| 05/13/2024 20:46:55 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False | |
| 05/13/2024 20:46:55 - INFO - __main__ - Training/evaluation parameters ParlerTTSTrainingArguments( | |
| _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=0.99, | |
| adam_epsilon=1e-08, | |
| audio_encoder_per_device_batch_size=4, | |
| 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=4, | |
| 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=1800, | |
| 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=None, | |
| eval_strategy=IntervalStrategy.EPOCH, | |
| evaluation_strategy=epoch, | |
| fp16=False, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| 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=8, | |
| gradient_checkpointing=True, | |
| gradient_checkpointing_kwargs=None, | |
| greater_is_better=None, | |
| group_by_length=True, | |
| half_precision_backend=auto, | |
| hub_always_push=False, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=True, | |
| include_num_input_tokens_seen=False, | |
| include_tokens_per_second=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=8e-05, | |
| 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=../output_dir_training_constant_concat/runs/May13_20-46-51_hf-dgx-01, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=5, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.COSINE, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_train_epochs=8, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=../output_dir_training_constant_concat/, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=16, | |
| per_device_train_batch_size=16, | |
| predict_with_generate=True, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<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=../output_dir_training_constant_concat/, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=500, | |
| save_strategy=IntervalStrategy.EPOCH, | |
| save_total_limit=5, | |
| seed=456, | |
| skip_memory_metrics=True, | |
| sortish_sampler=False, | |
| split_batches=None, | |
| 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=250, | |
| weight_decay=0.01, | |
| ) | |
| 05/13/2024 20:46:57 - WARNING - __main__ - Disabling fast tokenizer warning: https://github.com/huggingface/transformers/blob/main/src/transformers/tokenization_utils_base.py#L3231-L3235 | |
| loading configuration file preprocessor_config.json from cache at /raid/.cache/huggingface/models--parler-tts--dac_44khZ_8kbps/snapshots/db52bea859d9411e0beb44a3ea923a8731ee4197/preprocessor_config.json | |
| Feature extractor EncodecFeatureExtractor { | |
| "chunk_length_s": null, | |
| "feature_extractor_type": "EncodecFeatureExtractor", | |
| "feature_size": 1, | |
| "overlap": null, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 44100 | |
| } | |
| loading file spiece.model from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/spiece.model | |
| loading file tokenizer.json from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/tokenizer.json | |
| loading file added_tokens.json from cache at None | |
| loading file special_tokens_map.json from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/special_tokens_map.json | |
| loading file tokenizer_config.json from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/tokenizer_config.json | |
| You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers | |
| loading file spiece.model from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/spiece.model | |
| loading file tokenizer.json from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/tokenizer.json | |
| loading file added_tokens.json from cache at None | |
| loading file special_tokens_map.json from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/special_tokens_map.json | |
| loading file tokenizer_config.json from cache at /raid/.cache/huggingface/models--parler-tts--parler_tts_mini_v0.1/snapshots/e02fd18e77d38b49a85c7a9a85189a64b8472544/tokenizer_config.json | |
| Combining datasets...: 0%| | 0/4 [00:00<?, ?it/s] | |
| Combining datasets...: 0%| | 0/4 [03:35<?, ?it/s] | |
| Traceback (most recent call last): | |
| File "/raid/sanchit/parler-tts-mini-v0.1-expresso-concatenated-combined/run_parler_tts_training.py", line 1763, in <module> | |
| main() | |
| File "/raid/sanchit/parler-tts-mini-v0.1-expresso-concatenated-combined/run_parler_tts_training.py", line 950, in main | |
| raw_datasets["train"] = load_multiple_datasets( | |
| ^^^^^^^^^^^^^^^^^^^^^^^ | |
| File "/raid/sanchit/parler-tts-mini-v0.1-expresso-concatenated-combined/run_parler_tts_training.py", line 693, in load_multiple_datasets | |
| metadata_dataset = load_dataset( | |
| ^^^^^^^^^^^^^ | |
| File "/home/sanchit/miniconda3/envs/venv/lib/python3.11/site-packages/datasets/load.py", line 2587, in load_dataset | |
| builder_instance = load_dataset_builder( | |
| ^^^^^^^^^^^^^^^^^^^^^ | |
| File "/home/sanchit/miniconda3/envs/venv/lib/python3.11/site-packages/datasets/load.py", line 2296, in load_dataset_builder | |
| builder_instance: DatasetBuilder = builder_cls( | |
| ^^^^^^^^^^^^ | |
| File "/home/sanchit/miniconda3/envs/venv/lib/python3.11/site-packages/datasets/builder.py", line 374, in __init__ | |
| self.config, self.config_id = self._create_builder_config( | |
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | |
| File "/home/sanchit/miniconda3/envs/venv/lib/python3.11/site-packages/datasets/builder.py", line 599, in _create_builder_config | |
| raise ValueError( | |
| ValueError: BuilderConfig 'read' not found. Available: ['default'] |