 9%|▊ | 8644/100000 [2:13:30<14:52:21, 1.71it/s] Train steps ... : 9%|▊ | 8645/100000 [2:13:31<14:51:48, 1.71it/s] Train steps ... : 9%|▊ | 8646/100000 [2:13:31<14:52:20, 1.71it/s] Train steps ... : 9%|▊ | 8647/100000 [2:13:32<14:52:21, 1.71it/s] Train steps ... : 9%|▊ | 8648/100000 [2:13:33<14:54:49, 1.70it/s] Train steps ... : 9%|▊ | 8649/100000 [2:13:33<14:52:42, 1.71it/s] Train steps ... : 9%|▊ | 8650/100000 [2:13:34<14:52:22, 1.71it/s]Step... (8650 / 100000 | Loss: 1.4027955532073975, Learning Rate: 9.180904522613065e-05) Step... (8650 / 100000 | Loss: 1.3343850374221802, Learning Rate: 9.180904522613065e-05) Train steps ... : 9%|▊ | 8650/100000 [2:13:34<14:52:22, 1.71it/s] Train steps ... : 9%|▊ | 8651/100000 [2:13:34<14:52:04, 1.71it/s] Train steps ... : 9%|▊ | 8652/100000 [2:13:35<14:54:05, 1.70it/s] Train steps ... : 9%|▊ | 8653/100000 [2:13:35<14:52:30, 1.71it/s] Train steps ... : 9%|▊ | 8654/100000 [2:13:36<14:51:00, 1.71it/s] Train steps ... : 9%|▊ | 8655/100000 [2:13:37<14:55:51, 1.70it/s] Train steps ... : 9%|▊ | 8656/100000 [2:13:37<14:53:20, 1.70it/s] Train steps ... : 9%|▊ | 8657/100000 [2:13:38<14:53:04, 1.70it/s] Train steps ... : 9%|▊ | 8658/100000 [2:13:38<14:55:56, 1.70it/s] Train steps ... : 9%|▊ | 8659/100000 [2:13:39<14:53:05, 1.70it/s] Train steps ... : 9%|▊ | 8660/100000 [2:13:40<14:53:39, 1.70it/s] Train steps ... : 9%|▊ | 8661/100000 [2:13:40<14:53:14, 1.70it/s] Train steps ... : 9%|▊ | 8662/100000 [2:13:41<14:53:13, 1.70it/s] Train steps ... : 9%|▊ | 8663/100000 [2:13:41<14:51:23, 1.71it/s] Train steps ... : 9%|▊ | 8664/100000 [2:13:42<14:52:12, 1.71it/s] Train steps ... : 9%|▊ | 8665/100000 [2:13:43<14:51:51, 1.71it/s] Train steps ... : 9%|▊ | 8666/100000 [2:13:43<14:53:11, 1.70it/s] Train steps ... : 9%|▊ | 8667/100000 [2:13:44<14:52:54, 1.70it/s] Train steps ... : 9%|▊ | 8668/100000 [2:13:44<14:50:55, 1.71it/s] Train steps ... : 9%|▊ | 8669/100000 [2:13:45<14:50:38, 1.71it/s] Train steps ... : 9%|▊ | 8670/100000 [2:13:45<14:50:59, 1.71it/s] Train steps ... : 9%|▊ | 8671/100000 [2:13:46<14:51:49, 1.71it/s] Train steps ... : 9%|▊ | 8672/100000 [2:13:47<14:51:00, 1.71it/s] Train steps ... : 9%|▊ | 8673/100000 [2:13:47<14:51:21, 1.71it/s] Train steps ... : 9%|▊ | 8674/100000 [2:13:48<14:52:31, 1.71it/s] Train steps ... : 9%|▊ | 8675/100000 [2:13:48<14:51:20, 1.71it/s]Step... (8675 / 100000 | Loss: 2.0049006938934326, Learning Rate: 9.178391959798996e-05) Step... (8675 / 100000 | Loss: 1.4675991535186768, Learning Rate: 9.178391959798996e-05) Train steps ... : 9%|▊ | 8675/100000 [2:13:49<14:51:20, 1.71it/s] Train steps ... : 9%|▊ | 8676/100000 [2:13:49<14:50:40, 1.71it/s] Train steps ... : 9%|▊ | 8677/100000 [2:13:50<14:52:56, 1.70it/s] Train steps ... : 9%|▊ | 8678/100000 [2:13:50<14:52:50, 1.70it/s] Train steps ... : 9%|▊ | 8679/100000 [2:13:51<14:52:44, 1.70it/s] Train steps ... : 9%|▊ | 8680/100000 [2:13:51<14:51:48, 1.71it/s] Train steps ... : 9%|▊ | 8681/100000 [2:13:52<14:51:35, 1.71it/s] Train steps ... : 9%|▊ | 8682/100000 [2:13:52<14:51:20, 1.71it/s] Train steps ... : 9%|▊ | 8683/100000 [2:13:53<14:55:33, 1.70it/s] Train steps ... : 9%|▊ | 8684/100000 [2:13:54<14:55:20, 1.70it/s] Train steps ... : 9%|▊ | 8685/100000 [2:13:54<14:56:02, 1.70it/s] Train steps ... : 9%|▊ | 8686/100000 [2:13:55<14:55:28, 1.70it/s] Train steps ... : 9%|▊ | 8687/100000 [2:13:55<14:54:10, 1.70it/s] Train steps ... : 9%|▊ | 8688/100000 [2:13:56<14:54:44, 1.70it/s] Train steps ... : 9%|▊ | 8689/100000 [2:13:57<14:53:44, 1.70it/s] Train steps ... : 9%|▊ | 8690/100000 [2:13:57<14:53:42, 1.70it/s] Train steps ... : 9%|▊ | 8691/100000 [2:13:58<14:55:38, 1.70it/s] Train steps ... : 9%|▊ | 8692/100000 [2:13:58<14:53:35, 1.70it/s] Train steps ... : 9%|▊ | 8693/100000 [2:13:59<14:53:09, 1.70it/s] Train steps ... : 9%|▊ | 8694/100000 [2:14:00<14:51:34, 1.71it/s] Train steps ... : 9%|▊ | 8695/100000 [2:14:00<14:51:55, 1.71it/s] Train steps ... : 9%|▊ | 8696/100000 [2:14:01<14:52:33, 1.70it/s] Train steps ... : 9%|▊ | 8697/100000 [2:14:01<14:52:20, 1.71it/s] Train steps ... : 9%|▊ | 8698/100000 [2:14:02<14:52:50, 1.70it/s] Train steps ... : 9%|▊ | 8699/100000 [2:14:02<14:50:55, 1.71it/s] Train steps ... : 9%|▊ | 8700/100000 [2:14:03<14:51:34, 1.71it/s]Step... (8700 / 100000 | Loss: 1.765478491783142, Learning Rate: 9.175879396984926e-05) Step... (8700 / 100000 | Loss: 1.364217758178711, Learning Rate: 9.175879396984926e-05) Train steps ... : 9%|▊ | 8700/100000 [2:14:03<14:51:34, 1.71it/s] Train steps ... : 9%|▊ | 8701/100000 [2:14:04<14:51:52, 1.71it/s] Train steps ... : 9%|▊ | 8702/100000 [2:14:04<14:53:09, 1.70it/s] Train steps ... : 9%|▊ | 8703/100000 [2:14:05<14:52:56, 1.70it/s] Train steps ... : 9%|▊ | 8704/100000 [2:14:05<14:51:54, 1.71it/s] Train steps ... : 9%|▊ | 8705/100000 [2:14:06<14:51:44, 1.71it/s] Train steps ... : 9%|▊ | 8706/100000 [2:14:07<14:51:50, 1.71it/s] Train steps ... : 9%|▊ | 8707/100000 [2:14:07<14:54:16, 1.70it/s] Train steps ... : 9%|▊ | 8708/100000 [2:14:08<14:51:08, 1.71it/s] Train steps ... : 9%|▊ | 8709/100000 [2:14:08<14:51:25, 1.71it/s] Train steps ... : 9%|▊ | 8710/100000 [2:14:09<14:52:18, 1.71it/s] Train steps ... : 9%|▊ | 8711/100000 [2:14:10<14:50:13, 1.71it/s] Train steps ... : 9%|▊ | 8712/100000 [2:14:10<14:51:21, 1.71it/s] Train steps ... : 9%|▊ | 8713/100000 [2:14:11<14:50:14, 1.71it/s] Train steps ... : 9%|▊ | 8714/100000 [2:14:11<14:50:32, 1.71it/s] Train steps ... : 9%|▊ | 8715/100000 [2:14:12<14:50:29, 1.71it/s] Train steps ... : 9%|▊ | 8716/100000 [2:14:12<14:51:18, 1.71it/s] Train steps ... : 9%|▊ | 8717/100000 [2:14:13<14:53:09, 1.70it/s] Train steps ... : 9%|▊ | 8718/100000 [2:14:14<14:51:13, 1.71it/s] Train steps ... : 9%|▊ | 8719/100000 [2:14:14<14:52:31, 1.70it/s] Train steps ... : 9%|▊ | 8720/100000 [2:14:15<14:51:40, 1.71it/s] Train steps ... : 9%|▊ | 8721/100000 [2:14:15<14:51:27, 1.71it/s] Train steps ... : 9%|▊ | 8722/100000 [2:14:16<14:51:40, 1.71it/s] Train steps ... : 9%|▊ | 8723/100000 [2:14:17<14:52:53, 1.70it/s] Train steps ... : 9%|▊ | 8724/100000 [2:14:17<14:50:06, 1.71it/s] Train steps ... : 9%|▊ | 8725/100000 [2:14:18<14:50:48, 1.71it/s]Step... (8725 / 100000 | Loss: 1.6051307916641235, Learning Rate: 9.173366834170854e-05) Step... (8725 / 100000 | Loss: 1.488816261291504, Learning Rate: 9.173366834170854e-05) Train steps ... : 9%|▊ | 8725/100000 [2:14:18<14:50:48, 1.71it/s] Train steps ... : 9%|▊ | 8726/100000 [2:14:18<14:51:38, 1.71it/s] Train steps ... : 9%|▊ | 8727/100000 [2:14:19<14:50:12, 1.71it/s] Train steps ... : 9%|▊ | 8728/100000 [2:14:19<14:50:47, 1.71it/s] Train steps ... : 9%|▊ | 8729/100000 [2:14:20<14:53:32, 1.70it/s] Train steps ... : 9%|▊ | 8730/100000 [2:14:21<14:49:35, 1.71it/s] Train steps ... : 9%|▊ | 8731/100000 [2:14:21<14:50:15, 1.71it/s] Train steps ... : 9%|▊ | 8732/100000 [2:14:22<14:51:16, 1.71it/s] Train steps ... : 9%|▊ | 8733/100000 [2:14:22<14:52:17, 1.70it/s] Train steps ... : 9%|▊ | 8734/100000 [2:14:23<14:51:35, 1.71it/s] Train steps ... : 9%|▊ | 8735/100000 [2:14:24<14:50:05, 1.71it/s] Train steps ... : 9%|▊ | 8736/100000 [2:14:24<14:51:00, 1.71it/s] Train steps ... : 9%|▊ | 8737/100000 [2:14:25<14:51:09, 1.71it/s] Train steps ... : 9%|▊ | 8738/100000 [2:14:25<14:49:57, 1.71it/s] Train steps ... : 9%|▊ | 8739/100000 [2:14:26<14:51:48, 1.71it/s] Train steps ... : 9%|▊ | 8740/100000 [2:14:27<14:51:28, 1.71it/s] Train steps ... : 9%|▊ | 8741/100000 [2:14:27<14:51:40, 1.71it/s] Train steps ... : 9%|▊ | 8742/100000 [2:14:28<14:49:45, 1.71it/s] Train steps ... : 9%|▊ | 8743/100000 [2:14:28<14:49:03, 1.71it/s] Train steps ... : 9%|▊ | 8744/100000 [2:14:29<14:51:00, 1.71it/s] Train steps ... : 9%|▊ | 8745/100000 [2:14:29<14:49:16, 1.71it/s] Train steps ... : 9%|▊ | 8746/100000 [2:14:30<14:49:33, 1.71it/s] Train steps ... : 9%|▊ | 8747/100000 [2:14:31<14:48:59, 1.71it/s] Train steps ... : 9%|▊ | 8748/100000 [2:14:31<14:49:49, 1.71it/s] Train steps ... : 9%|▊ | 8749/100000 [2:14:32<14:53:49, 1.70it/s] Train steps ... : 9%|▉ | 8750/100000 [2:14:32<14:53:45, 1.70it/s]Step... (8750 / 100000 | Loss: 1.4231822490692139, Learning Rate: 9.170854271356785e-05) Step... (8750 / 100000 | Loss: 1.0975637435913086, Learning Rate: 9.170854271356785e-05) Train steps ... : 9%|▉ | 8750/100000 [2:14:33<14:53:45, 1.70it/s] Train steps ... : 9%|▉ | 8751/100000 [2:14:33<14:52:31, 1.70it/s] Train steps ... : 9%|▉ | 8752/100000 [2:14:34<14:52:21, 1.70it/s] Train steps ... : 9%|▉ | 8753/100000 [2:14:34<14:51:01, 1.71it/s] Train steps ... : 9%|▉ | 8754/100000 [2:14:35<14:50:08, 1.71it/s] Train steps ... : 9%|▉ | 8755/100000 [2:14:35<14:51:50, 1.71it/s] Train steps ... : 9%|▉ | 8756/100000 [2:14:36<14:50:43, 1.71it/s] Train steps ... : 9%|▉ | 8757/100000 [2:14:36<14:50:33, 1.71it/s] Train steps ... : 9%|▉ | 8758/100000 [2:14:37<14:51:41, 1.71it/s] Train steps ... : 9%|▉ | 8759/100000 [2:14:38<14:51:22, 1.71it/s] Train steps ... : 9%|▉ | 8760/100000 [2:14:38<14:51:25, 1.71it/s] Train steps ... : 9%|▉ | 8761/100000 [2:14:39<14:50:20, 1.71it/s] Train steps ... : 9%|▉ | 8762/100000 [2:14:39<14:52:27, 1.70it/s] Train steps ... : 9%|▉ | 8763/100000 [2:14:40<14:52:57, 1.70it/s] Train steps ... : 9%|▉ | 8764/100000 [2:14:41<14:53:35, 1.70it/s] Train steps ... : 9%|▉ | 8765/100000 [2:14:41<14:51:21, 1.71it/s] Train steps ... : 9%|▉ | 8766/100000 [2:14:42<14:53:02, 1.70it/s] Train steps ... : 9%|▉ | 8767/100000 [2:14:42<14:52:41, 1.70it/s] Train steps ... : 9%|▉ | 8768/100000 [2:14:43<14:51:59, 1.70it/s] Train steps ... : 9%|▉ | 8769/100000 [2:14:44<14:51:42, 1.71it/s] Train steps ... : 9%|▉ | 8770/100000 [2:14:44<14:50:28, 1.71it/s] Train steps ... : 9%|▉ | 8771/100000 [2:14:45<14:49:37, 1.71it/s] Train steps ... : 9%|▉ | 8772/100000 [2:14:45<14:49:07, 1.71it/s] Train steps ... : 9%|▉ | 8773/100000 [2:14:46<14:49:46, 1.71it/s] Train steps ... : 9%|▉ | 8774/100000 [2:14:46<14:53:13, 1.70it/s] Train steps ... : 9%|▉ | 8775/100000 [2:14:47<14:51:35, 1.71it/s]Step... (8775 / 100000 | Loss: 1.9249417781829834, Learning Rate: 9.168341708542713e-05) Step... (8775 / 100000 | Loss: 1.4599920511245728, Learning Rate: 9.168341708542713e-05) Train steps ... : 9%|▉ | 8775/100000 [2:14:47<14:51:35, 1.71it/s] Train steps ... : 9%|▉ | 8776/100000 [2:14:48<14:51:35, 1.71it/s] Train steps ... : 9%|▉ | 8777/100000 [2:14:48<14:51:45, 1.70it/s] Train steps ... : 9%|▉ | 8778/100000 [2:14:49<14:52:56, 1.70it/s] Train steps ... : 9%|▉ | 8779/100000 [2:14:49<14:51:25, 1.71it/s] Train steps ... : 9%|▉ | 8780/100000 [2:14:50<14:51:02, 1.71it/s] Train steps ... : 9%|▉ | 8781/100000 [2:14:51<14:52:54, 1.70it/s] Train steps ... : 9%|▉ | 8782/100000 [2:14:51<14:51:34, 1.71it/s] Train steps ... : 9%|▉ | 8783/100000 [2:14:52<14:53:01, 1.70it/s] Train steps ... : 9%|▉ | 8784/100000 [2:14:52<14:53:53, 1.70it/s] Train steps ... : 9%|▉ | 8785/100000 [2:14:53<14:51:18, 1.71it/s] Train steps ... : 9%|▉ | 8786/100000 [2:14:53<14:51:51, 1.70it/s] Train steps ... : 9%|▉ | 8787/100000 [2:14:54<14:51:14, 1.71it/s] Train steps ... : 9%|▉ | 8788/100000 [2:14:55<14:51:46, 1.70it/s] Train steps ... : 9%|▉ | 8789/100000 [2:14:55<14:51:24, 1.71it/s] Train steps ... : 9%|▉ | 8790/100000 [2:14:56<14:54:53, 1.70it/s] Train steps ... : 9%|▉ | 8791/100000 [2:14:56<14:52:53, 1.70it/s] Train steps ... : 9%|▉ | 8792/100000 [2:14:57<14:52:54, 1.70it/s] Train steps ... : 9%|▉ | 8793/100000 [2:14:58<14:50:56, 1.71it/s] Train steps ... : 9%|▉ | 8794/100000 [2:14:58<14:50:04, 1.71it/s] Train steps ... : 9%|▉ | 8795/100000 [2:14:59<14:50:26, 1.71it/s] Train steps ... : 9%|▉ | 8796/100000 [2:14:59<14:50:41, 1.71it/s] Train steps ... : 9%|▉ | 8797/100000 [2:15:00<14:50:21, 1.71it/s] Train steps ... : 9%|▉ | 8798/100000 [2:15:01<14:50:41, 1.71it/s] Train steps ... : 9%|▉ | 8799/100000 [2:15:01<14:48:57, 1.71it/s] Train steps ... : 9%|▉ | 8800/100000 [2:15:02<14:52:30, 1.70it/s]Step... (8800 / 100000 | Loss: 1.0938615798950195, Learning Rate: 9.165829145728644e-05) Step... (8800 / 100000 | Loss: 1.3408868312835693, Learning Rate: 9.165829145728644e-05) Train steps ... : 9%|▉ | 8800/100000 [2:15:02<14:52:30, 1.70it/s] Train steps ... : 9%|▉ | 8801/100000 [2:15:02<14:52:37, 1.70it/s] Train steps ... : 9%|▉ | 8802/100000 [2:15:03<14:51:32, 1.70it/s] Train steps ... : 9%|▉ | 8803/100000 [2:15:03<14:54:49, 1.70it/s] Train steps ... : 9%|▉ | 8804/100000 [2:15:04<14:53:44, 1.70it/s] Train steps ... : 9%|▉ | 8805/100000 [2:15:05<14:51:16, 1.71it/s] Train steps ... : 9%|▉ | 8806/100000 [2:15:05<14:50:49, 1.71it/s] Train steps ... : 9%|▉ | 8807/100000 [2:15:06<14:53:22, 1.70it/s] Train steps ... : 9%|▉ | 8808/100000 [2:15:06<14:52:08, 1.70it/s] Train steps ... : 9%|▉ | 8809/100000 [2:15:07<14:52:19, 1.70it/s] Train steps ... : 9%|▉ | 8810/100000 [2:15:08<14:52:13, 1.70it/s] Train steps ... : 9%|▉ | 8811/100000 [2:15:08<14:51:00, 1.71it/s] Train steps ... : 9%|▉ | 8812/100000 [2:15:09<14:49:50, 1.71it/s] Train steps ... : 9%|▉ | 8813/100000 [2:15:09<14:50:59, 1.71it/s] Train steps ... : 9%|▉ | 8814/100000 [2:15:10<14:50:33, 1.71it/s] Train steps ... : 9%|▉ | 8815/100000 [2:15:10<14:49:04, 1.71it/s] Train steps ... : 9%|▉ | 8816/100000 [2:15:11<14:53:01, 1.70it/s] Train steps ... : 9%|▉ | 8817/100000 [2:15:12<14:52:00, 1.70it/s] Train steps ... : 9%|▉ | 8818/100000 [2:15:12<14:50:00, 1.71it/s] Train steps ... : 9%|▉ | 8819/100000 [2:15:13<14:51:15, 1.71it/s] Train steps ... : 9%|▉ | 8820/100000 [2:15:13<14:50:52, 1.71it/s] Train steps ... : 9%|▉ | 8821/100000 [2:15:14<14:51:31, 1.70it/s] Train steps ... : 9%|▉ | 8822/100000 [2:15:15<14:52:04, 1.70it/s] Train steps ... : 9%|▉ | 8823/100000 [2:15:15<14:51:46, 1.70it/s] Train steps ... : 9%|▉ | 8824/100000 [2:15:16<14:51:28, 1.70it/s] Train steps ... : 9%|▉ | 8825/100000 [2:15:16<14:50:23, 1.71it/s]Step... (8825 / 100000 | Loss: 0.9051076769828796, Learning Rate: 9.163316582914573e-05) Step... (8825 / 100000 | Loss: 1.0986073017120361, Learning Rate: 9.163316582914573e-05) Train steps ... : 9%|▉ | 8825/100000 [2:15:17<14:50:23, 1.71it/s] Train steps ... : 9%|▉ | 8826/100000 [2:15:17<14:50:00, 1.71it/s] Train steps ... : 9%|▉ | 8827/100000 [2:15:18<14:49:10, 1.71it/s] Train steps ... : 9%|▉ | 8828/100000 [2:15:18<14:49:18, 1.71it/s] Train steps ... : 9%|▉ | 8829/100000 [2:15:19<14:52:32, 1.70it/s] Train steps ... : 9%|▉ | 8830/100000 [2:15:19<14:50:49, 1.71it/s] Train steps ... : 9%|▉ | 8831/100000 [2:15:20<14:50:41, 1.71it/s] Train steps ... : 9%|▉ | 8832/100000 [2:15:20<14:49:48, 1.71it/s] Train steps ... : 9%|▉ | 8833/100000 [2:15:21<14:49:38, 1.71it/s] Train steps ... : 9%|▉ | 8834/100000 [2:15:22<14:49:57, 1.71it/s] Train steps ... : 9%|▉ | 8835/100000 [2:15:22<14:48:06, 1.71it/s] Train steps ... : 9%|▉ | 8836/100000 [2:15:23<14:49:23, 1.71it/s] Train steps ... : 9%|▉ | 8837/100000 [2:15:23<14:51:18, 1.70it/s] Train steps ... : 9%|▉ | 8838/100000 [2:15:24<14:50:32, 1.71it/s] Train steps ... : 9%|▉ | 8839/100000 [2:15:25<14:53:24, 1.70it/s] Train steps ... : 9%|▉ | 8840/100000 [2:15:25<14:51:17, 1.70it/s] Train steps ... : 9%|▉ | 8841/100000 [2:15:26<14:49:56, 1.71it/s] Train steps ... : 9%|▉ | 8842/100000 [2:15:26<14:52:49, 1.70it/s] Train steps ... : 9%|▉ | 8843/100000 [2:15:27<14:48:55, 1.71it/s] Train steps ... : 9%|▉ | 8844/100000 [2:15:27<14:47:58, 1.71it/s] Train steps ... : 9%|▉ | 8845/100000 [2:15:28<14:47:51, 1.71it/s] Train steps ... : 9%|▉ | 8846/100000 [2:15:29<14:48:18, 1.71it/s] Train steps ... : 9%|▉ | 8847/100000 [2:15:29<14:48:57, 1.71it/s] Train steps ... : 9%|▉ | 8848/100000 [2:15:30<14:50:14, 1.71it/s] Train steps ... : 9%|▉ | 8849/100000 [2:15:30<14:49:36, 1.71it/s] Train steps ... : 9%|▉ | 8850/100000 [2:15:31<14:49:45, 1.71it/s]Step... (8850 / 100000 | Loss: 1.4186862707138062, Learning Rate: 9.160804020100504e-05) Step... (8850 / 100000 | Loss: 1.5897011756896973, Learning Rate: 9.160804020100504e-05) Train steps ... : 9%|▉ | 8850/100000 [2:15:31<14:49:45, 1.71it/s] Train steps ... : 9%|▉ | 8851/100000 [2:15:32<14:49:43, 1.71it/s] Train steps ... : 9%|▉ | 8852/100000 [2:15:32<14:51:27, 1.70it/s] Train steps ... : 9%|▉ | 8853/100000 [2:15:33<14:52:27, 1.70it/s] Train steps ... : 9%|▉ | 8854/100000 [2:15:33<14:53:15, 1.70it/s] Train steps ... : 9%|▉ | 8855/100000 [2:15:34<14:51:40, 1.70it/s] Train steps ... : 9%|▉ | 8856/100000 [2:15:35<14:50:02, 1.71it/s] Train steps ... : 9%|▉ | 8857/100000 [2:15:35<14:51:10, 1.70it/s] Train steps ... : 9%|▉ | 8858/100000 [2:15:36<14:51:11, 1.70it/s] Train steps ... : 9%|▉ | 8859/100000 [2:15:36<14:51:56, 1.70it/s] Train steps ... : 9%|▉ | 8860/100000 [2:15:37<14:51:08, 1.70it/s] Train steps ... : 9%|▉ | 8861/100000 [2:15:37<14:50:55, 1.70it/s] Train steps ... : 9%|▉ | 8862/100000 [2:15:38<14:50:33, 1.71it/s] Train steps ... : 9%|▉ | 8863/100000 [2:15:39<14:51:36, 1.70it/s] Train steps ... : 9%|▉ | 8864/100000 [2:15:39<14:50:07, 1.71it/s] Train steps ... : 9%|▉ | 8865/100000 [2:15:40<14:52:25, 1.70it/s] Train steps ... : 9%|▉ | 8866/100000 [2:15:40<14:50:12, 1.71it/s] Train steps ... : 9%|▉ | 8867/100000 [2:15:41<14:53:08, 1.70it/s] Train steps ... : 9%|▉ | 8868/100000 [2:15:42<14:52:00, 1.70it/s] Train steps ... : 9%|▉ | 8869/100000 [2:15:42<14:50:27, 1.71it/s] Train steps ... : 9%|▉ | 8870/100000 [2:15:43<14:49:58, 1.71it/s] Train steps ... : 9%|▉ | 8871/100000 [2:15:43<14:49:10, 1.71it/s] Train steps ... : 9%|▉ | 8872/100000 [2:15:44<14:48:34, 1.71it/s] Train steps ... : 9%|▉ | 8873/100000 [2:15:44<14:52:04, 1.70it/s] Train steps ... : 9%|▉ | 8874/100000 [2:15:45<14:50:38, 1.71it/s] Train steps ... : 9%|▉ | 8875/100000 [2:15:46<14:52:00, 1.70it/s]Step... (8875 / 100000 | Loss: 1.098772406578064, Learning Rate: 9.158291457286433e-05) Step... (8875 / 100000 | Loss: 1.4754546880722046, Learning Rate: 9.158291457286433e-05) Train steps ... : 9%|▉ | 8875/100000 [2:15:46<14:52:00, 1.70it/s] Train steps ... : 9%|▉ | 8876/100000 [2:15:46<14:51:15, 1.70it/s] Train steps ... : 9%|▉ | 8877/100000 [2:15:47<14:50:49, 1.70it/s] Train steps ... : 9%|▉ | 8878/100000 [2:15:47<14:50:59, 1.70it/s] Train steps ... : 9%|▉ | 8879/100000 [2:15:48<14:50:43, 1.70it/s] Train steps ... : 9%|▉ | 8880/100000 [2:15:49<14:49:09, 1.71it/s] Train steps ... : 9%|▉ | 8881/100000 [2:15:49<14:49:41, 1.71it/s] Train steps ... : 9%|▉ | 8882/100000 [2:15:50<14:51:33, 1.70it/s] Train steps ... : 9%|▉ | 8883/100000 [2:15:50<14:50:28, 1.71it/s] Train steps ... : 9%|▉ | 8884/100000 [2:15:51<14:52:59, 1.70it/s] Train steps ... : 9%|▉ | 8885/100000 [2:15:52<14:50:04, 1.71it/s] Train steps ... : 9%|▉ | 8886/100000 [2:15:52<14:48:43, 1.71it/s] Train steps ... : 9%|▉ | 8887/100000 [2:15:53<14:53:10, 1.70it/s] Train steps ... : 9%|▉ | 8888/100000 [2:15:53<14:50:10, 1.71it/s] Train steps ... : 9%|▉ | 8889/100000 [2:15:54<14:48:28, 1.71it/s] Train steps ... : 9%|▉ | 8890/100000 [2:15:54<14:53:48, 1.70it/s] Train steps ... : 9%|▉ | 8891/100000 [2:15:55<14:54:58, 1.70it/s] Train steps ... : 9%|▉ | 8892/100000 [2:15:56<14:53:30, 1.70it/s] Train steps ... : 9%|▉ | 8893/100000 [2:15:56<14:53:58, 1.70it/s] Train steps ... : 9%|▉ | 8894/100000 [2:15:57<14:52:28, 1.70it/s] Train steps ... : 9%|▉ | 8895/100000 [2:15:57<14:50:18, 1.71it/s] Train steps ... : 9%|▉ | 8896/100000 [2:15:58<14:50:17, 1.71it/s] Train steps ... : 9%|▉ | 8897/100000 [2:15:59<14:48:36, 1.71it/s] Train steps ... : 9%|▉ | 8898/100000 [2:15:59<14:50:18, 1.71it/s] Train steps ... : 9%|▉ | 8899/100000 [2:16:00<14:48:40, 1.71it/s] Train steps ... : 9%|▉ | 8900/100000 [2:16:00<14:48:10, 1.71it/s]Step... (8900 / 100000 | Loss: 1.0863323211669922, Learning Rate: 9.155778894472362e-05) Step... (8900 / 100000 | Loss: 1.6944944858551025, Learning Rate: 9.155778894472362e-05) Train steps ... : 9%|▉ | 8900/100000 [2:16:01<14:48:10, 1.71it/s] Train steps ... : 9%|▉ | 8901/100000 [2:16:01<14:48:36, 1.71it/s] Train steps ... : 9%|▉ | 8902/100000 [2:16:01<14:47:57, 1.71it/s] Train steps ... : 9%|▉ | 8903/100000 [2:16:02<14:49:19, 1.71it/s] Train steps ... : 9%|▉ | 8904/100000 [2:16:03<14:51:26, 1.70it/s] Train steps ... : 9%|▉ | 8905/100000 [2:16:03<14:50:57, 1.70it/s] Train steps ... : 9%|▉ | 8906/100000 [2:16:04<14:49:52, 1.71it/s] Train steps ... : 9%|▉ | 8907/100000 [2:16:04<14:49:18, 1.71it/s] Train steps ... : 9%|▉ | 8908/100000 [2:16:05<14:51:51, 1.70it/s] Train steps ... : 9%|▉ | 8909/100000 [2:16:06<14:49:26, 1.71it/s] Train steps ... : 9%|▉ | 8910/100000 [2:16:06<14:50:33, 1.70it/s] Train steps ... : 9%|▉ | 8911/100000 [2:16:07<14:51:03, 1.70it/s] Train steps ... : 9%|▉ | 8912/100000 [2:16:07<14:48:32, 1.71it/s] Train steps ... : 9%|▉ | 8913/100000 [2:16:08<14:49:18, 1.71it/s] Train steps ... : 9%|▉ | 8914/100000 [2:16:09<14:51:57, 1.70it/s] Train steps ... : 9%|▉ | 8915/100000 [2:16:09<14:48:33, 1.71it/s] Train steps ... : 9%|▉ | 8916/100000 [2:16:10<14:48:05, 1.71it/s] Train steps ... : 9%|▉ | 8917/100000 [2:16:10<14:47:57, 1.71it/s] Train steps ... : 9%|▉ | 8918/100000 [2:16:11<14:47:34, 1.71it/s] Train steps ... : 9%|▉ | 8919/100000 [2:16:11<14:48:30, 1.71it/s] Train steps ... : 9%|▉ | 8920/100000 [2:16:12<14:48:19, 1.71it/s] Train steps ... : 9%|▉ | 8921/100000 [2:16:13<14:47:48, 1.71it/s] Train steps ... : 9%|▉ | 8922/100000 [2:16:13<14:50:02, 1.71it/s] Train steps ... : 9%|▉ | 8923/100000 [2:16:14<14:48:22, 1.71it/s] Train steps ... : 9%|▉ | 8924/100000 [2:16:14<14:48:28, 1.71it/s] Train steps ... : 9%|▉ | 8925/100000 [2:16:15<14:49:51, 1.71it/s]Step... (8925 / 100000 | Loss: 1.0170985460281372, Learning Rate: 9.153266331658293e-05) Step... (8925 / 100000 | Loss: 2.1126489639282227, Learning Rate: 9.153266331658293e-05) Train steps ... : 9%|▉ | 8925/100000 [2:16:15<14:49:51, 1.71it/s] Train steps ... : 9%|▉ | 8926/100000 [2:16:16<14:51:08, 1.70it/s] Train steps ... : 9%|▉ | 8927/100000 [2:16:16<14:52:19, 1.70it/s] Train steps ... : 9%|▉ | 8928/100000 [2:16:17<14:51:44, 1.70it/s] Train steps ... : 9%|▉ | 8929/100000 [2:16:17<14:50:08, 1.71it/s] Train steps ... : 9%|▉ | 8930/100000 [2:16:18<14:49:39, 1.71it/s] Train steps ... : 9%|▉ | 8931/100000 [2:16:18<14:49:54, 1.71it/s] Train steps ... : 9%|▉ | 8932/100000 [2:16:19<14:50:54, 1.70it/s] Train steps ... : 9%|▉ | 8933/100000 [2:16:20<14:50:52, 1.70it/s] Train steps ... : 9%|▉ | 8934/100000 [2:16:20<14:50:28, 1.70it/s] Train steps ... : 9%|▉ | 8935/100000 [2:16:21<14:50:45, 1.70it/s] Train steps ... : 9%|▉ | 8936/100000 [2:16:21<14:49:46, 1.71it/s] Train steps ... : 9%|▉ | 8937/100000 [2:16:22<14:50:12, 1.70it/s] Train steps ... : 9%|▉ | 8938/100000 [2:16:23<14:48:03, 1.71it/s] Train steps ... : 9%|▉ | 8939/100000 [2:16:23<14:50:14, 1.70it/s] Train steps ... : 9%|▉ | 8940/100000 [2:16:24<14:51:06, 1.70it/s] Train steps ... : 9%|▉ | 8941/100000 [2:16:24<14:48:51, 1.71it/s] Train steps ... : 9%|▉ | 8942/100000 [2:16:25<14:49:47, 1.71it/s] Train steps ... : 9%|▉ | 8943/100000 [2:16:26<14:49:57, 1.71it/s] Train steps ... : 9%|▉ | 8944/100000 [2:16:26<14:49:20, 1.71it/s] Train steps ... : 9%|▉ | 8945/100000 [2:16:27<14:49:58, 1.71it/s] Train steps ... : 9%|▉ | 8946/100000 [2:16:27<14:49:55, 1.71it/s] Train steps ... : 9%|▉ | 8947/100000 [2:16:28<14:49:09, 1.71it/s] Train steps ... : 9%|▉ | 8948/100000 [2:16:28<14:49:03, 1.71it/s] Train steps ... : 9%|▉ | 8949/100000 [2:16:29<14:48:46, 1.71it/s] Train steps ... : 9%|▉ | 8950/100000 [2:16:30<14:47:29, 1.71it/s]Step... (8950 / 100000 | Loss: 0.9283075332641602, Learning Rate: 9.150753768844221e-05) Step... (8950 / 100000 | Loss: 1.6132532358169556, Learning Rate: 9.150753768844221e-05) Train steps ... : 9%|▉ | 8950/100000 [2:16:30<14:47:29, 1.71it/s] Train steps ... : 9%|▉ | 8951/100000 [2:16:30<14:47:52, 1.71it/s] Train steps ... : 9%|▉ | 8952/100000 [2:16:31<14:46:48, 1.71it/s] Train steps ... : 9%|▉ | 8953/100000 [2:16:31<14:49:18, 1.71it/s] Train steps ... : 9%|▉ | 8954/100000 [2:16:32<14:47:18, 1.71it/s] Train steps ... : 9%|▉ | 8955/100000 [2:16:33<14:49:32, 1.71it/s] Train steps ... : 9%|▉ | 8956/100000 [2:16:33<14:48:07, 1.71it/s] Train steps ... : 9%|▉ | 8957/100000 [2:16:34<14:49:16, 1.71it/s] Train steps ... : 9%|▉ | 8958/100000 [2:16:34<14:49:28, 1.71it/s] Train steps ... : 9%|▉ | 8959/100000 [2:16:35<14:49:46, 1.71it/s] Train steps ... : 9%|▉ | 8960/100000 [2:16:35<14:48:15, 1.71it/s] Train steps ... : 9%|▉ | 8961/100000 [2:16:36<14:49:56, 1.70it/s] Train steps ... : 9%|▉ | 8962/100000 [2:16:37<14:49:22, 1.71it/s] Train steps ... : 9%|▉ | 8963/100000 [2:16:37<14:48:13, 1.71it/s] Train steps ... : 9%|▉ | 8964/100000 [2:16:38<14:50:53, 1.70it/s] Train steps ... : 9%|▉ | 8965/100000 [2:16:38<14:50:46, 1.70it/s] Train steps ... : 9%|▉ | 8966/100000 [2:16:39<14:49:16, 1.71it/s] Train steps ... : 9%|▉ | 8967/100000 [2:16:40<14:50:12, 1.70it/s] Train steps ... : 9%|▉ | 8968/100000 [2:16:40<14:51:27, 1.70it/s] Train steps ... : 9%|▉ | 8969/100000 [2:16:41<14:47:37, 1.71it/s] Train steps ... : 9%|▉ | 8970/100000 [2:16:41<14:50:23, 1.70it/s] Train steps ... : 9%|▉ | 8971/100000 [2:16:42<14:48:36, 1.71it/s] Train steps ... : 9%|▉ | 8972/100000 [2:16:43<14:50:16, 1.70it/s] Train steps ... : 9%|▉ | 8973/100000 [2:16:43<14:48:00, 1.71it/s] Train steps ... : 9%|▉ | 8974/100000 [2:16:44<14:47:49, 1.71it/s] Train steps ... : 9%|▉ | 8975/100000 [2:16:44<14:48:09, 1.71it/s]Step... (8975 / 100000 | Loss: 1.1703567504882812, Learning Rate: 9.148241206030152e-05) Step... (8975 / 100000 | Loss: 0.7979527115821838, Learning Rate: 9.148241206030152e-05) Train steps ... : 9%|▉ | 8975/100000 [2:16:45<14:48:09, 1.71it/s] Train steps ... : 9%|▉ | 8976/100000 [2:16:45<14:47:50, 1.71it/s] Train steps ... : 9%|▉ | 8977/100000 [2:16:45<14:48:07, 1.71it/s] Train steps ... : 9%|▉ | 8978/100000 [2:16:46<14:48:21, 1.71it/s] Train steps ... : 9%|▉ | 8979/100000 [2:16:47<14:49:57, 1.70it/s] Train steps ... : 9%|▉ | 8980/100000 [2:16:47<14:49:11, 1.71it/s] Train steps ... : 9%|▉ | 8981/100000 [2:16:48<14:48:36, 1.71it/s] Train steps ... : 9%|▉ | 8982/100000 [2:16:48<14:49:35, 1.71it/s] Train steps ... : 9%|▉ | 8983/100000 [2:16:49<14:48:06, 1.71it/s] Train steps ... : 9%|▉ | 8984/100000 [2:16:50<14:47:20, 1.71it/s] Train steps ... : 9%|▉ | 8985/100000 [2:16:50<14:48:08, 1.71it/s] Train steps ... : 9%|▉ | 8986/100000 [2:16:51<14:48:24, 1.71it/s] Train steps ... : 9%|▉ | 8987/100000 [2:16:51<14:49:13, 1.71it/s] Train steps ... : 9%|▉ | 8988/100000 [2:16:52<14:47:12, 1.71it/s] Train steps ... : 9%|▉ | 8989/100000 [2:16:52<14:47:53, 1.71it/s] Train steps ... : 9%|▉ | 8990/100000 [2:16:53<14:49:17, 1.71it/s] Train steps ... : 9%|▉ | 8991/100000 [2:16:54<14:48:58, 1.71it/s] Train steps ... : 9%|▉ | 8992/100000 [2:16:54<14:50:45, 1.70it/s] Train steps ... : 9%|▉ | 8993/100000 [2:16:55<14:49:57, 1.70it/s] Train steps ... : 9%|▉ | 8994/100000 [2:16:55<14:49:50, 1.70it/s] Train steps ... : 9%|▉ | 8995/100000 [2:16:56<14:49:06, 1.71it/s] Train steps ... : 9%|▉ | 8996/100000 [2:16:57<14:49:21, 1.71it/s] Train steps ... : 9%|▉ | 8997/100000 [2:16:57<14:50:19, 1.70it/s] Train steps ... : 9%|▉ | 8998/100000 [2:16:58<14:49:30, 1.71it/s] Train steps ... : 9%|▉ | 8999/100000 [2:16:58<14:48:52, 1.71it/s] Train steps ... : 9%|▉ | 9000/100000 [2:16:59<14:49:37, 1.70it/s]Step... (9000 / 100000 | Loss: 1.4928407669067383, Learning Rate: 9.14572864321608e-05) Step... (9000 / 100000 | Loss: 1.3168442249298096, Learning Rate: 9.14572864321608e-05) Train steps ... : 9%|▉ | 9000/100000 [2:16:59<14:49:37, 1.70it/s] Train steps ... : 9%|▉ | 9001/100000 [2:17:00<14:49:14, 1.71it/s] Train steps ... : 9%|▉ | 9002/100000 [2:17:00<14:50:21, 1.70it/s] Train steps ... : 9%|▉ | 9003/100000 [2:17:01<14:47:18, 1.71it/s] Train steps ... : 9%|▉ | 9004/100000 [2:17:01<14:46:44, 1.71it/s] Train steps ... : 9%|▉ | 9005/100000 [2:17:02<14:47:50, 1.71it/s] Train steps ... : 9%|▉ | 9006/100000 [2:17:02<14:48:05, 1.71it/s] Train steps ... : 9%|▉ | 9007/100000 [2:17:03<14:48:16, 1.71it/s] Train steps ... : 9%|▉ | 9008/100000 [2:17:04<14:52:02, 1.70it/s] Train steps ... : 9%|▉ | 9009/100000 [2:17:04<14:50:50, 1.70it/s] Train steps ... : 9%|▉ | 9010/100000 [2:17:05<14:48:53, 1.71it/s] Train steps ... : 9%|▉ | 9011/100000 [2:17:05<14:48:22, 1.71it/s] Train steps ... : 9%|▉ | 9012/100000 [2:17:06<14:48:54, 1.71it/s] Train steps ... : 9%|▉ | 9013/100000 [2:17:07<14:51:26, 1.70it/s] Train steps ... : 9%|▉ | 9014/100000 [2:17:07<14:47:26, 1.71it/s] Train steps ... : 9%|▉ | 9015/100000 [2:17:08<14:48:38, 1.71it/s] Train steps ... : 9%|▉ | 9016/100000 [2:17:08<14:49:43, 1.70it/s] Train steps ... : 9%|▉ | 9017/100000 [2:17:09<14:47:55, 1.71it/s] Train steps ... : 9%|▉ | 9018/100000 [2:17:09<14:48:55, 1.71it/s] Train steps ... : 9%|▉ | 9019/100000 [2:17:10<14:48:13, 1.71it/s] Train steps ... : 9%|▉ | 9020/100000 [2:17:11<14:47:07, 1.71it/s] Train steps ... : 9%|▉ | 9021/100000 [2:17:11<14:47:03, 1.71it/s] Train steps ... : 9%|▉ | 9022/100000 [2:17:12<14:47:05, 1.71it/s] Train steps ... : 9%|▉ | 9023/100000 [2:17:12<14:48:36, 1.71it/s] Train steps ... : 9%|▉ | 9024/100000 [2:17:13<14:47:50, 1.71it/s] Train steps ... : 9%|▉ | 9025/100000 [2:17:14<14:48:48, 1.71it/s]Step... (9025 / 100000 | Loss: 1.5757863521575928, Learning Rate: 9.143216080402011e-05) Step... (9025 / 100000 | Loss: 1.4932186603546143, Learning Rate: 9.143216080402011e-05) Train steps ... : 9%|▉ | 9025/100000 [2:17:14<14:48:48, 1.71it/s] Train steps ... : 9%|▉ | 9026/100000 [2:17:14<14:48:40, 1.71it/s] Train steps ... : 9%|▉ | 9027/100000 [2:17:15<14:48:08, 1.71it/s] Train steps ... : 9%|▉ | 9028/100000 [2:17:15<14:49:51, 1.70it/s] Train steps ... : 9%|▉ | 9029/100000 [2:17:16<14:46:50, 1.71it/s] Train steps ... : 9%|▉ | 9030/100000 [2:17:17<14:46:04, 1.71it/s] Train steps ... : 9%|▉ | 9031/100000 [2:17:17<14:46:08, 1.71it/s] Train steps ... : 9%|▉ | 9032/100000 [2:17:18<14:48:16, 1.71it/s] Train steps ... : 9%|▉ | 9033/100000 [2:17:18<14:48:02, 1.71it/s] Train steps ... : 9%|▉ | 9034/100000 [2:17:19<14:48:37, 1.71it/s] Train steps ... : 9%|▉ | 9035/100000 [2:17:19<14:49:19, 1.70it/s] Train steps ... : 9%|▉ | 9036/100000 [2:17:20<14:48:42, 1.71it/s] Train steps ... : 9%|▉ | 9037/100000 [2:17:21<14:50:02, 1.70it/s] Train steps ... : 9%|▉ | 9038/100000 [2:17:21<14:49:46, 1.70it/s] Train steps ... : 9%|▉ | 9039/100000 [2:17:22<14:48:29, 1.71it/s] Train steps ... : 9%|▉ | 9040/100000 [2:17:22<14:50:18, 1.70it/s] Train steps ... : 9%|▉ | 9041/100000 [2:17:23<14:48:22, 1.71it/s] Train steps ... : 9%|▉ | 9042/100000 [2:17:24<14:50:26, 1.70it/s] Train steps ... : 9%|▉ | 9043/100000 [2:17:24<14:49:11, 1.70it/s] Train steps ... : 9%|▉ | 9044/100000 [2:17:25<14:47:55, 1.71it/s] Train steps ... : 9%|▉ | 9045/100000 [2:17:25<14:47:27, 1.71it/s] Train steps ... : 9%|▉ | 9046/100000 [2:17:26<14:47:20, 1.71it/s] Train steps ... : 9%|▉ | 9047/100000 [2:17:26<14:46:18, 1.71it/s] Train steps ... : 9%|▉ | 9048/100000 [2:17:27<14:46:19, 1.71it/s] Train steps ... : 9%|▉ | 9049/100000 [2:17:28<14:47:28, 1.71it/s] Train steps ... : 9%|▉ | 9050/100000 [2:17:28<14:47:18, 1.71it/s]Step... (9050 / 100000 | Loss: 1.696610450744629, Learning Rate: 9.14070351758794e-05) Step... (9050 / 100000 | Loss: 1.7672977447509766, Learning Rate: 9.14070351758794e-05) Train steps ... : 9%|▉ | 9050/100000 [2:17:29<14:47:18, 1.71it/s] Train steps ... : 9%|▉ | 9051/100000 [2:17:29<14:46:58, 1.71it/s] Train steps ... : 9%|▉ | 9052/100000 [2:17:29<14:48:13, 1.71it/s] Train steps ... : 9%|▉ | 9053/100000 [2:17:30<14:47:25, 1.71it/s] Train steps ... : 9%|▉ | 9054/100000 [2:17:31<14:48:36, 1.71it/s] Train steps ... : 9%|▉ | 9055/100000 [2:17:31<14:48:02, 1.71it/s] Train steps ... : 9%|▉ | 9056/100000 [2:17:32<14:46:47, 1.71it/s] Train steps ... : 9%|▉ | 9057/100000 [2:17:32<14:48:26, 1.71it/s] Train steps ... : 9%|▉ | 9058/100000 [2:17:33<14:48:33, 1.71it/s] Train steps ... : 9%|▉ | 9059/100000 [2:17:34<14:48:33, 1.71it/s] Train steps ... : 9%|▉ | 9060/100000 [2:17:34<14:47:49, 1.71it/s] Train steps ... : 9%|▉ | 9061/100000 [2:17:35<14:46:18, 1.71it/s] Train steps ... : 9%|▉ | 9062/100000 [2:17:35<14:46:20, 1.71it/s] Train steps ... : 9%|▉ | 9063/100000 [2:17:36<14:46:34, 1.71it/s] Train steps ... : 9%|▉ | 9064/100000 [2:17:36<14:46:11, 1.71it/s] Train steps ... : 9%|▉ | 9065/100000 [2:17:37<14:47:29, 1.71it/s] Train steps ... : 9%|▉ | 9066/100000 [2:17:38<14:46:10, 1.71it/s] Train steps ... : 9%|▉ | 9067/100000 [2:17:38<14:46:04, 1.71it/s] Train steps ... : 9%|▉ | 9068/100000 [2:17:39<14:47:15, 1.71it/s] Train steps ... : 9%|▉ | 9069/100000 [2:17:39<14:48:47, 1.71it/s] Train steps ... : 9%|▉ | 9070/100000 [2:17:40<14:47:09, 1.71it/s] Train steps ... : 9%|▉ | 9071/100000 [2:17:41<14:47:13, 1.71it/s] Train steps ... : 9%|▉ | 9072/100000 [2:17:41<14:48:27, 1.71it/s] Train steps ... : 9%|▉ | 9073/100000 [2:17:42<14:46:08, 1.71it/s] Train steps ... : 9%|▉ | 9074/100000 [2:17:42<14:48:54, 1.70it/s] Train steps ... : 9%|▉ | 9075/100000 [2:17:43<14:50:30, 1.70it/s]Step... (9075 / 100000 | Loss: 1.4168388843536377, Learning Rate: 9.138190954773869e-05) Step... (9075 / 100000 | Loss: 1.8178856372833252, Learning Rate: 9.138190954773869e-05) Train steps ... : 9%|▉ | 9075/100000 [2:17:43<14:50:30, 1.70it/s] Train steps ... : 9%|▉ | 9076/100000 [2:17:43<14:47:25, 1.71it/s] Train steps ... : 9%|▉ | 9077/100000 [2:17:44<14:47:10, 1.71it/s] Train steps ... : 9%|▉ | 9078/100000 [2:17:45<14:46:46, 1.71it/s] Train steps ... : 9%|▉ | 9079/100000 [2:17:45<14:46:34, 1.71it/s] Train steps ... : 9%|▉ | 9080/100000 [2:17:46<14:45:58, 1.71it/s] Train steps ... : 9%|▉ | 9081/100000 [2:17:46<14:47:11, 1.71it/s] Train steps ... : 9%|▉ | 9082/100000 [2:17:47<14:49:08, 1.70it/s] Train steps ... : 9%|▉ | 9083/100000 [2:17:48<14:49:15, 1.70it/s] Train steps ... : 9%|▉ | 9084/100000 [2:17:48<14:46:31, 1.71it/s] Train steps ... : 9%|▉ | 9085/100000 [2:17:49<14:48:45, 1.70it/s] Train steps ... : 9%|▉ | 9086/100000 [2:17:49<14:47:24, 1.71it/s] Train steps ... : 9%|▉ | 9087/100000 [2:17:50<14:47:26, 1.71it/s] Train steps ... : 9%|▉ | 9088/100000 [2:17:50<14:46:41, 1.71it/s] Train steps ... : 9%|▉ | 9089/100000 [2:17:51<14:47:18, 1.71it/s] Train steps ... : 9%|▉ | 9090/100000 [2:17:52<14:46:30, 1.71it/s] Train steps ... : 9%|▉ | 9091/100000 [2:17:52<14:46:55, 1.71it/s] Train steps ... : 9%|▉ | 9092/100000 [2:17:53<14:46:01, 1.71it/s] Train steps ... : 9%|▉ | 9093/100000 [2:17:53<14:45:32, 1.71it/s] Train steps ... : 9%|▉ | 9094/100000 [2:17:54<14:46:46, 1.71it/s] Train steps ... : 9%|▉ | 9095/100000 [2:17:55<14:46:29, 1.71it/s] Train steps ... : 9%|▉ | 9096/100000 [2:17:55<14:47:15, 1.71it/s] Train steps ... : 9%|▉ | 9097/100000 [2:17:56<14:47:49, 1.71it/s] Train steps ... : 9%|▉ | 9098/100000 [2:17:56<14:49:11, 1.70it/s] Train steps ... : 9%|▉ | 9099/100000 [2:17:57<14:47:05, 1.71it/s] Train steps ... : 9%|▉ | 9100/100000 [2:17:58<14:46:58, 1.71it/s]Step... (9100 / 100000 | Loss: 1.412731409072876, Learning Rate: 9.1356783919598e-05) Step... (9100 / 100000 | Loss: 1.2752033472061157, Learning Rate: 9.1356783919598e-05) Train steps ... : 9%|▉ | 9100/100000 [2:17:58<14:46:58, 1.71it/s] Train steps ... : 9%|▉ | 9101/100000 [2:17:58<14:47:49, 1.71it/s] Train steps ... : 9%|▉ | 9102/100000 [2:17:59<14:47:01, 1.71it/s] Train steps ... : 9%|▉ | 9103/100000 [2:17:59<14:48:09, 1.71it/s] Train steps ... : 9%|▉ | 9104/100000 [2:18:00<14:46:08, 1.71it/s] Train steps ... : 9%|▉ | 9105/100000 [2:18:00<14:47:30, 1.71it/s] Train steps ... : 9%|▉ | 9106/100000 [2:18:01<14:48:16, 1.71it/s] Train steps ... : 9%|▉ | 9107/100000 [2:18:02<14:49:01, 1.70it/s] Train steps ... : 9%|▉ | 9108/100000 [2:18:02<14:47:52, 1.71it/s] Train steps ... : 9%|▉ | 9109/100000 [2:18:03<14:53:21, 1.70it/s] Train steps ... : 9%|▉ | 9110/100000 [2:18:03<14:50:09, 1.70it/s] Train steps ... : 9%|▉ | 9111/100000 [2:18:04<14:50:39, 1.70it/s] Train steps ... : 9%|▉ | 9112/100000 [2:18:05<14:53:14, 1.70it/s] Train steps ... : 9%|▉ | 9113/100000 [2:18:05<14:52:46, 1.70it/s] Train steps ... : 9%|▉ | 9114/100000 [2:18:06<14:51:49, 1.70it/s] Train steps ... : 9%|▉ | 9115/100000 [2:18:06<14:52:35, 1.70it/s] Train steps ... : 9%|▉ | 9116/100000 [2:18:07<14:50:49, 1.70it/s] Train steps ... : 9%|▉ | 9117/100000 [2:18:08<14:52:35, 1.70it/s] Train steps ... : 9%|▉ | 9118/100000 [2:18:08<14:52:21, 1.70it/s] Train steps ... : 9%|▉ | 9119/100000 [2:18:09<14:51:31, 1.70it/s] Train steps ... : 9%|▉ | 9120/100000 [2:18:09<14:56:13, 1.69it/s] Train steps ... : 9%|▉ | 9121/100000 [2:18:10<14:51:25, 1.70it/s] Train steps ... : 9%|▉ | 9122/100000 [2:18:10<14:53:26, 1.70it/s] Train steps ... : 9%|▉ | 9123/100000 [2:18:11<14:48:31, 1.70it/s] Train steps ... : 9%|▉ | 9124/100000 [2:18:12<14:54:34, 1.69it/s] Train steps ... : 9%|▉ | 9125/100000 [2:18:12<14:46:48, 1.71it/s]Step... (9125 / 100000 | Loss: 1.1137464046478271, Learning Rate: 9.133165829145728e-05) Step... (9125 / 100000 | Loss: 1.6093488931655884, Learning Rate: 9.133165829145728e-05) Train steps ... : 9%|▉ | 9125/100000 [2:18:13<14:46:48, 1.71it/s] Train steps ... : 9%|▉ | 9126/100000 [2:18:13<14:50:33, 1.70it/s] Train steps ... : 9%|▉ | 9127/100000 [2:18:13<14:49:28, 1.70it/s] Train steps ... : 9%|▉ | 9128/100000 [2:18:14<14:53:17, 1.70it/s] Train steps ... : 9%|▉ | 9129/100000 [2:18:15<14:47:48, 1.71it/s] Train steps ... : 9%|▉ | 9130/100000 [2:18:15<14:49:58, 1.70it/s] Train steps ... : 9%|▉ | 9131/100000 [2:18:16<14:52:53, 1.70it/s] Train steps ... : 9%|▉ | 9132/100000 [2:18:16<14:48:21, 1.70it/s] Train steps ... : 9%|▉ | 9133/100000 [2:18:17<14:46:43, 1.71it/s] Train steps ... : 9%|▉ | 9134/100000 [2:18:17<14:45:58, 1.71it/s] Train steps ... : 9%|▉ | 9135/100000 [2:18:18<14:45:57, 1.71it/s] Train steps ... : 9%|▉ | 9136/100000 [2:18:19<14:46:35, 1.71it/s] Train steps ... : 9%|▉ | 9137/100000 [2:18:19<14:46:03, 1.71it/s] Train steps ... : 9%|▉ | 9138/100000 [2:18:20<14:47:24, 1.71it/s] Train steps ... : 9%|▉ | 9139/100000 [2:18:20<14:48:24, 1.70it/s] Train steps ... : 9%|▉ | 9140/100000 [2:18:21<14:46:30, 1.71it/s] Train steps ... : 9%|▉ | 9141/100000 [2:18:22<14:46:41, 1.71it/s] Train steps ... : 9%|▉ | 9142/100000 [2:18:22<14:47:21, 1.71it/s] Train steps ... : 9%|▉ | 9143/100000 [2:18:23<14:47:08, 1.71it/s] Train steps ... : 9%|▉ | 9144/100000 [2:18:23<14:46:14, 1.71it/s] Train steps ... : 9%|▉ | 9145/100000 [2:18:24<14:47:22, 1.71it/s] Train steps ... : 9%|▉ | 9146/100000 [2:18:25<14:47:28, 1.71it/s] Train steps ... : 9%|▉ | 9147/100000 [2:18:25<14:47:50, 1.71it/s] Train steps ... : 9%|▉ | 9148/100000 [2:18:26<14:48:07, 1.70it/s] Train steps ... : 9%|▉ | 9149/100000 [2:18:26<14:47:48, 1.71it/s] Train steps ... : 9%|▉ | 9150/100000 [2:18:27<14:47:22, 1.71it/s]Step... (9150 / 100000 | Loss: 1.9099528789520264, Learning Rate: 9.13065326633166e-05) Step... (9150 / 100000 | Loss: 1.561030387878418, Learning Rate: 9.13065326633166e-05) Train steps ... : 9%|▉ | 9150/100000 [2:18:27<14:47:22, 1.71it/s] Train steps ... : 9%|▉ | 9151/100000 [2:18:27<14:49:43, 1.70it/s] Train steps ... : 9%|▉ | 9152/100000 [2:18:28<14:54:02, 1.69it/s] Train steps ... : 9%|▉ | 9153/100000 [2:18:29<14:50:37, 1.70it/s] Train steps ... : 9%|▉ | 9154/100000 [2:18:29<14:53:27, 1.69it/s] Train steps ... : 9%|▉ | 9155/100000 [2:18:30<14:51:39, 1.70it/s] Train steps ... : 9%|▉ | 9156/100000 [2:18:30<14:47:01, 1.71it/s] Train steps ... : 9%|▉ | 9157/100000 [2:18:31<14:49:04, 1.70it/s] Train steps ... : 9%|▉ | 9158/100000 [2:18:32<14:48:18, 1.70it/s] Train steps ... : 9%|▉ | 9159/100000 [2:18:32<14:45:53, 1.71it/s] Train steps ... : 9%|▉ | 9160/100000 [2:18:33<14:47:06, 1.71it/s] Train steps ... : 9%|▉ | 9161/100000 [2:18:33<14:47:33, 1.71it/s] Train steps ... : 9%|▉ | 9162/100000 [2:18:34<14:47:51, 1.71it/s] Train steps ... : 9%|▉ | 9163/100000 [2:18:34<14:46:00, 1.71it/s] Train steps ... : 9%|▉ | 9164/100000 [2:18:35<14:45:42, 1.71it/s] Train steps ... : 9%|▉ | 9165/100000 [2:18:36<14:45:15, 1.71it/s] Train steps ... : 9%|▉ | 9166/100000 [2:18:36<14:48:25, 1.70it/s] Train steps ... : 9%|▉ | 9167/100000 [2:18:37<14:45:44, 1.71it/s] Train steps ... : 9%|▉ | 9168/100000 [2:18:37<14:47:21, 1.71it/s] Train steps ... : 9%|▉ | 9169/100000 [2:18:38<14:45:09, 1.71it/s] Train steps ... : 9%|▉ | 9170/100000 [2:18:39<14:46:35, 1.71it/s] Train steps ... : 9%|▉ | 9171/100000 [2:18:39<14:50:17, 1.70it/s] Train steps ... : 9%|▉ | 9172/100000 [2:18:40<14:45:24, 1.71it/s] Train steps ... : 9%|▉ | 9173/100000 [2:18:40<14:46:37, 1.71it/s] Train steps ... : 9%|▉ | 9174/100000 [2:18:41<14:49:53, 1.70it/s] Train steps ... : 9%|▉ | 9175/100000 [2:18:42<14:45:52, 1.71it/s]Step... (9175 / 100000 | Loss: 1.7987890243530273, Learning Rate: 9.128140703517588e-05) Step... (9175 / 100000 | Loss: 1.1749513149261475, Learning Rate: 9.128140703517588e-05) Train steps ... : 9%|▉ | 9175/100000 [2:18:42<14:45:52, 1.71it/s] Train steps ... : 9%|▉ | 9176/100000 [2:18:42<14:46:53, 1.71it/s] Train steps ... : 9%|▉ | 9177/100000 [2:18:43<14:47:23, 1.71it/s] Train steps ... : 9%|▉ | 9178/100000 [2:18:43<14:45:22, 1.71it/s] Train steps ... : 9%|▉ | 9179/100000 [2:18:44<14:47:10, 1.71it/s] Train steps ... : 9%|▉ | 9180/100000 [2:18:44<14:47:18, 1.71it/s] Train steps ... : 9%|▉ | 9181/100000 [2:18:45<14:48:43, 1.70it/s] Train steps ... : 9%|▉ | 9182/100000 [2:18:46<14:46:26, 1.71it/s] Train steps ... : 9%|▉ | 9183/100000 [2:18:46<14:46:14, 1.71it/s] Train steps ... : 9%|▉ | 9184/100000 [2:18:47<14:47:08, 1.71it/s] Train steps ... : 9%|▉ | 9185/100000 [2:18:47<14:45:40, 1.71it/s] Train steps ... : 9%|▉ | 9186/100000 [2:18:48<14:47:15, 1.71it/s] Train steps ... : 9%|▉ | 9187/100000 [2:18:49<14:48:09, 1.70it/s] Train steps ... : 9%|▉ | 9188/100000 [2:18:49<14:46:11, 1.71it/s] Train steps ... : 9%|▉ | 9189/100000 [2:18:50<14:45:26, 1.71it/s] Train steps ... : 9%|▉ | 9190/100000 [2:18:50<14:44:55, 1.71it/s] Train steps ... : 9%|▉ | 9191/100000 [2:18:51<14:45:06, 1.71it/s] Train steps ... : 9%|▉ | 9192/100000 [2:18:51<14:45:24, 1.71it/s] Train steps ... : 9%|▉ | 9193/100000 [2:18:52<14:44:12, 1.71it/s] Train steps ... : 9%|▉ | 9194/100000 [2:18:53<14:46:08, 1.71it/s] Train steps ... : 9%|▉ | 9195/100000 [2:18:53<14:45:36, 1.71it/s] Train steps ... : 9%|▉ | 9196/100000 [2:18:54<14:45:47, 1.71it/s] Train steps ... : 9%|▉ | 9197/100000 [2:18:54<14:47:27, 1.71it/s] Train steps ... : 9%|▉ | 9198/100000 [2:18:55<14:45:49, 1.71it/s] Train steps ... : 9%|▉ | 9199/100000 [2:18:56<14:47:26, 1.71it/s] Train steps ... : 9%|▉ | 9200/100000 [2:18:56<14:45:05, 1.71it/s]Step... (9200 / 100000 | Loss: 1.362597942352295, Learning Rate: 9.125628140703519e-05) Step... (9200 / 100000 | Loss: 1.1331244707107544, Learning Rate: 9.125628140703519e-05) Train steps ... : 9%|▉ | 9200/100000 [2:18:56<14:45:05, 1.71it/s] Train steps ... : 9%|▉ | 9201/100000 [2:18:57<14:46:28, 1.71it/s] Train steps ... : 9%|▉ | 9202/100000 [2:18:57<14:46:12, 1.71it/s] Train steps ... : 9%|▉ | 9203/100000 [2:18:58<14:46:20, 1.71it/s] Train steps ... : 9%|▉ | 9204/100000 [2:18:59<14:46:29, 1.71it/s] Train steps ... : 9%|▉ | 9205/100000 [2:18:59<14:46:01, 1.71it/s] Train steps ... : 9%|▉ | 9206/100000 [2:19:00<14:46:27, 1.71it/s] Train steps ... : 9%|▉ | 9207/100000 [2:19:00<14:46:44, 1.71it/s] Train steps ... : 9%|▉ | 9208/100000 [2:19:01<14:46:24, 1.71it/s] Train steps ... : 9%|▉ | 9209/100000 [2:19:01<14:47:52, 1.70it/s] Train steps ... : 9%|▉ | 9210/100000 [2:19:02<14:45:51, 1.71it/s] Train steps ... : 9%|▉ | 9211/100000 [2:19:03<14:45:49, 1.71it/s] Train steps ... : 9%|▉ | 9212/100000 [2:19:03<14:45:03, 1.71it/s] Train steps ... : 9%|▉ | 9213/100000 [2:19:04<14:47:42, 1.70it/s] Train steps ... : 9%|▉ | 9214/100000 [2:19:04<14:44:18, 1.71it/s] Train steps ... : 9%|▉ | 9215/100000 [2:19:05<14:44:28, 1.71it/s] Train steps ... : 9%|▉ | 9216/100000 [2:19:06<14:43:33, 1.71it/s] Train steps ... : 9%|▉ | 9217/100000 [2:19:06<14:43:46, 1.71it/s] Train steps ... : 9%|▉ | 9218/100000 [2:19:07<14:43:21, 1.71it/s] Train steps ... : 9%|▉ | 9219/100000 [2:19:07<14:43:28, 1.71it/s] Train steps ... : 9%|▉ | 9220/100000 [2:19:08<14:44:56, 1.71it/s] Train steps ... : 9%|▉ | 9221/100000 [2:19:08<14:45:57, 1.71it/s] Train steps ... : 9%|▉ | 9222/100000 [2:19:09<14:45:25, 1.71it/s] Train steps ... : 9%|▉ | 9223/100000 [2:19:10<14:44:52, 1.71it/s] Train steps ... : 9%|▉ | 9224/100000 [2:19:10<14:45:31, 1.71it/s] Train steps ... : 9%|▉ | 9225/100000 [2:19:11<14:45:54, 1.71it/s]Step... (9225 / 100000 | Loss: 1.2539386749267578, Learning Rate: 9.123115577889447e-05) Step... (9225 / 100000 | Loss: 1.047942876815796, Learning Rate: 9.123115577889447e-05) Train steps ... : 9%|▉ | 9225/100000 [2:19:11<14:45:54, 1.71it/s] Train steps ... : 9%|▉ | 9226/100000 [2:19:11<14:47:39, 1.70it/s] Train steps ... : 9%|▉ | 9227/100000 [2:19:12<14:46:41, 1.71it/s] Train steps ... : 9%|▉ | 9228/100000 [2:19:13<14:49:52, 1.70it/s] Train steps ... : 9%|▉ | 9229/100000 [2:19:13<14:48:00, 1.70it/s] Train steps ... : 9%|▉ | 9230/100000 [2:19:14<14:46:09, 1.71it/s] Train steps ... : 9%|▉ | 9231/100000 [2:19:14<14:47:02, 1.71it/s] Train steps ... : 9%|▉ | 9232/100000 [2:19:15<14:44:51, 1.71it/s] Train steps ... : 9%|▉ | 9233/100000 [2:19:15<14:47:34, 1.70it/s] Train steps ... : 9%|▉ | 9234/100000 [2:19:16<14:45:15, 1.71it/s] Train steps ... : 9%|▉ | 9235/100000 [2:19:17<14:45:13, 1.71it/s] Train steps ... : 9%|▉ | 9236/100000 [2:19:17<14:46:22, 1.71it/s] Train steps ... : 9%|▉ | 9237/100000 [2:19:18<14:45:45, 1.71it/s] Train steps ... : 9%|▉ | 9238/100000 [2:19:18<14:46:25, 1.71it/s] Train steps ... : 9%|▉ | 9239/100000 [2:19:19<14:48:46, 1.70it/s] Train steps ... : 9%|▉ | 9240/100000 [2:19:20<14:48:51, 1.70it/s] Train steps ... : 9%|▉ | 9241/100000 [2:19:20<14:47:25, 1.70it/s] Train steps ... : 9%|▉ | 9242/100000 [2:19:21<14:49:18, 1.70it/s] Train steps ... : 9%|▉ | 9243/100000 [2:19:21<14:45:47, 1.71it/s] Train steps ... : 9%|▉ | 9244/100000 [2:19:22<14:46:39, 1.71it/s] Train steps ... : 9%|▉ | 9245/100000 [2:19:23<14:47:27, 1.70it/s] Train steps ... : 9%|▉ | 9246/100000 [2:19:23<14:45:06, 1.71it/s] Train steps ... : 9%|▉ | 9247/100000 [2:19:24<14:45:44, 1.71it/s] Train steps ... : 9%|▉ | 9248/100000 [2:19:24<14:44:10, 1.71it/s] Train steps ... : 9%|▉ | 9249/100000 [2:19:25<14:44:05, 1.71it/s] Train steps ... : 9%|▉ | 9250/100000 [2:19:25<14:44:40, 1.71it/s]Step... (9250 / 100000 | Loss: 1.508413314819336, Learning Rate: 9.120603015075377e-05) Step... (9250 / 100000 | Loss: 1.6736390590667725, Learning Rate: 9.120603015075377e-05) Train steps ... : 9%|▉ | 9250/100000 [2:19:26<14:44:40, 1.71it/s] Train steps ... : 9%|▉ | 9251/100000 [2:19:26<14:44:47, 1.71it/s] Train steps ... : 9%|▉ | 9252/100000 [2:19:27<14:45:36, 1.71it/s] Train steps ... : 9%|▉ | 9253/100000 [2:19:27<14:43:49, 1.71it/s] Train steps ... : 9%|▉ | 9254/100000 [2:19:28<14:43:57, 1.71it/s] Train steps ... : 9%|▉ | 9255/100000 [2:19:28<14:44:37, 1.71it/s] Train steps ... : 9%|▉ | 9256/100000 [2:19:29<14:45:22, 1.71it/s] Train steps ... : 9%|▉ | 9257/100000 [2:19:30<14:43:49, 1.71it/s] Train steps ... : 9%|▉ | 9258/100000 [2:19:30<14:43:50, 1.71it/s] Train steps ... : 9%|▉ | 9259/100000 [2:19:31<14:44:25, 1.71it/s] Train steps ... : 9%|▉ | 9260/100000 [2:19:31<14:43:21, 1.71it/s] Train steps ... : 9%|▉ | 9261/100000 [2:19:32<14:43:30, 1.71it/s] Train steps ... : 9%|▉ | 9262/100000 [2:19:32<14:43:21, 1.71it/s] Train steps ... : 9%|▉ | 9263/100000 [2:19:33<14:42:53, 1.71it/s] Train steps ... : 9%|▉ | 9264/100000 [2:19:34<14:43:16, 1.71it/s] Train steps ... : 9%|▉ | 9265/100000 [2:19:34<14:43:37, 1.71it/s] Train steps ... : 9%|▉ | 9266/100000 [2:19:35<14:44:16, 1.71it/s] Train steps ... : 9%|▉ | 9267/100000 [2:19:35<14:43:41, 1.71it/s] Train steps ... : 9%|▉ | 9268/100000 [2:19:36<14:43:36, 1.71it/s] Train steps ... : 9%|▉ | 9269/100000 [2:19:37<14:44:34, 1.71it/s] Train steps ... : 9%|▉ | 9270/100000 [2:19:37<14:46:00, 1.71it/s] Train steps ... : 9%|▉ | 9271/100000 [2:19:38<14:45:36, 1.71it/s] Train steps ... : 9%|▉ | 9272/100000 [2:19:38<14:44:42, 1.71it/s] Train steps ... : 9%|▉ | 9273/100000 [2:19:39<14:45:24, 1.71it/s] Train steps ... : 9%|▉ | 9274/100000 [2:19:39<14:44:54, 1.71it/s] Train steps ... : 9%|▉ | 9275/100000 [2:19:40<14:44:38, 1.71it/s]Step... (9275 / 100000 | Loss: 0.9018685817718506, Learning Rate: 9.118090452261306e-05) Step... (9275 / 100000 | Loss: 1.4575650691986084, Learning Rate: 9.118090452261306e-05) Train steps ... : 9%|▉ | 9275/100000 [2:19:40<14:44:38, 1.71it/s] Train steps ... : 9%|▉ | 9276/100000 [2:19:41<14:45:28, 1.71it/s] Train steps ... : 9%|▉ | 9277/100000 [2:19:41<14:44:23, 1.71it/s] Train steps ... : 9%|▉ | 9278/100000 [2:19:42<14:46:39, 1.71it/s] Train steps ... : 9%|▉ | 9279/100000 [2:19:42<14:44:13, 1.71it/s] Train steps ... : 9%|▉ | 9280/100000 [2:19:43<14:46:57, 1.70it/s] Train steps ... : 9%|▉ | 9281/100000 [2:19:44<14:44:47, 1.71it/s] Train steps ... : 9%|▉ | 9282/100000 [2:19:44<14:48:45, 1.70it/s] Train steps ... : 9%|▉ | 9283/100000 [2:19:45<14:46:30, 1.71it/s] Train steps ... : 9%|▉ | 9284/100000 [2:19:45<14:48:44, 1.70it/s] Train steps ... : 9%|▉ | 9285/100000 [2:19:46<14:47:44, 1.70it/s] Train steps ... : 9%|▉ | 9286/100000 [2:19:47<14:46:19, 1.71it/s] Train steps ... : 9%|▉ | 9287/100000 [2:19:47<14:46:33, 1.71it/s] Train steps ... : 9%|▉ | 9288/100000 [2:19:48<14:45:08, 1.71it/s] Train steps ... : 9%|▉ | 9289/100000 [2:19:48<14:45:40, 1.71it/s] Train steps ... : 9%|▉ | 9290/100000 [2:19:49<14:44:13, 1.71it/s] Train steps ... : 9%|▉ | 9291/100000 [2:19:49<14:43:56, 1.71it/s] Train steps ... : 9%|▉ | 9292/100000 [2:19:50<14:46:16, 1.71it/s] Train steps ... : 9%|▉ | 9293/100000 [2:19:51<14:45:33, 1.71it/s] Train steps ... : 9%|▉ | 9294/100000 [2:19:51<14:48:12, 1.70it/s] Train steps ... : 9%|▉ | 9295/100000 [2:19:52<14:49:34, 1.70it/s] Train steps ... : 9%|▉ | 9296/100000 [2:19:52<14:46:07, 1.71it/s] Train steps ... : 9%|▉ | 9297/100000 [2:19:53<14:43:43, 1.71it/s] Train steps ... : 9%|▉ | 9298/100000 [2:19:54<14:45:13, 1.71it/s] Train steps ... : 9%|▉ | 9299/100000 [2:19:54<14:46:27, 1.71it/s] Train steps ... : 9%|▉ | 9300/100000 [2:19:55<14:44:45, 1.71it/s]Step... (9300 / 100000 | Loss: 1.1282685995101929, Learning Rate: 9.115577889447236e-05) Step... (9300 / 100000 | Loss: 1.5769891738891602, Learning Rate: 9.115577889447236e-05) Train steps ... : 9%|▉ | 9300/100000 [2:19:55<14:44:45, 1.71it/s] Train steps ... : 9%|▉ | 9301/100000 [2:19:55<14:48:48, 1.70it/s] Train steps ... : 9%|▉ | 9302/100000 [2:19:56<14:45:43, 1.71it/s] Train steps ... : 9%|▉ | 9303/100000 [2:19:56<14:47:11, 1.70it/s] Train steps ... : 9%|▉ | 9304/100000 [2:19:57<14:46:43, 1.70it/s] Train steps ... : 9%|▉ | 9305/100000 [2:19:58<14:47:31, 1.70it/s] Train steps ... : 9%|▉ | 9306/100000 [2:19:58<14:46:15, 1.71it/s] Train steps ... : 9%|▉ | 9307/100000 [2:19:59<14:44:53, 1.71it/s] Train steps ... : 9%|▉ | 9308/100000 [2:19:59<14:43:51, 1.71it/s] Train steps ... : 9%|▉ | 9309/100000 [2:20:00<14:44:06, 1.71it/s] Train steps ... : 9%|▉ | 9310/100000 [2:20:01<14:45:05, 1.71it/s] Train steps ... : 9%|▉ | 9311/100000 [2:20:01<14:44:42, 1.71it/s] Train steps ... : 9%|▉ | 9312/100000 [2:20:02<14:47:54, 1.70it/s] Train steps ... : 9%|▉ | 9313/100000 [2:20:02<14:45:02, 1.71it/s] Train steps ... : 9%|▉ | 9314/100000 [2:20:03<14:46:35, 1.70it/s] Train steps ... : 9%|▉ | 9315/100000 [2:20:04<14:45:24, 1.71it/s] Train steps ... : 9%|▉ | 9316/100000 [2:20:04<14:46:33, 1.70it/s] Train steps ... : 9%|▉ | 9317/100000 [2:20:05<14:45:19, 1.71it/s] Train steps ... : 9%|▉ | 9318/100000 [2:20:05<14:46:45, 1.70it/s] Train steps ... : 9%|▉ | 9319/100000 [2:20:06<14:45:59, 1.71it/s] Train steps ... : 9%|▉ | 9320/100000 [2:20:06<14:46:43, 1.70it/s] Train steps ... : 9%|▉ | 9321/100000 [2:20:07<14:46:56, 1.70it/s] Train steps ... : 9%|▉ | 9322/100000 [2:20:08<14:46:00, 1.71it/s] Train steps ... : 9%|▉ | 9323/100000 [2:20:08<14:45:16, 1.71it/s] Train steps ... : 9%|▉ | 9324/100000 [2:20:09<14:46:01, 1.71it/s] Train steps ... : 9%|▉ | 9325/100000 [2:20:09<14:45:02, 1.71it/s]Step... (9325 / 100000 | Loss: 0.925187349319458, Learning Rate: 9.113065326633167e-05) Step... (9325 / 100000 | Loss: 1.4254413843154907, Learning Rate: 9.113065326633167e-05) Train steps ... : 9%|▉ | 9325/100000 [2:20:10<14:45:02, 1.71it/s] Train steps ... : 9%|▉ | 9326/100000 [2:20:10<14:47:25, 1.70it/s] Train steps ... : 9%|▉ | 9327/100000 [2:20:11<14:45:16, 1.71it/s] Train steps ... : 9%|▉ | 9328/100000 [2:20:11<14:45:35, 1.71it/s] Train steps ... : 9%|▉ | 9329/100000 [2:20:12<14:47:47, 1.70it/s] Train steps ... : 9%|▉ | 9330/100000 [2:20:12<14:47:20, 1.70it/s] Train steps ... : 9%|▉ | 9331/100000 [2:20:13<14:46:23, 1.70it/s] Train steps ... : 9%|▉ | 9332/100000 [2:20:13<14:47:18, 1.70it/s] Train steps ... : 9%|▉ | 9333/100000 [2:20:14<14:46:16, 1.71it/s] Train steps ... : 9%|▉ | 9334/100000 [2:20:15<14:44:39, 1.71it/s] Train steps ... : 9%|▉ | 9335/100000 [2:20:15<14:45:23, 1.71it/s] Train steps ... : 9%|▉ | 9336/100000 [2:20:16<14:44:01, 1.71it/s] Train steps ... : 9%|▉ | 9337/100000 [2:20:16<14:44:14, 1.71it/s] Train steps ... : 9%|▉ | 9338/100000 [2:20:17<14:46:56, 1.70it/s] Train steps ... : 9%|▉ | 9339/100000 [2:20:18<14:45:46, 1.71it/s] Train steps ... : 9%|▉ | 9340/100000 [2:20:18<14:44:18, 1.71it/s] Train steps ... : 9%|▉ | 9341/100000 [2:20:19<14:45:19, 1.71it/s] Train steps ... : 9%|▉ | 9342/100000 [2:20:19<14:48:20, 1.70it/s] Train steps ... : 9%|▉ | 9343/100000 [2:20:20<14:45:27, 1.71it/s] Train steps ... : 9%|▉ | 9344/100000 [2:20:21<14:44:43, 1.71it/s] Train steps ... : 9%|▉ | 9345/100000 [2:20:21<14:43:53, 1.71it/s] Train steps ... : 9%|▉ | 9346/100000 [2:20:22<14:44:41, 1.71it/s] Train steps ... : 9%|▉ | 9347/100000 [2:20:22<14:44:21, 1.71it/s] Train steps ... : 9%|▉ | 9348/100000 [2:20:23<14:44:04, 1.71it/s] Train steps ... : 9%|▉ | 9349/100000 [2:20:23<14:44:03, 1.71it/s] Train steps ... : 9%|▉ | 9350/100000 [2:20:24<14:44:49, 1.71it/s]Step... (9350 / 100000 | Loss: 1.0658183097839355, Learning Rate: 9.110552763819095e-05) Step... (9350 / 100000 | Loss: 1.6353753805160522, Learning Rate: 9.110552763819095e-05) Train steps ... : 9%|▉ | 9350/100000 [2:20:24<14:44:49, 1.71it/s] Train steps ... : 9%|▉ | 9351/100000 [2:20:25<14:46:14, 1.70it/s] Train steps ... : 9%|▉ | 9352/100000 [2:20:25<14:43:54, 1.71it/s] Train steps ... : 9%|▉ | 9353/100000 [2:20:26<14:45:01, 1.71it/s] Train steps ... : 9%|▉ | 9354/100000 [2:20:26<14:43:37, 1.71it/s] Train steps ... : 9%|▉ | 9355/100000 [2:20:27<14:44:09, 1.71it/s] Train steps ... : 9%|▉ | 9356/100000 [2:20:28<14:43:19, 1.71it/s] Train steps ... : 9%|▉ | 9357/100000 [2:20:28<14:44:21, 1.71it/s] Train steps ... : 9%|▉ | 9358/100000 [2:20:29<14:43:41, 1.71it/s] Train steps ... : 9%|▉ | 9359/100000 [2:20:29<14:43:54, 1.71it/s] Train steps ... : 9%|▉ | 9360/100000 [2:20:30<14:44:53, 1.71it/s] Train steps ... : 9%|▉ | 9361/100000 [2:20:30<14:43:56, 1.71it/s] Train steps ... : 9%|▉ | 9362/100000 [2:20:31<14:44:49, 1.71it/s] Train steps ... : 9%|▉ | 9363/100000 [2:20:32<14:45:55, 1.71it/s] Train steps ... : 9%|▉ | 9364/100000 [2:20:32<14:46:20, 1.70it/s] Train steps ... : 9%|▉ | 9365/100000 [2:20:33<14:46:17, 1.70it/s] Train steps ... : 9%|▉ | 9366/100000 [2:20:33<14:46:29, 1.70it/s] Train steps ... : 9%|▉ | 9367/100000 [2:20:34<14:45:54, 1.71it/s] Train steps ... : 9%|▉ | 9368/100000 [2:20:35<14:44:00, 1.71it/s] Train steps ... : 9%|▉ | 9369/100000 [2:20:35<14:43:58, 1.71it/s] Train steps ... : 9%|▉ | 9370/100000 [2:20:36<14:45:36, 1.71it/s] Train steps ... : 9%|▉ | 9371/100000 [2:20:36<14:45:33, 1.71it/s] Train steps ... : 9%|▉ | 9372/100000 [2:20:37<14:45:03, 1.71it/s] Train steps ... : 9%|▉ | 9373/100000 [2:20:38<14:45:06, 1.71it/s] Train steps ... : 9%|▉ | 9374/100000 [2:20:38<14:47:36, 1.70it/s] Train steps ... : 9%|▉ | 9375/100000 [2:20:39<14:45:57, 1.70it/s]Step... (9375 / 100000 | Loss: 1.1875861883163452, Learning Rate: 9.108040201005026e-05) Step... (9375 / 100000 | Loss: 1.3808324337005615, Learning Rate: 9.108040201005026e-05) Train steps ... : 9%|▉ | 9375/100000 [2:20:39<14:45:57, 1.70it/s] Train steps ... : 9%|▉ | 9376/100000 [2:20:39<14:45:00, 1.71it/s] Train steps ... : 9%|▉ | 9377/100000 [2:20:40<14:43:55, 1.71it/s] Train steps ... : 9%|▉ | 9378/100000 [2:20:40<14:43:23, 1.71it/s] Train steps ... : 9%|▉ | 9379/100000 [2:20:41<14:45:54, 1.70it/s] Train steps ... : 9%|▉ | 9380/100000 [2:20:42<14:44:28, 1.71it/s] Train steps ... : 9%|▉ | 9381/100000 [2:20:42<14:44:31, 1.71it/s] Train steps ... : 9%|▉ | 9382/100000 [2:20:43<14:43:25, 1.71it/s] Train steps ... : 9%|▉ | 9383/100000 [2:20:43<14:46:04, 1.70it/s] Train steps ... : 9%|▉ | 9384/100000 [2:20:44<14:43:43, 1.71it/s] Train steps ... : 9%|▉ | 9385/100000 [2:20:45<14:42:51, 1.71it/s] Train steps ... : 9%|▉ | 9386/100000 [2:20:45<14:44:23, 1.71it/s] Train steps ... : 9%|▉ | 9387/100000 [2:20:46<14:46:09, 1.70it/s] Train steps ... : 9%|▉ | 9388/100000 [2:20:46<14:46:26, 1.70it/s] Train steps ... : 9%|▉ | 9389/100000 [2:20:47<14:46:07, 1.70it/s] Train steps ... : 9%|▉ | 9390/100000 [2:20:47<14:45:09, 1.71it/s] Train steps ... : 9%|▉ | 9391/100000 [2:20:48<14:45:37, 1.71it/s] Train steps ... : 9%|▉ | 9392/100000 [2:20:49<14:44:49, 1.71it/s] Train steps ... : 9%|▉ | 9393/100000 [2:20:49<14:45:34, 1.71it/s] Train steps ... : 9%|▉ | 9394/100000 [2:20:50<14:43:40, 1.71it/s] Train steps ... : 9%|▉ | 9395/100000 [2:20:50<14:45:44, 1.70it/s] Train steps ... : 9%|▉ | 9396/100000 [2:20:51<14:45:00, 1.71it/s] Train steps ... : 9%|▉ | 9397/100000 [2:20:52<14:45:08, 1.71it/s] Train steps ... : 9%|▉ | 9398/100000 [2:20:52<14:45:10, 1.71it/s] Train steps ... : 9%|▉ | 9399/100000 [2:20:53<14:44:47, 1.71it/s] Train steps ... : 9%|▉ | 9400/100000 [2:20:53<14:43:36, 1.71it/s]Step... (9400 / 100000 | Loss: 1.620875597000122, Learning Rate: 9.105527638190955e-05) Step... (9400 / 100000 | Loss: 1.6473677158355713, Learning Rate: 9.105527638190955e-05) Train steps ... : 9%|▉ | 9400/100000 [2:20:54<14:43:36, 1.71it/s] Train steps ... : 9%|▉ | 9401/100000 [2:20:54<14:45:42, 1.70it/s] Train steps ... : 9%|▉ | 9402/100000 [2:20:54<14:45:45, 1.70it/s] Train steps ... : 9%|▉ | 9403/100000 [2:20:55<14:45:48, 1.70it/s] Train steps ... : 9%|▉ | 9404/100000 [2:20:56<14:47:48, 1.70it/s] Train steps ... : 9%|▉ | 9405/100000 [2:20:56<14:44:31, 1.71it/s] Train steps ... : 9%|▉ | 9406/100000 [2:20:57<14:47:07, 1.70it/s] Train steps ... : 9%|▉ | 9407/100000 [2:20:57<14:45:07, 1.71it/s] Train steps ... : 9%|▉ | 9408/100000 [2:20:58<14:46:21, 1.70it/s] Train steps ... : 9%|▉ | 9409/100000 [2:20:59<14:44:33, 1.71it/s] Train steps ... : 9%|▉ | 9410/100000 [2:20:59<14:42:22, 1.71it/s] Train steps ... : 9%|▉ | 9411/100000 [2:21:00<14:44:12, 1.71it/s] Train steps ... : 9%|▉ | 9412/100000 [2:21:00<14:43:53, 1.71it/s] Train steps ... : 9%|▉ | 9413/100000 [2:21:01<14:45:00, 1.71it/s] Train steps ... : 9%|▉ | 9414/100000 [2:21:02<14:45:46, 1.70it/s] Train steps ... : 9%|▉ | 9415/100000 [2:21:02<14:44:59, 1.71it/s] Train steps ... : 9%|▉ | 9416/100000 [2:21:03<14:49:15, 1.70it/s] Train steps ... : 9%|▉ | 9417/100000 [2:21:03<14:46:35, 1.70it/s] Train steps ... : 9%|▉ | 9418/100000 [2:21:04<14:48:59, 1.70it/s] Train steps ... : 9%|▉ | 9419/100000 [2:21:04<14:44:53, 1.71it/s] Train steps ... : 9%|▉ | 9420/100000 [2:21:05<14:43:14, 1.71it/s] Train steps ... : 9%|▉ | 9421/100000 [2:21:06<14:44:51, 1.71it/s] Train steps ... : 9%|▉ | 9422/100000 [2:21:06<14:48:06, 1.70it/s] Train steps ... : 9%|▉ | 9423/100000 [2:21:07<14:44:15, 1.71it/s] Train steps ... : 9%|▉ | 9424/100000 [2:21:07<14:47:33, 1.70it/s] Train steps ... : 9%|▉ | 9425/100000 [2:21:08<14:45:39, 1.70it/s]Step... (9425 / 100000 | Loss: 1.0083062648773193, Learning Rate: 9.103015075376884e-05) Step... (9425 / 100000 | Loss: 1.2988755702972412, Learning Rate: 9.103015075376884e-05) Train steps ... : 9%|▉ | 9425/100000 [2:21:08<14:45:39, 1.70it/s] Train steps ... : 9%|▉ | 9426/100000 [2:21:09<14:46:33, 1.70it/s] Train steps ... : 9%|▉ | 9427/100000 [2:21:09<14:45:09, 1.71it/s] Train steps ... : 9%|▉ | 9428/100000 [2:21:10<14:45:41, 1.70it/s] Train steps ... : 9%|▉ | 9429/100000 [2:21:10<14:45:57, 1.70it/s] Train steps ... : 9%|▉ | 9430/100000 [2:21:11<14:45:48, 1.70it/s] Train steps ... : 9%|▉ | 9431/100000 [2:21:12<14:46:50, 1.70it/s] Train steps ... : 9%|▉ | 9432/100000 [2:21:12<14:46:36, 1.70it/s] Train steps ... : 9%|▉ | 9433/100000 [2:21:13<14:45:41, 1.70it/s] Train steps ... : 9%|▉ | 9434/100000 [2:21:13<14:45:06, 1.71it/s] Train steps ... : 9%|▉ | 9435/100000 [2:21:14<14:46:05, 1.70it/s] Train steps ... : 9%|▉ | 9436/100000 [2:21:14<14:44:59, 1.71it/s] Train steps ... : 9%|▉ | 9437/100000 [2:21:15<14:46:40, 1.70it/s] Train steps ... : 9%|▉ | 9438/100000 [2:21:16<14:46:31, 1.70it/s] Train steps ... : 9%|▉ | 9439/100000 [2:21:16<14:47:57, 1.70it/s] Train steps ... : 9%|▉ | 9440/100000 [2:21:17<14:45:43, 1.70it/s] Train steps ... : 9%|▉ | 9441/100000 [2:21:17<14:45:45, 1.70it/s] Train steps ... : 9%|▉ | 9442/100000 [2:21:18<14:45:21, 1.70it/s] Train steps ... : 9%|▉ | 9443/100000 [2:21:19<14:46:52, 1.70it/s] Train steps ... : 9%|▉ | 9444/100000 [2:21:19<14:47:49, 1.70it/s] Train steps ... : 9%|▉ | 9445/100000 [2:21:20<14:46:29, 1.70it/s] Train steps ... : 9%|▉ | 9446/100000 [2:21:20<14:47:37, 1.70it/s] Train steps ... : 9%|▉ | 9447/100000 [2:21:21<14:45:41, 1.70it/s] Train steps ... : 9%|▉ | 9448/100000 [2:21:21<14:44:27, 1.71it/s] Train steps ... : 9%|▉ | 9449/100000 [2:21:22<14:46:16, 1.70it/s] Train steps ... : 9%|▉ | 9450/100000 [2:21:23<14:44:46, 1.71it/s]Step... (9450 / 100000 | Loss: 1.2329423427581787, Learning Rate: 9.100502512562814e-05) Step... (9450 / 100000 | Loss: 1.1246767044067383, Learning Rate: 9.100502512562814e-05) Train steps ... : 9%|▉ | 9450/100000 [2:21:23<14:44:46, 1.71it/s] Train steps ... : 9%|▉ | 9451/100000 [2:21:23<14:46:56, 1.70it/s] Train steps ... : 9%|▉ | 9452/100000 [2:21:24<14:44:51, 1.71it/s] Train steps ... : 9%|▉ | 9453/100000 [2:21:24<14:43:06, 1.71it/s] Train steps ... : 9%|▉ | 9454/100000 [2:21:25<14:43:02, 1.71it/s] Train steps ... : 9%|▉ | 9455/100000 [2:21:26<14:45:39, 1.70it/s] Train steps ... : 9%|▉ | 9456/100000 [2:21:26<14:43:31, 1.71it/s] Train steps ... : 9%|▉ | 9457/100000 [2:21:27<14:44:46, 1.71it/s] Train steps ... : 9%|▉ | 9458/100000 [2:21:27<14:43:29, 1.71it/s] Train steps ... : 9%|▉ | 9459/100000 [2:21:28<14:44:52, 1.71it/s] Train steps ... : 9%|▉ | 9460/100000 [2:21:29<14:44:37, 1.71it/s] Train steps ... : 9%|▉ | 9461/100000 [2:21:29<14:48:06, 1.70it/s] Train steps ... : 9%|▉ | 9462/100000 [2:21:30<14:43:33, 1.71it/s] Train steps ... : 9%|▉ | 9463/100000 [2:21:30<14:44:26, 1.71it/s] Train steps ... : 9%|▉ | 9464/100000 [2:21:31<14:43:50, 1.71it/s] Train steps ... : 9%|▉ | 9465/100000 [2:21:31<14:44:41, 1.71it/s] Train steps ... : 9%|▉ | 9466/100000 [2:21:32<14:44:14, 1.71it/s] Train steps ... : 9%|▉ | 9467/100000 [2:21:33<14:45:38, 1.70it/s] Train steps ... : 9%|▉ | 9468/100000 [2:21:33<14:43:50, 1.71it/s] Train steps ... : 9%|▉ | 9469/100000 [2:21:34<14:46:39, 1.70it/s] Train steps ... : 9%|▉ | 9470/100000 [2:21:34<14:45:48, 1.70it/s] Train steps ... : 9%|▉ | 9471/100000 [2:21:35<14:45:53, 1.70it/s] Train steps ... : 9%|▉ | 9472/100000 [2:21:36<14:45:22, 1.70it/s] Train steps ... : 9%|▉ | 9473/100000 [2:21:36<14:44:50, 1.71it/s] Train steps ... : 9%|▉ | 9474/100000 [2:21:37<14:45:13, 1.70it/s] Train steps ... : 9%|▉ | 9475/100000 [2:21:37<14:45:08, 1.70it/s]Step... (9475 / 100000 | Loss: 1.4606887102127075, Learning Rate: 9.097989949748744e-05) Step... (9475 / 100000 | Loss: 1.1777069568634033, Learning Rate: 9.097989949748744e-05) Train steps ... : 9%|▉ | 9475/100000 [2:21:38<14:45:08, 1.70it/s] Train steps ... : 9%|▉ | 9476/100000 [2:21:38<14:45:21, 1.70it/s] Train steps ... : 9%|▉ | 9477/100000 [2:21:39<14:45:16, 1.70it/s] Train steps ... : 9%|▉ | 9478/100000 [2:21:39<14:43:48, 1.71it/s] Train steps ... : 9%|▉ | 9479/100000 [2:21:40<14:43:14, 1.71it/s] Train steps ... : 9%|▉ | 9480/100000 [2:21:40<14:44:48, 1.71it/s] Train steps ... : 9%|▉ | 9481/100000 [2:21:41<14:45:46, 1.70it/s] Train steps ... : 9%|▉ | 9482/100000 [2:21:41<14:42:38, 1.71it/s] Train steps ... : 9%|▉ | 9483/100000 [2:21:42<14:42:40, 1.71it/s] Train steps ... : 9%|▉ | 9484/100000 [2:21:43<14:41:43, 1.71it/s] Train steps ... : 9%|▉ | 9485/100000 [2:21:43<14:44:16, 1.71it/s] Train steps ... : 9%|▉ | 9486/100000 [2:21:44<14:45:42, 1.70it/s] Train steps ... : 9%|▉ | 9487/100000 [2:21:44<14:43:41, 1.71it/s] Train steps ... : 9%|▉ | 9488/100000 [2:21:45<14:43:30, 1.71it/s] Train steps ... : 9%|▉ | 9489/100000 [2:21:46<14:44:15, 1.71it/s] Train steps ... : 9%|▉ | 9490/100000 [2:21:46<14:46:26, 1.70it/s] Train steps ... : 9%|▉ | 9491/100000 [2:21:47<14:45:42, 1.70it/s] Train steps ... : 9%|▉ | 9492/100000 [2:21:47<14:46:56, 1.70it/s] Train steps ... : 9%|▉ | 9493/100000 [2:21:48<14:44:42, 1.71it/s] Train steps ... : 9%|▉ | 9494/100000 [2:21:48<14:43:35, 1.71it/s] Train steps ... : 9%|▉ | 9495/100000 [2:21:49<14:45:25, 1.70it/s] Train steps ... : 9%|▉ | 9496/100000 [2:21:50<14:46:02, 1.70it/s] Train steps ... : 9%|▉ | 9497/100000 [2:21:50<14:44:44, 1.70it/s] Train steps ... : 9%|▉ | 9498/100000 [2:21:51<14:44:05, 1.71it/s] Train steps ... : 9%|▉ | 9499/100000 [2:21:51<14:45:49, 1.70it/s] Train steps ... : 10%|▉ | 9500/100000 [2:21:52<14:46:07, 1.70it/s]Step... (9500 / 100000 | Loss: 1.045730710029602, Learning Rate: 9.095477386934675e-05) Step... (9500 / 100000 | Loss: 1.6484401226043701, Learning Rate: 9.095477386934675e-05) Train steps ... : 10%|▉ | 9500/100000 [2:21:52<14:46:07, 1.70it/s] Train steps ... : 10%|▉ | 9501/100000 [2:21:53<14:46:25, 1.70it/s] Train steps ... : 10%|▉ | 9502/100000 [2:21:53<14:44:24, 1.71it/s] Train steps ... : 10%|▉ | 9503/100000 [2:21:54<14:42:54, 1.71it/s] Train steps ... : 10%|▉ | 9504/100000 [2:21:54<14:42:44, 1.71it/s] Train steps ... : 10%|▉ | 9505/100000 [2:21:55<14:43:19, 1.71it/s] Train steps ... : 10%|▉ | 9506/100000 [2:21:56<14:43:25, 1.71it/s] Train steps ... : 10%|▉ | 9507/100000 [2:21:56<14:43:11, 1.71it/s] Train steps ... : 10%|▉ | 9508/100000 [2:21:57<14:44:03, 1.71it/s] Train steps ... : 10%|▉ | 9509/100000 [2:21:57<14:44:26, 1.71it/s] Train steps ... : 10%|▉ | 9510/100000 [2:21:58<14:47:11, 1.70it/s] Train steps ... : 10%|▉ | 9511/100000 [2:21:58<14:47:39, 1.70it/s] Train steps ... : 10%|▉ | 9512/100000 [2:21:59<14:48:29, 1.70it/s] Train steps ... : 10%|▉ | 9513/100000 [2:22:00<14:46:29, 1.70it/s] Train steps ... : 10%|▉ | 9514/100000 [2:22:00<14:46:24, 1.70it/s] Train steps ... : 10%|▉ | 9515/100000 [2:22:01<14:44:48, 1.70it/s] Train steps ... : 10%|▉ | 9516/100000 [2:22:01<14:44:08, 1.71it/s] Train steps ... : 10%|▉ | 9517/100000 [2:22:02<14:45:23, 1.70it/s] Train steps ... : 10%|▉ | 9518/100000 [2:22:03<14:42:25, 1.71it/s] Train steps ... : 10%|▉ | 9519/100000 [2:22:03<14:43:34, 1.71it/s] Train steps ... : 10%|▉ | 9520/100000 [2:22:04<14:45:16, 1.70it/s] Train steps ... : 10%|▉ | 9521/100000 [2:22:04<14:43:50, 1.71it/s] Train steps ... : 10%|▉ | 9522/100000 [2:22:05<14:43:12, 1.71it/s] Train steps ... : 10%|▉ | 9523/100000 [2:22:05<14:44:26, 1.70it/s] Train steps ... : 10%|▉ | 9524/100000 [2:22:06<14:46:21, 1.70it/s] Train steps ... : 10%|▉ | 9525/100000 [2:22:07<14:45:24, 1.70it/s]Step... (9525 / 100000 | Loss: 1.0171869993209839, Learning Rate: 9.092964824120603e-05) Step... (9525 / 100000 | Loss: 1.2581415176391602, Learning Rate: 9.092964824120603e-05) Train steps ... : 10%|▉ | 9525/100000 [2:22:07<14:45:24, 1.70it/s] Train steps ... : 10%|▉ | 9526/100000 [2:22:07<14:45:01, 1.70it/s] Train steps ... : 10%|▉ | 9527/100000 [2:22:08<14:44:23, 1.71it/s] Train steps ... : 10%|▉ | 9528/100000 [2:22:08<14:44:10, 1.71it/s] Train steps ... : 10%|▉ | 9529/100000 [2:22:09<14:43:31, 1.71it/s] Train steps ... : 10%|▉ | 9530/100000 [2:22:10<14:43:41, 1.71it/s] Train steps ... : 10%|▉ | 9531/100000 [2:22:10<14:43:00, 1.71it/s] Train steps ... : 10%|▉ | 9532/100000 [2:22:11<14:42:00, 1.71it/s] Train steps ... : 10%|▉ | 9533/100000 [2:22:11<14:42:28, 1.71it/s] Train steps ... : 10%|▉ | 9534/100000 [2:22:12<14:43:59, 1.71it/s] Train steps ... : 10%|▉ | 9535/100000 [2:22:13<14:42:32, 1.71it/s] Train steps ... : 10%|▉ | 9536/100000 [2:22:13<14:43:32, 1.71it/s] Train steps ... : 10%|▉ | 9537/100000 [2:22:14<14:43:14, 1.71it/s] Train steps ... : 10%|▉ | 9538/100000 [2:22:14<14:47:39, 1.70it/s] Train steps ... : 10%|▉ | 9539/100000 [2:22:15<14:48:16, 1.70it/s] Train steps ... : 10%|▉ | 9540/100000 [2:22:15<14:50:25, 1.69it/s] Train steps ... : 10%|▉ | 9541/100000 [2:22:16<14:47:46, 1.70it/s] Train steps ... : 10%|▉ | 9542/100000 [2:22:17<14:46:34, 1.70it/s] Train steps ... : 10%|▉ | 9543/100000 [2:22:17<14:46:26, 1.70it/s] Train steps ... : 10%|▉ | 9544/100000 [2:22:18<14:46:53, 1.70it/s] Train steps ... : 10%|▉ | 9545/100000 [2:22:18<14:44:56, 1.70it/s] Train steps ... : 10%|▉ | 9546/100000 [2:22:19<14:43:11, 1.71it/s] Train steps ... : 10%|▉ | 9547/100000 [2:22:20<14:43:50, 1.71it/s] Train steps ... : 10%|▉ | 9548/100000 [2:22:20<14:44:38, 1.70it/s] Train steps ... : 10%|▉ | 9549/100000 [2:22:21<14:44:26, 1.70it/s] Train steps ... : 10%|▉ | 9550/100000 [2:22:21<14:43:21, 1.71it/s]Step... (9550 / 100000 | Loss: 1.1942646503448486, Learning Rate: 9.090452261306534e-05) Step... (9550 / 100000 | Loss: 0.9860605001449585, Learning Rate: 9.090452261306534e-05) Train steps ... : 10%|▉ | 9550/100000 [2:22:22<14:43:21, 1.71it/s] Train steps ... : 10%|▉ | 9551/100000 [2:22:22<14:44:43, 1.70it/s] Train steps ... : 10%|▉ | 9552/100000 [2:22:23<14:43:42, 1.71it/s] Train steps ... : 10%|▉ | 9553/100000 [2:22:23<14:43:54, 1.71it/s] Train steps ... : 10%|▉ | 9554/100000 [2:22:24<14:43:00, 1.71it/s] Train steps ... : 10%|▉ | 9555/100000 [2:22:24<14:45:24, 1.70it/s] Train steps ... : 10%|▉ | 9556/100000 [2:22:25<14:41:53, 1.71it/s] Train steps ... : 10%|▉ | 9557/100000 [2:22:25<14:41:49, 1.71it/s] Train steps ... : 10%|▉ | 9558/100000 [2:22:26<14:41:02, 1.71it/s] Train steps ... : 10%|▉ | 9559/100000 [2:22:27<14:43:29, 1.71it/s] Train steps ... : 10%|▉ | 9560/100000 [2:22:27<14:40:42, 1.71it/s] Train steps ... : 10%|▉ | 9561/100000 [2:22:28<14:43:28, 1.71it/s] Train steps ... : 10%|▉ | 9562/100000 [2:22:28<14:43:00, 1.71it/s] Train steps ... : 10%|▉ | 9563/100000 [2:22:29<14:40:48, 1.71it/s] Train steps ... : 10%|▉ | 9564/100000 [2:22:30<14:40:41, 1.71it/s] Train steps ... : 10%|▉ | 9565/100000 [2:22:30<14:43:58, 1.71it/s] Train steps ... : 10%|▉ | 9566/100000 [2:22:31<14:45:30, 1.70it/s] Train steps ... : 10%|▉ | 9567/100000 [2:22:31<14:42:30, 1.71it/s] Train steps ... : 10%|▉ | 9568/100000 [2:22:32<14:42:04, 1.71it/s] Train steps ... : 10%|▉ | 9569/100000 [2:22:32<14:42:23, 1.71it/s] Train steps ... : 10%|▉ | 9570/100000 [2:22:33<14:45:31, 1.70it/s] Train steps ... : 10%|▉ | 9571/100000 [2:22:34<14:44:01, 1.70it/s] Train steps ... : 10%|▉ | 9572/100000 [2:22:34<14:45:49, 1.70it/s] Train steps ... : 10%|▉ | 9573/100000 [2:22:35<14:44:47, 1.70it/s] Train steps ... : 10%|▉ | 9574/100000 [2:22:35<14:44:12, 1.70it/s] Train steps ... : 10%|▉ | 9575/100000 [2:22:36<14:46:08, 1.70it/s]Step... (9575 / 100000 | Loss: 1.3858013153076172, Learning Rate: 9.087939698492462e-05) Step... (9575 / 100000 | Loss: 1.6997191905975342, Learning Rate: 9.087939698492462e-05) Train steps ... : 10%|▉ | 9575/100000 [2:22:36<14:46:08, 1.70it/s] Train steps ... : 10%|▉ | 9576/100000 [2:22:37<14:46:49, 1.70it/s] Train steps ... : 10%|▉ | 9577/100000 [2:22:37<14:45:34, 1.70it/s] Train steps ... : 10%|▉ | 9578/100000 [2:22:38<14:45:11, 1.70it/s] Train steps ... : 10%|▉ | 9579/100000 [2:22:38<14:48:09, 1.70it/s] Train steps ... : 10%|▉ | 9580/100000 [2:22:39<14:44:49, 1.70it/s] Train steps ... : 10%|▉ | 9581/100000 [2:22:40<14:45:16, 1.70it/s] Train steps ... : 10%|▉ | 9582/100000 [2:22:40<14:45:21, 1.70it/s] Train steps ... : 10%|▉ | 9583/100000 [2:22:41<14:45:06, 1.70it/s] Train steps ... : 10%|▉ | 9584/100000 [2:22:41<14:46:37, 1.70it/s] Train steps ... : 10%|▉ | 9585/100000 [2:22:42<14:45:04, 1.70it/s] Train steps ... : 10%|▉ | 9586/100000 [2:22:42<14:44:18, 1.70it/s] Train steps ... : 10%|▉ | 9587/100000 [2:22:43<14:45:31, 1.70it/s] Train steps ... : 10%|▉ | 9588/100000 [2:22:44<14:43:30, 1.71it/s] Train steps ... : 10%|▉ | 9589/100000 [2:22:44<14:44:45, 1.70it/s] Train steps ... : 10%|▉ | 9590/100000 [2:22:45<14:44:46, 1.70it/s] Train steps ... : 10%|▉ | 9591/100000 [2:22:45<14:43:18, 1.71it/s] Train steps ... : 10%|▉ | 9592/100000 [2:22:46<14:43:27, 1.71it/s] Train steps ... : 10%|▉ | 9593/100000 [2:22:47<14:44:22, 1.70it/s] Train steps ... : 10%|▉ | 9594/100000 [2:22:47<14:43:33, 1.71it/s] Train steps ... : 10%|▉ | 9595/100000 [2:22:48<14:42:25, 1.71it/s] Train steps ... : 10%|▉ | 9596/100000 [2:22:48<14:42:49, 1.71it/s] Train steps ... : 10%|▉ | 9597/100000 [2:22:49<14:42:28, 1.71it/s] Train steps ... : 10%|▉ | 9598/100000 [2:22:49<14:42:34, 1.71it/s] Train steps ... : 10%|▉ | 9599/100000 [2:22:50<14:43:09, 1.71it/s] Train steps ... : 10%|▉ | 9600/100000 [2:22:51<14:42:20, 1.71it/s]Step... (9600 / 100000 | Loss: 1.237194299697876, Learning Rate: 9.085427135678392e-05) Step... (9600 / 100000 | Loss: 1.1588289737701416, Learning Rate: 9.085427135678392e-05) Train steps ... : 10%|▉ | 9600/100000 [2:22:51<14:42:20, 1.71it/s] Train steps ... : 10%|▉ | 9601/100000 [2:22:51<14:41:57, 1.71it/s] Train steps ... : 10%|▉ | 9602/100000 [2:22:52<14:41:05, 1.71it/s] Train steps ... : 10%|▉ | 9603/100000 [2:22:52<14:41:55, 1.71it/s] Train steps ... : 10%|▉ | 9604/100000 [2:22:53<14:43:00, 1.71it/s] Train steps ... : 10%|▉ | 9605/100000 [2:22:54<14:43:38, 1.70it/s] Train steps ... : 10%|▉ | 9606/100000 [2:22:54<14:41:38, 1.71it/s] Train steps ... : 10%|▉ | 9607/100000 [2:22:55<14:42:51, 1.71it/s] Train steps ... : 10%|▉ | 9608/100000 [2:22:55<14:41:10, 1.71it/s] Train steps ... : 10%|▉ | 9609/100000 [2:22:56<14:40:58, 1.71it/s] Train steps ... : 10%|▉ | 9610/100000 [2:22:57<14:40:44, 1.71it/s] Train steps ... : 10%|▉ | 9611/100000 [2:22:57<14:40:42, 1.71it/s] Train steps ... : 10%|▉ | 9612/100000 [2:22:58<14:40:50, 1.71it/s] Train steps ... : 10%|▉ | 9613/100000 [2:22:58<14:40:57, 1.71it/s] Train steps ... : 10%|▉ | 9614/100000 [2:22:59<14:41:07, 1.71it/s] Train steps ... : 10%|▉ | 9615/100000 [2:22:59<14:43:52, 1.70it/s] Train steps ... : 10%|▉ | 9616/100000 [2:23:00<14:40:58, 1.71it/s] Train steps ... : 10%|▉ | 9617/100000 [2:23:01<14:42:44, 1.71it/s] Train steps ... : 10%|▉ | 9618/100000 [2:23:01<14:44:49, 1.70it/s] Train steps ... : 10%|▉ | 9619/100000 [2:23:02<14:42:59, 1.71it/s] Train steps ... : 10%|▉ | 9620/100000 [2:23:02<14:44:32, 1.70it/s] Train steps ... : 10%|▉ | 9621/100000 [2:23:03<14:41:47, 1.71it/s] Train steps ... : 10%|▉ | 9622/100000 [2:23:04<14:43:18, 1.71it/s] Train steps ... : 10%|▉ | 9623/100000 [2:23:04<14:41:19, 1.71it/s] Train steps ... : 10%|▉ | 9624/100000 [2:23:05<14:42:39, 1.71it/s] Train steps ... : 10%|▉ | 9625/100000 [2:23:05<14:42:42, 1.71it/s]Step... (9625 / 100000 | Loss: 1.4099366664886475, Learning Rate: 9.082914572864322e-05) Step... (9625 / 100000 | Loss: 1.3022658824920654, Learning Rate: 9.082914572864322e-05) Train steps ... : 10%|▉ | 9625/100000 [2:23:06<14:42:42, 1.71it/s] Train steps ... : 10%|▉ | 9626/100000 [2:23:06<14:43:15, 1.71it/s] Train steps ... : 10%|▉ | 9627/100000 [2:23:06<14:44:08, 1.70it/s] Train steps ... : 10%|▉ | 9628/100000 [2:23:07<14:45:54, 1.70it/s] Train steps ... : 10%|▉ | 9629/100000 [2:23:08<14:44:22, 1.70it/s] Train steps ... : 10%|▉ | 9630/100000 [2:23:08<14:42:47, 1.71it/s] Train steps ... : 10%|▉ | 9631/100000 [2:23:09<14:43:20, 1.71it/s] Train steps ... : 10%|▉ | 9632/100000 [2:23:09<14:42:39, 1.71it/s] Train steps ... : 10%|▉ | 9633/100000 [2:23:10<14:43:32, 1.70it/s] Train steps ... : 10%|▉ | 9634/100000 [2:23:11<14:43:13, 1.71it/s] Train steps ... : 10%|▉ | 9635/100000 [2:23:11<14:41:48, 1.71it/s] Train steps ... : 10%|▉ | 9636/100000 [2:23:12<14:42:22, 1.71it/s] Train steps ... : 10%|▉ | 9637/100000 [2:23:12<14:43:22, 1.70it/s] Train steps ... : 10%|▉ | 9638/100000 [2:23:13<14:44:04, 1.70it/s] Train steps ... : 10%|▉ | 9639/100000 [2:23:14<14:44:00, 1.70it/s] Train steps ... : 10%|▉ | 9640/100000 [2:23:14<14:41:02, 1.71it/s] Train steps ... : 10%|▉ | 9641/100000 [2:23:15<14:41:13, 1.71it/s] Train steps ... : 10%|▉ | 9642/100000 [2:23:15<14:41:17, 1.71it/s] Train steps ... : 10%|▉ | 9643/100000 [2:23:16<14:42:14, 1.71it/s] Train steps ... : 10%|▉ | 9644/100000 [2:23:16<14:40:40, 1.71it/s] Train steps ... : 10%|▉ | 9645/100000 [2:23:17<14:41:09, 1.71it/s] Train steps ... : 10%|▉ | 9646/100000 [2:23:18<14:41:14, 1.71it/s] Train steps ... : 10%|▉ | 9647/100000 [2:23:18<14:41:13, 1.71it/s] Train steps ... : 10%|▉ | 9648/100000 [2:23:19<14:43:00, 1.71it/s] Train steps ... : 10%|▉ | 9649/100000 [2:23:19<14:42:35, 1.71it/s] Train steps ... : 10%|▉ | 9650/100000 [2:23:20<14:43:50, 1.70it/s]Step... (9650 / 100000 | Loss: 1.5726054906845093, Learning Rate: 9.080402010050251e-05) Step... (9650 / 100000 | Loss: 1.485288381576538, Learning Rate: 9.080402010050251e-05) Train steps ... : 10%|▉ | 9650/100000 [2:23:20<14:43:50, 1.70it/s] Train steps ... : 10%|▉ | 9651/100000 [2:23:21<14:41:00, 1.71it/s] Train steps ... : 10%|▉ | 9652/100000 [2:23:21<14:42:23, 1.71it/s] Train steps ... : 10%|▉ | 9653/100000 [2:23:22<14:41:37, 1.71it/s] Train steps ... : 10%|▉ | 9654/100000 [2:23:22<14:45:08, 1.70it/s] Train steps ... : 10%|▉ | 9655/100000 [2:23:23<14:46:27, 1.70it/s] Train steps ... : 10%|▉ | 9656/100000 [2:23:23<14:43:23, 1.70it/s] Train steps ... : 10%|▉ | 9657/100000 [2:23:24<14:42:30, 1.71it/s] Train steps ... : 10%|▉ | 9658/100000 [2:23:25<14:41:26, 1.71it/s] Train steps ... : 10%|▉ | 9659/100000 [2:23:25<14:40:07, 1.71it/s] Train steps ... : 10%|▉ | 9660/100000 [2:23:26<14:41:06, 1.71it/s] Train steps ... : 10%|▉ | 9661/100000 [2:23:26<14:41:11, 1.71it/s] Train steps ... : 10%|▉ | 9662/100000 [2:23:27<14:43:12, 1.70it/s] Train steps ... : 10%|▉ | 9663/100000 [2:23:28<14:43:05, 1.70it/s] Train steps ... : 10%|▉ | 9664/100000 [2:23:28<14:44:12, 1.70it/s] Train steps ... : 10%|▉ | 9665/100000 [2:23:29<14:42:46, 1.71it/s] Train steps ... : 10%|▉ | 9666/100000 [2:23:29<14:43:17, 1.70it/s] Train steps ... : 10%|▉ | 9667/100000 [2:23:30<14:42:52, 1.71it/s] Train steps ... : 10%|▉ | 9668/100000 [2:23:31<14:44:45, 1.70it/s] Train steps ... : 10%|▉ | 9669/100000 [2:23:31<14:45:23, 1.70it/s] Train steps ... : 10%|▉ | 9670/100000 [2:23:32<14:44:24, 1.70it/s] Train steps ... : 10%|▉ | 9671/100000 [2:23:32<14:44:27, 1.70it/s] Train steps ... : 10%|▉ | 9672/100000 [2:23:33<14:43:08, 1.70it/s] Train steps ... : 10%|▉ | 9673/100000 [2:23:33<14:43:01, 1.70it/s] Train steps ... : 10%|▉ | 9674/100000 [2:23:34<14:44:43, 1.70it/s] Train steps ... : 10%|▉ | 9675/100000 [2:23:35<14:42:06, 1.71it/s]Step... (9675 / 100000 | Loss: 1.1552937030792236, Learning Rate: 9.077889447236181e-05) Step... (9675 / 100000 | Loss: 1.6329057216644287, Learning Rate: 9.077889447236181e-05) Train steps ... : 10%|▉ | 9675/100000 [2:23:35<14:42:06, 1.71it/s] Train steps ... : 10%|▉ | 9676/100000 [2:23:35<14:43:27, 1.70it/s] Train steps ... : 10%|▉ | 9677/100000 [2:23:36<14:42:05, 1.71it/s] Train steps ... : 10%|▉ | 9678/100000 [2:23:36<14:42:09, 1.71it/s] Train steps ... : 10%|▉ | 9679/100000 [2:23:37<14:42:49, 1.71it/s] Train steps ... : 10%|▉ | 9680/100000 [2:23:38<14:41:21, 1.71it/s] Train steps ... : 10%|▉ | 9681/100000 [2:23:38<14:42:12, 1.71it/s] Train steps ... : 10%|▉ | 9682/100000 [2:23:39<14:40:59, 1.71it/s] Train steps ... : 10%|▉ | 9683/100000 [2:23:39<14:41:31, 1.71it/s] Train steps ... : 10%|▉ | 9684/100000 [2:23:40<14:40:41, 1.71it/s] Train steps ... : 10%|▉ | 9685/100000 [2:23:40<14:40:41, 1.71it/s] Train steps ... : 10%|▉ | 9686/100000 [2:23:41<14:39:55, 1.71it/s] Train steps ... : 10%|▉ | 9687/100000 [2:23:42<14:41:02, 1.71it/s] Train steps ... : 10%|▉ | 9688/100000 [2:23:42<14:41:29, 1.71it/s] Train steps ... : 10%|▉ | 9689/100000 [2:23:43<14:41:35, 1.71it/s] Train steps ... : 10%|▉ | 9690/100000 [2:23:43<14:42:42, 1.71it/s] Train steps ... : 10%|▉ | 9691/100000 [2:23:44<14:43:28, 1.70it/s] Train steps ... : 10%|▉ | 9692/100000 [2:23:45<14:44:23, 1.70it/s] Train steps ... : 10%|▉ | 9693/100000 [2:23:45<14:43:40, 1.70it/s] Train steps ... : 10%|▉ | 9694/100000 [2:23:46<14:44:55, 1.70it/s] Train steps ... : 10%|▉ | 9695/100000 [2:23:46<14:42:58, 1.70it/s] Train steps ... : 10%|▉ | 9696/100000 [2:23:47<14:44:46, 1.70it/s] Train steps ... : 10%|▉ | 9697/100000 [2:23:48<14:44:15, 1.70it/s] Train steps ... : 10%|▉ | 9698/100000 [2:23:48<14:43:10, 1.70it/s] Train steps ... : 10%|▉ | 9699/100000 [2:23:49<14:44:32, 1.70it/s] Train steps ... : 10%|▉ | 9700/100000 [2:23:49<14:42:25, 1.71it/s]Step... (9700 / 100000 | Loss: 1.432665467262268, Learning Rate: 9.075376884422111e-05) Step... (9700 / 100000 | Loss: 1.28318190574646, Learning Rate: 9.075376884422111e-05) Train steps ... : 10%|▉ | 9700/100000 [2:23:50<14:42:25, 1.71it/s] Train steps ... : 10%|▉ | 9701/100000 [2:23:50<14:45:13, 1.70it/s] Train steps ... : 10%|▉ | 9702/100000 [2:23:50<14:42:16, 1.71it/s] Train steps ... : 10%|▉ | 9703/100000 [2:23:51<14:43:24, 1.70it/s] Train steps ... : 10%|▉ | 9704/100000 [2:23:52<14:45:07, 1.70it/s] Train steps ... : 10%|▉ | 9705/100000 [2:23:52<14:42:58, 1.70it/s] Train steps ... : 10%|▉ | 9706/100000 [2:23:53<14:43:06, 1.70it/s] Train steps ... : 10%|▉ | 9707/100000 [2:23:53<14:41:15, 1.71it/s] Train steps ... : 10%|▉ | 9708/100000 [2:23:54<14:43:02, 1.70it/s] Train steps ... : 10%|▉ | 9709/100000 [2:23:55<14:42:18, 1.71it/s] Train steps ... : 10%|▉ | 9710/100000 [2:23:55<14:43:13, 1.70it/s] Train steps ... : 10%|▉ | 9711/100000 [2:23:56<14:41:51, 1.71it/s] Train steps ... : 10%|▉ | 9712/100000 [2:23:56<14:40:27, 1.71it/s] Train steps ... : 10%|▉ | 9713/100000 [2:23:57<14:40:07, 1.71it/s] Train steps ... : 10%|▉ | 9714/100000 [2:23:57<14:41:03, 1.71it/s] Train steps ... : 10%|▉ | 9715/100000 [2:23:58<14:39:49, 1.71it/s] Train steps ... : 10%|▉ | 9716/100000 [2:23:59<14:41:55, 1.71it/s] Train steps ... : 10%|▉ | 9717/100000 [2:23:59<14:41:11, 1.71it/s] Train steps ... : 10%|▉ | 9718/100000 [2:24:00<14:42:41, 1.70it/s] Train steps ... : 10%|▉ | 9719/100000 [2:24:00<14:42:09, 1.71it/s] Train steps ... : 10%|▉ | 9720/100000 [2:24:01<14:41:50, 1.71it/s] Train steps ... : 10%|▉ | 9721/100000 [2:24:02<14:44:43, 1.70it/s] Train steps ... : 10%|▉ | 9722/100000 [2:24:02<14:41:06, 1.71it/s] Train steps ... : 10%|▉ | 9723/100000 [2:24:03<14:41:51, 1.71it/s] Train steps ... : 10%|▉ | 9724/100000 [2:24:03<14:41:22, 1.71it/s] Train steps ... : 10%|▉ | 9725/100000 [2:24:04<14:41:46, 1.71it/s]Step... (9725 / 100000 | Loss: 1.2576916217803955, Learning Rate: 9.072864321608042e-05) Step... (9725 / 100000 | Loss: 0.935117781162262, Learning Rate: 9.072864321608042e-05) Train steps ... : 10%|▉ | 9725/100000 [2:24:04<14:41:46, 1.71it/s] Train steps ... : 10%|▉ | 9726/100000 [2:24:05<14:42:06, 1.71it/s] Train steps ... : 10%|▉ | 9727/100000 [2:24:05<14:41:32, 1.71it/s] Train steps ... : 10%|▉ | 9728/100000 [2:24:06<14:41:20, 1.71it/s] Train steps ... : 10%|▉ | 9729/100000 [2:24:06<14:41:31, 1.71it/s] Train steps ... : 10%|▉ | 9730/100000 [2:24:07<14:41:54, 1.71it/s] Train steps ... : 10%|▉ | 9731/100000 [2:24:07<14:42:45, 1.70it/s] Train steps ... : 10%|▉ | 9732/100000 [2:24:08<14:41:12, 1.71it/s] Train steps ... : 10%|▉ | 9733/100000 [2:24:09<14:40:05, 1.71it/s] Train steps ... : 10%|▉ | 9734/100000 [2:24:09<14:40:03, 1.71it/s] Train steps ... : 10%|▉ | 9735/100000 [2:24:10<14:41:32, 1.71it/s] Train steps ... : 10%|▉ | 9736/100000 [2:24:10<14:40:19, 1.71it/s] Train steps ... : 10%|▉ | 9737/100000 [2:24:11<14:40:17, 1.71it/s] Train steps ... : 10%|▉ | 9738/100000 [2:24:12<14:40:57, 1.71it/s] Train steps ... : 10%|▉ | 9739/100000 [2:24:12<14:43:15, 1.70it/s] Train steps ... : 10%|▉ | 9740/100000 [2:24:13<14:41:39, 1.71it/s] Train steps ... : 10%|▉ | 9741/100000 [2:24:13<14:42:15, 1.71it/s] Train steps ... : 10%|▉ | 9742/100000 [2:24:14<14:41:59, 1.71it/s] Train steps ... : 10%|▉ | 9743/100000 [2:24:14<14:41:13, 1.71it/s] Train steps ... : 10%|▉ | 9744/100000 [2:24:15<14:41:05, 1.71it/s] Train steps ... : 10%|▉ | 9745/100000 [2:24:16<14:40:12, 1.71it/s] Train steps ... : 10%|▉ | 9746/100000 [2:24:16<14:39:48, 1.71it/s] Train steps ... : 10%|▉ | 9747/100000 [2:24:17<14:40:29, 1.71it/s] Train steps ... : 10%|▉ | 9748/100000 [2:24:17<14:40:31, 1.71it/s] Train steps ... : 10%|▉ | 9749/100000 [2:24:18<14:39:44, 1.71it/s] Train steps ... : 10%|▉ | 9750/100000 [2:24:19<14:40:52, 1.71it/s]Step... (9750 / 100000 | Loss: 1.1465697288513184, Learning Rate: 9.07035175879397e-05) Step... (9750 / 100000 | Loss: 1.0719271898269653, Learning Rate: 9.07035175879397e-05) Train steps ... : 10%|▉ | 9750/100000 [2:24:19<14:40:52, 1.71it/s] Train steps ... : 10%|▉ | 9751/100000 [2:24:19<14:38:53, 1.71it/s] Train steps ... : 10%|▉ | 9752/100000 [2:24:20<14:39:40, 1.71it/s] Train steps ... : 10%|▉ | 9753/100000 [2:24:20<14:39:15, 1.71it/s] Train steps ... : 10%|▉ | 9754/100000 [2:24:21<14:40:21, 1.71it/s] Train steps ... : 10%|▉ | 9755/100000 [2:24:21<14:39:31, 1.71it/s] Train steps ... : 10%|▉ | 9756/100000 [2:24:22<14:40:53, 1.71it/s] Train steps ... : 10%|▉ | 9757/100000 [2:24:23<14:44:14, 1.70it/s] Train steps ... : 10%|▉ | 9758/100000 [2:24:23<14:44:03, 1.70it/s] Train steps ... : 10%|▉ | 9759/100000 [2:24:24<14:41:34, 1.71it/s] Train steps ... : 10%|▉ | 9760/100000 [2:24:24<14:41:42, 1.71it/s] Train steps ... : 10%|▉ | 9761/100000 [2:24:25<14:41:41, 1.71it/s] Train steps ... : 10%|▉ | 9762/100000 [2:24:26<14:41:42, 1.71it/s] Train steps ... : 10%|▉ | 9763/100000 [2:24:26<14:41:10, 1.71it/s] Train steps ... : 10%|▉ | 9764/100000 [2:24:27<14:41:16, 1.71it/s] Train steps ... : 10%|▉ | 9765/100000 [2:24:27<14:45:16, 1.70it/s] Train steps ... : 10%|▉ | 9766/100000 [2:24:28<14:42:52, 1.70it/s] Train steps ... : 10%|▉ | 9767/100000 [2:24:29<14:44:02, 1.70it/s] Train steps ... : 10%|▉ | 9768/100000 [2:24:29<14:44:22, 1.70it/s] Train steps ... : 10%|▉ | 9769/100000 [2:24:30<14:44:46, 1.70it/s] Train steps ... : 10%|▉ | 9770/100000 [2:24:30<14:41:27, 1.71it/s] Train steps ... : 10%|▉ | 9771/100000 [2:24:31<14:41:52, 1.71it/s] Train steps ... : 10%|▉ | 9772/100000 [2:24:31<14:42:56, 1.70it/s] Train steps ... : 10%|▉ | 9773/100000 [2:24:32<14:41:49, 1.71it/s] Train steps ... : 10%|▉ | 9774/100000 [2:24:33<14:44:07, 1.70it/s] Train steps ... : 10%|▉ | 9775/100000 [2:24:33<14:41:05, 1.71it/s]Step... (9775 / 100000 | Loss: 0.8741927146911621, Learning Rate: 9.0678391959799e-05) Step... (9775 / 100000 | Loss: 1.433618187904358, Learning Rate: 9.0678391959799e-05) Train steps ... : 10%|▉ | 9775/100000 [2:24:34<14:41:05, 1.71it/s] Train steps ... : 10%|▉ | 9776/100000 [2:24:34<14:41:32, 1.71it/s] Train steps ... : 10%|▉ | 9777/100000 [2:24:34<14:41:17, 1.71it/s] Train steps ... : 10%|▉ | 9778/100000 [2:24:35<14:40:23, 1.71it/s] Train steps ... : 10%|▉ | 9779/100000 [2:24:36<14:42:54, 1.70it/s] Train steps ... : 10%|▉ | 9780/100000 [2:24:36<14:42:54, 1.70it/s] Train steps ... : 10%|▉ | 9781/100000 [2:24:37<14:41:28, 1.71it/s] Train steps ... : 10%|▉ | 9782/100000 [2:24:37<14:41:04, 1.71it/s] Train steps ... : 10%|▉ | 9783/100000 [2:24:38<14:42:44, 1.70it/s] Train steps ... : 10%|▉ | 9784/100000 [2:24:39<14:41:25, 1.71it/s] Train steps ... : 10%|▉ | 9785/100000 [2:24:39<14:41:41, 1.71it/s] Train steps ... : 10%|▉ | 9786/100000 [2:24:40<14:42:36, 1.70it/s] Train steps ... : 10%|▉ | 9787/100000 [2:24:40<14:41:30, 1.71it/s] Train steps ... : 10%|▉ | 9788/100000 [2:24:41<14:41:03, 1.71it/s] Train steps ... : 10%|▉ | 9789/100000 [2:24:41<14:40:07, 1.71it/s] Train steps ... : 10%|▉ | 9790/100000 [2:24:42<14:40:29, 1.71it/s] Train steps ... : 10%|▉ | 9791/100000 [2:24:43<14:41:21, 1.71it/s] Train steps ... : 10%|▉ | 9792/100000 [2:24:43<14:40:00, 1.71it/s] Train steps ... : 10%|▉ | 9793/100000 [2:24:44<14:39:58, 1.71it/s] Train steps ... : 10%|▉ | 9794/100000 [2:24:44<14:39:51, 1.71it/s] Train steps ... : 10%|▉ | 9795/100000 [2:24:45<14:40:13, 1.71it/s] Train steps ... : 10%|▉ | 9796/100000 [2:24:46<14:39:07, 1.71it/s] Train steps ... : 10%|▉ | 9797/100000 [2:24:46<14:38:51, 1.71it/s] Train steps ... : 10%|▉ | 9798/100000 [2:24:47<14:38:11, 1.71it/s] Train steps ... : 10%|▉ | 9799/100000 [2:24:47<14:37:50, 1.71it/s] Train steps ... : 10%|▉ | 9800/100000 [2:24:48<14:39:25, 1.71it/s]Step... (9800 / 100000 | Loss: 1.1243138313293457, Learning Rate: 9.06532663316583e-05) Step... (9800 / 100000 | Loss: 1.1187281608581543, Learning Rate: 9.06532663316583e-05) Train steps ... : 10%|▉ | 9800/100000 [2:24:48<14:39:25, 1.71it/s] Train steps ... : 10%|▉ | 9801/100000 [2:24:48<14:41:47, 1.70it/s] Train steps ... : 10%|▉ | 9802/100000 [2:24:49<14:40:56, 1.71it/s] Train steps ... : 10%|▉ | 9803/100000 [2:24:50<14:41:45, 1.70it/s] Train steps ... : 10%|▉ | 9804/100000 [2:24:50<14:41:15, 1.71it/s] Train steps ... : 10%|▉ | 9805/100000 [2:24:51<14:40:17, 1.71it/s] Train steps ... : 10%|▉ | 9806/100000 [2:24:51<14:40:07, 1.71it/s] Train steps ... : 10%|▉ | 9807/100000 [2:24:52<14:42:38, 1.70it/s] Train steps ... : 10%|▉ | 9808/100000 [2:24:53<14:40:42, 1.71it/s] Train steps ... : 10%|▉ | 9809/100000 [2:24:53<14:40:35, 1.71it/s] Train steps ... : 10%|▉ | 9810/100000 [2:24:54<14:41:30, 1.71it/s] Train steps ... : 10%|▉ | 9811/100000 [2:24:54<14:40:02, 1.71it/s] Train steps ... : 10%|▉ | 9812/100000 [2:24:55<14:41:39, 1.70it/s] Train steps ... : 10%|▉ | 9813/100000 [2:24:55<14:40:14, 1.71it/s] Train steps ... : 10%|▉ | 9814/100000 [2:24:56<14:41:23, 1.71it/s] Train steps ... : 10%|▉ | 9815/100000 [2:24:57<14:41:59, 1.70it/s] Train steps ... : 10%|▉ | 9816/100000 [2:24:57<14:41:38, 1.70it/s] Train steps ... : 10%|▉ | 9817/100000 [2:24:58<14:42:27, 1.70it/s] Train steps ... : 10%|▉ | 9818/100000 [2:24:58<14:41:57, 1.70it/s] Train steps ... : 10%|▉ | 9819/100000 [2:24:59<14:42:02, 1.70it/s] Train steps ... : 10%|▉ | 9820/100000 [2:25:00<14:42:27, 1.70it/s] Train steps ... : 10%|▉ | 9821/100000 [2:25:00<14:44:11, 1.70it/s] Train steps ... : 10%|▉ | 9822/100000 [2:25:01<14:41:44, 1.70it/s] Train steps ... : 10%|▉ | 9823/100000 [2:25:01<14:41:48, 1.70it/s] Train steps ... : 10%|▉ | 9824/100000 [2:25:02<14:40:19, 1.71it/s] Train steps ... : 10%|▉ | 9825/100000 [2:25:03<14:40:35, 1.71it/s]Step... (9825 / 100000 | Loss: 1.0111945867538452, Learning Rate: 9.062814070351759e-05) Step... (9825 / 100000 | Loss: 1.119375228881836, Learning Rate: 9.062814070351759e-05) Train steps ... : 10%|▉ | 9825/100000 [2:25:03<14:40:35, 1.71it/s] Train steps ... : 10%|▉ | 9826/100000 [2:25:03<14:41:24, 1.71it/s] Train steps ... : 10%|▉ | 9827/100000 [2:25:04<14:41:19, 1.71it/s] Train steps ... : 10%|▉ | 9828/100000 [2:25:04<14:41:21, 1.71it/s] Train steps ... : 10%|▉ | 9829/100000 [2:25:05<14:41:17, 1.71it/s] Train steps ... : 10%|▉ | 9830/100000 [2:25:05<14:40:06, 1.71it/s] Train steps ... : 10%|▉ | 9831/100000 [2:25:06<14:41:04, 1.71it/s] Train steps ... : 10%|▉ | 9832/100000 [2:25:07<14:40:36, 1.71it/s] Train steps ... : 10%|▉ | 9833/100000 [2:25:07<14:43:19, 1.70it/s] Train steps ... : 10%|▉ | 9834/100000 [2:25:08<14:42:50, 1.70it/s] Train steps ... : 10%|▉ | 9835/100000 [2:25:08<14:41:35, 1.70it/s] Train steps ... : 10%|▉ | 9836/100000 [2:25:09<14:40:33, 1.71it/s] Train steps ... : 10%|▉ | 9837/100000 [2:25:10<14:41:08, 1.71it/s] Train steps ... : 10%|▉ | 9838/100000 [2:25:10<14:41:09, 1.71it/s] Train steps ... : 10%|▉ | 9839/100000 [2:25:11<14:40:14, 1.71it/s] Train steps ... : 10%|▉ | 9840/100000 [2:25:11<14:42:16, 1.70it/s] Train steps ... : 10%|▉ | 9841/100000 [2:25:12<14:40:06, 1.71it/s] Train steps ... : 10%|▉ | 9842/100000 [2:25:13<14:39:26, 1.71it/s] Train steps ... : 10%|▉ | 9843/100000 [2:25:13<14:42:47, 1.70it/s] Train steps ... : 10%|▉ | 9844/100000 [2:25:14<14:43:59, 1.70it/s] Train steps ... : 10%|▉ | 9845/100000 [2:25:14<14:41:09, 1.71it/s] Train steps ... : 10%|▉ | 9846/100000 [2:25:15<14:41:09, 1.71it/s] Train steps ... : 10%|▉ | 9847/100000 [2:25:15<14:42:17, 1.70it/s] Train steps ... : 10%|▉ | 9848/100000 [2:25:16<14:42:02, 1.70it/s] Train steps ... : 10%|▉ | 9849/100000 [2:25:17<14:40:06, 1.71it/s] Train steps ... : 10%|▉ | 9850/100000 [2:25:17<14:41:54, 1.70it/s]Step... (9850 / 100000 | Loss: 1.5622754096984863, Learning Rate: 9.060301507537689e-05) Step... (9850 / 100000 | Loss: 1.3462519645690918, Learning Rate: 9.060301507537689e-05) Train steps ... : 10%|▉ | 9850/100000 [2:25:18<14:41:54, 1.70it/s] Train steps ... : 10%|▉ | 9851/100000 [2:25:18<14:40:52, 1.71it/s] Train steps ... : 10%|▉ | 9852/100000 [2:25:18<14:39:51, 1.71it/s] Train steps ... : 10%|▉ | 9853/100000 [2:25:19<14:39:12, 1.71it/s] Train steps ... : 10%|▉ | 9854/100000 [2:25:20<14:40:30, 1.71it/s] Train steps ... : 10%|▉ | 9855/100000 [2:25:20<14:39:23, 1.71it/s] Train steps ... : 10%|▉ | 9856/100000 [2:25:21<14:38:18, 1.71it/s] Train steps ... : 10%|▉ | 9857/100000 [2:25:21<14:41:11, 1.70it/s] Train steps ... : 10%|▉ | 9858/100000 [2:25:22<14:42:23, 1.70it/s] Train steps ... : 10%|▉ | 9859/100000 [2:25:22<14:40:20, 1.71it/s] Train steps ... : 10%|▉ | 9860/100000 [2:25:23<14:43:04, 1.70it/s] Train steps ... : 10%|▉ | 9861/100000 [2:25:24<14:41:12, 1.70it/s] Train steps ... : 10%|▉ | 9862/100000 [2:25:24<14:42:27, 1.70it/s] Train steps ... : 10%|▉ | 9863/100000 [2:25:25<14:40:17, 1.71it/s] Train steps ... : 10%|▉ | 9864/100000 [2:25:25<14:39:23, 1.71it/s] Train steps ... : 10%|▉ | 9865/100000 [2:25:26<14:39:31, 1.71it/s] Train steps ... : 10%|▉ | 9866/100000 [2:25:27<14:38:13, 1.71it/s] Train steps ... : 10%|▉ | 9867/100000 [2:25:27<14:38:20, 1.71it/s] Train steps ... : 10%|▉ | 9868/100000 [2:25:28<14:38:17, 1.71it/s] Train steps ... : 10%|▉ | 9869/100000 [2:25:28<14:38:27, 1.71it/s] Train steps ... : 10%|▉ | 9870/100000 [2:25:29<14:38:46, 1.71it/s] Train steps ... : 10%|▉ | 9871/100000 [2:25:29<14:39:36, 1.71it/s] Train steps ... : 10%|▉ | 9872/100000 [2:25:30<14:38:58, 1.71it/s] Train steps ... : 10%|▉ | 9873/100000 [2:25:31<14:37:47, 1.71it/s] Train steps ... : 10%|▉ | 9874/100000 [2:25:31<14:38:50, 1.71it/s] Train steps ... : 10%|▉ | 9875/100000 [2:25:32<14:41:07, 1.70it/s]Step... (9875 / 100000 | Loss: 1.2087361812591553, Learning Rate: 9.057788944723618e-05) Step... (9875 / 100000 | Loss: 1.5269060134887695, Learning Rate: 9.057788944723618e-05) Train steps ... : 10%|▉ | 9875/100000 [2:25:32<14:41:07, 1.70it/s] Train steps ... : 10%|▉ | 9876/100000 [2:25:32<14:41:15, 1.70it/s] Train steps ... : 10%|▉ | 9877/100000 [2:25:33<14:42:23, 1.70it/s] Train steps ... : 10%|▉ | 9878/100000 [2:25:34<14:44:29, 1.70it/s] Train steps ... : 10%|▉ | 9879/100000 [2:25:34<14:48:02, 1.69it/s] Train steps ... : 10%|▉ | 9880/100000 [2:25:35<14:46:55, 1.69it/s] Train steps ... : 10%|▉ | 9881/100000 [2:25:35<14:44:26, 1.70it/s] Train steps ... : 10%|▉ | 9882/100000 [2:25:36<14:43:44, 1.70it/s] Train steps ... : 10%|▉ | 9883/100000 [2:25:37<14:43:12, 1.70it/s] Train steps ... : 10%|▉ | 9884/100000 [2:25:37<14:40:56, 1.70it/s] Train steps ... : 10%|▉ | 9885/100000 [2:25:38<14:40:13, 1.71it/s] Train steps ... : 10%|▉ | 9886/100000 [2:25:38<14:39:59, 1.71it/s] Train steps ... : 10%|▉ | 9887/100000 [2:25:39<14:42:15, 1.70it/s] Train steps ... : 10%|▉ | 9888/100000 [2:25:39<14:41:56, 1.70it/s] Train steps ... : 10%|▉ | 9889/100000 [2:25:40<14:41:16, 1.70it/s] Train steps ... : 10%|▉ | 9890/100000 [2:25:41<14:39:29, 1.71it/s] Train steps ... : 10%|▉ | 9891/100000 [2:25:41<14:41:25, 1.70it/s] Train steps ... : 10%|▉ | 9892/100000 [2:25:42<14:43:15, 1.70it/s] Train steps ... : 10%|▉ | 9893/100000 [2:25:42<14:44:02, 1.70it/s] Train steps ... : 10%|▉ | 9894/100000 [2:25:43<14:40:51, 1.70it/s] Train steps ... : 10%|▉ | 9895/100000 [2:25:44<14:44:28, 1.70it/s] Train steps ... : 10%|▉ | 9896/100000 [2:25:44<14:41:21, 1.70it/s] Train steps ... : 10%|▉ | 9897/100000 [2:25:45<14:40:58, 1.70it/s] Train steps ... : 10%|▉ | 9898/100000 [2:25:45<14:40:21, 1.71it/s] Train steps ... : 10%|▉ | 9899/100000 [2:25:46<14:40:26, 1.71it/s] Train steps ... : 10%|▉ | 9900/100000 [2:25:47<14:39:53, 1.71it/s]Step... (9900 / 100000 | Loss: 1.179511308670044, Learning Rate: 9.055276381909548e-05) Step... (9900 / 100000 | Loss: 1.1730540990829468, Learning Rate: 9.055276381909548e-05) Train steps ... : 10%|▉ | 9900/100000 [2:25:47<14:39:53, 1.71it/s] Train steps ... : 10%|▉ | 9901/100000 [2:25:47<14:39:53, 1.71it/s] Train steps ... : 10%|▉ | 9902/100000 [2:25:48<14:38:37, 1.71it/s] Train steps ... : 10%|▉ | 9903/100000 [2:25:48<14:40:00, 1.71it/s] Train steps ... : 10%|▉ | 9904/100000 [2:25:49<14:36:47, 1.71it/s] Train steps ... : 10%|▉ | 9905/100000 [2:25:49<14:38:05, 1.71it/s] Train steps ... : 10%|▉ | 9906/100000 [2:25:50<14:37:47, 1.71it/s] Train steps ... : 10%|▉ | 9907/100000 [2:25:51<14:37:53, 1.71it/s] Train steps ... : 10%|▉ | 9908/100000 [2:25:51<14:38:37, 1.71it/s] Train steps ... : 10%|▉ | 9909/100000 [2:25:52<14:40:37, 1.71it/s] Train steps ... : 10%|▉ | 9910/100000 [2:25:52<14:38:40, 1.71it/s] Train steps ... : 10%|▉ | 9911/100000 [2:25:53<14:39:08, 1.71it/s] Train steps ... : 10%|▉ | 9912/100000 [2:25:54<14:39:45, 1.71it/s] Train steps ... : 10%|▉ | 9913/100000 [2:25:54<14:37:48, 1.71it/s] Train steps ... : 10%|▉ | 9914/100000 [2:25:55<14:37:26, 1.71it/s] Train steps ... : 10%|▉ | 9915/100000 [2:25:55<14:39:22, 1.71it/s] Train steps ... : 10%|▉ | 9916/100000 [2:25:56<14:40:51, 1.70it/s] Train steps ... : 10%|▉ | 9917/100000 [2:25:56<14:37:36, 1.71it/s] Train steps ... : 10%|▉ | 9918/100000 [2:25:57<14:39:55, 1.71it/s] Train steps ... : 10%|▉ | 9919/100000 [2:25:58<14:38:58, 1.71it/s] Train steps ... : 10%|▉ | 9920/100000 [2:25:58<14:39:06, 1.71it/s] Train steps ... : 10%|▉ | 9921/100000 [2:25:59<14:38:27, 1.71it/s] Train steps ... : 10%|▉ | 9922/100000 [2:25:59<14:38:23, 1.71it/s] Train steps ... : 10%|▉ | 9923/100000 [2:26:00<14:38:46, 1.71it/s] Train steps ... : 10%|▉ | 9924/100000 [2:26:01<14:38:57, 1.71it/s] Train steps ... : 10%|▉ | 9925/100000 [2:26:01<14:39:20, 1.71it/s]Step... (9925 / 100000 | Loss: 1.4417437314987183, Learning Rate: 9.052763819095478e-05) Step... (9925 / 100000 | Loss: 0.7576231956481934, Learning Rate: 9.052763819095478e-05) Train steps ... : 10%|▉ | 9925/100000 [2:26:01<14:39:20, 1.71it/s] Train steps ... : 10%|▉ | 9926/100000 [2:26:02<14:40:17, 1.71it/s] Train steps ... : 10%|▉ | 9927/100000 [2:26:02<14:40:27, 1.71it/s] Train steps ... : 10%|▉ | 9928/100000 [2:26:03<14:40:07, 1.71it/s] Train steps ... : 10%|▉ | 9929/100000 [2:26:04<14:39:51, 1.71it/s] Train steps ... : 10%|▉ | 9930/100000 [2:26:04<14:39:04, 1.71it/s] Train steps ... : 10%|▉ | 9931/100000 [2:26:05<14:39:03, 1.71it/s] Train steps ... : 10%|▉ | 9932/100000 [2:26:05<14:38:59, 1.71it/s] Train steps ... : 10%|▉ | 9933/100000 [2:26:06<14:38:23, 1.71it/s] Train steps ... : 10%|▉ | 9934/100000 [2:26:06<14:37:54, 1.71it/s] Train steps ... : 10%|▉ | 9935/100000 [2:26:07<14:38:19, 1.71it/s] Train steps ... : 10%|▉ | 9936/100000 [2:26:08<14:37:23, 1.71it/s] Train steps ... : 10%|▉ | 9937/100000 [2:26:08<14:36:51, 1.71it/s] Train steps ... : 10%|▉ | 9938/100000 [2:26:09<14:38:31, 1.71it/s] Train steps ... : 10%|▉ | 9939/100000 [2:26:09<14:37:48, 1.71it/s] Train steps ... : 10%|▉ | 9940/100000 [2:26:10<14:38:20, 1.71it/s] Train steps ... : 10%|▉ | 9941/100000 [2:26:11<14:39:10, 1.71it/s] Train steps ... : 10%|▉ | 9942/100000 [2:26:11<14:41:40, 1.70it/s] Train steps ... : 10%|▉ | 9943/100000 [2:26:12<14:39:28, 1.71it/s] Train steps ... : 10%|▉ | 9944/100000 [2:26:12<14:40:06, 1.71it/s] Train steps ... : 10%|▉ | 9945/100000 [2:26:13<14:39:01, 1.71it/s] Train steps ... : 10%|▉ | 9946/100000 [2:26:13<14:39:19, 1.71it/s] Train steps ... : 10%|▉ | 9947/100000 [2:26:14<14:39:34, 1.71it/s] Train steps ... : 10%|▉ | 9948/100000 [2:26:15<14:39:19, 1.71it/s] Train steps ... : 10%|▉ | 9949/100000 [2:26:15<14:39:40, 1.71it/s] Train steps ... : 10%|▉ | 9950/100000 [2:26:16<14:41:12, 1.70it/s]Step... (9950 / 100000 | Loss: 1.500316858291626, Learning Rate: 9.050251256281407e-05) Step... (9950 / 100000 | Loss: 1.1012412309646606, Learning Rate: 9.050251256281407e-05) Train steps ... : 10%|▉ | 9950/100000 [2:26:16<14:41:12, 1.70it/s] Train steps ... : 10%|▉ | 9951/100000 [2:26:16<14:40:09, 1.71it/s] Train steps ... : 10%|▉ | 9952/100000 [2:26:17<14:38:44, 1.71it/s] Train steps ... : 10%|▉ | 9953/100000 [2:26:18<14:38:40, 1.71it/s] Train steps ... : 10%|▉ | 9954/100000 [2:26:18<14:39:11, 1.71it/s] Train steps ... : 10%|▉ | 9955/100000 [2:26:19<14:40:23, 1.70it/s] Train steps ... : 10%|▉ | 9956/100000 [2:26:19<14:40:40, 1.70it/s] Train steps ... : 10%|▉ | 9957/100000 [2:26:20<14:38:38, 1.71it/s] Train steps ... : 10%|▉ | 9958/100000 [2:26:20<14:42:21, 1.70it/s] Train steps ... : 10%|▉ | 9959/100000 [2:26:21<14:41:25, 1.70it/s] Train steps ... : 10%|▉ | 9960/100000 [2:26:22<14:39:31, 1.71it/s] Train steps ... : 10%|▉ | 9961/100000 [2:26:22<14:39:55, 1.71it/s] Train steps ... : 10%|▉ | 9962/100000 [2:26:23<14:41:32, 1.70it/s] Train steps ... : 10%|▉ | 9963/100000 [2:26:23<14:39:28, 1.71it/s] Train steps ... : 10%|▉ | 9964/100000 [2:26:24<14:42:47, 1.70it/s] Train steps ... : 10%|▉ | 9965/100000 [2:26:25<14:37:56, 1.71it/s] Train steps ... : 10%|▉ | 9966/100000 [2:26:25<14:39:27, 1.71it/s] Train steps ... : 10%|▉ | 9967/100000 [2:26:26<14:38:06, 1.71it/s] Train steps ... : 10%|▉ | 9968/100000 [2:26:26<14:37:26, 1.71it/s] Train steps ... : 10%|▉ | 9969/100000 [2:26:27<14:39:11, 1.71it/s] Train steps ... : 10%|▉ | 9970/100000 [2:26:28<14:38:40, 1.71it/s] Train steps ... : 10%|▉ | 9971/100000 [2:26:28<14:38:35, 1.71it/s] Train steps ... : 10%|▉ | 9972/100000 [2:26:29<14:37:51, 1.71it/s] Train steps ... : 10%|▉ | 9973/100000 [2:26:29<14:39:11, 1.71it/s] Train steps ... : 10%|▉ | 9974/100000 [2:26:30<14:36:49, 1.71it/s] Train steps ... : 10%|▉ | 9975/100000 [2:26:30<14:38:18, 1.71it/s]Step... (9975 / 100000 | Loss: 1.2703478336334229, Learning Rate: 9.047738693467337e-05) Step... (9975 / 100000 | Loss: 1.3818659782409668, Learning Rate: 9.047738693467337e-05) Train steps ... : 10%|▉ | 9975/100000 [2:26:31<14:38:18, 1.71it/s] Train steps ... : 10%|▉ | 9976/100000 [2:26:31<14:39:20, 1.71it/s] Train steps ... : 10%|▉ | 9977/100000 [2:26:32<14:38:50, 1.71it/s] Train steps ... : 10%|▉ | 9978/100000 [2:26:32<14:40:43, 1.70it/s] Train steps ... : 10%|▉ | 9979/100000 [2:26:33<14:40:07, 1.70it/s] Train steps ... : 10%|▉ | 9980/100000 [2:26:33<14:39:23, 1.71it/s] Train steps ... : 10%|▉ | 9981/100000 [2:26:34<14:39:23, 1.71it/s] Train steps ... : 10%|▉ | 9982/100000 [2:26:35<14:41:31, 1.70it/s] Train steps ... : 10%|▉ | 9983/100000 [2:26:35<14:40:08, 1.70it/s] Train steps ... : 10%|▉ | 9984/100000 [2:26:36<14:40:23, 1.70it/s] Train steps ... : 10%|▉ | 9985/100000 [2:26:36<14:40:06, 1.70it/s] Train steps ... : 10%|▉ | 9986/100000 [2:26:37<14:39:03, 1.71it/s] Train steps ... : 10%|▉ | 9987/100000 [2:26:37<14:38:05, 1.71it/s] Train steps ... : 10%|▉ | 9988/100000 [2:26:38<14:38:04, 1.71it/s] Train steps ... : 10%|▉ | 9989/100000 [2:26:39<14:38:13, 1.71it/s] Train steps ... : 10%|▉ | 9990/100000 [2:26:39<14:37:50, 1.71it/s] Train steps ... : 10%|▉ | 9991/100000 [2:26:40<14:38:26, 1.71it/s] Train steps ... : 10%|▉ | 9992/100000 [2:26:40<14:37:42, 1.71it/s] Train steps ... : 10%|▉ | 9993/100000 [2:26:41<14:37:08, 1.71it/s] Train steps ... : 10%|▉ | 9994/100000 [2:26:42<14:37:54, 1.71it/s] Train steps ... : 10%|▉ | 9995/100000 [2:26:42<14:39:33, 1.71it/s] Train steps ... : 10%|▉ | 9996/100000 [2:26:43<14:38:39, 1.71it/s] Train steps ... : 10%|▉ | 9997/100000 [2:26:43<14:42:05, 1.70it/s] Train steps ... : 10%|▉ | 9998/100000 [2:26:44<14:40:43, 1.70it/s] Train steps ... : 10%|▉ | 9999/100000 [2:26:45<14:39:00, 1.71it/s] Train steps ... : 10%|█ | 10000/100000 [2:26:45<14:39:49, 1.70it/s]Step... (10000 / 100000 | Loss: 1.1623427867889404, Learning Rate: 9.045226130653267e-05) Step... (10000 / 100000 | Loss: 1.040871500968933, Learning Rate: 9.045226130653267e-05) Train steps ... : 10%|█ | 10000/100000 [2:26:45<14:39:49, 1.70it/s]06/17/2024 18:21:12 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-10000-epoch-0 06/17/2024 18:21:12 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading 06/17/2024 18:21:16 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-10000-epoch-0/model.safetensors 06/17/2024 18:21:16 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading 06/17/2024 18:21:20 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-10000-epoch-0/model_1.safetensors 06/17/2024 18:21:20 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-10000-epoch-0/optimizer.bin 06/17/2024 18:21:20 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-10000-epoch-0/scheduler.bin 06/17/2024 18:21:20 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-10000-epoch-0/sampler.bin 06/17/2024 18:21:20 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-10000-epoch-0/sampler_1.bin 06/17/2024 18:21:20 - INFO - accelerate.checkpointing - Random states saved in checkpoint-10000-epoch-0/random_states_0.pkl /opt/conda/lib/python3.10/site-packages/huggingface_hub/hf_api.py:3664: UserWarning: Warnings while validating metadata in README.md: - empty or missing yaml metadata in repo card warnings.warn(f"Warnings while validating metadata in README.md:\n{message}") 0%| | 0/5 [00:00