Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999365683476055,
+    "total_flos": 2.4957269414919537e+18,
+    "train_loss": 1.201914404482746,
+    "train_runtime": 115316.4416,
+    "train_samples_per_second": 4.375,
+    "train_steps_per_second": 0.034
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<|image|>' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{ '<|eot_id|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
+}

config.json

@@ -0,0 +1,224 @@
+{
+  "architectures": [
+    "MllamaForConditionalGeneration"
+  ],
+  "image_token_index": 128256,
+  "model_type": "mllama",
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "cross_attention_layers": [
+      3,
+      8,
+      13,
+      18,
+      23,
+      28,
+      33,
+      38
+    ],
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 131072,
+    "min_length": 0,
+    "model_type": "mllama_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 128004,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128256
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_heads": 16,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 560,
+    "initializer_range": 0.02,
+    "intermediate_layers_indices": [
+      3,
+      7,
+      15,
+      23,
+      30
+    ],
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_num_tiles": 4,
+    "min_length": 0,
+    "model_type": "mllama_vision_model",
+    "no_repeat_ngram_size": 0,
+    "norm_eps": 1e-05,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_global_layers": 8,
+    "num_hidden_layers": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "supported_aspect_ratios": [
+      [
+        1,
+        1
+      ],
+      [
+        1,
+        2
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        1,
+        4
+      ],
+      [
+        2,
+        1
+      ],
+      [
+        2,
+        2
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        4,
+        1
+      ]
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_output_dim": 7680
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c037b069d656a16ca9378a2376289cdad595ac1fa9c0ccd29596a50cf5a63d6b
+size 4992622346

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ed5765a767db81e05bab5957d250f19b5a563701eadbbb7d96a996b8666d39
+size 4966251712

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021d26dcba0d86eb8118a524646fa8f60b3ea0e91a2a57f6a53b44e4e1c17802
+size 4915919704

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5644f37a0ba66b52f23a5016e687e52f2031d53fca87ce002d27a4e4edc6eb0d
+size 4999823980

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9d08f24f859d028e833663cafa5de1ae796b55c912d14b93337f54474e970e
+size 1465943128

model.safetensors.index.json

@@ -0,0 +1,913 @@
+{
+  "metadata": {
+    "total_size": 21340441670
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn_attn_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn_mlp_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn_attn_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn_mlp_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn_attn_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn_mlp_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn_attn_gate": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn_mlp_gate": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn_attn_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn_mlp_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.norm.weight": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.bias": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.weight": "model-00005-of-00005.safetensors",
+    "vision_model.class_embedding": "model-00001-of-00005.safetensors",
+    "vision_model.gated_positional_embedding.embedding": "model-00001-of-00005.safetensors",
+    "vision_model.gated_positional_embedding.gate": "model-00001-of-00005.safetensors",
+    "vision_model.gated_positional_embedding.tile_embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_post.bias": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_post.weight": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_pre.bias": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_pre.weight": "model-00001-of-00005.safetensors",
+    "vision_model.patch_embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.post_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.post_tile_positional_embedding.gate": "model-00001-of-00005.safetensors",
+    "vision_model.pre_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.pre_tile_positional_embedding.gate": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "MllamaImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_image_tiles": 4,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 560,
+    "width": 560
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2071 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|step_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- for content in message['content'] %}\n        {%- if content['type'] == 'image' %}\n            {%- set image_ns.has_images = true %}\n        {%- endif %}\n    {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n    {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n    {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n    {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999365683476055,
+    "total_flos": 2.4957269414919537e+18,
+    "train_loss": 1.201914404482746,
+    "train_runtime": 115316.4416,
+    "train_samples_per_second": 4.375,
+    "train_steps_per_second": 0.034
+}

trainer_log.jsonl

@@ -0,0 +1,395 @@
+{"current_steps": 10, "total_steps": 3941, "loss": 1.8967, "learning_rate": 1.2658227848101266e-07, "epoch": 0.002537266095781795, "percentage": 0.25, "elapsed_time": "0:04:46", "remaining_time": "1 day, 7:15:07"}
+{"current_steps": 20, "total_steps": 3941, "loss": 1.8962, "learning_rate": 2.5316455696202533e-07, "epoch": 0.00507453219156359, "percentage": 0.51, "elapsed_time": "0:09:29", "remaining_time": "1 day, 7:00:51"}
+{"current_steps": 30, "total_steps": 3941, "loss": 1.8773, "learning_rate": 3.79746835443038e-07, "epoch": 0.007611798287345386, "percentage": 0.76, "elapsed_time": "0:14:11", "remaining_time": "1 day, 6:49:07"}
+{"current_steps": 40, "total_steps": 3941, "loss": 1.7742, "learning_rate": 5.063291139240507e-07, "epoch": 0.01014906438312718, "percentage": 1.01, "elapsed_time": "0:18:52", "remaining_time": "1 day, 6:40:24"}
+{"current_steps": 50, "total_steps": 3941, "loss": 1.7141, "learning_rate": 6.329113924050634e-07, "epoch": 0.012686330478908976, "percentage": 1.27, "elapsed_time": "0:23:33", "remaining_time": "1 day, 6:33:47"}
+{"current_steps": 60, "total_steps": 3941, "loss": 1.6293, "learning_rate": 7.59493670886076e-07, "epoch": 0.015223596574690771, "percentage": 1.52, "elapsed_time": "0:28:14", "remaining_time": "1 day, 6:26:43"}
+{"current_steps": 70, "total_steps": 3941, "loss": 1.5743, "learning_rate": 8.860759493670887e-07, "epoch": 0.017760862670472565, "percentage": 1.78, "elapsed_time": "0:32:55", "remaining_time": "1 day, 6:21:03"}
+{"current_steps": 80, "total_steps": 3941, "loss": 1.5202, "learning_rate": 1.0126582278481013e-06, "epoch": 0.02029812876625436, "percentage": 2.03, "elapsed_time": "0:37:37", "remaining_time": "1 day, 6:15:56"}
+{"current_steps": 90, "total_steps": 3941, "loss": 1.4872, "learning_rate": 1.139240506329114e-06, "epoch": 0.022835394862036156, "percentage": 2.28, "elapsed_time": "0:42:18", "remaining_time": "1 day, 6:10:37"}
+{"current_steps": 100, "total_steps": 3941, "loss": 1.4824, "learning_rate": 1.2658227848101267e-06, "epoch": 0.02537266095781795, "percentage": 2.54, "elapsed_time": "0:47:00", "remaining_time": "1 day, 6:05:47"}
+{"current_steps": 110, "total_steps": 3941, "loss": 1.4456, "learning_rate": 1.3924050632911392e-06, "epoch": 0.027909927053599747, "percentage": 2.79, "elapsed_time": "0:51:43", "remaining_time": "1 day, 6:01:24"}
+{"current_steps": 120, "total_steps": 3941, "loss": 1.4253, "learning_rate": 1.518987341772152e-06, "epoch": 0.030447193149381543, "percentage": 3.04, "elapsed_time": "0:56:24", "remaining_time": "1 day, 5:56:01"}
+{"current_steps": 130, "total_steps": 3941, "loss": 1.4119, "learning_rate": 1.6455696202531647e-06, "epoch": 0.032984459245163335, "percentage": 3.3, "elapsed_time": "1:01:06", "remaining_time": "1 day, 5:51:21"}
+{"current_steps": 140, "total_steps": 3941, "loss": 1.3944, "learning_rate": 1.7721518987341774e-06, "epoch": 0.03552172534094513, "percentage": 3.55, "elapsed_time": "1:05:47", "remaining_time": "1 day, 5:46:23"}
+{"current_steps": 150, "total_steps": 3941, "loss": 1.3937, "learning_rate": 1.8987341772151901e-06, "epoch": 0.038058991436726926, "percentage": 3.81, "elapsed_time": "1:10:28", "remaining_time": "1 day, 5:41:04"}
+{"current_steps": 160, "total_steps": 3941, "loss": 1.3624, "learning_rate": 2.0253164556962026e-06, "epoch": 0.04059625753250872, "percentage": 4.06, "elapsed_time": "1:15:10", "remaining_time": "1 day, 5:36:30"}
+{"current_steps": 170, "total_steps": 3941, "loss": 1.3854, "learning_rate": 2.1518987341772153e-06, "epoch": 0.04313352362829052, "percentage": 4.31, "elapsed_time": "1:19:53", "remaining_time": "1 day, 5:32:07"}
+{"current_steps": 180, "total_steps": 3941, "loss": 1.3745, "learning_rate": 2.278481012658228e-06, "epoch": 0.04567078972407231, "percentage": 4.57, "elapsed_time": "1:24:35", "remaining_time": "1 day, 5:27:27"}
+{"current_steps": 190, "total_steps": 3941, "loss": 1.3616, "learning_rate": 2.4050632911392408e-06, "epoch": 0.04820805581985411, "percentage": 4.82, "elapsed_time": "1:29:17", "remaining_time": "1 day, 5:22:45"}
+{"current_steps": 200, "total_steps": 3941, "loss": 1.3802, "learning_rate": 2.5316455696202535e-06, "epoch": 0.0507453219156359, "percentage": 5.07, "elapsed_time": "1:33:57", "remaining_time": "1 day, 5:17:38"}
+{"current_steps": 210, "total_steps": 3941, "loss": 1.3501, "learning_rate": 2.6582278481012658e-06, "epoch": 0.0532825880114177, "percentage": 5.33, "elapsed_time": "1:38:38", "remaining_time": "1 day, 5:12:34"}
+{"current_steps": 220, "total_steps": 3941, "loss": 1.3529, "learning_rate": 2.7848101265822785e-06, "epoch": 0.055819854107199494, "percentage": 5.58, "elapsed_time": "1:43:20", "remaining_time": "1 day, 5:07:58"}
+{"current_steps": 230, "total_steps": 3941, "loss": 1.3425, "learning_rate": 2.9113924050632912e-06, "epoch": 0.05835712020298129, "percentage": 5.84, "elapsed_time": "1:48:01", "remaining_time": "1 day, 5:03:03"}
+{"current_steps": 240, "total_steps": 3941, "loss": 1.3268, "learning_rate": 3.037974683544304e-06, "epoch": 0.060894386298763085, "percentage": 6.09, "elapsed_time": "1:52:42", "remaining_time": "1 day, 4:58:03"}
+{"current_steps": 250, "total_steps": 3941, "loss": 1.3391, "learning_rate": 3.164556962025317e-06, "epoch": 0.06343165239454487, "percentage": 6.34, "elapsed_time": "1:57:23", "remaining_time": "1 day, 4:53:12"}
+{"current_steps": 260, "total_steps": 3941, "loss": 1.331, "learning_rate": 3.2911392405063294e-06, "epoch": 0.06596891849032667, "percentage": 6.6, "elapsed_time": "2:02:05", "remaining_time": "1 day, 4:48:27"}
+{"current_steps": 270, "total_steps": 3941, "loss": 1.3318, "learning_rate": 3.417721518987342e-06, "epoch": 0.06850618458610847, "percentage": 6.85, "elapsed_time": "2:06:47", "remaining_time": "1 day, 4:43:52"}
+{"current_steps": 280, "total_steps": 3941, "loss": 1.3356, "learning_rate": 3.544303797468355e-06, "epoch": 0.07104345068189026, "percentage": 7.1, "elapsed_time": "2:11:29", "remaining_time": "1 day, 4:39:18"}
+{"current_steps": 290, "total_steps": 3941, "loss": 1.32, "learning_rate": 3.6708860759493675e-06, "epoch": 0.07358071677767206, "percentage": 7.36, "elapsed_time": "2:16:11", "remaining_time": "1 day, 4:34:36"}
+{"current_steps": 300, "total_steps": 3941, "loss": 1.3224, "learning_rate": 3.7974683544303802e-06, "epoch": 0.07611798287345385, "percentage": 7.61, "elapsed_time": "2:20:52", "remaining_time": "1 day, 4:29:49"}
+{"current_steps": 310, "total_steps": 3941, "loss": 1.3176, "learning_rate": 3.924050632911393e-06, "epoch": 0.07865524896923565, "percentage": 7.87, "elapsed_time": "2:25:34", "remaining_time": "1 day, 4:25:04"}
+{"current_steps": 320, "total_steps": 3941, "loss": 1.2962, "learning_rate": 4.050632911392405e-06, "epoch": 0.08119251506501744, "percentage": 8.12, "elapsed_time": "2:30:14", "remaining_time": "1 day, 4:20:03"}
+{"current_steps": 330, "total_steps": 3941, "loss": 1.3005, "learning_rate": 4.177215189873418e-06, "epoch": 0.08372978116079924, "percentage": 8.37, "elapsed_time": "2:34:55", "remaining_time": "1 day, 4:15:14"}
+{"current_steps": 340, "total_steps": 3941, "loss": 1.3031, "learning_rate": 4.303797468354431e-06, "epoch": 0.08626704725658103, "percentage": 8.63, "elapsed_time": "2:39:38", "remaining_time": "1 day, 4:10:50"}
+{"current_steps": 350, "total_steps": 3941, "loss": 1.3107, "learning_rate": 4.430379746835443e-06, "epoch": 0.08880431335236283, "percentage": 8.88, "elapsed_time": "2:44:20", "remaining_time": "1 day, 4:06:13"}
+{"current_steps": 360, "total_steps": 3941, "loss": 1.2886, "learning_rate": 4.556962025316456e-06, "epoch": 0.09134157944814462, "percentage": 9.13, "elapsed_time": "2:49:02", "remaining_time": "1 day, 4:01:25"}
+{"current_steps": 370, "total_steps": 3941, "loss": 1.2954, "learning_rate": 4.683544303797468e-06, "epoch": 0.09387884554392642, "percentage": 9.39, "elapsed_time": "2:53:42", "remaining_time": "1 day, 3:56:34"}
+{"current_steps": 380, "total_steps": 3941, "loss": 1.2959, "learning_rate": 4.8101265822784815e-06, "epoch": 0.09641611163970822, "percentage": 9.64, "elapsed_time": "2:58:25", "remaining_time": "1 day, 3:51:57"}
+{"current_steps": 390, "total_steps": 3941, "loss": 1.2918, "learning_rate": 4.936708860759495e-06, "epoch": 0.09895337773549001, "percentage": 9.9, "elapsed_time": "3:03:08", "remaining_time": "1 day, 3:47:29"}
+{"current_steps": 400, "total_steps": 3941, "loss": 1.2952, "learning_rate": 4.999975471465892e-06, "epoch": 0.1014906438312718, "percentage": 10.15, "elapsed_time": "3:07:50", "remaining_time": "1 day, 3:42:52"}
+{"current_steps": 410, "total_steps": 3941, "loss": 1.2812, "learning_rate": 4.999779246080933e-06, "epoch": 0.1040279099270536, "percentage": 10.4, "elapsed_time": "3:12:37", "remaining_time": "1 day, 3:38:57"}
+{"current_steps": 420, "total_steps": 3941, "loss": 1.2532, "learning_rate": 4.999386810712926e-06, "epoch": 0.1065651760228354, "percentage": 10.66, "elapsed_time": "3:17:28", "remaining_time": "1 day, 3:35:32"}
+{"current_steps": 430, "total_steps": 3941, "loss": 1.2982, "learning_rate": 4.9987981961644855e-06, "epoch": 0.1091024421186172, "percentage": 10.91, "elapsed_time": "3:22:10", "remaining_time": "1 day, 3:30:46"}
+{"current_steps": 440, "total_steps": 3941, "loss": 1.271, "learning_rate": 4.998013448636512e-06, "epoch": 0.11163970821439899, "percentage": 11.16, "elapsed_time": "3:26:51", "remaining_time": "1 day, 3:25:59"}
+{"current_steps": 450, "total_steps": 3941, "loss": 1.2825, "learning_rate": 4.997032629724564e-06, "epoch": 0.11417697431018078, "percentage": 11.42, "elapsed_time": "3:31:32", "remaining_time": "1 day, 3:21:08"}
+{"current_steps": 460, "total_steps": 3941, "loss": 1.2765, "learning_rate": 4.995855816414024e-06, "epoch": 0.11671424040596258, "percentage": 11.67, "elapsed_time": "3:36:15", "remaining_time": "1 day, 3:16:27"}
+{"current_steps": 470, "total_steps": 3941, "loss": 1.2585, "learning_rate": 4.9944831010740576e-06, "epoch": 0.11925150650174438, "percentage": 11.93, "elapsed_time": "3:40:56", "remaining_time": "1 day, 3:11:38"}
+{"current_steps": 480, "total_steps": 3941, "loss": 1.2929, "learning_rate": 4.992914591450358e-06, "epoch": 0.12178877259752617, "percentage": 12.18, "elapsed_time": "3:45:37", "remaining_time": "1 day, 3:06:51"}
+{"current_steps": 490, "total_steps": 3941, "loss": 1.2733, "learning_rate": 4.991150410656697e-06, "epoch": 0.12432603869330797, "percentage": 12.43, "elapsed_time": "3:50:19", "remaining_time": "1 day, 3:02:05"}
+{"current_steps": 500, "total_steps": 3941, "loss": 1.2558, "learning_rate": 4.9891906971652545e-06, "epoch": 0.12686330478908975, "percentage": 12.69, "elapsed_time": "3:55:04", "remaining_time": "1 day, 2:57:44"}
+{"current_steps": 510, "total_steps": 3941, "loss": 1.2659, "learning_rate": 4.987035604795753e-06, "epoch": 0.12940057088487156, "percentage": 12.94, "elapsed_time": "4:12:18", "remaining_time": "1 day, 4:17:20"}
+{"current_steps": 520, "total_steps": 3941, "loss": 1.2606, "learning_rate": 4.984685302703385e-06, "epoch": 0.13193783698065334, "percentage": 13.19, "elapsed_time": "4:16:58", "remaining_time": "1 day, 4:10:37"}
+{"current_steps": 530, "total_steps": 3941, "loss": 1.2785, "learning_rate": 4.982139975365533e-06, "epoch": 0.13447510307643515, "percentage": 13.45, "elapsed_time": "4:21:45", "remaining_time": "1 day, 4:04:36"}
+{"current_steps": 540, "total_steps": 3941, "loss": 1.2709, "learning_rate": 4.979399822567292e-06, "epoch": 0.13701236917221693, "percentage": 13.7, "elapsed_time": "4:26:47", "remaining_time": "1 day, 4:00:15"}
+{"current_steps": 550, "total_steps": 3941, "loss": 1.248, "learning_rate": 4.976465059385788e-06, "epoch": 0.13954963526799874, "percentage": 13.96, "elapsed_time": "4:32:56", "remaining_time": "1 day, 4:02:47"}
+{"current_steps": 560, "total_steps": 3941, "loss": 1.2462, "learning_rate": 4.973335916173294e-06, "epoch": 0.14208690136378052, "percentage": 14.21, "elapsed_time": "4:39:45", "remaining_time": "1 day, 4:09:02"}
+{"current_steps": 570, "total_steps": 3941, "loss": 1.2533, "learning_rate": 4.970012638539152e-06, "epoch": 0.14462416745956233, "percentage": 14.46, "elapsed_time": "4:45:01", "remaining_time": "1 day, 4:05:38"}
+{"current_steps": 580, "total_steps": 3941, "loss": 1.2526, "learning_rate": 4.966495487330496e-06, "epoch": 0.1471614335553441, "percentage": 14.72, "elapsed_time": "4:50:24", "remaining_time": "1 day, 4:02:52"}
+{"current_steps": 590, "total_steps": 3941, "loss": 1.265, "learning_rate": 4.962784738611774e-06, "epoch": 0.14969869965112592, "percentage": 14.97, "elapsed_time": "4:55:04", "remaining_time": "1 day, 3:55:56"}
+{"current_steps": 600, "total_steps": 3941, "loss": 1.2733, "learning_rate": 4.958880683643082e-06, "epoch": 0.1522359657469077, "percentage": 15.22, "elapsed_time": "4:59:45", "remaining_time": "1 day, 3:49:06"}
+{"current_steps": 610, "total_steps": 3941, "loss": 1.2626, "learning_rate": 4.954783628857302e-06, "epoch": 0.1547732318426895, "percentage": 15.48, "elapsed_time": "5:04:25", "remaining_time": "1 day, 3:42:23"}
+{"current_steps": 620, "total_steps": 3941, "loss": 1.2657, "learning_rate": 4.95049389583605e-06, "epoch": 0.1573104979384713, "percentage": 15.73, "elapsed_time": "5:09:07", "remaining_time": "1 day, 3:35:49"}
+{"current_steps": 630, "total_steps": 3941, "loss": 1.2372, "learning_rate": 4.9460118212844355e-06, "epoch": 0.1598477640342531, "percentage": 15.99, "elapsed_time": "5:13:47", "remaining_time": "1 day, 3:29:07"}
+{"current_steps": 640, "total_steps": 3941, "loss": 1.2355, "learning_rate": 4.941337757004631e-06, "epoch": 0.16238503013003489, "percentage": 16.24, "elapsed_time": "5:18:29", "remaining_time": "1 day, 3:22:44"}
+{"current_steps": 650, "total_steps": 3941, "loss": 1.2439, "learning_rate": 4.936472069868262e-06, "epoch": 0.1649222962258167, "percentage": 16.49, "elapsed_time": "5:23:10", "remaining_time": "1 day, 3:16:13"}
+{"current_steps": 660, "total_steps": 3941, "loss": 1.2384, "learning_rate": 4.931415141787607e-06, "epoch": 0.16745956232159848, "percentage": 16.75, "elapsed_time": "5:27:53", "remaining_time": "1 day, 3:10:01"}
+{"current_steps": 670, "total_steps": 3941, "loss": 1.2452, "learning_rate": 4.926167369685626e-06, "epoch": 0.16999682841738029, "percentage": 17.0, "elapsed_time": "5:32:35", "remaining_time": "1 day, 3:03:42"}
+{"current_steps": 680, "total_steps": 3941, "loss": 1.2564, "learning_rate": 4.920729165464799e-06, "epoch": 0.17253409451316207, "percentage": 17.25, "elapsed_time": "5:37:18", "remaining_time": "1 day, 2:57:37"}
+{"current_steps": 690, "total_steps": 3941, "loss": 1.2695, "learning_rate": 4.915100955974802e-06, "epoch": 0.17507136060894388, "percentage": 17.51, "elapsed_time": "5:42:01", "remaining_time": "1 day, 2:51:29"}
+{"current_steps": 700, "total_steps": 3941, "loss": 1.2379, "learning_rate": 4.909283182978998e-06, "epoch": 0.17760862670472566, "percentage": 17.76, "elapsed_time": "5:46:41", "remaining_time": "1 day, 2:45:12"}
+{"current_steps": 710, "total_steps": 3941, "loss": 1.2483, "learning_rate": 4.903276303119765e-06, "epoch": 0.18014589280050744, "percentage": 18.02, "elapsed_time": "5:51:23", "remaining_time": "1 day, 2:39:06"}
+{"current_steps": 720, "total_steps": 3941, "loss": 1.2493, "learning_rate": 4.897080787882656e-06, "epoch": 0.18268315889628925, "percentage": 18.27, "elapsed_time": "5:56:04", "remaining_time": "1 day, 2:32:57"}
+{"current_steps": 730, "total_steps": 3941, "loss": 1.2635, "learning_rate": 4.890697123559385e-06, "epoch": 0.18522042499207103, "percentage": 18.52, "elapsed_time": "6:00:45", "remaining_time": "1 day, 2:26:50"}
+{"current_steps": 740, "total_steps": 3941, "loss": 1.2439, "learning_rate": 4.884125811209665e-06, "epoch": 0.18775769108785284, "percentage": 18.78, "elapsed_time": "6:05:35", "remaining_time": "1 day, 2:21:24"}
+{"current_steps": 750, "total_steps": 3941, "loss": 1.2423, "learning_rate": 4.877367366621874e-06, "epoch": 0.19029495718363462, "percentage": 19.03, "elapsed_time": "6:10:17", "remaining_time": "1 day, 2:15:29"}
+{"current_steps": 760, "total_steps": 3941, "loss": 1.2322, "learning_rate": 4.870422320272576e-06, "epoch": 0.19283222327941643, "percentage": 19.28, "elapsed_time": "6:14:58", "remaining_time": "1 day, 2:09:29"}
+{"current_steps": 770, "total_steps": 3941, "loss": 1.2354, "learning_rate": 4.863291217284872e-06, "epoch": 0.1953694893751982, "percentage": 19.54, "elapsed_time": "6:19:41", "remaining_time": "1 day, 2:03:38"}
+{"current_steps": 780, "total_steps": 3941, "loss": 1.2257, "learning_rate": 4.855974617385629e-06, "epoch": 0.19790675547098002, "percentage": 19.79, "elapsed_time": "6:24:22", "remaining_time": "1 day, 1:57:40"}
+{"current_steps": 790, "total_steps": 3941, "loss": 1.2477, "learning_rate": 4.8484730948615336e-06, "epoch": 0.2004440215667618, "percentage": 20.05, "elapsed_time": "6:29:04", "remaining_time": "1 day, 1:51:53"}
+{"current_steps": 800, "total_steps": 3941, "loss": 1.242, "learning_rate": 4.840787238514019e-06, "epoch": 0.2029812876625436, "percentage": 20.3, "elapsed_time": "6:33:46", "remaining_time": "1 day, 1:46:01"}
+{"current_steps": 810, "total_steps": 3941, "loss": 1.2481, "learning_rate": 4.832917651613055e-06, "epoch": 0.2055185537583254, "percentage": 20.55, "elapsed_time": "6:38:27", "remaining_time": "1 day, 1:40:14"}
+{"current_steps": 820, "total_steps": 3941, "loss": 1.2422, "learning_rate": 4.824864951849787e-06, "epoch": 0.2080558198541072, "percentage": 20.81, "elapsed_time": "6:43:10", "remaining_time": "1 day, 1:34:32"}
+{"current_steps": 830, "total_steps": 3941, "loss": 1.2296, "learning_rate": 4.8166297712880635e-06, "epoch": 0.210593085949889, "percentage": 21.06, "elapsed_time": "6:47:54", "remaining_time": "1 day, 1:28:54"}
+{"current_steps": 840, "total_steps": 3941, "loss": 1.2185, "learning_rate": 4.808212756314815e-06, "epoch": 0.2131303520456708, "percentage": 21.31, "elapsed_time": "6:52:36", "remaining_time": "1 day, 1:23:12"}
+{"current_steps": 850, "total_steps": 3941, "loss": 1.2348, "learning_rate": 4.7996145675893255e-06, "epoch": 0.21566761814145258, "percentage": 21.57, "elapsed_time": "6:57:19", "remaining_time": "1 day, 1:17:35"}
+{"current_steps": 860, "total_steps": 3941, "loss": 1.259, "learning_rate": 4.7908358799913735e-06, "epoch": 0.2182048842372344, "percentage": 21.82, "elapsed_time": "7:02:01", "remaining_time": "1 day, 1:11:56"}
+{"current_steps": 870, "total_steps": 3941, "loss": 1.2305, "learning_rate": 4.781877382568261e-06, "epoch": 0.22074215033301617, "percentage": 22.08, "elapsed_time": "7:06:44", "remaining_time": "1 day, 1:06:21"}
+{"current_steps": 880, "total_steps": 3941, "loss": 1.2343, "learning_rate": 4.772739778480729e-06, "epoch": 0.22327941642879798, "percentage": 22.33, "elapsed_time": "7:11:25", "remaining_time": "1 day, 1:00:42"}
+{"current_steps": 890, "total_steps": 3941, "loss": 1.2194, "learning_rate": 4.7634237849477645e-06, "epoch": 0.22581668252457976, "percentage": 22.58, "elapsed_time": "7:16:08", "remaining_time": "1 day, 0:55:07"}
+{"current_steps": 900, "total_steps": 3941, "loss": 1.2267, "learning_rate": 4.7539301331903125e-06, "epoch": 0.22835394862036157, "percentage": 22.84, "elapsed_time": "7:21:00", "remaining_time": "1 day, 0:50:06"}
+{"current_steps": 910, "total_steps": 3941, "loss": 1.2132, "learning_rate": 4.7442595683738705e-06, "epoch": 0.23089121471614335, "percentage": 23.09, "elapsed_time": "7:25:55", "remaining_time": "1 day, 0:45:15"}
+{"current_steps": 920, "total_steps": 3941, "loss": 1.2094, "learning_rate": 4.734412849550007e-06, "epoch": 0.23342848081192516, "percentage": 23.34, "elapsed_time": "7:30:37", "remaining_time": "1 day, 0:39:43"}
+{"current_steps": 930, "total_steps": 3941, "loss": 1.2294, "learning_rate": 4.7243907495967815e-06, "epoch": 0.23596574690770694, "percentage": 23.6, "elapsed_time": "7:35:20", "remaining_time": "1 day, 0:34:14"}
+{"current_steps": 940, "total_steps": 3941, "loss": 1.2208, "learning_rate": 4.7141940551580824e-06, "epoch": 0.23850301300348875, "percentage": 23.85, "elapsed_time": "7:40:02", "remaining_time": "1 day, 0:28:41"}
+{"current_steps": 950, "total_steps": 3941, "loss": 1.2324, "learning_rate": 4.703823566581877e-06, "epoch": 0.24104027909927053, "percentage": 24.11, "elapsed_time": "7:44:42", "remaining_time": "1 day, 0:23:04"}
+{"current_steps": 960, "total_steps": 3941, "loss": 1.2222, "learning_rate": 4.693280097857398e-06, "epoch": 0.24357754519505234, "percentage": 24.36, "elapsed_time": "7:49:26", "remaining_time": "1 day, 0:17:43"}
+{"current_steps": 970, "total_steps": 3941, "loss": 1.2185, "learning_rate": 4.6825644765512475e-06, "epoch": 0.24611481129083412, "percentage": 24.61, "elapsed_time": "7:54:10", "remaining_time": "1 day, 0:12:19"}
+{"current_steps": 980, "total_steps": 3941, "loss": 1.2192, "learning_rate": 4.6716775437424465e-06, "epoch": 0.24865207738661593, "percentage": 24.87, "elapsed_time": "7:58:53", "remaining_time": "1 day, 0:06:54"}
+{"current_steps": 990, "total_steps": 3941, "loss": 1.2241, "learning_rate": 4.660620153956409e-06, "epoch": 0.25118934348239774, "percentage": 25.12, "elapsed_time": "8:03:36", "remaining_time": "1 day, 0:01:31"}
+{"current_steps": 1000, "total_steps": 3941, "loss": 1.2281, "learning_rate": 4.649393175097879e-06, "epoch": 0.2537266095781795, "percentage": 25.37, "elapsed_time": "8:08:17", "remaining_time": "23:56:03"}
+{"current_steps": 1010, "total_steps": 3941, "loss": 1.2286, "learning_rate": 4.637997488382801e-06, "epoch": 0.2562638756739613, "percentage": 25.63, "elapsed_time": "8:20:09", "remaining_time": "1 day, 0:11:26"}
+{"current_steps": 1020, "total_steps": 3941, "loss": 1.2217, "learning_rate": 4.626433988269156e-06, "epoch": 0.2588011417697431, "percentage": 25.88, "elapsed_time": "8:24:51", "remaining_time": "1 day, 0:05:45"}
+{"current_steps": 1030, "total_steps": 3941, "loss": 1.2181, "learning_rate": 4.614703582386755e-06, "epoch": 0.2613384078655249, "percentage": 26.14, "elapsed_time": "8:29:33", "remaining_time": "1 day, 0:00:07"}
+{"current_steps": 1040, "total_steps": 3941, "loss": 1.2382, "learning_rate": 4.602807191465993e-06, "epoch": 0.2638756739613067, "percentage": 26.39, "elapsed_time": "8:34:13", "remaining_time": "23:54:23"}
+{"current_steps": 1050, "total_steps": 3941, "loss": 1.2359, "learning_rate": 4.5907457492655895e-06, "epoch": 0.2664129400570885, "percentage": 26.64, "elapsed_time": "8:38:56", "remaining_time": "23:48:48"}
+{"current_steps": 1060, "total_steps": 3941, "loss": 1.2154, "learning_rate": 4.578520202499286e-06, "epoch": 0.2689502061528703, "percentage": 26.9, "elapsed_time": "8:43:41", "remaining_time": "23:43:21"}
+{"current_steps": 1070, "total_steps": 3941, "loss": 1.2279, "learning_rate": 4.566131510761548e-06, "epoch": 0.27148747224865205, "percentage": 27.15, "elapsed_time": "8:48:22", "remaining_time": "23:37:43"}
+{"current_steps": 1080, "total_steps": 3941, "loss": 1.2276, "learning_rate": 4.553580646452238e-06, "epoch": 0.27402473834443386, "percentage": 27.4, "elapsed_time": "8:53:07", "remaining_time": "23:32:17"}
+{"current_steps": 1090, "total_steps": 3941, "loss": 1.2159, "learning_rate": 4.5408685947002915e-06, "epoch": 0.27656200444021567, "percentage": 27.66, "elapsed_time": "8:57:48", "remaining_time": "23:26:41"}
+{"current_steps": 1100, "total_steps": 3941, "loss": 1.209, "learning_rate": 4.5279963532864e-06, "epoch": 0.2790992705359975, "percentage": 27.91, "elapsed_time": "9:02:29", "remaining_time": "23:21:07"}
+{"current_steps": 1110, "total_steps": 3941, "loss": 1.2227, "learning_rate": 4.5149649325646875e-06, "epoch": 0.28163653663177923, "percentage": 28.17, "elapsed_time": "9:07:12", "remaining_time": "23:15:37"}
+{"current_steps": 1120, "total_steps": 3941, "loss": 1.2299, "learning_rate": 4.501775355383406e-06, "epoch": 0.28417380272756104, "percentage": 28.42, "elapsed_time": "9:11:56", "remaining_time": "23:10:11"}
+{"current_steps": 1130, "total_steps": 3941, "loss": 1.1972, "learning_rate": 4.48842865700466e-06, "epoch": 0.28671106882334285, "percentage": 28.67, "elapsed_time": "9:16:39", "remaining_time": "23:04:45"}
+{"current_steps": 1140, "total_steps": 3941, "loss": 1.2043, "learning_rate": 4.474925885023136e-06, "epoch": 0.28924833491912466, "percentage": 28.93, "elapsed_time": "9:21:25", "remaining_time": "22:59:24"}
+{"current_steps": 1150, "total_steps": 3941, "loss": 1.2107, "learning_rate": 4.461268099283886e-06, "epoch": 0.2917856010149064, "percentage": 29.18, "elapsed_time": "9:26:06", "remaining_time": "22:53:56"}
+{"current_steps": 1160, "total_steps": 3941, "loss": 1.2014, "learning_rate": 4.4474563717991345e-06, "epoch": 0.2943228671106882, "percentage": 29.43, "elapsed_time": "9:30:50", "remaining_time": "22:48:32"}
+{"current_steps": 1170, "total_steps": 3941, "loss": 1.2068, "learning_rate": 4.433491786664134e-06, "epoch": 0.29686013320647003, "percentage": 29.69, "elapsed_time": "9:35:30", "remaining_time": "22:43:01"}
+{"current_steps": 1180, "total_steps": 3941, "loss": 1.2276, "learning_rate": 4.419375439972075e-06, "epoch": 0.29939739930225184, "percentage": 29.94, "elapsed_time": "9:40:12", "remaining_time": "22:37:35"}
+{"current_steps": 1190, "total_steps": 3941, "loss": 1.217, "learning_rate": 4.405108439728057e-06, "epoch": 0.3019346653980336, "percentage": 30.2, "elapsed_time": "9:44:55", "remaining_time": "22:32:11"}
+{"current_steps": 1200, "total_steps": 3941, "loss": 1.2141, "learning_rate": 4.390691905762111e-06, "epoch": 0.3044719314938154, "percentage": 30.45, "elapsed_time": "9:49:37", "remaining_time": "22:26:48"}
+{"current_steps": 1210, "total_steps": 3941, "loss": 1.2067, "learning_rate": 4.376126969641311e-06, "epoch": 0.3070091975895972, "percentage": 30.7, "elapsed_time": "9:54:21", "remaining_time": "22:21:28"}
+{"current_steps": 1220, "total_steps": 3941, "loss": 1.2126, "learning_rate": 4.361414774580952e-06, "epoch": 0.309546463685379, "percentage": 30.96, "elapsed_time": "9:59:03", "remaining_time": "22:16:06"}
+{"current_steps": 1230, "total_steps": 3941, "loss": 1.1928, "learning_rate": 4.34655647535482e-06, "epoch": 0.3120837297811608, "percentage": 31.21, "elapsed_time": "10:03:46", "remaining_time": "22:10:45"}
+{"current_steps": 1240, "total_steps": 3941, "loss": 1.2233, "learning_rate": 4.3315532382045535e-06, "epoch": 0.3146209958769426, "percentage": 31.46, "elapsed_time": "10:08:28", "remaining_time": "22:05:22"}
+{"current_steps": 1250, "total_steps": 3941, "loss": 1.2208, "learning_rate": 4.3164062407480974e-06, "epoch": 0.3171582619727244, "percentage": 31.72, "elapsed_time": "10:13:09", "remaining_time": "22:00:01"}
+{"current_steps": 1260, "total_steps": 3941, "loss": 1.2009, "learning_rate": 4.301116671887281e-06, "epoch": 0.3196955280685062, "percentage": 31.97, "elapsed_time": "10:17:52", "remaining_time": "21:54:41"}
+{"current_steps": 1270, "total_steps": 3941, "loss": 1.2188, "learning_rate": 4.285685731714493e-06, "epoch": 0.32223279416428796, "percentage": 32.23, "elapsed_time": "10:22:32", "remaining_time": "21:49:18"}
+{"current_steps": 1280, "total_steps": 3941, "loss": 1.1947, "learning_rate": 4.270114631418487e-06, "epoch": 0.32477006026006977, "percentage": 32.48, "elapsed_time": "10:27:15", "remaining_time": "21:43:59"}
+{"current_steps": 1290, "total_steps": 3941, "loss": 1.2063, "learning_rate": 4.254404593189316e-06, "epoch": 0.3273073263558516, "percentage": 32.73, "elapsed_time": "10:31:56", "remaining_time": "21:38:40"}
+{"current_steps": 1300, "total_steps": 3941, "loss": 1.1988, "learning_rate": 4.238556850122394e-06, "epoch": 0.3298445924516334, "percentage": 32.99, "elapsed_time": "10:36:38", "remaining_time": "21:33:21"}
+{"current_steps": 1310, "total_steps": 3941, "loss": 1.2084, "learning_rate": 4.222572646121723e-06, "epoch": 0.33238185854741514, "percentage": 33.24, "elapsed_time": "10:41:30", "remaining_time": "21:28:24"}
+{"current_steps": 1320, "total_steps": 3941, "loss": 1.209, "learning_rate": 4.2064532358022446e-06, "epoch": 0.33491912464319695, "percentage": 33.49, "elapsed_time": "10:46:32", "remaining_time": "21:23:47"}
+{"current_steps": 1330, "total_steps": 3941, "loss": 1.2069, "learning_rate": 4.190199884391371e-06, "epoch": 0.33745639073897876, "percentage": 33.75, "elapsed_time": "10:51:13", "remaining_time": "21:18:28"}
+{"current_steps": 1340, "total_steps": 3941, "loss": 1.2291, "learning_rate": 4.173813867629672e-06, "epoch": 0.33999365683476057, "percentage": 34.0, "elapsed_time": "10:55:54", "remaining_time": "21:13:09"}
+{"current_steps": 1350, "total_steps": 3941, "loss": 1.1787, "learning_rate": 4.157296471670747e-06, "epoch": 0.3425309229305423, "percentage": 34.26, "elapsed_time": "11:00:35", "remaining_time": "21:07:51"}
+{"current_steps": 1360, "total_steps": 3941, "loss": 1.1972, "learning_rate": 4.140648992980269e-06, "epoch": 0.34506818902632413, "percentage": 34.51, "elapsed_time": "11:05:19", "remaining_time": "21:02:38"}
+{"current_steps": 1370, "total_steps": 3941, "loss": 1.2193, "learning_rate": 4.1238727382342245e-06, "epoch": 0.34760545512210594, "percentage": 34.76, "elapsed_time": "11:09:59", "remaining_time": "20:57:20"}
+{"current_steps": 1380, "total_steps": 3941, "loss": 1.1896, "learning_rate": 4.106969024216348e-06, "epoch": 0.35014272121788775, "percentage": 35.02, "elapsed_time": "11:14:44", "remaining_time": "20:52:11"}
+{"current_steps": 1390, "total_steps": 3941, "loss": 1.1916, "learning_rate": 4.089939177714778e-06, "epoch": 0.3526799873136695, "percentage": 35.27, "elapsed_time": "11:19:27", "remaining_time": "20:46:58"}
+{"current_steps": 1400, "total_steps": 3941, "loss": 1.2037, "learning_rate": 4.0727845354178995e-06, "epoch": 0.3552172534094513, "percentage": 35.52, "elapsed_time": "11:24:08", "remaining_time": "20:41:42"}
+{"current_steps": 1410, "total_steps": 3941, "loss": 1.2243, "learning_rate": 4.055506443809441e-06, "epoch": 0.3577545195052331, "percentage": 35.78, "elapsed_time": "11:28:48", "remaining_time": "20:36:26"}
+{"current_steps": 1420, "total_steps": 3941, "loss": 1.1927, "learning_rate": 4.038106259062778e-06, "epoch": 0.3602917856010149, "percentage": 36.03, "elapsed_time": "11:33:31", "remaining_time": "20:31:14"}
+{"current_steps": 1430, "total_steps": 3941, "loss": 1.2077, "learning_rate": 4.020585346934493e-06, "epoch": 0.3628290516967967, "percentage": 36.29, "elapsed_time": "11:38:10", "remaining_time": "20:25:57"}
+{"current_steps": 1440, "total_steps": 3941, "loss": 1.2, "learning_rate": 4.002945082657167e-06, "epoch": 0.3653663177925785, "percentage": 36.54, "elapsed_time": "11:42:55", "remaining_time": "20:20:50"}
+{"current_steps": 1450, "total_steps": 3941, "loss": 1.1917, "learning_rate": 3.985186850831446e-06, "epoch": 0.3679035838883603, "percentage": 36.79, "elapsed_time": "11:47:36", "remaining_time": "20:15:38"}
+{"current_steps": 1460, "total_steps": 3941, "loss": 1.1917, "learning_rate": 3.967312045317357e-06, "epoch": 0.37044084998414206, "percentage": 37.05, "elapsed_time": "11:52:17", "remaining_time": "20:10:23"}
+{"current_steps": 1470, "total_steps": 3941, "loss": 1.207, "learning_rate": 3.9493220691249e-06, "epoch": 0.37297811607992387, "percentage": 37.3, "elapsed_time": "11:57:04", "remaining_time": "20:05:21"}
+{"current_steps": 1480, "total_steps": 3941, "loss": 1.1963, "learning_rate": 3.931218334303933e-06, "epoch": 0.3755153821757057, "percentage": 37.55, "elapsed_time": "12:01:52", "remaining_time": "20:00:21"}
+{"current_steps": 1490, "total_steps": 3941, "loss": 1.201, "learning_rate": 3.913002261833331e-06, "epoch": 0.3780526482714875, "percentage": 37.81, "elapsed_time": "12:06:32", "remaining_time": "19:55:08"}
+{"current_steps": 1500, "total_steps": 3941, "loss": 1.2088, "learning_rate": 3.894675281509455e-06, "epoch": 0.38058991436726924, "percentage": 38.06, "elapsed_time": "12:11:15", "remaining_time": "19:50:00"}
+{"current_steps": 1510, "total_steps": 3941, "loss": 1.216, "learning_rate": 3.876238831833927e-06, "epoch": 0.38312718046305105, "percentage": 38.32, "elapsed_time": "12:21:18", "remaining_time": "19:53:28"}
+{"current_steps": 1520, "total_steps": 3941, "loss": 1.211, "learning_rate": 3.857694359900719e-06, "epoch": 0.38566444655883286, "percentage": 38.57, "elapsed_time": "12:26:00", "remaining_time": "19:48:12"}
+{"current_steps": 1530, "total_steps": 3941, "loss": 1.173, "learning_rate": 3.83904332128257e-06, "epoch": 0.3882017126546147, "percentage": 38.82, "elapsed_time": "12:30:42", "remaining_time": "19:42:58"}
+{"current_steps": 1540, "total_steps": 3941, "loss": 1.1883, "learning_rate": 3.820287179916736e-06, "epoch": 0.3907389787503964, "percentage": 39.08, "elapsed_time": "12:35:25", "remaining_time": "19:37:47"}
+{"current_steps": 1550, "total_steps": 3941, "loss": 1.2002, "learning_rate": 3.8014274079900842e-06, "epoch": 0.39327624484617824, "percentage": 39.33, "elapsed_time": "12:40:11", "remaining_time": "19:32:39"}
+{"current_steps": 1560, "total_steps": 3941, "loss": 1.2019, "learning_rate": 3.7824654858235433e-06, "epoch": 0.39581351094196005, "percentage": 39.58, "elapsed_time": "12:44:52", "remaining_time": "19:27:24"}
+{"current_steps": 1570, "total_steps": 3941, "loss": 1.1936, "learning_rate": 3.763402901755905e-06, "epoch": 0.39835077703774185, "percentage": 39.84, "elapsed_time": "12:49:33", "remaining_time": "19:22:10"}
+{"current_steps": 1580, "total_steps": 3941, "loss": 1.1872, "learning_rate": 3.7442411520270096e-06, "epoch": 0.4008880431335236, "percentage": 40.09, "elapsed_time": "12:54:15", "remaining_time": "19:16:58"}
+{"current_steps": 1590, "total_steps": 3941, "loss": 1.197, "learning_rate": 3.7249817406602996e-06, "epoch": 0.4034253092293054, "percentage": 40.35, "elapsed_time": "12:58:56", "remaining_time": "19:11:45"}
+{"current_steps": 1600, "total_steps": 3941, "loss": 1.1983, "learning_rate": 3.7056261793447707e-06, "epoch": 0.4059625753250872, "percentage": 40.6, "elapsed_time": "13:03:38", "remaining_time": "19:06:33"}
+{"current_steps": 1610, "total_steps": 3941, "loss": 1.1853, "learning_rate": 3.686175987316317e-06, "epoch": 0.40849984142086904, "percentage": 40.85, "elapsed_time": "13:08:20", "remaining_time": "19:01:22"}
+{"current_steps": 1620, "total_steps": 3941, "loss": 1.1925, "learning_rate": 3.6666326912384854e-06, "epoch": 0.4110371075166508, "percentage": 41.11, "elapsed_time": "13:13:01", "remaining_time": "18:56:10"}
+{"current_steps": 1630, "total_steps": 3941, "loss": 1.1954, "learning_rate": 3.6469978250826433e-06, "epoch": 0.4135743736124326, "percentage": 41.36, "elapsed_time": "13:17:44", "remaining_time": "18:51:01"}
+{"current_steps": 1640, "total_steps": 3941, "loss": 1.209, "learning_rate": 3.6272729300075808e-06, "epoch": 0.4161116397082144, "percentage": 41.61, "elapsed_time": "13:22:26", "remaining_time": "18:45:52"}
+{"current_steps": 1650, "total_steps": 3941, "loss": 1.185, "learning_rate": 3.6074595542385387e-06, "epoch": 0.4186489058039962, "percentage": 41.87, "elapsed_time": "13:27:07", "remaining_time": "18:40:40"}
+{"current_steps": 1660, "total_steps": 3941, "loss": 1.2068, "learning_rate": 3.5875592529456926e-06, "epoch": 0.421186171899778, "percentage": 42.12, "elapsed_time": "13:31:49", "remaining_time": "18:35:31"}
+{"current_steps": 1670, "total_steps": 3941, "loss": 1.1777, "learning_rate": 3.567573588122079e-06, "epoch": 0.4237234379955598, "percentage": 42.38, "elapsed_time": "13:36:30", "remaining_time": "18:30:20"}
+{"current_steps": 1680, "total_steps": 3941, "loss": 1.1843, "learning_rate": 3.5475041284609977e-06, "epoch": 0.4262607040913416, "percentage": 42.63, "elapsed_time": "13:41:11", "remaining_time": "18:25:11"}
+{"current_steps": 1690, "total_steps": 3941, "loss": 1.1777, "learning_rate": 3.527352449232886e-06, "epoch": 0.4287979701871234, "percentage": 42.88, "elapsed_time": "13:45:54", "remaining_time": "18:20:03"}
+{"current_steps": 1700, "total_steps": 3941, "loss": 1.1888, "learning_rate": 3.5071201321616673e-06, "epoch": 0.43133523628290515, "percentage": 43.14, "elapsed_time": "13:50:38", "remaining_time": "18:14:58"}
+{"current_steps": 1710, "total_steps": 3941, "loss": 1.1901, "learning_rate": 3.4868087653006045e-06, "epoch": 0.43387250237868696, "percentage": 43.39, "elapsed_time": "13:55:20", "remaining_time": "18:09:50"}
+{"current_steps": 1720, "total_steps": 3941, "loss": 1.2107, "learning_rate": 3.466419942907652e-06, "epoch": 0.4364097684744688, "percentage": 43.64, "elapsed_time": "14:00:01", "remaining_time": "18:04:42"}
+{"current_steps": 1730, "total_steps": 3941, "loss": 1.1918, "learning_rate": 3.445955265320321e-06, "epoch": 0.4389470345702506, "percentage": 43.9, "elapsed_time": "14:04:42", "remaining_time": "17:59:34"}
+{"current_steps": 1740, "total_steps": 3941, "loss": 1.189, "learning_rate": 3.425416338830067e-06, "epoch": 0.44148430066603234, "percentage": 44.15, "elapsed_time": "14:09:24", "remaining_time": "17:54:26"}
+{"current_steps": 1750, "total_steps": 3941, "loss": 1.183, "learning_rate": 3.4048047755562093e-06, "epoch": 0.44402156676181415, "percentage": 44.4, "elapsed_time": "14:14:10", "remaining_time": "17:49:26"}
+{"current_steps": 1760, "total_steps": 3941, "loss": 1.1882, "learning_rate": 3.3841221933193965e-06, "epoch": 0.44655883285759596, "percentage": 44.66, "elapsed_time": "14:18:58", "remaining_time": "17:44:26"}
+{"current_steps": 1770, "total_steps": 3941, "loss": 1.1911, "learning_rate": 3.3633702155146216e-06, "epoch": 0.4490960989533777, "percentage": 44.91, "elapsed_time": "14:23:39", "remaining_time": "17:39:19"}
+{"current_steps": 1780, "total_steps": 3941, "loss": 1.1811, "learning_rate": 3.342550470983798e-06, "epoch": 0.4516333650491595, "percentage": 45.17, "elapsed_time": "14:28:22", "remaining_time": "17:34:15"}
+{"current_steps": 1790, "total_steps": 3941, "loss": 1.1865, "learning_rate": 3.3216645938879134e-06, "epoch": 0.45417063114494133, "percentage": 45.42, "elapsed_time": "14:33:06", "remaining_time": "17:29:11"}
+{"current_steps": 1800, "total_steps": 3941, "loss": 1.1842, "learning_rate": 3.3007142235787624e-06, "epoch": 0.45670789724072314, "percentage": 45.67, "elapsed_time": "14:37:46", "remaining_time": "17:24:04"}
+{"current_steps": 1810, "total_steps": 3941, "loss": 1.1776, "learning_rate": 3.2797010044702697e-06, "epoch": 0.4592451633365049, "percentage": 45.93, "elapsed_time": "14:42:28", "remaining_time": "17:18:58"}
+{"current_steps": 1820, "total_steps": 3941, "loss": 1.1917, "learning_rate": 3.258626585909422e-06, "epoch": 0.4617824294322867, "percentage": 46.18, "elapsed_time": "14:47:10", "remaining_time": "17:13:53"}
+{"current_steps": 1830, "total_steps": 3941, "loss": 1.1789, "learning_rate": 3.2374926220468067e-06, "epoch": 0.4643196955280685, "percentage": 46.43, "elapsed_time": "14:51:51", "remaining_time": "17:08:48"}
+{"current_steps": 1840, "total_steps": 3941, "loss": 1.1733, "learning_rate": 3.216300771706776e-06, "epoch": 0.4668569616238503, "percentage": 46.69, "elapsed_time": "14:56:36", "remaining_time": "17:03:47"}
+{"current_steps": 1850, "total_steps": 3941, "loss": 1.1712, "learning_rate": 3.1950526982572484e-06, "epoch": 0.4693942277196321, "percentage": 46.94, "elapsed_time": "15:01:18", "remaining_time": "16:58:43"}
+{"current_steps": 1860, "total_steps": 3941, "loss": 1.1815, "learning_rate": 3.1737500694791424e-06, "epoch": 0.4719314938154139, "percentage": 47.2, "elapsed_time": "15:05:58", "remaining_time": "16:53:37"}
+{"current_steps": 1870, "total_steps": 3941, "loss": 1.1863, "learning_rate": 3.1523945574354763e-06, "epoch": 0.4744687599111957, "percentage": 47.45, "elapsed_time": "15:10:40", "remaining_time": "16:48:33"}
+{"current_steps": 1880, "total_steps": 3941, "loss": 1.1834, "learning_rate": 3.130987838340126e-06, "epoch": 0.4770060260069775, "percentage": 47.7, "elapsed_time": "15:15:23", "remaining_time": "16:43:31"}
+{"current_steps": 1890, "total_steps": 3941, "loss": 1.184, "learning_rate": 3.1095315924262544e-06, "epoch": 0.47954329210275926, "percentage": 47.96, "elapsed_time": "15:20:08", "remaining_time": "16:38:30"}
+{"current_steps": 1900, "total_steps": 3941, "loss": 1.1748, "learning_rate": 3.0880275038144296e-06, "epoch": 0.48208055819854106, "percentage": 48.21, "elapsed_time": "15:24:49", "remaining_time": "16:33:27"}
+{"current_steps": 1910, "total_steps": 3941, "loss": 1.1647, "learning_rate": 3.066477260380441e-06, "epoch": 0.4846178242943229, "percentage": 48.46, "elapsed_time": "15:29:29", "remaining_time": "16:28:22"}
+{"current_steps": 1920, "total_steps": 3941, "loss": 1.1906, "learning_rate": 3.044882553622808e-06, "epoch": 0.4871550903901047, "percentage": 48.72, "elapsed_time": "15:34:10", "remaining_time": "16:23:18"}
+{"current_steps": 1930, "total_steps": 3941, "loss": 1.1653, "learning_rate": 3.0232450785300207e-06, "epoch": 0.48969235648588644, "percentage": 48.97, "elapsed_time": "15:38:53", "remaining_time": "16:18:17"}
+{"current_steps": 1940, "total_steps": 3941, "loss": 1.1869, "learning_rate": 3.0015665334474937e-06, "epoch": 0.49222962258166825, "percentage": 49.23, "elapsed_time": "15:43:34", "remaining_time": "16:13:14"}
+{"current_steps": 1950, "total_steps": 3941, "loss": 1.1707, "learning_rate": 2.9798486199442627e-06, "epoch": 0.49476688867745006, "percentage": 49.48, "elapsed_time": "15:48:16", "remaining_time": "16:08:12"}
+{"current_steps": 1960, "total_steps": 3941, "loss": 1.192, "learning_rate": 2.958093042679429e-06, "epoch": 0.49730415477323187, "percentage": 49.73, "elapsed_time": "15:53:00", "remaining_time": "16:03:12"}
+{"current_steps": 1970, "total_steps": 3941, "loss": 1.1762, "learning_rate": 2.9363015092683566e-06, "epoch": 0.4998414208690136, "percentage": 49.99, "elapsed_time": "15:57:41", "remaining_time": "15:58:10"}
+{"current_steps": 1980, "total_steps": 3941, "loss": 1.169, "learning_rate": 2.9144757301486387e-06, "epoch": 0.5023786869647955, "percentage": 50.24, "elapsed_time": "16:02:22", "remaining_time": "15:53:08"}
+{"current_steps": 1990, "total_steps": 3941, "loss": 1.174, "learning_rate": 2.8926174184458484e-06, "epoch": 0.5049159530605772, "percentage": 50.49, "elapsed_time": "16:07:04", "remaining_time": "15:48:07"}
+{"current_steps": 2000, "total_steps": 3941, "loss": 1.1596, "learning_rate": 2.8707282898390703e-06, "epoch": 0.507453219156359, "percentage": 50.75, "elapsed_time": "16:11:49", "remaining_time": "15:43:09"}
+{"current_steps": 2010, "total_steps": 3941, "loss": 1.1636, "learning_rate": 2.848810062426236e-06, "epoch": 0.5099904852521409, "percentage": 51.0, "elapsed_time": "16:23:27", "remaining_time": "15:44:47"}
+{"current_steps": 2020, "total_steps": 3941, "loss": 1.1622, "learning_rate": 2.82686445658927e-06, "epoch": 0.5125277513479226, "percentage": 51.26, "elapsed_time": "16:28:08", "remaining_time": "15:39:42"}
+{"current_steps": 2030, "total_steps": 3941, "loss": 1.1679, "learning_rate": 2.8048931948590537e-06, "epoch": 0.5150650174437044, "percentage": 51.51, "elapsed_time": "16:32:50", "remaining_time": "15:34:38"}
+{"current_steps": 2040, "total_steps": 3941, "loss": 1.1883, "learning_rate": 2.7828980017802236e-06, "epoch": 0.5176022835394862, "percentage": 51.76, "elapsed_time": "16:37:31", "remaining_time": "15:29:33"}
+{"current_steps": 2050, "total_steps": 3941, "loss": 1.173, "learning_rate": 2.760880603775811e-06, "epoch": 0.520139549635268, "percentage": 52.02, "elapsed_time": "16:42:11", "remaining_time": "15:24:27"}
+{"current_steps": 2060, "total_steps": 3941, "loss": 1.191, "learning_rate": 2.73884272901173e-06, "epoch": 0.5226768157310498, "percentage": 52.27, "elapsed_time": "16:46:52", "remaining_time": "15:19:22"}
+{"current_steps": 2070, "total_steps": 3941, "loss": 1.1717, "learning_rate": 2.7167861072611374e-06, "epoch": 0.5252140818268316, "percentage": 52.52, "elapsed_time": "16:51:34", "remaining_time": "15:14:19"}
+{"current_steps": 2080, "total_steps": 3941, "loss": 1.1638, "learning_rate": 2.6947124697686553e-06, "epoch": 0.5277513479226134, "percentage": 52.78, "elapsed_time": "16:56:16", "remaining_time": "15:09:16"}
+{"current_steps": 2090, "total_steps": 3941, "loss": 1.1682, "learning_rate": 2.6726235491144886e-06, "epoch": 0.5302886140183952, "percentage": 53.03, "elapsed_time": "17:00:57", "remaining_time": "15:04:12"}
+{"current_steps": 2100, "total_steps": 3941, "loss": 1.1645, "learning_rate": 2.650521079078433e-06, "epoch": 0.532825880114177, "percentage": 53.29, "elapsed_time": "17:05:39", "remaining_time": "14:59:09"}
+{"current_steps": 2110, "total_steps": 3941, "loss": 1.1646, "learning_rate": 2.6284067945037855e-06, "epoch": 0.5353631462099587, "percentage": 53.54, "elapsed_time": "17:10:21", "remaining_time": "14:54:06"}
+{"current_steps": 2120, "total_steps": 3941, "loss": 1.1705, "learning_rate": 2.6062824311611775e-06, "epoch": 0.5379004123057406, "percentage": 53.79, "elapsed_time": "17:15:03", "remaining_time": "14:49:04"}
+{"current_steps": 2130, "total_steps": 3941, "loss": 1.1573, "learning_rate": 2.5841497256123326e-06, "epoch": 0.5404376784015223, "percentage": 54.05, "elapsed_time": "17:19:44", "remaining_time": "14:44:01"}
+{"current_steps": 2140, "total_steps": 3941, "loss": 1.165, "learning_rate": 2.5620104150737626e-06, "epoch": 0.5429749444973041, "percentage": 54.3, "elapsed_time": "17:24:24", "remaining_time": "14:38:57"}
+{"current_steps": 2150, "total_steps": 3941, "loss": 1.1701, "learning_rate": 2.5398662372804105e-06, "epoch": 0.545512210593086, "percentage": 54.55, "elapsed_time": "17:29:05", "remaining_time": "14:33:54"}
+{"current_steps": 2160, "total_steps": 3941, "loss": 1.1475, "learning_rate": 2.517718930349254e-06, "epoch": 0.5480494766888677, "percentage": 54.81, "elapsed_time": "17:33:46", "remaining_time": "14:28:52"}
+{"current_steps": 2170, "total_steps": 3941, "loss": 1.1483, "learning_rate": 2.495570232642881e-06, "epoch": 0.5505867427846496, "percentage": 55.06, "elapsed_time": "17:38:26", "remaining_time": "14:23:49"}
+{"current_steps": 2180, "total_steps": 3941, "loss": 1.1689, "learning_rate": 2.47342188263304e-06, "epoch": 0.5531240088804313, "percentage": 55.32, "elapsed_time": "17:43:10", "remaining_time": "14:18:49"}
+{"current_steps": 2190, "total_steps": 3941, "loss": 1.1614, "learning_rate": 2.4512756187641936e-06, "epoch": 0.5556612749762131, "percentage": 55.57, "elapsed_time": "17:47:51", "remaining_time": "14:13:48"}
+{"current_steps": 2200, "total_steps": 3941, "loss": 1.1606, "learning_rate": 2.4291331793170545e-06, "epoch": 0.558198541071995, "percentage": 55.82, "elapsed_time": "17:52:32", "remaining_time": "14:08:46"}
+{"current_steps": 2210, "total_steps": 3941, "loss": 1.1817, "learning_rate": 2.4069963022721597e-06, "epoch": 0.5607358071677767, "percentage": 56.08, "elapsed_time": "17:57:13", "remaining_time": "14:03:45"}
+{"current_steps": 2220, "total_steps": 3941, "loss": 1.1682, "learning_rate": 2.3848667251734424e-06, "epoch": 0.5632730732635585, "percentage": 56.33, "elapsed_time": "18:01:54", "remaining_time": "13:58:43"}
+{"current_steps": 2230, "total_steps": 3941, "loss": 1.1526, "learning_rate": 2.3627461849918604e-06, "epoch": 0.5658103393593403, "percentage": 56.58, "elapsed_time": "18:06:35", "remaining_time": "13:53:42"}
+{"current_steps": 2240, "total_steps": 3941, "loss": 1.1562, "learning_rate": 2.3406364179890532e-06, "epoch": 0.5683476054551221, "percentage": 56.84, "elapsed_time": "18:11:19", "remaining_time": "13:48:43"}
+{"current_steps": 2250, "total_steps": 3941, "loss": 1.1592, "learning_rate": 2.3185391595810635e-06, "epoch": 0.570884871550904, "percentage": 57.09, "elapsed_time": "18:15:59", "remaining_time": "13:43:41"}
+{"current_steps": 2260, "total_steps": 3941, "loss": 1.1432, "learning_rate": 2.2964561442021255e-06, "epoch": 0.5734221376466857, "percentage": 57.35, "elapsed_time": "18:20:41", "remaining_time": "13:38:41"}
+{"current_steps": 2270, "total_steps": 3941, "loss": 1.1594, "learning_rate": 2.2743891051685222e-06, "epoch": 0.5759594037424675, "percentage": 57.6, "elapsed_time": "18:25:25", "remaining_time": "13:33:43"}
+{"current_steps": 2280, "total_steps": 3941, "loss": 1.1627, "learning_rate": 2.2523397745425387e-06, "epoch": 0.5784966698382493, "percentage": 57.85, "elapsed_time": "18:30:07", "remaining_time": "13:28:44"}
+{"current_steps": 2290, "total_steps": 3941, "loss": 1.1669, "learning_rate": 2.2303098829965124e-06, "epoch": 0.5810339359340311, "percentage": 58.11, "elapsed_time": "18:34:51", "remaining_time": "13:23:46"}
+{"current_steps": 2300, "total_steps": 3941, "loss": 1.1631, "learning_rate": 2.208301159676987e-06, "epoch": 0.5835712020298128, "percentage": 58.36, "elapsed_time": "18:39:36", "remaining_time": "13:18:49"}
+{"current_steps": 2310, "total_steps": 3941, "loss": 1.1435, "learning_rate": 2.1863153320689958e-06, "epoch": 0.5861084681255947, "percentage": 58.61, "elapsed_time": "18:44:17", "remaining_time": "13:13:49"}
+{"current_steps": 2320, "total_steps": 3941, "loss": 1.1499, "learning_rate": 2.164354125860462e-06, "epoch": 0.5886457342213764, "percentage": 58.87, "elapsed_time": "18:49:00", "remaining_time": "13:08:50"}
+{"current_steps": 2330, "total_steps": 3941, "loss": 1.1832, "learning_rate": 2.1424192648067582e-06, "epoch": 0.5911830003171583, "percentage": 59.12, "elapsed_time": "18:53:42", "remaining_time": "13:03:51"}
+{"current_steps": 2340, "total_steps": 3941, "loss": 1.1503, "learning_rate": 2.120512470595396e-06, "epoch": 0.5937202664129401, "percentage": 59.38, "elapsed_time": "18:58:23", "remaining_time": "12:58:52"}
+{"current_steps": 2350, "total_steps": 3941, "loss": 1.1601, "learning_rate": 2.098635462710898e-06, "epoch": 0.5962575325087218, "percentage": 59.63, "elapsed_time": "19:03:06", "remaining_time": "12:53:54"}
+{"current_steps": 2360, "total_steps": 3941, "loss": 1.1641, "learning_rate": 2.0767899582998293e-06, "epoch": 0.5987947986045037, "percentage": 59.88, "elapsed_time": "19:07:49", "remaining_time": "12:48:56"}
+{"current_steps": 2370, "total_steps": 3941, "loss": 1.1417, "learning_rate": 2.054977672036018e-06, "epoch": 0.6013320647002854, "percentage": 60.14, "elapsed_time": "19:12:30", "remaining_time": "12:43:57"}
+{"current_steps": 2380, "total_steps": 3941, "loss": 1.1482, "learning_rate": 2.033200315985969e-06, "epoch": 0.6038693307960672, "percentage": 60.39, "elapsed_time": "19:17:11", "remaining_time": "12:38:58"}
+{"current_steps": 2390, "total_steps": 3941, "loss": 1.1497, "learning_rate": 2.011459599474483e-06, "epoch": 0.6064065968918491, "percentage": 60.64, "elapsed_time": "19:21:52", "remaining_time": "12:33:59"}
+{"current_steps": 2400, "total_steps": 3941, "loss": 1.1583, "learning_rate": 1.989757228950491e-06, "epoch": 0.6089438629876308, "percentage": 60.9, "elapsed_time": "19:26:32", "remaining_time": "12:29:00"}
+{"current_steps": 2410, "total_steps": 3941, "loss": 1.1528, "learning_rate": 1.9680949078531097e-06, "epoch": 0.6114811290834127, "percentage": 61.15, "elapsed_time": "19:31:14", "remaining_time": "12:24:03"}
+{"current_steps": 2420, "total_steps": 3941, "loss": 1.1594, "learning_rate": 1.9464743364779388e-06, "epoch": 0.6140183951791944, "percentage": 61.41, "elapsed_time": "19:35:59", "remaining_time": "12:19:07"}
+{"current_steps": 2430, "total_steps": 3941, "loss": 1.1428, "learning_rate": 1.924897211843606e-06, "epoch": 0.6165556612749762, "percentage": 61.66, "elapsed_time": "19:40:41", "remaining_time": "12:14:09"}
+{"current_steps": 2440, "total_steps": 3941, "loss": 1.1321, "learning_rate": 1.9033652275585624e-06, "epoch": 0.619092927370758, "percentage": 61.91, "elapsed_time": "19:45:23", "remaining_time": "12:09:12"}
+{"current_steps": 2450, "total_steps": 3941, "loss": 1.1568, "learning_rate": 1.8818800736881518e-06, "epoch": 0.6216301934665398, "percentage": 62.17, "elapsed_time": "19:50:04", "remaining_time": "12:04:14"}
+{"current_steps": 2460, "total_steps": 3941, "loss": 1.1594, "learning_rate": 1.8604434366219573e-06, "epoch": 0.6241674595623216, "percentage": 62.42, "elapsed_time": "19:54:46", "remaining_time": "11:59:17"}
+{"current_steps": 2470, "total_steps": 3941, "loss": 1.1588, "learning_rate": 1.8390569989414303e-06, "epoch": 0.6267047256581034, "percentage": 62.67, "elapsed_time": "19:59:29", "remaining_time": "11:54:21"}
+{"current_steps": 2480, "total_steps": 3941, "loss": 1.1535, "learning_rate": 1.8177224392878279e-06, "epoch": 0.6292419917538852, "percentage": 62.93, "elapsed_time": "20:04:10", "remaining_time": "11:49:23"}
+{"current_steps": 2490, "total_steps": 3941, "loss": 1.1339, "learning_rate": 1.7964414322304525e-06, "epoch": 0.6317792578496669, "percentage": 63.18, "elapsed_time": "20:08:53", "remaining_time": "11:44:27"}
+{"current_steps": 2500, "total_steps": 3941, "loss": 1.1388, "learning_rate": 1.7752156481352123e-06, "epoch": 0.6343165239454488, "percentage": 63.44, "elapsed_time": "20:13:34", "remaining_time": "11:39:30"}
+{"current_steps": 2510, "total_steps": 3941, "loss": 1.1374, "learning_rate": 1.7540467530335172e-06, "epoch": 0.6368537900412305, "percentage": 63.69, "elapsed_time": "20:24:28", "remaining_time": "11:38:05"}
+{"current_steps": 2520, "total_steps": 3941, "loss": 1.1587, "learning_rate": 1.732936408491504e-06, "epoch": 0.6393910561370124, "percentage": 63.94, "elapsed_time": "20:29:09", "remaining_time": "11:33:06"}
+{"current_steps": 2530, "total_steps": 3941, "loss": 1.1572, "learning_rate": 1.7118862714796253e-06, "epoch": 0.6419283222327942, "percentage": 64.2, "elapsed_time": "20:33:50", "remaining_time": "11:28:07"}
+{"current_steps": 2540, "total_steps": 3941, "loss": 1.141, "learning_rate": 1.6908979942425868e-06, "epoch": 0.6444655883285759, "percentage": 64.45, "elapsed_time": "20:38:33", "remaining_time": "11:23:09"}
+{"current_steps": 2550, "total_steps": 3941, "loss": 1.1581, "learning_rate": 1.6699732241696636e-06, "epoch": 0.6470028544243578, "percentage": 64.7, "elapsed_time": "20:43:14", "remaining_time": "11:18:10"}
+{"current_steps": 2560, "total_steps": 3941, "loss": 1.1466, "learning_rate": 1.649113603665396e-06, "epoch": 0.6495401205201395, "percentage": 64.96, "elapsed_time": "20:47:56", "remaining_time": "11:13:12"}
+{"current_steps": 2570, "total_steps": 3941, "loss": 1.1615, "learning_rate": 1.628320770020673e-06, "epoch": 0.6520773866159213, "percentage": 65.21, "elapsed_time": "20:52:38", "remaining_time": "11:08:14"}
+{"current_steps": 2580, "total_steps": 3941, "loss": 1.1641, "learning_rate": 1.6075963552842211e-06, "epoch": 0.6546146527117032, "percentage": 65.47, "elapsed_time": "20:57:22", "remaining_time": "11:03:17"}
+{"current_steps": 2590, "total_steps": 3941, "loss": 1.142, "learning_rate": 1.5869419861345042e-06, "epoch": 0.6571519188074849, "percentage": 65.72, "elapsed_time": "21:02:06", "remaining_time": "10:58:20"}
+{"current_steps": 2600, "total_steps": 3941, "loss": 1.1469, "learning_rate": 1.5663592837520453e-06, "epoch": 0.6596891849032668, "percentage": 65.97, "elapsed_time": "21:06:47", "remaining_time": "10:53:22"}
+{"current_steps": 2610, "total_steps": 3941, "loss": 1.1598, "learning_rate": 1.5458498636921727e-06, "epoch": 0.6622264509990485, "percentage": 66.23, "elapsed_time": "21:11:29", "remaining_time": "10:48:24"}
+{"current_steps": 2620, "total_steps": 3941, "loss": 1.1582, "learning_rate": 1.5254153357582208e-06, "epoch": 0.6647637170948303, "percentage": 66.48, "elapsed_time": "21:16:09", "remaining_time": "10:43:26"}
+{"current_steps": 2630, "total_steps": 3941, "loss": 1.1452, "learning_rate": 1.5050573038751693e-06, "epoch": 0.6673009831906122, "percentage": 66.73, "elapsed_time": "21:20:50", "remaining_time": "10:38:28"}
+{"current_steps": 2640, "total_steps": 3941, "loss": 1.1297, "learning_rate": 1.4847773659637546e-06, "epoch": 0.6698382492863939, "percentage": 66.99, "elapsed_time": "21:25:34", "remaining_time": "10:33:32"}
+{"current_steps": 2650, "total_steps": 3941, "loss": 1.1603, "learning_rate": 1.4645771138150433e-06, "epoch": 0.6723755153821757, "percentage": 67.24, "elapsed_time": "21:30:14", "remaining_time": "10:28:34"}
+{"current_steps": 2660, "total_steps": 3941, "loss": 1.1439, "learning_rate": 1.4444581329654916e-06, "epoch": 0.6749127814779575, "percentage": 67.5, "elapsed_time": "21:34:57", "remaining_time": "10:23:37"}
+{"current_steps": 2670, "total_steps": 3941, "loss": 1.1749, "learning_rate": 1.424422002572502e-06, "epoch": 0.6774500475737393, "percentage": 67.75, "elapsed_time": "21:39:38", "remaining_time": "10:18:40"}
+{"current_steps": 2680, "total_steps": 3941, "loss": 1.1545, "learning_rate": 1.404470295290461e-06, "epoch": 0.6799873136695211, "percentage": 68.0, "elapsed_time": "21:44:21", "remaining_time": "10:13:43"}
+{"current_steps": 2690, "total_steps": 3941, "loss": 1.149, "learning_rate": 1.3846045771473116e-06, "epoch": 0.6825245797653029, "percentage": 68.26, "elapsed_time": "21:49:02", "remaining_time": "10:08:46"}
+{"current_steps": 2700, "total_steps": 3941, "loss": 1.1394, "learning_rate": 1.3648264074216282e-06, "epoch": 0.6850618458610847, "percentage": 68.51, "elapsed_time": "21:53:43", "remaining_time": "10:03:49"}
+{"current_steps": 2710, "total_steps": 3941, "loss": 1.1463, "learning_rate": 1.345137338520231e-06, "epoch": 0.6875991119568665, "percentage": 68.76, "elapsed_time": "21:58:24", "remaining_time": "9:58:52"}
+{"current_steps": 2720, "total_steps": 3941, "loss": 1.1521, "learning_rate": 1.3255389158563299e-06, "epoch": 0.6901363780526483, "percentage": 69.02, "elapsed_time": "22:03:06", "remaining_time": "9:53:56"}
+{"current_steps": 2730, "total_steps": 3941, "loss": 1.1437, "learning_rate": 1.3060326777282312e-06, "epoch": 0.69267364414843, "percentage": 69.27, "elapsed_time": "22:07:47", "remaining_time": "9:48:59"}
+{"current_steps": 2740, "total_steps": 3941, "loss": 1.1394, "learning_rate": 1.2866201551985935e-06, "epoch": 0.6952109102442119, "percentage": 69.53, "elapsed_time": "22:12:28", "remaining_time": "9:44:03"}
+{"current_steps": 2750, "total_steps": 3941, "loss": 1.1455, "learning_rate": 1.2673028719742461e-06, "epoch": 0.6977481763399936, "percentage": 69.78, "elapsed_time": "22:17:09", "remaining_time": "9:39:06"}
+{"current_steps": 2760, "total_steps": 3941, "loss": 1.1401, "learning_rate": 1.2480823442866017e-06, "epoch": 0.7002854424357755, "percentage": 70.03, "elapsed_time": "22:21:53", "remaining_time": "9:34:11"}
+{"current_steps": 2770, "total_steps": 3941, "loss": 1.156, "learning_rate": 1.2289600807726406e-06, "epoch": 0.7028227085315573, "percentage": 70.29, "elapsed_time": "22:26:34", "remaining_time": "9:29:15"}
+{"current_steps": 2780, "total_steps": 3941, "loss": 1.1615, "learning_rate": 1.2099375823564948e-06, "epoch": 0.705359974627339, "percentage": 70.54, "elapsed_time": "22:31:14", "remaining_time": "9:24:18"}
+{"current_steps": 2790, "total_steps": 3941, "loss": 1.1321, "learning_rate": 1.1910163421316447e-06, "epoch": 0.7078972407231209, "percentage": 70.79, "elapsed_time": "22:35:54", "remaining_time": "9:19:22"}
+{"current_steps": 2800, "total_steps": 3941, "loss": 1.153, "learning_rate": 1.1721978452437205e-06, "epoch": 0.7104345068189026, "percentage": 71.05, "elapsed_time": "22:40:35", "remaining_time": "9:14:26"}
+{"current_steps": 2810, "total_steps": 3941, "loss": 1.1551, "learning_rate": 1.1534835687739323e-06, "epoch": 0.7129717729146844, "percentage": 71.3, "elapsed_time": "22:45:17", "remaining_time": "9:09:31"}
+{"current_steps": 2820, "total_steps": 3941, "loss": 1.12, "learning_rate": 1.1348749816231347e-06, "epoch": 0.7155090390104663, "percentage": 71.56, "elapsed_time": "22:50:00", "remaining_time": "9:04:35"}
+{"current_steps": 2830, "total_steps": 3941, "loss": 1.1684, "learning_rate": 1.1163735443965298e-06, "epoch": 0.718046305106248, "percentage": 71.81, "elapsed_time": "22:54:45", "remaining_time": "8:59:41"}
+{"current_steps": 2840, "total_steps": 3941, "loss": 1.1414, "learning_rate": 1.0979807092890205e-06, "epoch": 0.7205835712020298, "percentage": 72.06, "elapsed_time": "22:59:26", "remaining_time": "8:54:46"}
+{"current_steps": 2850, "total_steps": 3941, "loss": 1.1355, "learning_rate": 1.079697919971232e-06, "epoch": 0.7231208372978116, "percentage": 72.32, "elapsed_time": "23:04:08", "remaining_time": "8:49:51"}
+{"current_steps": 2860, "total_steps": 3941, "loss": 1.122, "learning_rate": 1.0615266114761932e-06, "epoch": 0.7256581033935934, "percentage": 72.57, "elapsed_time": "23:08:49", "remaining_time": "8:44:56"}
+{"current_steps": 2870, "total_steps": 3941, "loss": 1.1422, "learning_rate": 1.0434682100866995e-06, "epoch": 0.7281953694893752, "percentage": 72.82, "elapsed_time": "23:13:30", "remaining_time": "8:40:00"}
+{"current_steps": 2880, "total_steps": 3941, "loss": 1.1312, "learning_rate": 1.0255241332233636e-06, "epoch": 0.730732635585157, "percentage": 73.08, "elapsed_time": "23:18:12", "remaining_time": "8:35:06"}
+{"current_steps": 2890, "total_steps": 3941, "loss": 1.1271, "learning_rate": 1.0076957893333602e-06, "epoch": 0.7332699016809388, "percentage": 73.33, "elapsed_time": "23:22:53", "remaining_time": "8:30:11"}
+{"current_steps": 2900, "total_steps": 3941, "loss": 1.154, "learning_rate": 9.899845777798777e-07, "epoch": 0.7358071677767206, "percentage": 73.59, "elapsed_time": "23:27:35", "remaining_time": "8:25:16"}
+{"current_steps": 2910, "total_steps": 3941, "loss": 1.1359, "learning_rate": 9.723918887322757e-07, "epoch": 0.7383444338725024, "percentage": 73.84, "elapsed_time": "23:32:16", "remaining_time": "8:20:21"}
+{"current_steps": 2920, "total_steps": 3941, "loss": 1.1313, "learning_rate": 9.549191030569751e-07, "epoch": 0.7408816999682841, "percentage": 74.09, "elapsed_time": "23:36:57", "remaining_time": "8:15:27"}
+{"current_steps": 2930, "total_steps": 3941, "loss": 1.1319, "learning_rate": 9.375675922090707e-07, "epoch": 0.743418966064066, "percentage": 74.35, "elapsed_time": "23:41:39", "remaining_time": "8:10:32"}
+{"current_steps": 2940, "total_steps": 3941, "loss": 1.1399, "learning_rate": 9.203387181246831e-07, "epoch": 0.7459562321598477, "percentage": 74.6, "elapsed_time": "23:46:20", "remaining_time": "8:05:38"}
+{"current_steps": 2950, "total_steps": 3941, "loss": 1.158, "learning_rate": 9.032338331140603e-07, "epoch": 0.7484934982556296, "percentage": 74.85, "elapsed_time": "23:51:01", "remaining_time": "8:00:43"}
+{"current_steps": 2960, "total_steps": 3941, "loss": 1.1486, "learning_rate": 8.862542797554341e-07, "epoch": 0.7510307643514114, "percentage": 75.11, "elapsed_time": "23:55:46", "remaining_time": "7:55:50"}
+{"current_steps": 2970, "total_steps": 3941, "loss": 1.1461, "learning_rate": 8.694013907896363e-07, "epoch": 0.7535680304471931, "percentage": 75.36, "elapsed_time": "1 day, 0:00:30", "remaining_time": "7:50:57"}
+{"current_steps": 2980, "total_steps": 3941, "loss": 1.1353, "learning_rate": 8.526764890154965e-07, "epoch": 0.756105296542975, "percentage": 75.62, "elapsed_time": "1 day, 0:05:11", "remaining_time": "7:46:02"}
+{"current_steps": 2990, "total_steps": 3941, "loss": 1.1553, "learning_rate": 8.36080887186011e-07, "epoch": 0.7586425626387567, "percentage": 75.87, "elapsed_time": "1 day, 0:09:54", "remaining_time": "7:41:09"}
+{"current_steps": 3000, "total_steps": 3941, "loss": 1.1598, "learning_rate": 8.19615887905301e-07, "epoch": 0.7611798287345385, "percentage": 76.12, "elapsed_time": "1 day, 0:14:35", "remaining_time": "7:36:15"}
+{"current_steps": 3010, "total_steps": 3941, "loss": 1.1318, "learning_rate": 8.032827835263773e-07, "epoch": 0.7637170948303204, "percentage": 76.38, "elapsed_time": "1 day, 0:27:04", "remaining_time": "7:33:46"}
+{"current_steps": 3020, "total_steps": 3941, "loss": 1.1188, "learning_rate": 7.87082856049696e-07, "epoch": 0.7662543609261021, "percentage": 76.63, "elapsed_time": "1 day, 0:31:47", "remaining_time": "7:28:50"}
+{"current_steps": 3030, "total_steps": 3941, "loss": 1.1351, "learning_rate": 7.710173770225335e-07, "epoch": 0.768791627021884, "percentage": 76.88, "elapsed_time": "1 day, 0:36:32", "remaining_time": "7:23:56"}
+{"current_steps": 3040, "total_steps": 3941, "loss": 1.1388, "learning_rate": 7.550876074391852e-07, "epoch": 0.7713288931176657, "percentage": 77.14, "elapsed_time": "1 day, 0:41:18", "remaining_time": "7:19:01"}
+{"current_steps": 3050, "total_steps": 3941, "loss": 1.1307, "learning_rate": 7.392947976419867e-07, "epoch": 0.7738661592134475, "percentage": 77.39, "elapsed_time": "1 day, 0:46:03", "remaining_time": "7:14:07"}
+{"current_steps": 3060, "total_steps": 3941, "loss": 1.1442, "learning_rate": 7.23640187223173e-07, "epoch": 0.7764034253092293, "percentage": 77.65, "elapsed_time": "1 day, 0:50:48", "remaining_time": "7:09:12"}
+{"current_steps": 3070, "total_steps": 3941, "loss": 1.147, "learning_rate": 7.081250049275804e-07, "epoch": 0.7789406914050111, "percentage": 77.9, "elapsed_time": "1 day, 0:55:29", "remaining_time": "7:04:17"}
+{"current_steps": 3080, "total_steps": 3941, "loss": 1.1461, "learning_rate": 6.927504685562075e-07, "epoch": 0.7814779575007929, "percentage": 78.15, "elapsed_time": "1 day, 1:00:11", "remaining_time": "6:59:22"}
+{"current_steps": 3090, "total_steps": 3941, "loss": 1.1272, "learning_rate": 6.775177848706193e-07, "epoch": 0.7840152235965747, "percentage": 78.41, "elapsed_time": "1 day, 1:04:52", "remaining_time": "6:54:27"}
+{"current_steps": 3100, "total_steps": 3941, "loss": 1.1478, "learning_rate": 6.624281494982359e-07, "epoch": 0.7865524896923565, "percentage": 78.66, "elapsed_time": "1 day, 1:09:34", "remaining_time": "6:49:32"}
+{"current_steps": 3110, "total_steps": 3941, "loss": 1.1411, "learning_rate": 6.474827468384811e-07, "epoch": 0.7890897557881383, "percentage": 78.91, "elapsed_time": "1 day, 1:14:16", "remaining_time": "6:44:36"}
+{"current_steps": 3120, "total_steps": 3941, "loss": 1.128, "learning_rate": 6.326827499698218e-07, "epoch": 0.7916270218839201, "percentage": 79.17, "elapsed_time": "1 day, 1:18:59", "remaining_time": "6:39:42"}
+{"current_steps": 3130, "total_steps": 3941, "loss": 1.1503, "learning_rate": 6.180293205576873e-07, "epoch": 0.7941642879797018, "percentage": 79.42, "elapsed_time": "1 day, 1:23:43", "remaining_time": "6:34:48"}
+{"current_steps": 3140, "total_steps": 3941, "loss": 1.1305, "learning_rate": 6.035236087632928e-07, "epoch": 0.7967015540754837, "percentage": 79.68, "elapsed_time": "1 day, 1:28:24", "remaining_time": "6:29:53"}
+{"current_steps": 3150, "total_steps": 3941, "loss": 1.1624, "learning_rate": 5.891667531533643e-07, "epoch": 0.7992388201712655, "percentage": 79.93, "elapsed_time": "1 day, 1:33:04", "remaining_time": "6:24:58"}
+{"current_steps": 3160, "total_steps": 3941, "loss": 1.1571, "learning_rate": 5.749598806107634e-07, "epoch": 0.8017760862670472, "percentage": 80.18, "elapsed_time": "1 day, 1:37:46", "remaining_time": "6:20:03"}
+{"current_steps": 3170, "total_steps": 3941, "loss": 1.1253, "learning_rate": 5.609041062460451e-07, "epoch": 0.8043133523628291, "percentage": 80.44, "elapsed_time": "1 day, 1:42:30", "remaining_time": "6:15:09"}
+{"current_steps": 3180, "total_steps": 3941, "loss": 1.1229, "learning_rate": 5.470005333099288e-07, "epoch": 0.8068506184586108, "percentage": 80.69, "elapsed_time": "1 day, 1:47:11", "remaining_time": "6:10:15"}
+{"current_steps": 3190, "total_steps": 3941, "loss": 1.1279, "learning_rate": 5.332502531067007e-07, "epoch": 0.8093878845543926, "percentage": 80.94, "elapsed_time": "1 day, 1:51:52", "remaining_time": "6:05:20"}
+{"current_steps": 3200, "total_steps": 3941, "loss": 1.1268, "learning_rate": 5.196543449085617e-07, "epoch": 0.8119251506501745, "percentage": 81.2, "elapsed_time": "1 day, 1:56:33", "remaining_time": "6:00:26"}
+{"current_steps": 3210, "total_steps": 3941, "loss": 1.1409, "learning_rate": 5.062138758709098e-07, "epoch": 0.8144624167459562, "percentage": 81.45, "elapsed_time": "1 day, 2:01:14", "remaining_time": "5:55:32"}
+{"current_steps": 3220, "total_steps": 3941, "loss": 1.1385, "learning_rate": 4.929299009485799e-07, "epoch": 0.8169996828417381, "percentage": 81.71, "elapsed_time": "1 day, 2:05:59", "remaining_time": "5:50:38"}
+{"current_steps": 3230, "total_steps": 3941, "loss": 1.1454, "learning_rate": 4.798034628130396e-07, "epoch": 0.8195369489375198, "percentage": 81.96, "elapsed_time": "1 day, 2:10:41", "remaining_time": "5:45:44"}
+{"current_steps": 3240, "total_steps": 3941, "loss": 1.1257, "learning_rate": 4.668355917705486e-07, "epoch": 0.8220742150333016, "percentage": 82.21, "elapsed_time": "1 day, 2:15:22", "remaining_time": "5:40:50"}
+{"current_steps": 3250, "total_steps": 3941, "loss": 1.1337, "learning_rate": 4.540273056812869e-07, "epoch": 0.8246114811290834, "percentage": 82.47, "elapsed_time": "1 day, 2:20:04", "remaining_time": "5:35:56"}
+{"current_steps": 3260, "total_steps": 3941, "loss": 1.1265, "learning_rate": 4.4137960987946707e-07, "epoch": 0.8271487472248652, "percentage": 82.72, "elapsed_time": "1 day, 2:24:46", "remaining_time": "5:31:03"}
+{"current_steps": 3270, "total_steps": 3941, "loss": 1.1303, "learning_rate": 4.2889349709441945e-07, "epoch": 0.829686013320647, "percentage": 82.97, "elapsed_time": "1 day, 2:29:28", "remaining_time": "5:26:09"}
+{"current_steps": 3280, "total_steps": 3941, "loss": 1.1401, "learning_rate": 4.165699473726756e-07, "epoch": 0.8322232794164288, "percentage": 83.23, "elapsed_time": "1 day, 2:34:12", "remaining_time": "5:21:16"}
+{"current_steps": 3290, "total_steps": 3941, "loss": 1.1413, "learning_rate": 4.044099280010405e-07, "epoch": 0.8347605455122106, "percentage": 83.48, "elapsed_time": "1 day, 2:38:53", "remaining_time": "5:16:22"}
+{"current_steps": 3300, "total_steps": 3941, "loss": 1.1189, "learning_rate": 3.9241439343067205e-07, "epoch": 0.8372978116079924, "percentage": 83.74, "elapsed_time": "1 day, 2:43:35", "remaining_time": "5:11:29"}
+{"current_steps": 3310, "total_steps": 3941, "loss": 1.1397, "learning_rate": 3.8058428520216407e-07, "epoch": 0.8398350777037742, "percentage": 83.99, "elapsed_time": "1 day, 2:48:15", "remaining_time": "5:06:35"}
+{"current_steps": 3320, "total_steps": 3941, "loss": 1.1348, "learning_rate": 3.689205318716424e-07, "epoch": 0.842372343799556, "percentage": 84.24, "elapsed_time": "1 day, 2:52:55", "remaining_time": "5:01:41"}
+{"current_steps": 3330, "total_steps": 3941, "loss": 1.1473, "learning_rate": 3.574240489378847e-07, "epoch": 0.8449096098953378, "percentage": 84.5, "elapsed_time": "1 day, 2:57:38", "remaining_time": "4:56:48"}
+{"current_steps": 3340, "total_steps": 3941, "loss": 1.1445, "learning_rate": 3.4609573877046054e-07, "epoch": 0.8474468759911196, "percentage": 84.75, "elapsed_time": "1 day, 3:02:18", "remaining_time": "4:51:55"}
+{"current_steps": 3350, "total_steps": 3941, "loss": 1.1434, "learning_rate": 3.3493649053890325e-07, "epoch": 0.8499841420869013, "percentage": 85.0, "elapsed_time": "1 day, 3:07:00", "remaining_time": "4:47:01"}
+{"current_steps": 3360, "total_steps": 3941, "loss": 1.1305, "learning_rate": 3.239471801429186e-07, "epoch": 0.8525214081826832, "percentage": 85.26, "elapsed_time": "1 day, 3:11:41", "remaining_time": "4:42:08"}
+{"current_steps": 3370, "total_steps": 3941, "loss": 1.1322, "learning_rate": 3.1312867014363534e-07, "epoch": 0.8550586742784649, "percentage": 85.51, "elapsed_time": "1 day, 3:16:21", "remaining_time": "4:37:15"}
+{"current_steps": 3380, "total_steps": 3941, "loss": 1.1303, "learning_rate": 3.024818096958995e-07, "epoch": 0.8575959403742468, "percentage": 85.77, "elapsed_time": "1 day, 3:21:03", "remaining_time": "4:32:22"}
+{"current_steps": 3390, "total_steps": 3941, "loss": 1.1259, "learning_rate": 2.920074344816268e-07, "epoch": 0.8601332064700286, "percentage": 86.02, "elapsed_time": "1 day, 3:25:44", "remaining_time": "4:27:29"}
+{"current_steps": 3400, "total_steps": 3941, "loss": 1.1299, "learning_rate": 2.8170636664420715e-07, "epoch": 0.8626704725658103, "percentage": 86.27, "elapsed_time": "1 day, 3:30:25", "remaining_time": "4:22:36"}
+{"current_steps": 3410, "total_steps": 3941, "loss": 1.1496, "learning_rate": 2.7157941472397393e-07, "epoch": 0.8652077386615922, "percentage": 86.53, "elapsed_time": "1 day, 3:35:06", "remaining_time": "4:17:43"}
+{"current_steps": 3420, "total_steps": 3941, "loss": 1.1242, "learning_rate": 2.6162737359474195e-07, "epoch": 0.8677450047573739, "percentage": 86.78, "elapsed_time": "1 day, 3:39:47", "remaining_time": "4:12:51"}
+{"current_steps": 3430, "total_steps": 3941, "loss": 1.1284, "learning_rate": 2.518510244014161e-07, "epoch": 0.8702822708531557, "percentage": 87.03, "elapsed_time": "1 day, 3:44:28", "remaining_time": "4:07:58"}
+{"current_steps": 3440, "total_steps": 3941, "loss": 1.1304, "learning_rate": 2.4225113449867834e-07, "epoch": 0.8728195369489375, "percentage": 87.29, "elapsed_time": "1 day, 3:49:09", "remaining_time": "4:03:05"}
+{"current_steps": 3450, "total_steps": 3941, "loss": 1.1282, "learning_rate": 2.3282845739075855e-07, "epoch": 0.8753568030447193, "percentage": 87.54, "elapsed_time": "1 day, 3:53:51", "remaining_time": "3:58:13"}
+{"current_steps": 3460, "total_steps": 3941, "loss": 1.1298, "learning_rate": 2.2358373267229006e-07, "epoch": 0.8778940691405012, "percentage": 87.79, "elapsed_time": "1 day, 3:58:32", "remaining_time": "3:53:20"}
+{"current_steps": 3470, "total_steps": 3941, "loss": 1.1256, "learning_rate": 2.1451768597025995e-07, "epoch": 0.8804313352362829, "percentage": 88.05, "elapsed_time": "1 day, 4:03:14", "remaining_time": "3:48:28"}
+{"current_steps": 3480, "total_steps": 3941, "loss": 1.1286, "learning_rate": 2.0563102888705027e-07, "epoch": 0.8829686013320647, "percentage": 88.3, "elapsed_time": "1 day, 4:07:55", "remaining_time": "3:43:36"}
+{"current_steps": 3490, "total_steps": 3941, "loss": 1.1252, "learning_rate": 1.9692445894458845e-07, "epoch": 0.8855058674278465, "percentage": 88.56, "elapsed_time": "1 day, 4:12:35", "remaining_time": "3:38:43"}
+{"current_steps": 3500, "total_steps": 3941, "loss": 1.1151, "learning_rate": 1.883986595295953e-07, "epoch": 0.8880431335236283, "percentage": 88.81, "elapsed_time": "1 day, 4:17:17", "remaining_time": "3:33:51"}
+{"current_steps": 3510, "total_steps": 3941, "loss": 1.1334, "learning_rate": 1.8005429983994487e-07, "epoch": 0.89058039961941, "percentage": 89.06, "elapsed_time": "1 day, 4:28:35", "remaining_time": "3:29:48"}
+{"current_steps": 3520, "total_steps": 3941, "loss": 1.1411, "learning_rate": 1.7189203483213984e-07, "epoch": 0.8931176657151919, "percentage": 89.32, "elapsed_time": "1 day, 4:33:16", "remaining_time": "3:24:54"}
+{"current_steps": 3530, "total_steps": 3941, "loss": 1.1236, "learning_rate": 1.6391250516990448e-07, "epoch": 0.8956549318109737, "percentage": 89.57, "elapsed_time": "1 day, 4:38:00", "remaining_time": "3:20:01"}
+{"current_steps": 3540, "total_steps": 3941, "loss": 1.1159, "learning_rate": 1.5611633717389467e-07, "epoch": 0.8981921979067554, "percentage": 89.82, "elapsed_time": "1 day, 4:42:42", "remaining_time": "3:15:08"}
+{"current_steps": 3550, "total_steps": 3941, "loss": 1.1368, "learning_rate": 1.4850414277254088e-07, "epoch": 0.9007294640025373, "percentage": 90.08, "elapsed_time": "1 day, 4:47:25", "remaining_time": "3:10:15"}
+{"current_steps": 3560, "total_steps": 3941, "loss": 1.1305, "learning_rate": 1.41076519454017e-07, "epoch": 0.903266730098319, "percentage": 90.33, "elapsed_time": "1 day, 4:52:08", "remaining_time": "3:05:22"}
+{"current_steps": 3570, "total_steps": 3941, "loss": 1.1264, "learning_rate": 1.3383405021933998e-07, "epoch": 0.9058039961941009, "percentage": 90.59, "elapsed_time": "1 day, 4:56:52", "remaining_time": "3:00:29"}
+{"current_steps": 3580, "total_steps": 3941, "loss": 1.1195, "learning_rate": 1.267773035366135e-07, "epoch": 0.9083412622898827, "percentage": 90.84, "elapsed_time": "1 day, 5:01:32", "remaining_time": "2:55:36"}
+{"current_steps": 3590, "total_steps": 3941, "loss": 1.1381, "learning_rate": 1.1990683329640567e-07, "epoch": 0.9108785283856644, "percentage": 91.09, "elapsed_time": "1 day, 5:06:14", "remaining_time": "2:50:43"}
+{"current_steps": 3600, "total_steps": 3941, "loss": 1.1315, "learning_rate": 1.1322317876827416e-07, "epoch": 0.9134157944814463, "percentage": 91.35, "elapsed_time": "1 day, 5:10:56", "remaining_time": "2:45:51"}
+{"current_steps": 3610, "total_steps": 3941, "loss": 1.1382, "learning_rate": 1.0672686455843934e-07, "epoch": 0.915953060577228, "percentage": 91.6, "elapsed_time": "1 day, 5:15:37", "remaining_time": "2:40:58"}
+{"current_steps": 3620, "total_steps": 3941, "loss": 1.119, "learning_rate": 1.004184005686068e-07, "epoch": 0.9184903266730098, "percentage": 91.85, "elapsed_time": "1 day, 5:20:19", "remaining_time": "2:36:05"}
+{"current_steps": 3630, "total_steps": 3941, "loss": 1.1316, "learning_rate": 9.429828195594459e-08, "epoch": 0.9210275927687916, "percentage": 92.11, "elapsed_time": "1 day, 5:25:00", "remaining_time": "2:31:13"}
+{"current_steps": 3640, "total_steps": 3941, "loss": 1.1316, "learning_rate": 8.836698909421848e-08, "epoch": 0.9235648588645734, "percentage": 92.36, "elapsed_time": "1 day, 5:29:40", "remaining_time": "2:26:20"}
+{"current_steps": 3650, "total_steps": 3941, "loss": 1.1305, "learning_rate": 8.2624987536086e-08, "epoch": 0.9261021249603553, "percentage": 92.62, "elapsed_time": "1 day, 5:34:42", "remaining_time": "2:21:29"}
+{"current_steps": 3660, "total_steps": 3941, "loss": 1.104, "learning_rate": 7.707272797655597e-08, "epoch": 0.928639391056137, "percentage": 92.87, "elapsed_time": "1 day, 5:39:28", "remaining_time": "2:16:37"}
+{"current_steps": 3670, "total_steps": 3941, "loss": 1.1392, "learning_rate": 7.171064621761121e-08, "epoch": 0.9311766571519188, "percentage": 93.12, "elapsed_time": "1 day, 5:44:10", "remaining_time": "2:11:44"}
+{"current_steps": 3680, "total_steps": 3941, "loss": 1.1307, "learning_rate": 6.653916313400483e-08, "epoch": 0.9337139232477006, "percentage": 93.38, "elapsed_time": "1 day, 5:48:56", "remaining_time": "2:06:52"}
+{"current_steps": 3690, "total_steps": 3941, "loss": 1.1311, "learning_rate": 6.155868464022218e-08, "epoch": 0.9362511893434824, "percentage": 93.63, "elapsed_time": "1 day, 5:53:41", "remaining_time": "2:02:00"}
+{"current_steps": 3700, "total_steps": 3941, "loss": 1.1396, "learning_rate": 5.676960165862333e-08, "epoch": 0.9387884554392641, "percentage": 93.88, "elapsed_time": "1 day, 5:58:28", "remaining_time": "1:57:08"}
+{"current_steps": 3710, "total_steps": 3941, "loss": 1.1142, "learning_rate": 5.217229008875696e-08, "epoch": 0.941325721535046, "percentage": 94.14, "elapsed_time": "1 day, 6:03:14", "remaining_time": "1:52:16"}
+{"current_steps": 3720, "total_steps": 3941, "loss": 1.1316, "learning_rate": 4.7767110777856285e-08, "epoch": 0.9438629876308278, "percentage": 94.39, "elapsed_time": "1 day, 6:08:02", "remaining_time": "1:47:24"}
+{"current_steps": 3730, "total_steps": 3941, "loss": 1.1291, "learning_rate": 4.355440949251638e-08, "epoch": 0.9464002537266096, "percentage": 94.65, "elapsed_time": "1 day, 6:12:49", "remaining_time": "1:42:32"}
+{"current_steps": 3740, "total_steps": 3941, "loss": 1.1377, "learning_rate": 3.953451689155369e-08, "epoch": 0.9489375198223914, "percentage": 94.9, "elapsed_time": "1 day, 6:17:39", "remaining_time": "1:37:41"}
+{"current_steps": 3750, "total_steps": 3941, "loss": 1.1341, "learning_rate": 3.5707748500053706e-08, "epoch": 0.9514747859181731, "percentage": 95.15, "elapsed_time": "1 day, 6:22:27", "remaining_time": "1:32:49"}
+{"current_steps": 3760, "total_steps": 3941, "loss": 1.1131, "learning_rate": 3.2074404684603325e-08, "epoch": 0.954012052013955, "percentage": 95.41, "elapsed_time": "1 day, 6:27:16", "remaining_time": "1:27:57"}
+{"current_steps": 3770, "total_steps": 3941, "loss": 1.1354, "learning_rate": 2.863477062971659e-08, "epoch": 0.9565493181097368, "percentage": 95.66, "elapsed_time": "1 day, 6:32:06", "remaining_time": "1:23:06"}
+{"current_steps": 3780, "total_steps": 3941, "loss": 1.1349, "learning_rate": 2.5389116315448768e-08, "epoch": 0.9590865842055185, "percentage": 95.91, "elapsed_time": "1 day, 6:36:57", "remaining_time": "1:18:14"}
+{"current_steps": 3790, "total_steps": 3941, "loss": 1.1358, "learning_rate": 2.2337696496206317e-08, "epoch": 0.9616238503013004, "percentage": 96.17, "elapsed_time": "1 day, 6:41:48", "remaining_time": "1:13:22"}
+{"current_steps": 3800, "total_steps": 3941, "loss": 1.1454, "learning_rate": 1.948075068075067e-08, "epoch": 0.9641611163970821, "percentage": 96.42, "elapsed_time": "1 day, 6:46:40", "remaining_time": "1:08:31"}
+{"current_steps": 3810, "total_steps": 3941, "loss": 1.121, "learning_rate": 1.6818503113398832e-08, "epoch": 0.966698382492864, "percentage": 96.68, "elapsed_time": "1 day, 6:51:33", "remaining_time": "1:03:39"}
+{"current_steps": 3820, "total_steps": 3941, "loss": 1.1279, "learning_rate": 1.4351162756422454e-08, "epoch": 0.9692356485886457, "percentage": 96.93, "elapsed_time": "1 day, 6:56:27", "remaining_time": "0:58:48"}
+{"current_steps": 3830, "total_steps": 3941, "loss": 1.1423, "learning_rate": 1.2078923273646236e-08, "epoch": 0.9717729146844275, "percentage": 97.18, "elapsed_time": "1 day, 7:01:21", "remaining_time": "0:53:56"}
+{"current_steps": 3840, "total_steps": 3941, "loss": 1.1206, "learning_rate": 1.0001963015247585e-08, "epoch": 0.9743101807802094, "percentage": 97.44, "elapsed_time": "1 day, 7:06:15", "remaining_time": "0:49:05"}
+{"current_steps": 3850, "total_steps": 3941, "loss": 1.1429, "learning_rate": 8.120445003755306e-09, "epoch": 0.9768474468759911, "percentage": 97.69, "elapsed_time": "1 day, 7:11:10", "remaining_time": "0:44:13"}
+{"current_steps": 3860, "total_steps": 3941, "loss": 1.1184, "learning_rate": 6.434516921257905e-09, "epoch": 0.9793847129717729, "percentage": 97.94, "elapsed_time": "1 day, 7:16:03", "remaining_time": "0:39:22"}
+{"current_steps": 3870, "total_steps": 3941, "loss": 1.143, "learning_rate": 4.9443110978078525e-09, "epoch": 0.9819219790675547, "percentage": 98.2, "elapsed_time": "1 day, 7:20:58", "remaining_time": "0:34:30"}
+{"current_steps": 3880, "total_steps": 3941, "loss": 1.1314, "learning_rate": 3.649944501037672e-09, "epoch": 0.9844592451633365, "percentage": 98.45, "elapsed_time": "1 day, 7:25:55", "remaining_time": "0:29:38"}
+{"current_steps": 3890, "total_steps": 3941, "loss": 1.1163, "learning_rate": 2.5515187269772866e-09, "epoch": 0.9869965112591182, "percentage": 98.71, "elapsed_time": "1 day, 7:30:51", "remaining_time": "0:24:47"}
+{"current_steps": 3900, "total_steps": 3941, "loss": 1.1519, "learning_rate": 1.6491199920809498e-09, "epoch": 0.9895337773549001, "percentage": 98.96, "elapsed_time": "1 day, 7:35:47", "remaining_time": "0:19:55"}
+{"current_steps": 3910, "total_steps": 3941, "loss": 1.1472, "learning_rate": 9.428191264596042e-10, "epoch": 0.9920710434506819, "percentage": 99.21, "elapsed_time": "1 day, 7:40:45", "remaining_time": "0:15:04"}
+{"current_steps": 3920, "total_steps": 3941, "loss": 1.1114, "learning_rate": 4.3267156832033085e-10, "epoch": 0.9946083095464637, "percentage": 99.47, "elapsed_time": "1 day, 7:45:43", "remaining_time": "0:10:12"}
+{"current_steps": 3930, "total_steps": 3941, "loss": 1.1338, "learning_rate": 1.187173596167712e-10, "epoch": 0.9971455756422455, "percentage": 99.72, "elapsed_time": "1 day, 7:50:41", "remaining_time": "0:05:20"}
+{"current_steps": 3940, "total_steps": 3941, "loss": 1.1399, "learning_rate": 9.811429044215282e-13, "epoch": 0.9996828417380272, "percentage": 99.97, "elapsed_time": "1 day, 7:55:39", "remaining_time": "0:00:29"}
+{"current_steps": 3941, "total_steps": 3941, "epoch": 0.9999365683476055, "percentage": 100.0, "elapsed_time": "1 day, 8:01:56", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2800 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999365683476055,
+  "eval_steps": 500,
+  "global_step": 3941,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002537266095781795,
+      "grad_norm": 112.85723727111593,
+      "learning_rate": 1.2658227848101266e-07,
+      "loss": 1.8967,
+      "step": 10
+    },
+    {
+      "epoch": 0.00507453219156359,
+      "grad_norm": 111.7277255600065,
+      "learning_rate": 2.5316455696202533e-07,
+      "loss": 1.8962,
+      "step": 20
+    },
+    {
+      "epoch": 0.007611798287345386,
+      "grad_norm": 100.54525732943956,
+      "learning_rate": 3.79746835443038e-07,
+      "loss": 1.8773,
+      "step": 30
+    },
+    {
+      "epoch": 0.01014906438312718,
+      "grad_norm": 60.43888528431074,
+      "learning_rate": 5.063291139240507e-07,
+      "loss": 1.7742,
+      "step": 40
+    },
+    {
+      "epoch": 0.012686330478908976,
+      "grad_norm": 28.26912001667364,
+      "learning_rate": 6.329113924050634e-07,
+      "loss": 1.7141,
+      "step": 50
+    },
+    {
+      "epoch": 0.015223596574690771,
+      "grad_norm": 27.480791814917016,
+      "learning_rate": 7.59493670886076e-07,
+      "loss": 1.6293,
+      "step": 60
+    },
+    {
+      "epoch": 0.017760862670472565,
+      "grad_norm": 20.239901551582367,
+      "learning_rate": 8.860759493670887e-07,
+      "loss": 1.5743,
+      "step": 70
+    },
+    {
+      "epoch": 0.02029812876625436,
+      "grad_norm": 11.923875375009446,
+      "learning_rate": 1.0126582278481013e-06,
+      "loss": 1.5202,
+      "step": 80
+    },
+    {
+      "epoch": 0.022835394862036156,
+      "grad_norm": 6.627037994110648,
+      "learning_rate": 1.139240506329114e-06,
+      "loss": 1.4872,
+      "step": 90
+    },
+    {
+      "epoch": 0.02537266095781795,
+      "grad_norm": 8.16791147643463,
+      "learning_rate": 1.2658227848101267e-06,
+      "loss": 1.4824,
+      "step": 100
+    },
+    {
+      "epoch": 0.027909927053599747,
+      "grad_norm": 9.357053020719055,
+      "learning_rate": 1.3924050632911392e-06,
+      "loss": 1.4456,
+      "step": 110
+    },
+    {
+      "epoch": 0.030447193149381543,
+      "grad_norm": 8.946206463663723,
+      "learning_rate": 1.518987341772152e-06,
+      "loss": 1.4253,
+      "step": 120
+    },
+    {
+      "epoch": 0.032984459245163335,
+      "grad_norm": 6.684895053435472,
+      "learning_rate": 1.6455696202531647e-06,
+      "loss": 1.4119,
+      "step": 130
+    },
+    {
+      "epoch": 0.03552172534094513,
+      "grad_norm": 5.858068093439728,
+      "learning_rate": 1.7721518987341774e-06,
+      "loss": 1.3944,
+      "step": 140
+    },
+    {
+      "epoch": 0.038058991436726926,
+      "grad_norm": 10.736099643334308,
+      "learning_rate": 1.8987341772151901e-06,
+      "loss": 1.3937,
+      "step": 150
+    },
+    {
+      "epoch": 0.04059625753250872,
+      "grad_norm": 5.52407932247684,
+      "learning_rate": 2.0253164556962026e-06,
+      "loss": 1.3624,
+      "step": 160
+    },
+    {
+      "epoch": 0.04313352362829052,
+      "grad_norm": 8.107714144715326,
+      "learning_rate": 2.1518987341772153e-06,
+      "loss": 1.3854,
+      "step": 170
+    },
+    {
+      "epoch": 0.04567078972407231,
+      "grad_norm": 5.726773653383632,
+      "learning_rate": 2.278481012658228e-06,
+      "loss": 1.3745,
+      "step": 180
+    },
+    {
+      "epoch": 0.04820805581985411,
+      "grad_norm": 5.421447552101552,
+      "learning_rate": 2.4050632911392408e-06,
+      "loss": 1.3616,
+      "step": 190
+    },
+    {
+      "epoch": 0.0507453219156359,
+      "grad_norm": 5.519589755451587,
+      "learning_rate": 2.5316455696202535e-06,
+      "loss": 1.3802,
+      "step": 200
+    },
+    {
+      "epoch": 0.0532825880114177,
+      "grad_norm": 4.997598050858228,
+      "learning_rate": 2.6582278481012658e-06,
+      "loss": 1.3501,
+      "step": 210
+    },
+    {
+      "epoch": 0.055819854107199494,
+      "grad_norm": 7.739443027895296,
+      "learning_rate": 2.7848101265822785e-06,
+      "loss": 1.3529,
+      "step": 220
+    },
+    {
+      "epoch": 0.05835712020298129,
+      "grad_norm": 14.153932111981923,
+      "learning_rate": 2.9113924050632912e-06,
+      "loss": 1.3425,
+      "step": 230
+    },
+    {
+      "epoch": 0.060894386298763085,
+      "grad_norm": 6.821474472121072,
+      "learning_rate": 3.037974683544304e-06,
+      "loss": 1.3268,
+      "step": 240
+    },
+    {
+      "epoch": 0.06343165239454487,
+      "grad_norm": 7.105335682421715,
+      "learning_rate": 3.164556962025317e-06,
+      "loss": 1.3391,
+      "step": 250
+    },
+    {
+      "epoch": 0.06596891849032667,
+      "grad_norm": 9.157922661641283,
+      "learning_rate": 3.2911392405063294e-06,
+      "loss": 1.331,
+      "step": 260
+    },
+    {
+      "epoch": 0.06850618458610847,
+      "grad_norm": 8.558636103035896,
+      "learning_rate": 3.417721518987342e-06,
+      "loss": 1.3318,
+      "step": 270
+    },
+    {
+      "epoch": 0.07104345068189026,
+      "grad_norm": 6.250103925808961,
+      "learning_rate": 3.544303797468355e-06,
+      "loss": 1.3356,
+      "step": 280
+    },
+    {
+      "epoch": 0.07358071677767206,
+      "grad_norm": 6.294667609868247,
+      "learning_rate": 3.6708860759493675e-06,
+      "loss": 1.32,
+      "step": 290
+    },
+    {
+      "epoch": 0.07611798287345385,
+      "grad_norm": 6.6361456210836725,
+      "learning_rate": 3.7974683544303802e-06,
+      "loss": 1.3224,
+      "step": 300
+    },
+    {
+      "epoch": 0.07865524896923565,
+      "grad_norm": 8.289069596597512,
+      "learning_rate": 3.924050632911393e-06,
+      "loss": 1.3176,
+      "step": 310
+    },
+    {
+      "epoch": 0.08119251506501744,
+      "grad_norm": 5.542830103144929,
+      "learning_rate": 4.050632911392405e-06,
+      "loss": 1.2962,
+      "step": 320
+    },
+    {
+      "epoch": 0.08372978116079924,
+      "grad_norm": 10.531069717984824,
+      "learning_rate": 4.177215189873418e-06,
+      "loss": 1.3005,
+      "step": 330
+    },
+    {
+      "epoch": 0.08626704725658103,
+      "grad_norm": 17.37898460345658,
+      "learning_rate": 4.303797468354431e-06,
+      "loss": 1.3031,
+      "step": 340
+    },
+    {
+      "epoch": 0.08880431335236283,
+      "grad_norm": 9.252485190691019,
+      "learning_rate": 4.430379746835443e-06,
+      "loss": 1.3107,
+      "step": 350
+    },
+    {
+      "epoch": 0.09134157944814462,
+      "grad_norm": 7.525737017146553,
+      "learning_rate": 4.556962025316456e-06,
+      "loss": 1.2886,
+      "step": 360
+    },
+    {
+      "epoch": 0.09387884554392642,
+      "grad_norm": 10.083996939013279,
+      "learning_rate": 4.683544303797468e-06,
+      "loss": 1.2954,
+      "step": 370
+    },
+    {
+      "epoch": 0.09641611163970822,
+      "grad_norm": 18.864544413704667,
+      "learning_rate": 4.8101265822784815e-06,
+      "loss": 1.2959,
+      "step": 380
+    },
+    {
+      "epoch": 0.09895337773549001,
+      "grad_norm": 15.18986427449958,
+      "learning_rate": 4.936708860759495e-06,
+      "loss": 1.2918,
+      "step": 390
+    },
+    {
+      "epoch": 0.1014906438312718,
+      "grad_norm": 8.154706578846366,
+      "learning_rate": 4.999975471465892e-06,
+      "loss": 1.2952,
+      "step": 400
+    },
+    {
+      "epoch": 0.1040279099270536,
+      "grad_norm": 8.626125448906336,
+      "learning_rate": 4.999779246080933e-06,
+      "loss": 1.2812,
+      "step": 410
+    },
+    {
+      "epoch": 0.1065651760228354,
+      "grad_norm": 14.880568433586623,
+      "learning_rate": 4.999386810712926e-06,
+      "loss": 1.2532,
+      "step": 420
+    },
+    {
+      "epoch": 0.1091024421186172,
+      "grad_norm": 10.892903720339616,
+      "learning_rate": 4.9987981961644855e-06,
+      "loss": 1.2982,
+      "step": 430
+    },
+    {
+      "epoch": 0.11163970821439899,
+      "grad_norm": 4.797131746271338,
+      "learning_rate": 4.998013448636512e-06,
+      "loss": 1.271,
+      "step": 440
+    },
+    {
+      "epoch": 0.11417697431018078,
+      "grad_norm": 18.557197921826557,
+      "learning_rate": 4.997032629724564e-06,
+      "loss": 1.2825,
+      "step": 450
+    },
+    {
+      "epoch": 0.11671424040596258,
+      "grad_norm": 15.001794851401208,
+      "learning_rate": 4.995855816414024e-06,
+      "loss": 1.2765,
+      "step": 460
+    },
+    {
+      "epoch": 0.11925150650174438,
+      "grad_norm": 10.965425508561747,
+      "learning_rate": 4.9944831010740576e-06,
+      "loss": 1.2585,
+      "step": 470
+    },
+    {
+      "epoch": 0.12178877259752617,
+      "grad_norm": 6.63862480684244,
+      "learning_rate": 4.992914591450358e-06,
+      "loss": 1.2929,
+      "step": 480
+    },
+    {
+      "epoch": 0.12432603869330797,
+      "grad_norm": 6.984972641361711,
+      "learning_rate": 4.991150410656697e-06,
+      "loss": 1.2733,
+      "step": 490
+    },
+    {
+      "epoch": 0.12686330478908975,
+      "grad_norm": 18.903688844829993,
+      "learning_rate": 4.9891906971652545e-06,
+      "loss": 1.2558,
+      "step": 500
+    },
+    {
+      "epoch": 0.12940057088487156,
+      "grad_norm": 7.177194302737898,
+      "learning_rate": 4.987035604795753e-06,
+      "loss": 1.2659,
+      "step": 510
+    },
+    {
+      "epoch": 0.13193783698065334,
+      "grad_norm": 10.981192386536817,
+      "learning_rate": 4.984685302703385e-06,
+      "loss": 1.2606,
+      "step": 520
+    },
+    {
+      "epoch": 0.13447510307643515,
+      "grad_norm": 9.47429133139194,
+      "learning_rate": 4.982139975365533e-06,
+      "loss": 1.2785,
+      "step": 530
+    },
+    {
+      "epoch": 0.13701236917221693,
+      "grad_norm": 17.731391325371494,
+      "learning_rate": 4.979399822567292e-06,
+      "loss": 1.2709,
+      "step": 540
+    },
+    {
+      "epoch": 0.13954963526799874,
+      "grad_norm": 13.256927828543148,
+      "learning_rate": 4.976465059385788e-06,
+      "loss": 1.248,
+      "step": 550
+    },
+    {
+      "epoch": 0.14208690136378052,
+      "grad_norm": 9.285697826647898,
+      "learning_rate": 4.973335916173294e-06,
+      "loss": 1.2462,
+      "step": 560
+    },
+    {
+      "epoch": 0.14462416745956233,
+      "grad_norm": 10.853767808913329,
+      "learning_rate": 4.970012638539152e-06,
+      "loss": 1.2533,
+      "step": 570
+    },
+    {
+      "epoch": 0.1471614335553441,
+      "grad_norm": 16.143378806845213,
+      "learning_rate": 4.966495487330496e-06,
+      "loss": 1.2526,
+      "step": 580
+    },
+    {
+      "epoch": 0.14969869965112592,
+      "grad_norm": 46.2688542748775,
+      "learning_rate": 4.962784738611774e-06,
+      "loss": 1.265,
+      "step": 590
+    },
+    {
+      "epoch": 0.1522359657469077,
+      "grad_norm": 6.132364126798611,
+      "learning_rate": 4.958880683643082e-06,
+      "loss": 1.2733,
+      "step": 600
+    },
+    {
+      "epoch": 0.1547732318426895,
+      "grad_norm": 7.964503594558826,
+      "learning_rate": 4.954783628857302e-06,
+      "loss": 1.2626,
+      "step": 610
+    },
+    {
+      "epoch": 0.1573104979384713,
+      "grad_norm": 13.68977454870837,
+      "learning_rate": 4.95049389583605e-06,
+      "loss": 1.2657,
+      "step": 620
+    },
+    {
+      "epoch": 0.1598477640342531,
+      "grad_norm": 14.540626560719817,
+      "learning_rate": 4.9460118212844355e-06,
+      "loss": 1.2372,
+      "step": 630
+    },
+    {
+      "epoch": 0.16238503013003489,
+      "grad_norm": 17.246204651829867,
+      "learning_rate": 4.941337757004631e-06,
+      "loss": 1.2355,
+      "step": 640
+    },
+    {
+      "epoch": 0.1649222962258167,
+      "grad_norm": 5.660216888492281,
+      "learning_rate": 4.936472069868262e-06,
+      "loss": 1.2439,
+      "step": 650
+    },
+    {
+      "epoch": 0.16745956232159848,
+      "grad_norm": 32.30203917124339,
+      "learning_rate": 4.931415141787607e-06,
+      "loss": 1.2384,
+      "step": 660
+    },
+    {
+      "epoch": 0.16999682841738029,
+      "grad_norm": 9.519199679528043,
+      "learning_rate": 4.926167369685626e-06,
+      "loss": 1.2452,
+      "step": 670
+    },
+    {
+      "epoch": 0.17253409451316207,
+      "grad_norm": 9.559300124244501,
+      "learning_rate": 4.920729165464799e-06,
+      "loss": 1.2564,
+      "step": 680
+    },
+    {
+      "epoch": 0.17507136060894388,
+      "grad_norm": 7.099728750507589,
+      "learning_rate": 4.915100955974802e-06,
+      "loss": 1.2695,
+      "step": 690
+    },
+    {
+      "epoch": 0.17760862670472566,
+      "grad_norm": 8.197172932423973,
+      "learning_rate": 4.909283182978998e-06,
+      "loss": 1.2379,
+      "step": 700
+    },
+    {
+      "epoch": 0.18014589280050744,
+      "grad_norm": 9.726988142249633,
+      "learning_rate": 4.903276303119765e-06,
+      "loss": 1.2483,
+      "step": 710
+    },
+    {
+      "epoch": 0.18268315889628925,
+      "grad_norm": 5.550536710160647,
+      "learning_rate": 4.897080787882656e-06,
+      "loss": 1.2493,
+      "step": 720
+    },
+    {
+      "epoch": 0.18522042499207103,
+      "grad_norm": 15.553779441262579,
+      "learning_rate": 4.890697123559385e-06,
+      "loss": 1.2635,
+      "step": 730
+    },
+    {
+      "epoch": 0.18775769108785284,
+      "grad_norm": 7.070319331844888,
+      "learning_rate": 4.884125811209665e-06,
+      "loss": 1.2439,
+      "step": 740
+    },
+    {
+      "epoch": 0.19029495718363462,
+      "grad_norm": 9.252450309844942,
+      "learning_rate": 4.877367366621874e-06,
+      "loss": 1.2423,
+      "step": 750
+    },
+    {
+      "epoch": 0.19283222327941643,
+      "grad_norm": 8.297702205658675,
+      "learning_rate": 4.870422320272576e-06,
+      "loss": 1.2322,
+      "step": 760
+    },
+    {
+      "epoch": 0.1953694893751982,
+      "grad_norm": 14.013643448769688,
+      "learning_rate": 4.863291217284872e-06,
+      "loss": 1.2354,
+      "step": 770
+    },
+    {
+      "epoch": 0.19790675547098002,
+      "grad_norm": 8.039135652565351,
+      "learning_rate": 4.855974617385629e-06,
+      "loss": 1.2257,
+      "step": 780
+    },
+    {
+      "epoch": 0.2004440215667618,
+      "grad_norm": 6.465541475557579,
+      "learning_rate": 4.8484730948615336e-06,
+      "loss": 1.2477,
+      "step": 790
+    },
+    {
+      "epoch": 0.2029812876625436,
+      "grad_norm": 38.736482675881,
+      "learning_rate": 4.840787238514019e-06,
+      "loss": 1.242,
+      "step": 800
+    },
+    {
+      "epoch": 0.2055185537583254,
+      "grad_norm": 6.2027098825049745,
+      "learning_rate": 4.832917651613055e-06,
+      "loss": 1.2481,
+      "step": 810
+    },
+    {
+      "epoch": 0.2080558198541072,
+      "grad_norm": 7.699764524449651,
+      "learning_rate": 4.824864951849787e-06,
+      "loss": 1.2422,
+      "step": 820
+    },
+    {
+      "epoch": 0.210593085949889,
+      "grad_norm": 7.045914854236814,
+      "learning_rate": 4.8166297712880635e-06,
+      "loss": 1.2296,
+      "step": 830
+    },
+    {
+      "epoch": 0.2131303520456708,
+      "grad_norm": 6.848231755692189,
+      "learning_rate": 4.808212756314815e-06,
+      "loss": 1.2185,
+      "step": 840
+    },
+    {
+      "epoch": 0.21566761814145258,
+      "grad_norm": 7.591181911551738,
+      "learning_rate": 4.7996145675893255e-06,
+      "loss": 1.2348,
+      "step": 850
+    },
+    {
+      "epoch": 0.2182048842372344,
+      "grad_norm": 13.992556734602806,
+      "learning_rate": 4.7908358799913735e-06,
+      "loss": 1.259,
+      "step": 860
+    },
+    {
+      "epoch": 0.22074215033301617,
+      "grad_norm": 13.882288651265467,
+      "learning_rate": 4.781877382568261e-06,
+      "loss": 1.2305,
+      "step": 870
+    },
+    {
+      "epoch": 0.22327941642879798,
+      "grad_norm": 8.53486541599463,
+      "learning_rate": 4.772739778480729e-06,
+      "loss": 1.2343,
+      "step": 880
+    },
+    {
+      "epoch": 0.22581668252457976,
+      "grad_norm": 9.455012927215373,
+      "learning_rate": 4.7634237849477645e-06,
+      "loss": 1.2194,
+      "step": 890
+    },
+    {
+      "epoch": 0.22835394862036157,
+      "grad_norm": 13.790102358483903,
+      "learning_rate": 4.7539301331903125e-06,
+      "loss": 1.2267,
+      "step": 900
+    },
+    {
+      "epoch": 0.23089121471614335,
+      "grad_norm": 14.2481962464266,
+      "learning_rate": 4.7442595683738705e-06,
+      "loss": 1.2132,
+      "step": 910
+    },
+    {
+      "epoch": 0.23342848081192516,
+      "grad_norm": 14.416373746309988,
+      "learning_rate": 4.734412849550007e-06,
+      "loss": 1.2094,
+      "step": 920
+    },
+    {
+      "epoch": 0.23596574690770694,
+      "grad_norm": 9.539618032350603,
+      "learning_rate": 4.7243907495967815e-06,
+      "loss": 1.2294,
+      "step": 930
+    },
+    {
+      "epoch": 0.23850301300348875,
+      "grad_norm": 5.29440353230921,
+      "learning_rate": 4.7141940551580824e-06,
+      "loss": 1.2208,
+      "step": 940
+    },
+    {
+      "epoch": 0.24104027909927053,
+      "grad_norm": 12.765581152374985,
+      "learning_rate": 4.703823566581877e-06,
+      "loss": 1.2324,
+      "step": 950
+    },
+    {
+      "epoch": 0.24357754519505234,
+      "grad_norm": 8.58495407107471,
+      "learning_rate": 4.693280097857398e-06,
+      "loss": 1.2222,
+      "step": 960
+    },
+    {
+      "epoch": 0.24611481129083412,
+      "grad_norm": 9.562572836922989,
+      "learning_rate": 4.6825644765512475e-06,
+      "loss": 1.2185,
+      "step": 970
+    },
+    {
+      "epoch": 0.24865207738661593,
+      "grad_norm": 9.23186285176845,
+      "learning_rate": 4.6716775437424465e-06,
+      "loss": 1.2192,
+      "step": 980
+    },
+    {
+      "epoch": 0.25118934348239774,
+      "grad_norm": 5.073620743419921,
+      "learning_rate": 4.660620153956409e-06,
+      "loss": 1.2241,
+      "step": 990
+    },
+    {
+      "epoch": 0.2537266095781795,
+      "grad_norm": 8.006469237916,
+      "learning_rate": 4.649393175097879e-06,
+      "loss": 1.2281,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2562638756739613,
+      "grad_norm": 8.265727241877757,
+      "learning_rate": 4.637997488382801e-06,
+      "loss": 1.2286,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2588011417697431,
+      "grad_norm": 6.416174543416175,
+      "learning_rate": 4.626433988269156e-06,
+      "loss": 1.2217,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2613384078655249,
+      "grad_norm": 7.028656405225393,
+      "learning_rate": 4.614703582386755e-06,
+      "loss": 1.2181,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2638756739613067,
+      "grad_norm": 5.865759830273811,
+      "learning_rate": 4.602807191465993e-06,
+      "loss": 1.2382,
+      "step": 1040
+    },
+    {
+      "epoch": 0.2664129400570885,
+      "grad_norm": 13.872254227369961,
+      "learning_rate": 4.5907457492655895e-06,
+      "loss": 1.2359,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2689502061528703,
+      "grad_norm": 13.664329240119352,
+      "learning_rate": 4.578520202499286e-06,
+      "loss": 1.2154,
+      "step": 1060
+    },
+    {
+      "epoch": 0.27148747224865205,
+      "grad_norm": 14.099557581365481,
+      "learning_rate": 4.566131510761548e-06,
+      "loss": 1.2279,
+      "step": 1070
+    },
+    {
+      "epoch": 0.27402473834443386,
+      "grad_norm": 9.810709350520776,
+      "learning_rate": 4.553580646452238e-06,
+      "loss": 1.2276,
+      "step": 1080
+    },
+    {
+      "epoch": 0.27656200444021567,
+      "grad_norm": 6.042192876271809,
+      "learning_rate": 4.5408685947002915e-06,
+      "loss": 1.2159,
+      "step": 1090
+    },
+    {
+      "epoch": 0.2790992705359975,
+      "grad_norm": 7.672603258347116,
+      "learning_rate": 4.5279963532864e-06,
+      "loss": 1.209,
+      "step": 1100
+    },
+    {
+      "epoch": 0.28163653663177923,
+      "grad_norm": 7.981333790512745,
+      "learning_rate": 4.5149649325646875e-06,
+      "loss": 1.2227,
+      "step": 1110
+    },
+    {
+      "epoch": 0.28417380272756104,
+      "grad_norm": 7.786264862698563,
+      "learning_rate": 4.501775355383406e-06,
+      "loss": 1.2299,
+      "step": 1120
+    },
+    {
+      "epoch": 0.28671106882334285,
+      "grad_norm": 23.110853155380898,
+      "learning_rate": 4.48842865700466e-06,
+      "loss": 1.1972,
+      "step": 1130
+    },
+    {
+      "epoch": 0.28924833491912466,
+      "grad_norm": 13.48010845409501,
+      "learning_rate": 4.474925885023136e-06,
+      "loss": 1.2043,
+      "step": 1140
+    },
+    {
+      "epoch": 0.2917856010149064,
+      "grad_norm": 9.52808074720464,
+      "learning_rate": 4.461268099283886e-06,
+      "loss": 1.2107,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2943228671106882,
+      "grad_norm": 7.355296672812608,
+      "learning_rate": 4.4474563717991345e-06,
+      "loss": 1.2014,
+      "step": 1160
+    },
+    {
+      "epoch": 0.29686013320647003,
+      "grad_norm": 6.320569333174802,
+      "learning_rate": 4.433491786664134e-06,
+      "loss": 1.2068,
+      "step": 1170
+    },
+    {
+      "epoch": 0.29939739930225184,
+      "grad_norm": 10.030481328592858,
+      "learning_rate": 4.419375439972075e-06,
+      "loss": 1.2276,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3019346653980336,
+      "grad_norm": 6.409643921761458,
+      "learning_rate": 4.405108439728057e-06,
+      "loss": 1.217,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3044719314938154,
+      "grad_norm": 8.589272885921144,
+      "learning_rate": 4.390691905762111e-06,
+      "loss": 1.2141,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3070091975895972,
+      "grad_norm": 8.928374282259929,
+      "learning_rate": 4.376126969641311e-06,
+      "loss": 1.2067,
+      "step": 1210
+    },
+    {
+      "epoch": 0.309546463685379,
+      "grad_norm": 6.743646650661921,
+      "learning_rate": 4.361414774580952e-06,
+      "loss": 1.2126,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3120837297811608,
+      "grad_norm": 11.981450710885838,
+      "learning_rate": 4.34655647535482e-06,
+      "loss": 1.1928,
+      "step": 1230
+    },
+    {
+      "epoch": 0.3146209958769426,
+      "grad_norm": 9.30568404144152,
+      "learning_rate": 4.3315532382045535e-06,
+      "loss": 1.2233,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3171582619727244,
+      "grad_norm": 9.124358676503277,
+      "learning_rate": 4.3164062407480974e-06,
+      "loss": 1.2208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3196955280685062,
+      "grad_norm": 9.471883506779196,
+      "learning_rate": 4.301116671887281e-06,
+      "loss": 1.2009,
+      "step": 1260
+    },
+    {
+      "epoch": 0.32223279416428796,
+      "grad_norm": 6.941617674454578,
+      "learning_rate": 4.285685731714493e-06,
+      "loss": 1.2188,
+      "step": 1270
+    },
+    {
+      "epoch": 0.32477006026006977,
+      "grad_norm": 12.5252338418682,
+      "learning_rate": 4.270114631418487e-06,
+      "loss": 1.1947,
+      "step": 1280
+    },
+    {
+      "epoch": 0.3273073263558516,
+      "grad_norm": 11.108780709122486,
+      "learning_rate": 4.254404593189316e-06,
+      "loss": 1.2063,
+      "step": 1290
+    },
+    {
+      "epoch": 0.3298445924516334,
+      "grad_norm": 8.555766487500795,
+      "learning_rate": 4.238556850122394e-06,
+      "loss": 1.1988,
+      "step": 1300
+    },
+    {
+      "epoch": 0.33238185854741514,
+      "grad_norm": 5.929688704429909,
+      "learning_rate": 4.222572646121723e-06,
+      "loss": 1.2084,
+      "step": 1310
+    },
+    {
+      "epoch": 0.33491912464319695,
+      "grad_norm": 7.403468884662153,
+      "learning_rate": 4.2064532358022446e-06,
+      "loss": 1.209,
+      "step": 1320
+    },
+    {
+      "epoch": 0.33745639073897876,
+      "grad_norm": 11.518020383952775,
+      "learning_rate": 4.190199884391371e-06,
+      "loss": 1.2069,
+      "step": 1330
+    },
+    {
+      "epoch": 0.33999365683476057,
+      "grad_norm": 8.809667396360213,
+      "learning_rate": 4.173813867629672e-06,
+      "loss": 1.2291,
+      "step": 1340
+    },
+    {
+      "epoch": 0.3425309229305423,
+      "grad_norm": 10.783849201384296,
+      "learning_rate": 4.157296471670747e-06,
+      "loss": 1.1787,
+      "step": 1350
+    },
+    {
+      "epoch": 0.34506818902632413,
+      "grad_norm": 5.923243263259089,
+      "learning_rate": 4.140648992980269e-06,
+      "loss": 1.1972,
+      "step": 1360
+    },
+    {
+      "epoch": 0.34760545512210594,
+      "grad_norm": 7.577491053933149,
+      "learning_rate": 4.1238727382342245e-06,
+      "loss": 1.2193,
+      "step": 1370
+    },
+    {
+      "epoch": 0.35014272121788775,
+      "grad_norm": 15.766504679065461,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 1.1896,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3526799873136695,
+      "grad_norm": 5.128475553118625,
+      "learning_rate": 4.089939177714778e-06,
+      "loss": 1.1916,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3552172534094513,
+      "grad_norm": 31.663873389243054,
+      "learning_rate": 4.0727845354178995e-06,
+      "loss": 1.2037,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3577545195052331,
+      "grad_norm": 5.0548828855937975,
+      "learning_rate": 4.055506443809441e-06,
+      "loss": 1.2243,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3602917856010149,
+      "grad_norm": 6.115218417588514,
+      "learning_rate": 4.038106259062778e-06,
+      "loss": 1.1927,
+      "step": 1420
+    },
+    {
+      "epoch": 0.3628290516967967,
+      "grad_norm": 12.060043038462219,
+      "learning_rate": 4.020585346934493e-06,
+      "loss": 1.2077,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3653663177925785,
+      "grad_norm": 5.116355293016737,
+      "learning_rate": 4.002945082657167e-06,
+      "loss": 1.2,
+      "step": 1440
+    },
+    {
+      "epoch": 0.3679035838883603,
+      "grad_norm": 7.955675984619225,
+      "learning_rate": 3.985186850831446e-06,
+      "loss": 1.1917,
+      "step": 1450
+    },
+    {
+      "epoch": 0.37044084998414206,
+      "grad_norm": 7.18463544096605,
+      "learning_rate": 3.967312045317357e-06,
+      "loss": 1.1917,
+      "step": 1460
+    },
+    {
+      "epoch": 0.37297811607992387,
+      "grad_norm": 13.238317735595116,
+      "learning_rate": 3.9493220691249e-06,
+      "loss": 1.207,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3755153821757057,
+      "grad_norm": 17.592657693606654,
+      "learning_rate": 3.931218334303933e-06,
+      "loss": 1.1963,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3780526482714875,
+      "grad_norm": 13.71018630119955,
+      "learning_rate": 3.913002261833331e-06,
+      "loss": 1.201,
+      "step": 1490
+    },
+    {
+      "epoch": 0.38058991436726924,
+      "grad_norm": 4.264076010568766,
+      "learning_rate": 3.894675281509455e-06,
+      "loss": 1.2088,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38312718046305105,
+      "grad_norm": 7.007776785175352,
+      "learning_rate": 3.876238831833927e-06,
+      "loss": 1.216,
+      "step": 1510
+    },
+    {
+      "epoch": 0.38566444655883286,
+      "grad_norm": 6.561717211592676,
+      "learning_rate": 3.857694359900719e-06,
+      "loss": 1.211,
+      "step": 1520
+    },
+    {
+      "epoch": 0.3882017126546147,
+      "grad_norm": 9.351379080752213,
+      "learning_rate": 3.83904332128257e-06,
+      "loss": 1.173,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3907389787503964,
+      "grad_norm": 5.389365116394579,
+      "learning_rate": 3.820287179916736e-06,
+      "loss": 1.1883,
+      "step": 1540
+    },
+    {
+      "epoch": 0.39327624484617824,
+      "grad_norm": 4.843914279235025,
+      "learning_rate": 3.8014274079900842e-06,
+      "loss": 1.2002,
+      "step": 1550
+    },
+    {
+      "epoch": 0.39581351094196005,
+      "grad_norm": 8.271741525384778,
+      "learning_rate": 3.7824654858235433e-06,
+      "loss": 1.2019,
+      "step": 1560
+    },
+    {
+      "epoch": 0.39835077703774185,
+      "grad_norm": 16.214867643854607,
+      "learning_rate": 3.763402901755905e-06,
+      "loss": 1.1936,
+      "step": 1570
+    },
+    {
+      "epoch": 0.4008880431335236,
+      "grad_norm": 6.671379474352313,
+      "learning_rate": 3.7442411520270096e-06,
+      "loss": 1.1872,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4034253092293054,
+      "grad_norm": 8.707941769488675,
+      "learning_rate": 3.7249817406602996e-06,
+      "loss": 1.197,
+      "step": 1590
+    },
+    {
+      "epoch": 0.4059625753250872,
+      "grad_norm": 6.5621327717722995,
+      "learning_rate": 3.7056261793447707e-06,
+      "loss": 1.1983,
+      "step": 1600
+    },
+    {
+      "epoch": 0.40849984142086904,
+      "grad_norm": 7.068156090864818,
+      "learning_rate": 3.686175987316317e-06,
+      "loss": 1.1853,
+      "step": 1610
+    },
+    {
+      "epoch": 0.4110371075166508,
+      "grad_norm": 7.890900003065767,
+      "learning_rate": 3.6666326912384854e-06,
+      "loss": 1.1925,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4135743736124326,
+      "grad_norm": 6.7232162942204665,
+      "learning_rate": 3.6469978250826433e-06,
+      "loss": 1.1954,
+      "step": 1630
+    },
+    {
+      "epoch": 0.4161116397082144,
+      "grad_norm": 10.010345842937971,
+      "learning_rate": 3.6272729300075808e-06,
+      "loss": 1.209,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4186489058039962,
+      "grad_norm": 5.740167290944564,
+      "learning_rate": 3.6074595542385387e-06,
+      "loss": 1.185,
+      "step": 1650
+    },
+    {
+      "epoch": 0.421186171899778,
+      "grad_norm": 7.619213938711831,
+      "learning_rate": 3.5875592529456926e-06,
+      "loss": 1.2068,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4237234379955598,
+      "grad_norm": 11.256221468519641,
+      "learning_rate": 3.567573588122079e-06,
+      "loss": 1.1777,
+      "step": 1670
+    },
+    {
+      "epoch": 0.4262607040913416,
+      "grad_norm": 5.7316159588312106,
+      "learning_rate": 3.5475041284609977e-06,
+      "loss": 1.1843,
+      "step": 1680
+    },
+    {
+      "epoch": 0.4287979701871234,
+      "grad_norm": 5.682433911486404,
+      "learning_rate": 3.527352449232886e-06,
+      "loss": 1.1777,
+      "step": 1690
+    },
+    {
+      "epoch": 0.43133523628290515,
+      "grad_norm": 6.786252039469139,
+      "learning_rate": 3.5071201321616673e-06,
+      "loss": 1.1888,
+      "step": 1700
+    },
+    {
+      "epoch": 0.43387250237868696,
+      "grad_norm": 5.407930902552358,
+      "learning_rate": 3.4868087653006045e-06,
+      "loss": 1.1901,
+      "step": 1710
+    },
+    {
+      "epoch": 0.4364097684744688,
+      "grad_norm": 6.399699747010517,
+      "learning_rate": 3.466419942907652e-06,
+      "loss": 1.2107,
+      "step": 1720
+    },
+    {
+      "epoch": 0.4389470345702506,
+      "grad_norm": 7.825821295728962,
+      "learning_rate": 3.445955265320321e-06,
+      "loss": 1.1918,
+      "step": 1730
+    },
+    {
+      "epoch": 0.44148430066603234,
+      "grad_norm": 9.488411335781475,
+      "learning_rate": 3.425416338830067e-06,
+      "loss": 1.189,
+      "step": 1740
+    },
+    {
+      "epoch": 0.44402156676181415,
+      "grad_norm": 5.88274413352344,
+      "learning_rate": 3.4048047755562093e-06,
+      "loss": 1.183,
+      "step": 1750
+    },
+    {
+      "epoch": 0.44655883285759596,
+      "grad_norm": 5.6831092141225055,
+      "learning_rate": 3.3841221933193965e-06,
+      "loss": 1.1882,
+      "step": 1760
+    },
+    {
+      "epoch": 0.4490960989533777,
+      "grad_norm": 19.983254773097197,
+      "learning_rate": 3.3633702155146216e-06,
+      "loss": 1.1911,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4516333650491595,
+      "grad_norm": 12.549540089577652,
+      "learning_rate": 3.342550470983798e-06,
+      "loss": 1.1811,
+      "step": 1780
+    },
+    {
+      "epoch": 0.45417063114494133,
+      "grad_norm": 5.976267812124573,
+      "learning_rate": 3.3216645938879134e-06,
+      "loss": 1.1865,
+      "step": 1790
+    },
+    {
+      "epoch": 0.45670789724072314,
+      "grad_norm": 9.218000333375254,
+      "learning_rate": 3.3007142235787624e-06,
+      "loss": 1.1842,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4592451633365049,
+      "grad_norm": 6.320981630879619,
+      "learning_rate": 3.2797010044702697e-06,
+      "loss": 1.1776,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4617824294322867,
+      "grad_norm": 6.190899234462718,
+      "learning_rate": 3.258626585909422e-06,
+      "loss": 1.1917,
+      "step": 1820
+    },
+    {
+      "epoch": 0.4643196955280685,
+      "grad_norm": 7.909431608694366,
+      "learning_rate": 3.2374926220468067e-06,
+      "loss": 1.1789,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4668569616238503,
+      "grad_norm": 5.69897203883322,
+      "learning_rate": 3.216300771706776e-06,
+      "loss": 1.1733,
+      "step": 1840
+    },
+    {
+      "epoch": 0.4693942277196321,
+      "grad_norm": 20.816445025574357,
+      "learning_rate": 3.1950526982572484e-06,
+      "loss": 1.1712,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4719314938154139,
+      "grad_norm": 11.982164138237327,
+      "learning_rate": 3.1737500694791424e-06,
+      "loss": 1.1815,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4744687599111957,
+      "grad_norm": 24.74208511970109,
+      "learning_rate": 3.1523945574354763e-06,
+      "loss": 1.1863,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4770060260069775,
+      "grad_norm": 7.842936948875007,
+      "learning_rate": 3.130987838340126e-06,
+      "loss": 1.1834,
+      "step": 1880
+    },
+    {
+      "epoch": 0.47954329210275926,
+      "grad_norm": 6.4021446109798505,
+      "learning_rate": 3.1095315924262544e-06,
+      "loss": 1.184,
+      "step": 1890
+    },
+    {
+      "epoch": 0.48208055819854106,
+      "grad_norm": 11.634701038383552,
+      "learning_rate": 3.0880275038144296e-06,
+      "loss": 1.1748,
+      "step": 1900
+    },
+    {
+      "epoch": 0.4846178242943229,
+      "grad_norm": 13.567790113056438,
+      "learning_rate": 3.066477260380441e-06,
+      "loss": 1.1647,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4871550903901047,
+      "grad_norm": 8.85124389947068,
+      "learning_rate": 3.044882553622808e-06,
+      "loss": 1.1906,
+      "step": 1920
+    },
+    {
+      "epoch": 0.48969235648588644,
+      "grad_norm": 4.941061338275534,
+      "learning_rate": 3.0232450785300207e-06,
+      "loss": 1.1653,
+      "step": 1930
+    },
+    {
+      "epoch": 0.49222962258166825,
+      "grad_norm": 6.532283199565601,
+      "learning_rate": 3.0015665334474937e-06,
+      "loss": 1.1869,
+      "step": 1940
+    },
+    {
+      "epoch": 0.49476688867745006,
+      "grad_norm": 9.662609662864591,
+      "learning_rate": 2.9798486199442627e-06,
+      "loss": 1.1707,
+      "step": 1950
+    },
+    {
+      "epoch": 0.49730415477323187,
+      "grad_norm": 7.538232506265863,
+      "learning_rate": 2.958093042679429e-06,
+      "loss": 1.192,
+      "step": 1960
+    },
+    {
+      "epoch": 0.4998414208690136,
+      "grad_norm": 72.64241187548325,
+      "learning_rate": 2.9363015092683566e-06,
+      "loss": 1.1762,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5023786869647955,
+      "grad_norm": 9.900383081254226,
+      "learning_rate": 2.9144757301486387e-06,
+      "loss": 1.169,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5049159530605772,
+      "grad_norm": 6.366667290767634,
+      "learning_rate": 2.8926174184458484e-06,
+      "loss": 1.174,
+      "step": 1990
+    },
+    {
+      "epoch": 0.507453219156359,
+      "grad_norm": 6.005401235845572,
+      "learning_rate": 2.8707282898390703e-06,
+      "loss": 1.1596,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5099904852521409,
+      "grad_norm": 8.195058772390636,
+      "learning_rate": 2.848810062426236e-06,
+      "loss": 1.1636,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5125277513479226,
+      "grad_norm": 6.0595964456253055,
+      "learning_rate": 2.82686445658927e-06,
+      "loss": 1.1622,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5150650174437044,
+      "grad_norm": 23.70711855670117,
+      "learning_rate": 2.8048931948590537e-06,
+      "loss": 1.1679,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5176022835394862,
+      "grad_norm": 5.907186404005163,
+      "learning_rate": 2.7828980017802236e-06,
+      "loss": 1.1883,
+      "step": 2040
+    },
+    {
+      "epoch": 0.520139549635268,
+      "grad_norm": 7.344357732813401,
+      "learning_rate": 2.760880603775811e-06,
+      "loss": 1.173,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5226768157310498,
+      "grad_norm": 7.426398590607293,
+      "learning_rate": 2.73884272901173e-06,
+      "loss": 1.191,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5252140818268316,
+      "grad_norm": 7.057487598088109,
+      "learning_rate": 2.7167861072611374e-06,
+      "loss": 1.1717,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5277513479226134,
+      "grad_norm": 7.223259822911996,
+      "learning_rate": 2.6947124697686553e-06,
+      "loss": 1.1638,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5302886140183952,
+      "grad_norm": 10.407626808887795,
+      "learning_rate": 2.6726235491144886e-06,
+      "loss": 1.1682,
+      "step": 2090
+    },
+    {
+      "epoch": 0.532825880114177,
+      "grad_norm": 6.589791365210622,
+      "learning_rate": 2.650521079078433e-06,
+      "loss": 1.1645,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5353631462099587,
+      "grad_norm": 11.999381746057887,
+      "learning_rate": 2.6284067945037855e-06,
+      "loss": 1.1646,
+      "step": 2110
+    },
+    {
+      "epoch": 0.5379004123057406,
+      "grad_norm": 7.613081340354655,
+      "learning_rate": 2.6062824311611775e-06,
+      "loss": 1.1705,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5404376784015223,
+      "grad_norm": 6.366501800737734,
+      "learning_rate": 2.5841497256123326e-06,
+      "loss": 1.1573,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5429749444973041,
+      "grad_norm": 18.74317163106254,
+      "learning_rate": 2.5620104150737626e-06,
+      "loss": 1.165,
+      "step": 2140
+    },
+    {
+      "epoch": 0.545512210593086,
+      "grad_norm": 11.370554877805095,
+      "learning_rate": 2.5398662372804105e-06,
+      "loss": 1.1701,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5480494766888677,
+      "grad_norm": 6.5553872071155554,
+      "learning_rate": 2.517718930349254e-06,
+      "loss": 1.1475,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5505867427846496,
+      "grad_norm": 5.741036264156473,
+      "learning_rate": 2.495570232642881e-06,
+      "loss": 1.1483,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5531240088804313,
+      "grad_norm": 6.767884733983484,
+      "learning_rate": 2.47342188263304e-06,
+      "loss": 1.1689,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5556612749762131,
+      "grad_norm": 13.529490798235566,
+      "learning_rate": 2.4512756187641936e-06,
+      "loss": 1.1614,
+      "step": 2190
+    },
+    {
+      "epoch": 0.558198541071995,
+      "grad_norm": 9.536331865874597,
+      "learning_rate": 2.4291331793170545e-06,
+      "loss": 1.1606,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5607358071677767,
+      "grad_norm": 4.782009512084195,
+      "learning_rate": 2.4069963022721597e-06,
+      "loss": 1.1817,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5632730732635585,
+      "grad_norm": 12.360173413460117,
+      "learning_rate": 2.3848667251734424e-06,
+      "loss": 1.1682,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5658103393593403,
+      "grad_norm": 6.111517885569779,
+      "learning_rate": 2.3627461849918604e-06,
+      "loss": 1.1526,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5683476054551221,
+      "grad_norm": 5.607775951834258,
+      "learning_rate": 2.3406364179890532e-06,
+      "loss": 1.1562,
+      "step": 2240
+    },
+    {
+      "epoch": 0.570884871550904,
+      "grad_norm": 14.959200098647552,
+      "learning_rate": 2.3185391595810635e-06,
+      "loss": 1.1592,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5734221376466857,
+      "grad_norm": 5.308853581413382,
+      "learning_rate": 2.2964561442021255e-06,
+      "loss": 1.1432,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5759594037424675,
+      "grad_norm": 7.548080678466621,
+      "learning_rate": 2.2743891051685222e-06,
+      "loss": 1.1594,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5784966698382493,
+      "grad_norm": 12.307106947771112,
+      "learning_rate": 2.2523397745425387e-06,
+      "loss": 1.1627,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5810339359340311,
+      "grad_norm": 6.981005935033202,
+      "learning_rate": 2.2303098829965124e-06,
+      "loss": 1.1669,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5835712020298128,
+      "grad_norm": 4.0554069435676805,
+      "learning_rate": 2.208301159676987e-06,
+      "loss": 1.1631,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5861084681255947,
+      "grad_norm": 5.723818233434463,
+      "learning_rate": 2.1863153320689958e-06,
+      "loss": 1.1435,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5886457342213764,
+      "grad_norm": 14.029515219171557,
+      "learning_rate": 2.164354125860462e-06,
+      "loss": 1.1499,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5911830003171583,
+      "grad_norm": 7.141317865826808,
+      "learning_rate": 2.1424192648067582e-06,
+      "loss": 1.1832,
+      "step": 2330
+    },
+    {
+      "epoch": 0.5937202664129401,
+      "grad_norm": 6.123987923859252,
+      "learning_rate": 2.120512470595396e-06,
+      "loss": 1.1503,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5962575325087218,
+      "grad_norm": 6.013035072240124,
+      "learning_rate": 2.098635462710898e-06,
+      "loss": 1.1601,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5987947986045037,
+      "grad_norm": 4.754989174196253,
+      "learning_rate": 2.0767899582998293e-06,
+      "loss": 1.1641,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6013320647002854,
+      "grad_norm": 14.321979761759893,
+      "learning_rate": 2.054977672036018e-06,
+      "loss": 1.1417,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6038693307960672,
+      "grad_norm": 10.760086157167773,
+      "learning_rate": 2.033200315985969e-06,
+      "loss": 1.1482,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6064065968918491,
+      "grad_norm": 12.684127714673926,
+      "learning_rate": 2.011459599474483e-06,
+      "loss": 1.1497,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6089438629876308,
+      "grad_norm": 6.757204304399067,
+      "learning_rate": 1.989757228950491e-06,
+      "loss": 1.1583,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6114811290834127,
+      "grad_norm": 14.606095290784646,
+      "learning_rate": 1.9680949078531097e-06,
+      "loss": 1.1528,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6140183951791944,
+      "grad_norm": 7.4618089543548995,
+      "learning_rate": 1.9464743364779388e-06,
+      "loss": 1.1594,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6165556612749762,
+      "grad_norm": 5.801205347666092,
+      "learning_rate": 1.924897211843606e-06,
+      "loss": 1.1428,
+      "step": 2430
+    },
+    {
+      "epoch": 0.619092927370758,
+      "grad_norm": 9.568596376954924,
+      "learning_rate": 1.9033652275585624e-06,
+      "loss": 1.1321,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6216301934665398,
+      "grad_norm": 6.223606964643186,
+      "learning_rate": 1.8818800736881518e-06,
+      "loss": 1.1568,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6241674595623216,
+      "grad_norm": 55.44156669240569,
+      "learning_rate": 1.8604434366219573e-06,
+      "loss": 1.1594,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6267047256581034,
+      "grad_norm": 10.778268976853173,
+      "learning_rate": 1.8390569989414303e-06,
+      "loss": 1.1588,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6292419917538852,
+      "grad_norm": 5.7854893075832745,
+      "learning_rate": 1.8177224392878279e-06,
+      "loss": 1.1535,
+      "step": 2480
+    },
+    {
+      "epoch": 0.6317792578496669,
+      "grad_norm": 13.300897200946059,
+      "learning_rate": 1.7964414322304525e-06,
+      "loss": 1.1339,
+      "step": 2490
+    },
+    {
+      "epoch": 0.6343165239454488,
+      "grad_norm": 7.933290169459755,
+      "learning_rate": 1.7752156481352123e-06,
+      "loss": 1.1388,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6368537900412305,
+      "grad_norm": 5.231248714361998,
+      "learning_rate": 1.7540467530335172e-06,
+      "loss": 1.1374,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6393910561370124,
+      "grad_norm": 8.049075294237095,
+      "learning_rate": 1.732936408491504e-06,
+      "loss": 1.1587,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6419283222327942,
+      "grad_norm": 10.356860200627077,
+      "learning_rate": 1.7118862714796253e-06,
+      "loss": 1.1572,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6444655883285759,
+      "grad_norm": 4.057173286082011,
+      "learning_rate": 1.6908979942425868e-06,
+      "loss": 1.141,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6470028544243578,
+      "grad_norm": 7.051670677225095,
+      "learning_rate": 1.6699732241696636e-06,
+      "loss": 1.1581,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6495401205201395,
+      "grad_norm": 7.595067587076725,
+      "learning_rate": 1.649113603665396e-06,
+      "loss": 1.1466,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6520773866159213,
+      "grad_norm": 6.1918160975787,
+      "learning_rate": 1.628320770020673e-06,
+      "loss": 1.1615,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6546146527117032,
+      "grad_norm": 14.301509764417062,
+      "learning_rate": 1.6075963552842211e-06,
+      "loss": 1.1641,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6571519188074849,
+      "grad_norm": 6.875665068775734,
+      "learning_rate": 1.5869419861345042e-06,
+      "loss": 1.142,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6596891849032668,
+      "grad_norm": 7.541794891346959,
+      "learning_rate": 1.5663592837520453e-06,
+      "loss": 1.1469,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6622264509990485,
+      "grad_norm": 12.46212690117266,
+      "learning_rate": 1.5458498636921727e-06,
+      "loss": 1.1598,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6647637170948303,
+      "grad_norm": 7.379528099438572,
+      "learning_rate": 1.5254153357582208e-06,
+      "loss": 1.1582,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6673009831906122,
+      "grad_norm": 4.907692232962446,
+      "learning_rate": 1.5050573038751693e-06,
+      "loss": 1.1452,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6698382492863939,
+      "grad_norm": 6.079547602614854,
+      "learning_rate": 1.4847773659637546e-06,
+      "loss": 1.1297,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6723755153821757,
+      "grad_norm": 5.450549895798723,
+      "learning_rate": 1.4645771138150433e-06,
+      "loss": 1.1603,
+      "step": 2650
+    },
+    {
+      "epoch": 0.6749127814779575,
+      "grad_norm": 4.368959175756317,
+      "learning_rate": 1.4444581329654916e-06,
+      "loss": 1.1439,
+      "step": 2660
+    },
+    {
+      "epoch": 0.6774500475737393,
+      "grad_norm": 9.44947484477195,
+      "learning_rate": 1.424422002572502e-06,
+      "loss": 1.1749,
+      "step": 2670
+    },
+    {
+      "epoch": 0.6799873136695211,
+      "grad_norm": 10.050734306484166,
+      "learning_rate": 1.404470295290461e-06,
+      "loss": 1.1545,
+      "step": 2680
+    },
+    {
+      "epoch": 0.6825245797653029,
+      "grad_norm": 12.005497232488006,
+      "learning_rate": 1.3846045771473116e-06,
+      "loss": 1.149,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6850618458610847,
+      "grad_norm": 5.9236681532953925,
+      "learning_rate": 1.3648264074216282e-06,
+      "loss": 1.1394,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6875991119568665,
+      "grad_norm": 9.66814179972378,
+      "learning_rate": 1.345137338520231e-06,
+      "loss": 1.1463,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6901363780526483,
+      "grad_norm": 37.98586030031826,
+      "learning_rate": 1.3255389158563299e-06,
+      "loss": 1.1521,
+      "step": 2720
+    },
+    {
+      "epoch": 0.69267364414843,
+      "grad_norm": 4.6889018268529705,
+      "learning_rate": 1.3060326777282312e-06,
+      "loss": 1.1437,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6952109102442119,
+      "grad_norm": 14.32310959027276,
+      "learning_rate": 1.2866201551985935e-06,
+      "loss": 1.1394,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6977481763399936,
+      "grad_norm": 6.337986082170704,
+      "learning_rate": 1.2673028719742461e-06,
+      "loss": 1.1455,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7002854424357755,
+      "grad_norm": 15.376375293741257,
+      "learning_rate": 1.2480823442866017e-06,
+      "loss": 1.1401,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7028227085315573,
+      "grad_norm": 5.041231343225159,
+      "learning_rate": 1.2289600807726406e-06,
+      "loss": 1.156,
+      "step": 2770
+    },
+    {
+      "epoch": 0.705359974627339,
+      "grad_norm": 6.869042630836821,
+      "learning_rate": 1.2099375823564948e-06,
+      "loss": 1.1615,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7078972407231209,
+      "grad_norm": 12.482011259323276,
+      "learning_rate": 1.1910163421316447e-06,
+      "loss": 1.1321,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7104345068189026,
+      "grad_norm": 6.399176247127537,
+      "learning_rate": 1.1721978452437205e-06,
+      "loss": 1.153,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7129717729146844,
+      "grad_norm": 6.270550675278331,
+      "learning_rate": 1.1534835687739323e-06,
+      "loss": 1.1551,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7155090390104663,
+      "grad_norm": 4.695573760402524,
+      "learning_rate": 1.1348749816231347e-06,
+      "loss": 1.12,
+      "step": 2820
+    },
+    {
+      "epoch": 0.718046305106248,
+      "grad_norm": 6.7962150090749995,
+      "learning_rate": 1.1163735443965298e-06,
+      "loss": 1.1684,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7205835712020298,
+      "grad_norm": 8.834255061556856,
+      "learning_rate": 1.0979807092890205e-06,
+      "loss": 1.1414,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7231208372978116,
+      "grad_norm": 6.053865837653651,
+      "learning_rate": 1.079697919971232e-06,
+      "loss": 1.1355,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7256581033935934,
+      "grad_norm": 19.55990021937961,
+      "learning_rate": 1.0615266114761932e-06,
+      "loss": 1.122,
+      "step": 2860
+    },
+    {
+      "epoch": 0.7281953694893752,
+      "grad_norm": 8.424559736567739,
+      "learning_rate": 1.0434682100866995e-06,
+      "loss": 1.1422,
+      "step": 2870
+    },
+    {
+      "epoch": 0.730732635585157,
+      "grad_norm": 5.986352186146355,
+      "learning_rate": 1.0255241332233636e-06,
+      "loss": 1.1312,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7332699016809388,
+      "grad_norm": 20.203613019858313,
+      "learning_rate": 1.0076957893333602e-06,
+      "loss": 1.1271,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7358071677767206,
+      "grad_norm": 19.714820742115197,
+      "learning_rate": 9.899845777798777e-07,
+      "loss": 1.154,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7383444338725024,
+      "grad_norm": 13.735614202784944,
+      "learning_rate": 9.723918887322757e-07,
+      "loss": 1.1359,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7408816999682841,
+      "grad_norm": 6.129734292866207,
+      "learning_rate": 9.549191030569751e-07,
+      "loss": 1.1313,
+      "step": 2920
+    },
+    {
+      "epoch": 0.743418966064066,
+      "grad_norm": 7.37718825001788,
+      "learning_rate": 9.375675922090707e-07,
+      "loss": 1.1319,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7459562321598477,
+      "grad_norm": 4.427499085813396,
+      "learning_rate": 9.203387181246831e-07,
+      "loss": 1.1399,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7484934982556296,
+      "grad_norm": 29.506989634102897,
+      "learning_rate": 9.032338331140603e-07,
+      "loss": 1.158,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7510307643514114,
+      "grad_norm": 5.7586848271722495,
+      "learning_rate": 8.862542797554341e-07,
+      "loss": 1.1486,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7535680304471931,
+      "grad_norm": 8.650793498941589,
+      "learning_rate": 8.694013907896363e-07,
+      "loss": 1.1461,
+      "step": 2970
+    },
+    {
+      "epoch": 0.756105296542975,
+      "grad_norm": 25.74372735382993,
+      "learning_rate": 8.526764890154965e-07,
+      "loss": 1.1353,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7586425626387567,
+      "grad_norm": 5.0755009425487625,
+      "learning_rate": 8.36080887186011e-07,
+      "loss": 1.1553,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7611798287345385,
+      "grad_norm": 5.4429094875047115,
+      "learning_rate": 8.19615887905301e-07,
+      "loss": 1.1598,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7637170948303204,
+      "grad_norm": 6.821786199139472,
+      "learning_rate": 8.032827835263773e-07,
+      "loss": 1.1318,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7662543609261021,
+      "grad_norm": 4.919272329647964,
+      "learning_rate": 7.87082856049696e-07,
+      "loss": 1.1188,
+      "step": 3020
+    },
+    {
+      "epoch": 0.768791627021884,
+      "grad_norm": 6.777841153958167,
+      "learning_rate": 7.710173770225335e-07,
+      "loss": 1.1351,
+      "step": 3030
+    },
+    {
+      "epoch": 0.7713288931176657,
+      "grad_norm": 9.668494091003875,
+      "learning_rate": 7.550876074391852e-07,
+      "loss": 1.1388,
+      "step": 3040
+    },
+    {
+      "epoch": 0.7738661592134475,
+      "grad_norm": 5.891510434517859,
+      "learning_rate": 7.392947976419867e-07,
+      "loss": 1.1307,
+      "step": 3050
+    },
+    {
+      "epoch": 0.7764034253092293,
+      "grad_norm": 4.629328829939173,
+      "learning_rate": 7.23640187223173e-07,
+      "loss": 1.1442,
+      "step": 3060
+    },
+    {
+      "epoch": 0.7789406914050111,
+      "grad_norm": 12.582358698587784,
+      "learning_rate": 7.081250049275804e-07,
+      "loss": 1.147,
+      "step": 3070
+    },
+    {
+      "epoch": 0.7814779575007929,
+      "grad_norm": 12.6779267097399,
+      "learning_rate": 6.927504685562075e-07,
+      "loss": 1.1461,
+      "step": 3080
+    },
+    {
+      "epoch": 0.7840152235965747,
+      "grad_norm": 4.951520708126675,
+      "learning_rate": 6.775177848706193e-07,
+      "loss": 1.1272,
+      "step": 3090
+    },
+    {
+      "epoch": 0.7865524896923565,
+      "grad_norm": 8.236149543257104,
+      "learning_rate": 6.624281494982359e-07,
+      "loss": 1.1478,
+      "step": 3100
+    },
+    {
+      "epoch": 0.7890897557881383,
+      "grad_norm": 15.16637456873453,
+      "learning_rate": 6.474827468384811e-07,
+      "loss": 1.1411,
+      "step": 3110
+    },
+    {
+      "epoch": 0.7916270218839201,
+      "grad_norm": 11.435649281181314,
+      "learning_rate": 6.326827499698218e-07,
+      "loss": 1.128,
+      "step": 3120
+    },
+    {
+      "epoch": 0.7941642879797018,
+      "grad_norm": 7.369755927934268,
+      "learning_rate": 6.180293205576873e-07,
+      "loss": 1.1503,
+      "step": 3130
+    },
+    {
+      "epoch": 0.7967015540754837,
+      "grad_norm": 7.910994986606561,
+      "learning_rate": 6.035236087632928e-07,
+      "loss": 1.1305,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7992388201712655,
+      "grad_norm": 4.538240411984233,
+      "learning_rate": 5.891667531533643e-07,
+      "loss": 1.1624,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8017760862670472,
+      "grad_norm": 7.092761380330254,
+      "learning_rate": 5.749598806107634e-07,
+      "loss": 1.1571,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8043133523628291,
+      "grad_norm": 6.547620136814868,
+      "learning_rate": 5.609041062460451e-07,
+      "loss": 1.1253,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8068506184586108,
+      "grad_norm": 5.7902809800252175,
+      "learning_rate": 5.470005333099288e-07,
+      "loss": 1.1229,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8093878845543926,
+      "grad_norm": 7.71191733136425,
+      "learning_rate": 5.332502531067007e-07,
+      "loss": 1.1279,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8119251506501745,
+      "grad_norm": 4.0181700071905295,
+      "learning_rate": 5.196543449085617e-07,
+      "loss": 1.1268,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8144624167459562,
+      "grad_norm": 8.13336313004874,
+      "learning_rate": 5.062138758709098e-07,
+      "loss": 1.1409,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8169996828417381,
+      "grad_norm": 9.802266531368725,
+      "learning_rate": 4.929299009485799e-07,
+      "loss": 1.1385,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8195369489375198,
+      "grad_norm": 6.636513914507316,
+      "learning_rate": 4.798034628130396e-07,
+      "loss": 1.1454,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8220742150333016,
+      "grad_norm": 4.227565986903538,
+      "learning_rate": 4.668355917705486e-07,
+      "loss": 1.1257,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8246114811290834,
+      "grad_norm": 8.17867439720174,
+      "learning_rate": 4.540273056812869e-07,
+      "loss": 1.1337,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8271487472248652,
+      "grad_norm": 5.424511876014973,
+      "learning_rate": 4.4137960987946707e-07,
+      "loss": 1.1265,
+      "step": 3260
+    },
+    {
+      "epoch": 0.829686013320647,
+      "grad_norm": 7.92386965501813,
+      "learning_rate": 4.2889349709441945e-07,
+      "loss": 1.1303,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8322232794164288,
+      "grad_norm": 10.370529382382568,
+      "learning_rate": 4.165699473726756e-07,
+      "loss": 1.1401,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8347605455122106,
+      "grad_norm": 7.578569844581463,
+      "learning_rate": 4.044099280010405e-07,
+      "loss": 1.1413,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8372978116079924,
+      "grad_norm": 4.726374382802555,
+      "learning_rate": 3.9241439343067205e-07,
+      "loss": 1.1189,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8398350777037742,
+      "grad_norm": 7.984970758900439,
+      "learning_rate": 3.8058428520216407e-07,
+      "loss": 1.1397,
+      "step": 3310
+    },
+    {
+      "epoch": 0.842372343799556,
+      "grad_norm": 9.346707987442102,
+      "learning_rate": 3.689205318716424e-07,
+      "loss": 1.1348,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8449096098953378,
+      "grad_norm": 5.016282437243575,
+      "learning_rate": 3.574240489378847e-07,
+      "loss": 1.1473,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8474468759911196,
+      "grad_norm": 6.2078193804951365,
+      "learning_rate": 3.4609573877046054e-07,
+      "loss": 1.1445,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8499841420869013,
+      "grad_norm": 5.5201202597039085,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 1.1434,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8525214081826832,
+      "grad_norm": 17.229253814968214,
+      "learning_rate": 3.239471801429186e-07,
+      "loss": 1.1305,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8550586742784649,
+      "grad_norm": 8.70530756713737,
+      "learning_rate": 3.1312867014363534e-07,
+      "loss": 1.1322,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8575959403742468,
+      "grad_norm": 7.012844741047474,
+      "learning_rate": 3.024818096958995e-07,
+      "loss": 1.1303,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8601332064700286,
+      "grad_norm": 4.756022687074469,
+      "learning_rate": 2.920074344816268e-07,
+      "loss": 1.1259,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8626704725658103,
+      "grad_norm": 4.7358895032579555,
+      "learning_rate": 2.8170636664420715e-07,
+      "loss": 1.1299,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8652077386615922,
+      "grad_norm": 8.683945332579281,
+      "learning_rate": 2.7157941472397393e-07,
+      "loss": 1.1496,
+      "step": 3410
+    },
+    {
+      "epoch": 0.8677450047573739,
+      "grad_norm": 5.37690958165037,
+      "learning_rate": 2.6162737359474195e-07,
+      "loss": 1.1242,
+      "step": 3420
+    },
+    {
+      "epoch": 0.8702822708531557,
+      "grad_norm": 7.164420959217891,
+      "learning_rate": 2.518510244014161e-07,
+      "loss": 1.1284,
+      "step": 3430
+    },
+    {
+      "epoch": 0.8728195369489375,
+      "grad_norm": 7.002358607609309,
+      "learning_rate": 2.4225113449867834e-07,
+      "loss": 1.1304,
+      "step": 3440
+    },
+    {
+      "epoch": 0.8753568030447193,
+      "grad_norm": 4.573582959362798,
+      "learning_rate": 2.3282845739075855e-07,
+      "loss": 1.1282,
+      "step": 3450
+    },
+    {
+      "epoch": 0.8778940691405012,
+      "grad_norm": 4.899953600348181,
+      "learning_rate": 2.2358373267229006e-07,
+      "loss": 1.1298,
+      "step": 3460
+    },
+    {
+      "epoch": 0.8804313352362829,
+      "grad_norm": 5.271497221424272,
+      "learning_rate": 2.1451768597025995e-07,
+      "loss": 1.1256,
+      "step": 3470
+    },
+    {
+      "epoch": 0.8829686013320647,
+      "grad_norm": 6.165041784465411,
+      "learning_rate": 2.0563102888705027e-07,
+      "loss": 1.1286,
+      "step": 3480
+    },
+    {
+      "epoch": 0.8855058674278465,
+      "grad_norm": 11.088879537008697,
+      "learning_rate": 1.9692445894458845e-07,
+      "loss": 1.1252,
+      "step": 3490
+    },
+    {
+      "epoch": 0.8880431335236283,
+      "grad_norm": 9.424576280240377,
+      "learning_rate": 1.883986595295953e-07,
+      "loss": 1.1151,
+      "step": 3500
+    },
+    {
+      "epoch": 0.89058039961941,
+      "grad_norm": 5.754831282009581,
+      "learning_rate": 1.8005429983994487e-07,
+      "loss": 1.1334,
+      "step": 3510
+    },
+    {
+      "epoch": 0.8931176657151919,
+      "grad_norm": 10.215467753583647,
+      "learning_rate": 1.7189203483213984e-07,
+      "loss": 1.1411,
+      "step": 3520
+    },
+    {
+      "epoch": 0.8956549318109737,
+      "grad_norm": 12.91382494925556,
+      "learning_rate": 1.6391250516990448e-07,
+      "loss": 1.1236,
+      "step": 3530
+    },
+    {
+      "epoch": 0.8981921979067554,
+      "grad_norm": 10.128521645418763,
+      "learning_rate": 1.5611633717389467e-07,
+      "loss": 1.1159,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9007294640025373,
+      "grad_norm": 9.199799321868463,
+      "learning_rate": 1.4850414277254088e-07,
+      "loss": 1.1368,
+      "step": 3550
+    },
+    {
+      "epoch": 0.903266730098319,
+      "grad_norm": 4.892191302349406,
+      "learning_rate": 1.41076519454017e-07,
+      "loss": 1.1305,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9058039961941009,
+      "grad_norm": 5.956493220397556,
+      "learning_rate": 1.3383405021933998e-07,
+      "loss": 1.1264,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9083412622898827,
+      "grad_norm": 5.275784999413581,
+      "learning_rate": 1.267773035366135e-07,
+      "loss": 1.1195,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9108785283856644,
+      "grad_norm": 9.540366769966049,
+      "learning_rate": 1.1990683329640567e-07,
+      "loss": 1.1381,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9134157944814463,
+      "grad_norm": 4.801855741665693,
+      "learning_rate": 1.1322317876827416e-07,
+      "loss": 1.1315,
+      "step": 3600
+    },
+    {
+      "epoch": 0.915953060577228,
+      "grad_norm": 5.056163865646408,
+      "learning_rate": 1.0672686455843934e-07,
+      "loss": 1.1382,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9184903266730098,
+      "grad_norm": 8.706560880258346,
+      "learning_rate": 1.004184005686068e-07,
+      "loss": 1.119,
+      "step": 3620
+    },
+    {
+      "epoch": 0.9210275927687916,
+      "grad_norm": 6.266874220907701,
+      "learning_rate": 9.429828195594459e-08,
+      "loss": 1.1316,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9235648588645734,
+      "grad_norm": 4.598497385552673,
+      "learning_rate": 8.836698909421848e-08,
+      "loss": 1.1316,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9261021249603553,
+      "grad_norm": 5.423769767831511,
+      "learning_rate": 8.2624987536086e-08,
+      "loss": 1.1305,
+      "step": 3650
+    },
+    {
+      "epoch": 0.928639391056137,
+      "grad_norm": 7.1199155337882045,
+      "learning_rate": 7.707272797655597e-08,
+      "loss": 1.104,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9311766571519188,
+      "grad_norm": 5.964210281087181,
+      "learning_rate": 7.171064621761121e-08,
+      "loss": 1.1392,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9337139232477006,
+      "grad_norm": 7.0222277210918485,
+      "learning_rate": 6.653916313400483e-08,
+      "loss": 1.1307,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9362511893434824,
+      "grad_norm": 6.820545499544659,
+      "learning_rate": 6.155868464022218e-08,
+      "loss": 1.1311,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9387884554392641,
+      "grad_norm": 8.543306468091403,
+      "learning_rate": 5.676960165862333e-08,
+      "loss": 1.1396,
+      "step": 3700
+    },
+    {
+      "epoch": 0.941325721535046,
+      "grad_norm": 5.998847968884944,
+      "learning_rate": 5.217229008875696e-08,
+      "loss": 1.1142,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9438629876308278,
+      "grad_norm": 7.233927115402458,
+      "learning_rate": 4.7767110777856285e-08,
+      "loss": 1.1316,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9464002537266096,
+      "grad_norm": 14.818426116599344,
+      "learning_rate": 4.355440949251638e-08,
+      "loss": 1.1291,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9489375198223914,
+      "grad_norm": 11.275146260000886,
+      "learning_rate": 3.953451689155369e-08,
+      "loss": 1.1377,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9514747859181731,
+      "grad_norm": 4.976497150845647,
+      "learning_rate": 3.5707748500053706e-08,
+      "loss": 1.1341,
+      "step": 3750
+    },
+    {
+      "epoch": 0.954012052013955,
+      "grad_norm": 8.165947802169324,
+      "learning_rate": 3.2074404684603325e-08,
+      "loss": 1.1131,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9565493181097368,
+      "grad_norm": 7.141736239500508,
+      "learning_rate": 2.863477062971659e-08,
+      "loss": 1.1354,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9590865842055185,
+      "grad_norm": 6.6723385448588814,
+      "learning_rate": 2.5389116315448768e-08,
+      "loss": 1.1349,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9616238503013004,
+      "grad_norm": 9.205939869377257,
+      "learning_rate": 2.2337696496206317e-08,
+      "loss": 1.1358,
+      "step": 3790
+    },
+    {
+      "epoch": 0.9641611163970821,
+      "grad_norm": 6.430232530777119,
+      "learning_rate": 1.948075068075067e-08,
+      "loss": 1.1454,
+      "step": 3800
+    },
+    {
+      "epoch": 0.966698382492864,
+      "grad_norm": 4.597818211923664,
+      "learning_rate": 1.6818503113398832e-08,
+      "loss": 1.121,
+      "step": 3810
+    },
+    {
+      "epoch": 0.9692356485886457,
+      "grad_norm": 11.864724480832432,
+      "learning_rate": 1.4351162756422454e-08,
+      "loss": 1.1279,
+      "step": 3820
+    },
+    {
+      "epoch": 0.9717729146844275,
+      "grad_norm": 10.20794178542716,
+      "learning_rate": 1.2078923273646236e-08,
+      "loss": 1.1423,
+      "step": 3830
+    },
+    {
+      "epoch": 0.9743101807802094,
+      "grad_norm": 6.419864028983356,
+      "learning_rate": 1.0001963015247585e-08,
+      "loss": 1.1206,
+      "step": 3840
+    },
+    {
+      "epoch": 0.9768474468759911,
+      "grad_norm": 6.587741451008303,
+      "learning_rate": 8.120445003755306e-09,
+      "loss": 1.1429,
+      "step": 3850
+    },
+    {
+      "epoch": 0.9793847129717729,
+      "grad_norm": 4.807651227856488,
+      "learning_rate": 6.434516921257905e-09,
+      "loss": 1.1184,
+      "step": 3860
+    },
+    {
+      "epoch": 0.9819219790675547,
+      "grad_norm": 17.54136739327046,
+      "learning_rate": 4.9443110978078525e-09,
+      "loss": 1.143,
+      "step": 3870
+    },
+    {
+      "epoch": 0.9844592451633365,
+      "grad_norm": 84.07353671535705,
+      "learning_rate": 3.649944501037672e-09,
+      "loss": 1.1314,
+      "step": 3880
+    },
+    {
+      "epoch": 0.9869965112591182,
+      "grad_norm": 5.176156752927596,
+      "learning_rate": 2.5515187269772866e-09,
+      "loss": 1.1163,
+      "step": 3890
+    },
+    {
+      "epoch": 0.9895337773549001,
+      "grad_norm": 4.911729600848666,
+      "learning_rate": 1.6491199920809498e-09,
+      "loss": 1.1519,
+      "step": 3900
+    },
+    {
+      "epoch": 0.9920710434506819,
+      "grad_norm": 5.8502366235556345,
+      "learning_rate": 9.428191264596042e-10,
+      "loss": 1.1472,
+      "step": 3910
+    },
+    {
+      "epoch": 0.9946083095464637,
+      "grad_norm": 17.952194768106622,
+      "learning_rate": 4.3267156832033085e-10,
+      "loss": 1.1114,
+      "step": 3920
+    },
+    {
+      "epoch": 0.9971455756422455,
+      "grad_norm": 13.67739524605559,
+      "learning_rate": 1.187173596167712e-10,
+      "loss": 1.1338,
+      "step": 3930
+    },
+    {
+      "epoch": 0.9996828417380272,
+      "grad_norm": 10.095200847738084,
+      "learning_rate": 9.811429044215282e-13,
+      "loss": 1.1399,
+      "step": 3940
+    },
+    {
+      "epoch": 0.9999365683476055,
+      "step": 3941,
+      "total_flos": 2.4957269414919537e+18,
+      "train_loss": 1.201914404482746,
+      "train_runtime": 115316.4416,
+      "train_samples_per_second": 4.375,
+      "train_steps_per_second": 0.034
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3941,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4957269414919537e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fae0cd9b7ab758f195aa7cfb41094c42712228f1944485b09f22cbd2f987f37
+size 7160