Upload folder using huggingface_hub (#1)

- 40eea4af8b61274eacc827cb81672391d6c56440c76600897fc926c22ca7dd11 (980bdb9ae43da5329f4bce67c01317b78da46283)
- 49366e3724080b95425808e7d26202ccdce210eec363fe8c6f7d777c17d689d3 (9b6c218592bb389e969e7b17d779427f7325d99c)
- cf1802961afbc3dce27e74c60b61c0dc5bd220079e7a95507270a29da373f778 (63e8b8f416f98b770107f70cf304f192918df37c)
- b8f683d8e2bf7f94fdd1123c9107ffc200116d9466f661ef8f7fe46bf60273bf (9a43bcd5642032741368b33b27f0d82a9bbe6cf4)
- 432ca87bf09b49a0aebeff82146ecf26e530e4756c49d31d0a2e6492e1bad393 (c6ffea010fe9a42f44f66a1c3599ad6400ed6fe3)

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9992659652556888,
+    "total_flos": 1.136081069573931e+18,
+    "train_loss": 1.019411426333092,
+    "train_runtime": 37962.3304,
+    "train_samples_per_second": 3.444,
+    "train_steps_per_second": 0.027
+}

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 sha256:90b483ddea09ca66fe60c12f733117fe46c4ad777892abb7cb0e9f2a08d43309
+size 4992622346

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5819394ee50aa7f1e9527240376ff7fd0548822c04e2488779885fbed422e1
+size 4966251712

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c0e3ab638e77a23e285ec4e4c5bd13bf368aaa7f27779af89b7b23608e315f
+size 4915919704

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36771359cda9de186961c3c8b9cdf336e92ae56bb4f56788c214fbb6a50b9ad
+size 4999823980

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0fb4e57a167ce436f15062d368d26cd148cb199c7d4284c1e1149db42d1c35
+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": 0.9992659652556888,
+    "total_flos": 1.136081069573931e+18,
+    "train_loss": 1.019411426333092,
+    "train_runtime": 37962.3304,
+    "train_samples_per_second": 3.444,
+    "train_steps_per_second": 0.027
+}

trainer_log.jsonl

@@ -0,0 +1,103 @@
+{"current_steps": 10, "total_steps": 1021, "loss": 1.5489, "learning_rate": 4.854368932038835e-07, "epoch": 0.009787129924149743, "percentage": 0.98, "elapsed_time": "0:05:21", "remaining_time": "9:02:16"}
+{"current_steps": 20, "total_steps": 1021, "loss": 1.4928, "learning_rate": 9.70873786407767e-07, "epoch": 0.019574259848299486, "percentage": 1.96, "elapsed_time": "0:10:41", "remaining_time": "8:55:25"}
+{"current_steps": 30, "total_steps": 1021, "loss": 1.3729, "learning_rate": 1.4563106796116506e-06, "epoch": 0.029361389772449228, "percentage": 2.94, "elapsed_time": "0:16:06", "remaining_time": "8:52:22"}
+{"current_steps": 40, "total_steps": 1021, "loss": 1.2475, "learning_rate": 1.941747572815534e-06, "epoch": 0.03914851969659897, "percentage": 3.92, "elapsed_time": "0:21:34", "remaining_time": "8:48:58"}
+{"current_steps": 50, "total_steps": 1021, "loss": 1.1889, "learning_rate": 2.427184466019418e-06, "epoch": 0.048935649620748714, "percentage": 4.9, "elapsed_time": "0:26:49", "remaining_time": "8:40:48"}
+{"current_steps": 60, "total_steps": 1021, "loss": 1.1427, "learning_rate": 2.912621359223301e-06, "epoch": 0.058722779544898455, "percentage": 5.88, "elapsed_time": "0:32:09", "remaining_time": "8:34:59"}
+{"current_steps": 70, "total_steps": 1021, "loss": 1.0896, "learning_rate": 3.398058252427185e-06, "epoch": 0.0685099094690482, "percentage": 6.86, "elapsed_time": "0:37:26", "remaining_time": "8:28:41"}
+{"current_steps": 80, "total_steps": 1021, "loss": 1.104, "learning_rate": 3.883495145631068e-06, "epoch": 0.07829703939319795, "percentage": 7.84, "elapsed_time": "0:42:44", "remaining_time": "8:22:49"}
+{"current_steps": 90, "total_steps": 1021, "loss": 1.0746, "learning_rate": 4.368932038834952e-06, "epoch": 0.0880841693173477, "percentage": 8.81, "elapsed_time": "0:48:09", "remaining_time": "8:18:07"}
+{"current_steps": 100, "total_steps": 1021, "loss": 1.0793, "learning_rate": 4.854368932038836e-06, "epoch": 0.09787129924149743, "percentage": 9.79, "elapsed_time": "0:53:27", "remaining_time": "8:12:17"}
+{"current_steps": 110, "total_steps": 1021, "loss": 1.0692, "learning_rate": 4.999282701856139e-06, "epoch": 0.10765842916564718, "percentage": 10.77, "elapsed_time": "0:58:42", "remaining_time": "8:06:12"}
+{"current_steps": 120, "total_steps": 1021, "loss": 1.0731, "learning_rate": 4.995770395678171e-06, "epoch": 0.11744555908979691, "percentage": 11.75, "elapsed_time": "1:03:58", "remaining_time": "8:00:19"}
+{"current_steps": 130, "total_steps": 1021, "loss": 1.0464, "learning_rate": 4.989335440737587e-06, "epoch": 0.12723268901394666, "percentage": 12.73, "elapsed_time": "1:09:12", "remaining_time": "7:54:19"}
+{"current_steps": 140, "total_steps": 1021, "loss": 1.0434, "learning_rate": 4.979985372628657e-06, "epoch": 0.1370198189380964, "percentage": 13.71, "elapsed_time": "1:14:39", "remaining_time": "7:49:46"}
+{"current_steps": 150, "total_steps": 1021, "loss": 1.0441, "learning_rate": 4.967731140661878e-06, "epoch": 0.14680694886224616, "percentage": 14.69, "elapsed_time": "1:19:58", "remaining_time": "7:44:22"}
+{"current_steps": 160, "total_steps": 1021, "loss": 1.0386, "learning_rate": 4.952587095041882e-06, "epoch": 0.1565940787863959, "percentage": 15.67, "elapsed_time": "1:25:22", "remaining_time": "7:39:26"}
+{"current_steps": 170, "total_steps": 1021, "loss": 1.0565, "learning_rate": 4.934570970062765e-06, "epoch": 0.16638120871054562, "percentage": 16.65, "elapsed_time": "1:30:44", "remaining_time": "7:34:15"}
+{"current_steps": 180, "total_steps": 1021, "loss": 1.0441, "learning_rate": 4.913703863340504e-06, "epoch": 0.1761683386346954, "percentage": 17.63, "elapsed_time": "1:36:04", "remaining_time": "7:28:52"}
+{"current_steps": 190, "total_steps": 1021, "loss": 1.0396, "learning_rate": 4.890010211106795e-06, "epoch": 0.18595546855884512, "percentage": 18.61, "elapsed_time": "1:41:24", "remaining_time": "7:23:30"}
+{"current_steps": 200, "total_steps": 1021, "loss": 1.0295, "learning_rate": 4.86351775959322e-06, "epoch": 0.19574259848299486, "percentage": 19.59, "elapsed_time": "1:46:41", "remaining_time": "7:17:57"}
+{"current_steps": 210, "total_steps": 1021, "loss": 1.0465, "learning_rate": 4.834257532539292e-06, "epoch": 0.20552972840714462, "percentage": 20.57, "elapsed_time": "1:51:51", "remaining_time": "7:11:59"}
+{"current_steps": 220, "total_steps": 1021, "loss": 1.017, "learning_rate": 4.802263794862385e-06, "epoch": 0.21531685833129435, "percentage": 21.55, "elapsed_time": "1:57:05", "remaining_time": "7:06:20"}
+{"current_steps": 230, "total_steps": 1021, "loss": 1.0176, "learning_rate": 4.767574012532121e-06, "epoch": 0.2251039882554441, "percentage": 22.53, "elapsed_time": "2:02:18", "remaining_time": "7:00:38"}
+{"current_steps": 240, "total_steps": 1021, "loss": 1.0174, "learning_rate": 4.730228808696201e-06, "epoch": 0.23489111817959382, "percentage": 23.51, "elapsed_time": "2:07:37", "remaining_time": "6:55:19"}
+{"current_steps": 250, "total_steps": 1021, "loss": 1.0174, "learning_rate": 4.690271916109034e-06, "epoch": 0.24467824810374358, "percentage": 24.49, "elapsed_time": "2:12:48", "remaining_time": "6:49:35"}
+{"current_steps": 260, "total_steps": 1021, "loss": 1.0168, "learning_rate": 4.647750125918909e-06, "epoch": 0.2544653780278933, "percentage": 25.47, "elapsed_time": "2:17:59", "remaining_time": "6:43:53"}
+{"current_steps": 270, "total_steps": 1021, "loss": 1.0351, "learning_rate": 4.6027132328736515e-06, "epoch": 0.2642525079520431, "percentage": 26.44, "elapsed_time": "2:23:14", "remaining_time": "6:38:24"}
+{"current_steps": 280, "total_steps": 1021, "loss": 1.0105, "learning_rate": 4.555213977008946e-06, "epoch": 0.2740396378761928, "percentage": 27.42, "elapsed_time": "2:28:30", "remaining_time": "6:33:01"}
+{"current_steps": 290, "total_steps": 1021, "loss": 1.0227, "learning_rate": 4.50530798188761e-06, "epoch": 0.28382676780034255, "percentage": 28.4, "elapsed_time": "2:34:00", "remaining_time": "6:28:12"}
+{"current_steps": 300, "total_steps": 1021, "loss": 1.0178, "learning_rate": 4.453053689462131e-06, "epoch": 0.2936138977244923, "percentage": 29.38, "elapsed_time": "2:39:16", "remaining_time": "6:22:46"}
+{"current_steps": 310, "total_steps": 1021, "loss": 1.0091, "learning_rate": 4.398512291636768e-06, "epoch": 0.303401027648642, "percentage": 30.36, "elapsed_time": "2:44:32", "remaining_time": "6:17:22"}
+{"current_steps": 320, "total_steps": 1021, "loss": 1.0196, "learning_rate": 4.341747658609332e-06, "epoch": 0.3131881575727918, "percentage": 31.34, "elapsed_time": "2:49:51", "remaining_time": "6:12:06"}
+{"current_steps": 330, "total_steps": 1021, "loss": 1.0142, "learning_rate": 4.282826264076587e-06, "epoch": 0.32297528749694154, "percentage": 32.32, "elapsed_time": "2:55:05", "remaining_time": "6:06:38"}
+{"current_steps": 340, "total_steps": 1021, "loss": 1.0014, "learning_rate": 4.221817107390847e-06, "epoch": 0.33276241742109125, "percentage": 33.3, "elapsed_time": "3:00:18", "remaining_time": "6:01:09"}
+{"current_steps": 350, "total_steps": 1021, "loss": 1.0297, "learning_rate": 4.15879163275892e-06, "epoch": 0.342549547345241, "percentage": 34.28, "elapsed_time": "3:05:29", "remaining_time": "5:55:37"}
+{"current_steps": 360, "total_steps": 1021, "loss": 1.0155, "learning_rate": 4.093823645578037e-06, "epoch": 0.3523366772693908, "percentage": 35.26, "elapsed_time": "3:10:50", "remaining_time": "5:50:23"}
+{"current_steps": 370, "total_steps": 1021, "loss": 1.0136, "learning_rate": 4.02698922600672e-06, "epoch": 0.3621238071935405, "percentage": 36.24, "elapsed_time": "3:16:05", "remaining_time": "5:45:00"}
+{"current_steps": 380, "total_steps": 1021, "loss": 0.9889, "learning_rate": 3.958366639871826e-06, "epoch": 0.37191093711769024, "percentage": 37.22, "elapsed_time": "3:21:23", "remaining_time": "5:39:43"}
+{"current_steps": 390, "total_steps": 1021, "loss": 0.9959, "learning_rate": 3.888036247016073e-06, "epoch": 0.38169806704184, "percentage": 38.2, "elapsed_time": "3:26:42", "remaining_time": "5:34:26"}
+{"current_steps": 400, "total_steps": 1021, "loss": 1.0049, "learning_rate": 3.81608040719339e-06, "epoch": 0.3914851969659897, "percentage": 39.18, "elapsed_time": "3:31:57", "remaining_time": "5:29:03"}
+{"current_steps": 410, "total_steps": 1021, "loss": 1.0018, "learning_rate": 3.7425833836222947e-06, "epoch": 0.4012723268901395, "percentage": 40.16, "elapsed_time": "3:37:07", "remaining_time": "5:23:34"}
+{"current_steps": 420, "total_steps": 1021, "loss": 1.0152, "learning_rate": 3.6676312443102323e-06, "epoch": 0.41105945681428924, "percentage": 41.14, "elapsed_time": "3:42:34", "remaining_time": "5:18:29"}
+{"current_steps": 430, "total_steps": 1021, "loss": 1.0056, "learning_rate": 3.591311761264433e-06, "epoch": 0.42084658673843894, "percentage": 42.12, "elapsed_time": "3:47:49", "remaining_time": "5:13:08"}
+{"current_steps": 440, "total_steps": 1021, "loss": 0.9988, "learning_rate": 3.513714307707321e-06, "epoch": 0.4306337166625887, "percentage": 43.1, "elapsed_time": "3:53:08", "remaining_time": "5:07:50"}
+{"current_steps": 450, "total_steps": 1021, "loss": 0.9973, "learning_rate": 3.4349297534168242e-06, "epoch": 0.4404208465867384, "percentage": 44.07, "elapsed_time": "3:58:29", "remaining_time": "5:02:37"}
+{"current_steps": 460, "total_steps": 1021, "loss": 0.9841, "learning_rate": 3.3550503583141726e-06, "epoch": 0.4502079765108882, "percentage": 45.05, "elapsed_time": "4:03:47", "remaining_time": "4:57:18"}
+{"current_steps": 470, "total_steps": 1021, "loss": 0.9991, "learning_rate": 3.274169664423768e-06, "epoch": 0.45999510643503794, "percentage": 46.03, "elapsed_time": "4:09:09", "remaining_time": "4:52:05"}
+{"current_steps": 480, "total_steps": 1021, "loss": 0.9992, "learning_rate": 3.192382386331667e-06, "epoch": 0.46978223635918764, "percentage": 47.01, "elapsed_time": "4:14:25", "remaining_time": "4:46:45"}
+{"current_steps": 490, "total_steps": 1021, "loss": 1.004, "learning_rate": 3.109784300270943e-06, "epoch": 0.4795693662833374, "percentage": 47.99, "elapsed_time": "4:19:43", "remaining_time": "4:41:27"}
+{"current_steps": 500, "total_steps": 1021, "loss": 0.9892, "learning_rate": 3.0264721319638176e-06, "epoch": 0.48935649620748717, "percentage": 48.97, "elapsed_time": "4:25:06", "remaining_time": "4:36:14"}
+{"current_steps": 510, "total_steps": 1021, "loss": 0.9991, "learning_rate": 2.9425434433518985e-06, "epoch": 0.4991436261316369, "percentage": 49.95, "elapsed_time": "4:40:05", "remaining_time": "4:40:38"}
+{"current_steps": 520, "total_steps": 1021, "loss": 0.9946, "learning_rate": 2.8580965183471794e-06, "epoch": 0.5089307560557866, "percentage": 50.93, "elapsed_time": "4:46:05", "remaining_time": "4:35:38"}
+{"current_steps": 530, "total_steps": 1021, "loss": 1.0007, "learning_rate": 2.773230247737569e-06, "epoch": 0.5187178859799364, "percentage": 51.91, "elapsed_time": "4:52:07", "remaining_time": "4:30:37"}
+{"current_steps": 540, "total_steps": 1021, "loss": 0.997, "learning_rate": 2.6880440133817563e-06, "epoch": 0.5285050159040862, "percentage": 52.89, "elapsed_time": "4:58:32", "remaining_time": "4:25:54"}
+{"current_steps": 550, "total_steps": 1021, "loss": 0.9916, "learning_rate": 2.602637571829009e-06, "epoch": 0.5382921458282359, "percentage": 53.87, "elapsed_time": "5:05:27", "remaining_time": "4:21:35"}
+{"current_steps": 560, "total_steps": 1021, "loss": 0.9921, "learning_rate": 2.517110937500185e-06, "epoch": 0.5480792757523856, "percentage": 54.85, "elapsed_time": "5:13:48", "remaining_time": "4:18:19"}
+{"current_steps": 570, "total_steps": 1021, "loss": 0.9998, "learning_rate": 2.431564265566781e-06, "epoch": 0.5578664056765353, "percentage": 55.83, "elapsed_time": "5:21:38", "remaining_time": "4:14:29"}
+{"current_steps": 580, "total_steps": 1021, "loss": 0.9871, "learning_rate": 2.346097734665143e-06, "epoch": 0.5676535356006851, "percentage": 56.81, "elapsed_time": "5:28:09", "remaining_time": "4:09:30"}
+{"current_steps": 590, "total_steps": 1021, "loss": 0.9979, "learning_rate": 2.2608114295832053e-06, "epoch": 0.5774406655248349, "percentage": 57.79, "elapsed_time": "5:33:55", "remaining_time": "4:03:55"}
+{"current_steps": 600, "total_steps": 1021, "loss": 0.9724, "learning_rate": 2.175805224057129e-06, "epoch": 0.5872277954489846, "percentage": 58.77, "elapsed_time": "5:39:39", "remaining_time": "3:58:19"}
+{"current_steps": 610, "total_steps": 1021, "loss": 0.9937, "learning_rate": 2.0911786638150873e-06, "epoch": 0.5970149253731343, "percentage": 59.75, "elapsed_time": "5:45:28", "remaining_time": "3:52:46"}
+{"current_steps": 620, "total_steps": 1021, "loss": 0.9859, "learning_rate": 2.0070308500051715e-06, "epoch": 0.606802055297284, "percentage": 60.72, "elapsed_time": "5:50:58", "remaining_time": "3:47:00"}
+{"current_steps": 630, "total_steps": 1021, "loss": 0.9841, "learning_rate": 1.9234603231439e-06, "epoch": 0.6165891852214338, "percentage": 61.7, "elapsed_time": "5:56:13", "remaining_time": "3:41:05"}
+{"current_steps": 640, "total_steps": 1021, "loss": 0.9749, "learning_rate": 1.84056494772127e-06, "epoch": 0.6263763151455836, "percentage": 62.68, "elapsed_time": "6:01:23", "remaining_time": "3:35:08"}
+{"current_steps": 650, "total_steps": 1021, "loss": 0.985, "learning_rate": 1.7584417975974535e-06, "epoch": 0.6361634450697333, "percentage": 63.66, "elapsed_time": "6:06:48", "remaining_time": "3:29:21"}
+{"current_steps": 660, "total_steps": 1021, "loss": 0.9823, "learning_rate": 1.6771870423253473e-06, "epoch": 0.6459505749938831, "percentage": 64.64, "elapsed_time": "6:12:03", "remaining_time": "3:23:30"}
+{"current_steps": 670, "total_steps": 1021, "loss": 0.9905, "learning_rate": 1.5968958345321178e-06, "epoch": 0.6557377049180327, "percentage": 65.62, "elapsed_time": "6:17:15", "remaining_time": "3:17:38"}
+{"current_steps": 680, "total_steps": 1021, "loss": 0.9802, "learning_rate": 1.517662198491599e-06, "epoch": 0.6655248348421825, "percentage": 66.6, "elapsed_time": "6:22:30", "remaining_time": "3:11:48"}
+{"current_steps": 690, "total_steps": 1021, "loss": 0.9839, "learning_rate": 1.4395789200180343e-06, "epoch": 0.6753119647663323, "percentage": 67.58, "elapsed_time": "6:27:44", "remaining_time": "3:06:00"}
+{"current_steps": 700, "total_steps": 1021, "loss": 0.9746, "learning_rate": 1.362737437810114e-06, "epoch": 0.685099094690482, "percentage": 68.56, "elapsed_time": "6:32:58", "remaining_time": "3:00:12"}
+{"current_steps": 710, "total_steps": 1021, "loss": 0.9662, "learning_rate": 1.287227736372538e-06, "epoch": 0.6948862246146318, "percentage": 69.54, "elapsed_time": "6:38:11", "remaining_time": "2:54:25"}
+{"current_steps": 720, "total_steps": 1021, "loss": 0.9654, "learning_rate": 1.2131382406404866e-06, "epoch": 0.7046733545387815, "percentage": 70.52, "elapsed_time": "6:43:28", "remaining_time": "2:48:40"}
+{"current_steps": 730, "total_steps": 1021, "loss": 0.9687, "learning_rate": 1.1405557124304338e-06, "epoch": 0.7144604844629312, "percentage": 71.5, "elapsed_time": "6:48:48", "remaining_time": "2:42:57"}
+{"current_steps": 740, "total_steps": 1021, "loss": 0.9764, "learning_rate": 1.0695651488385168e-06, "epoch": 0.724247614387081, "percentage": 72.48, "elapsed_time": "6:54:06", "remaining_time": "2:37:14"}
+{"current_steps": 750, "total_steps": 1021, "loss": 0.9734, "learning_rate": 1.0002496827054806e-06, "epoch": 0.7340347443112307, "percentage": 73.46, "elapsed_time": "6:59:18", "remaining_time": "2:31:30"}
+{"current_steps": 760, "total_steps": 1021, "loss": 0.9731, "learning_rate": 9.326904852647345e-07, "epoch": 0.7438218742353805, "percentage": 74.44, "elapsed_time": "7:04:40", "remaining_time": "2:25:50"}
+{"current_steps": 770, "total_steps": 1021, "loss": 0.9717, "learning_rate": 8.669666710875319e-07, "epoch": 0.7536090041595302, "percentage": 75.42, "elapsed_time": "7:10:00", "remaining_time": "2:20:10"}
+{"current_steps": 780, "total_steps": 1021, "loss": 0.9721, "learning_rate": 8.031552054365905e-07, "epoch": 0.76339613408368, "percentage": 76.4, "elapsed_time": "7:15:19", "remaining_time": "2:14:30"}
+{"current_steps": 790, "total_steps": 1021, "loss": 0.9925, "learning_rate": 7.413308141366254e-07, "epoch": 0.7731832640078297, "percentage": 77.38, "elapsed_time": "7:20:36", "remaining_time": "2:08:50"}
+{"current_steps": 800, "total_steps": 1021, "loss": 0.9581, "learning_rate": 6.815658960673782e-07, "epoch": 0.7829703939319794, "percentage": 78.35, "elapsed_time": "7:25:50", "remaining_time": "2:03:09"}
+{"current_steps": 810, "total_steps": 1021, "loss": 0.9699, "learning_rate": 6.239304383815706e-07, "epoch": 0.7927575238561292, "percentage": 79.33, "elapsed_time": "7:31:05", "remaining_time": "1:57:30"}
+{"current_steps": 820, "total_steps": 1021, "loss": 0.9905, "learning_rate": 5.684919345471029e-07, "epoch": 0.802544653780279, "percentage": 80.31, "elapsed_time": "7:36:15", "remaining_time": "1:51:50"}
+{"current_steps": 830, "total_steps": 1021, "loss": 0.973, "learning_rate": 5.15315305309455e-07, "epoch": 0.8123317837044287, "percentage": 81.29, "elapsed_time": "7:41:32", "remaining_time": "1:46:12"}
+{"current_steps": 840, "total_steps": 1021, "loss": 0.9582, "learning_rate": 4.644628226668485e-07, "epoch": 0.8221189136285785, "percentage": 82.27, "elapsed_time": "7:46:44", "remaining_time": "1:40:34"}
+{"current_steps": 850, "total_steps": 1021, "loss": 0.9729, "learning_rate": 4.159940369472015e-07, "epoch": 0.8319060435527281, "percentage": 83.25, "elapsed_time": "7:52:04", "remaining_time": "1:34:58"}
+{"current_steps": 860, "total_steps": 1021, "loss": 0.9761, "learning_rate": 3.699657070722698e-07, "epoch": 0.8416931734768779, "percentage": 84.23, "elapsed_time": "7:57:18", "remaining_time": "1:29:21"}
+{"current_steps": 870, "total_steps": 1021, "loss": 0.9818, "learning_rate": 3.2643173409063976e-07, "epoch": 0.8514803034010276, "percentage": 85.21, "elapsed_time": "8:02:34", "remaining_time": "1:23:45"}
+{"current_steps": 880, "total_steps": 1021, "loss": 0.9636, "learning_rate": 2.854430980574002e-07, "epoch": 0.8612674333251774, "percentage": 86.19, "elapsed_time": "8:07:46", "remaining_time": "1:18:09"}
+{"current_steps": 890, "total_steps": 1021, "loss": 0.9636, "learning_rate": 2.4704779833442993e-07, "epoch": 0.8710545632493272, "percentage": 87.17, "elapsed_time": "8:13:02", "remaining_time": "1:12:34"}
+{"current_steps": 900, "total_steps": 1021, "loss": 0.963, "learning_rate": 2.1129079738118424e-07, "epoch": 0.8808416931734768, "percentage": 88.15, "elapsed_time": "8:18:17", "remaining_time": "1:06:59"}
+{"current_steps": 910, "total_steps": 1021, "loss": 0.9757, "learning_rate": 1.782139681018244e-07, "epoch": 0.8906288230976266, "percentage": 89.13, "elapsed_time": "8:23:32", "remaining_time": "1:01:25"}
+{"current_steps": 920, "total_steps": 1021, "loss": 0.9678, "learning_rate": 1.4785604481034639e-07, "epoch": 0.9004159530217763, "percentage": 90.11, "elapsed_time": "8:28:46", "remaining_time": "0:55:51"}
+{"current_steps": 930, "total_steps": 1021, "loss": 0.9595, "learning_rate": 1.202525778711172e-07, "epoch": 0.9102030829459261, "percentage": 91.09, "elapsed_time": "8:33:58", "remaining_time": "0:50:17"}
+{"current_steps": 940, "total_steps": 1021, "loss": 0.98, "learning_rate": 9.54358920679524e-08, "epoch": 0.9199902128700759, "percentage": 92.07, "elapsed_time": "8:39:21", "remaining_time": "0:44:45"}
+{"current_steps": 950, "total_steps": 1021, "loss": 0.964, "learning_rate": 7.343504875047814e-08, "epoch": 0.9297773427942256, "percentage": 93.05, "elapsed_time": "8:44:37", "remaining_time": "0:39:12"}
+{"current_steps": 960, "total_steps": 1021, "loss": 0.979, "learning_rate": 5.427581180210639e-08, "epoch": 0.9395644727183753, "percentage": 94.03, "elapsed_time": "8:50:02", "remaining_time": "0:33:40"}
+{"current_steps": 970, "total_steps": 1021, "loss": 0.9578, "learning_rate": 3.798061746947995e-08, "epoch": 0.949351602642525, "percentage": 95.0, "elapsed_time": "8:55:37", "remaining_time": "0:28:09"}
+{"current_steps": 980, "total_steps": 1021, "loss": 0.9759, "learning_rate": 2.456854808871201e-08, "epoch": 0.9591387325666748, "percentage": 95.98, "elapsed_time": "9:00:55", "remaining_time": "0:22:37"}
+{"current_steps": 990, "total_steps": 1021, "loss": 0.9691, "learning_rate": 1.4055309739195166e-08, "epoch": 0.9689258624908246, "percentage": 96.96, "elapsed_time": "9:06:26", "remaining_time": "0:17:06"}
+{"current_steps": 1000, "total_steps": 1021, "loss": 0.9866, "learning_rate": 6.453213851142226e-09, "epoch": 0.9787129924149743, "percentage": 97.94, "elapsed_time": "9:11:39", "remaining_time": "0:11:35"}
+{"current_steps": 1010, "total_steps": 1021, "loss": 0.9735, "learning_rate": 1.7711627883998383e-09, "epoch": 0.9885001223391241, "percentage": 98.92, "elapsed_time": "9:26:07", "remaining_time": "0:06:09"}
+{"current_steps": 1020, "total_steps": 1021, "loss": 0.9689, "learning_rate": 1.463942341850544e-11, "epoch": 0.9982872522632737, "percentage": 99.9, "elapsed_time": "9:31:51", "remaining_time": "0:00:33"}
+{"current_steps": 1021, "total_steps": 1021, "epoch": 0.9992659652556888, "percentage": 100.0, "elapsed_time": "10:32:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,756 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9992659652556888,
+  "eval_steps": 500,
+  "global_step": 1021,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009787129924149743,
+      "grad_norm": 90.15490074334751,
+      "learning_rate": 4.854368932038835e-07,
+      "loss": 1.5489,
+      "step": 10
+    },
+    {
+      "epoch": 0.019574259848299486,
+      "grad_norm": 58.23453270743763,
+      "learning_rate": 9.70873786407767e-07,
+      "loss": 1.4928,
+      "step": 20
+    },
+    {
+      "epoch": 0.029361389772449228,
+      "grad_norm": 16.767612840452053,
+      "learning_rate": 1.4563106796116506e-06,
+      "loss": 1.3729,
+      "step": 30
+    },
+    {
+      "epoch": 0.03914851969659897,
+      "grad_norm": 11.079321586087117,
+      "learning_rate": 1.941747572815534e-06,
+      "loss": 1.2475,
+      "step": 40
+    },
+    {
+      "epoch": 0.048935649620748714,
+      "grad_norm": 6.953520974579646,
+      "learning_rate": 2.427184466019418e-06,
+      "loss": 1.1889,
+      "step": 50
+    },
+    {
+      "epoch": 0.058722779544898455,
+      "grad_norm": 3.390499745911967,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 1.1427,
+      "step": 60
+    },
+    {
+      "epoch": 0.0685099094690482,
+      "grad_norm": 2.234261881443784,
+      "learning_rate": 3.398058252427185e-06,
+      "loss": 1.0896,
+      "step": 70
+    },
+    {
+      "epoch": 0.07829703939319795,
+      "grad_norm": 2.5807948782523944,
+      "learning_rate": 3.883495145631068e-06,
+      "loss": 1.104,
+      "step": 80
+    },
+    {
+      "epoch": 0.0880841693173477,
+      "grad_norm": 2.356465079616129,
+      "learning_rate": 4.368932038834952e-06,
+      "loss": 1.0746,
+      "step": 90
+    },
+    {
+      "epoch": 0.09787129924149743,
+      "grad_norm": 2.4234601720621023,
+      "learning_rate": 4.854368932038836e-06,
+      "loss": 1.0793,
+      "step": 100
+    },
+    {
+      "epoch": 0.10765842916564718,
+      "grad_norm": 2.117132974644545,
+      "learning_rate": 4.999282701856139e-06,
+      "loss": 1.0692,
+      "step": 110
+    },
+    {
+      "epoch": 0.11744555908979691,
+      "grad_norm": 1.8840717844600037,
+      "learning_rate": 4.995770395678171e-06,
+      "loss": 1.0731,
+      "step": 120
+    },
+    {
+      "epoch": 0.12723268901394666,
+      "grad_norm": 2.5216433561534317,
+      "learning_rate": 4.989335440737587e-06,
+      "loss": 1.0464,
+      "step": 130
+    },
+    {
+      "epoch": 0.1370198189380964,
+      "grad_norm": 2.4579666246587424,
+      "learning_rate": 4.979985372628657e-06,
+      "loss": 1.0434,
+      "step": 140
+    },
+    {
+      "epoch": 0.14680694886224616,
+      "grad_norm": 2.3287908973842755,
+      "learning_rate": 4.967731140661878e-06,
+      "loss": 1.0441,
+      "step": 150
+    },
+    {
+      "epoch": 0.1565940787863959,
+      "grad_norm": 2.0436369039725224,
+      "learning_rate": 4.952587095041882e-06,
+      "loss": 1.0386,
+      "step": 160
+    },
+    {
+      "epoch": 0.16638120871054562,
+      "grad_norm": 2.5733520388523945,
+      "learning_rate": 4.934570970062765e-06,
+      "loss": 1.0565,
+      "step": 170
+    },
+    {
+      "epoch": 0.1761683386346954,
+      "grad_norm": 1.8256543734485644,
+      "learning_rate": 4.913703863340504e-06,
+      "loss": 1.0441,
+      "step": 180
+    },
+    {
+      "epoch": 0.18595546855884512,
+      "grad_norm": 1.7844329038469422,
+      "learning_rate": 4.890010211106795e-06,
+      "loss": 1.0396,
+      "step": 190
+    },
+    {
+      "epoch": 0.19574259848299486,
+      "grad_norm": 3.2695230626975613,
+      "learning_rate": 4.86351775959322e-06,
+      "loss": 1.0295,
+      "step": 200
+    },
+    {
+      "epoch": 0.20552972840714462,
+      "grad_norm": 2.6115311678055653,
+      "learning_rate": 4.834257532539292e-06,
+      "loss": 1.0465,
+      "step": 210
+    },
+    {
+      "epoch": 0.21531685833129435,
+      "grad_norm": 2.422852080700085,
+      "learning_rate": 4.802263794862385e-06,
+      "loss": 1.017,
+      "step": 220
+    },
+    {
+      "epoch": 0.2251039882554441,
+      "grad_norm": 2.2578865515295283,
+      "learning_rate": 4.767574012532121e-06,
+      "loss": 1.0176,
+      "step": 230
+    },
+    {
+      "epoch": 0.23489111817959382,
+      "grad_norm": 2.087619836151659,
+      "learning_rate": 4.730228808696201e-06,
+      "loss": 1.0174,
+      "step": 240
+    },
+    {
+      "epoch": 0.24467824810374358,
+      "grad_norm": 1.999324934826496,
+      "learning_rate": 4.690271916109034e-06,
+      "loss": 1.0174,
+      "step": 250
+    },
+    {
+      "epoch": 0.2544653780278933,
+      "grad_norm": 3.372686449261057,
+      "learning_rate": 4.647750125918909e-06,
+      "loss": 1.0168,
+      "step": 260
+    },
+    {
+      "epoch": 0.2642525079520431,
+      "grad_norm": 2.5211594090463088,
+      "learning_rate": 4.6027132328736515e-06,
+      "loss": 1.0351,
+      "step": 270
+    },
+    {
+      "epoch": 0.2740396378761928,
+      "grad_norm": 3.6300783567036525,
+      "learning_rate": 4.555213977008946e-06,
+      "loss": 1.0105,
+      "step": 280
+    },
+    {
+      "epoch": 0.28382676780034255,
+      "grad_norm": 1.6572768717333426,
+      "learning_rate": 4.50530798188761e-06,
+      "loss": 1.0227,
+      "step": 290
+    },
+    {
+      "epoch": 0.2936138977244923,
+      "grad_norm": 2.021540908150653,
+      "learning_rate": 4.453053689462131e-06,
+      "loss": 1.0178,
+      "step": 300
+    },
+    {
+      "epoch": 0.303401027648642,
+      "grad_norm": 1.8651477439042456,
+      "learning_rate": 4.398512291636768e-06,
+      "loss": 1.0091,
+      "step": 310
+    },
+    {
+      "epoch": 0.3131881575727918,
+      "grad_norm": 2.43880182053301,
+      "learning_rate": 4.341747658609332e-06,
+      "loss": 1.0196,
+      "step": 320
+    },
+    {
+      "epoch": 0.32297528749694154,
+      "grad_norm": 2.8064493559277963,
+      "learning_rate": 4.282826264076587e-06,
+      "loss": 1.0142,
+      "step": 330
+    },
+    {
+      "epoch": 0.33276241742109125,
+      "grad_norm": 1.9574404119807658,
+      "learning_rate": 4.221817107390847e-06,
+      "loss": 1.0014,
+      "step": 340
+    },
+    {
+      "epoch": 0.342549547345241,
+      "grad_norm": 2.163660779817407,
+      "learning_rate": 4.15879163275892e-06,
+      "loss": 1.0297,
+      "step": 350
+    },
+    {
+      "epoch": 0.3523366772693908,
+      "grad_norm": 1.9653596257387018,
+      "learning_rate": 4.093823645578037e-06,
+      "loss": 1.0155,
+      "step": 360
+    },
+    {
+      "epoch": 0.3621238071935405,
+      "grad_norm": 2.2959542048619253,
+      "learning_rate": 4.02698922600672e-06,
+      "loss": 1.0136,
+      "step": 370
+    },
+    {
+      "epoch": 0.37191093711769024,
+      "grad_norm": 1.7061830149355224,
+      "learning_rate": 3.958366639871826e-06,
+      "loss": 0.9889,
+      "step": 380
+    },
+    {
+      "epoch": 0.38169806704184,
+      "grad_norm": 2.299910460880925,
+      "learning_rate": 3.888036247016073e-06,
+      "loss": 0.9959,
+      "step": 390
+    },
+    {
+      "epoch": 0.3914851969659897,
+      "grad_norm": 1.9452961119067358,
+      "learning_rate": 3.81608040719339e-06,
+      "loss": 1.0049,
+      "step": 400
+    },
+    {
+      "epoch": 0.4012723268901395,
+      "grad_norm": 2.744356349117842,
+      "learning_rate": 3.7425833836222947e-06,
+      "loss": 1.0018,
+      "step": 410
+    },
+    {
+      "epoch": 0.41105945681428924,
+      "grad_norm": 2.477879387395352,
+      "learning_rate": 3.6676312443102323e-06,
+      "loss": 1.0152,
+      "step": 420
+    },
+    {
+      "epoch": 0.42084658673843894,
+      "grad_norm": 2.1636493383526676,
+      "learning_rate": 3.591311761264433e-06,
+      "loss": 1.0056,
+      "step": 430
+    },
+    {
+      "epoch": 0.4306337166625887,
+      "grad_norm": 2.743033130906874,
+      "learning_rate": 3.513714307707321e-06,
+      "loss": 0.9988,
+      "step": 440
+    },
+    {
+      "epoch": 0.4404208465867384,
+      "grad_norm": 2.3096838919036093,
+      "learning_rate": 3.4349297534168242e-06,
+      "loss": 0.9973,
+      "step": 450
+    },
+    {
+      "epoch": 0.4502079765108882,
+      "grad_norm": 2.7080342141867586,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 0.9841,
+      "step": 460
+    },
+    {
+      "epoch": 0.45999510643503794,
+      "grad_norm": 1.8384006858146424,
+      "learning_rate": 3.274169664423768e-06,
+      "loss": 0.9991,
+      "step": 470
+    },
+    {
+      "epoch": 0.46978223635918764,
+      "grad_norm": 1.7788391832635966,
+      "learning_rate": 3.192382386331667e-06,
+      "loss": 0.9992,
+      "step": 480
+    },
+    {
+      "epoch": 0.4795693662833374,
+      "grad_norm": 1.9349340294062531,
+      "learning_rate": 3.109784300270943e-06,
+      "loss": 1.004,
+      "step": 490
+    },
+    {
+      "epoch": 0.48935649620748717,
+      "grad_norm": 2.089365671821631,
+      "learning_rate": 3.0264721319638176e-06,
+      "loss": 0.9892,
+      "step": 500
+    },
+    {
+      "epoch": 0.4991436261316369,
+      "grad_norm": 1.6583587633830374,
+      "learning_rate": 2.9425434433518985e-06,
+      "loss": 0.9991,
+      "step": 510
+    },
+    {
+      "epoch": 0.5089307560557866,
+      "grad_norm": 2.164226641765232,
+      "learning_rate": 2.8580965183471794e-06,
+      "loss": 0.9946,
+      "step": 520
+    },
+    {
+      "epoch": 0.5187178859799364,
+      "grad_norm": 2.595883151442786,
+      "learning_rate": 2.773230247737569e-06,
+      "loss": 1.0007,
+      "step": 530
+    },
+    {
+      "epoch": 0.5285050159040862,
+      "grad_norm": 1.9135033210807688,
+      "learning_rate": 2.6880440133817563e-06,
+      "loss": 0.997,
+      "step": 540
+    },
+    {
+      "epoch": 0.5382921458282359,
+      "grad_norm": 2.1997366611393776,
+      "learning_rate": 2.602637571829009e-06,
+      "loss": 0.9916,
+      "step": 550
+    },
+    {
+      "epoch": 0.5480792757523856,
+      "grad_norm": 4.036295629554255,
+      "learning_rate": 2.517110937500185e-06,
+      "loss": 0.9921,
+      "step": 560
+    },
+    {
+      "epoch": 0.5578664056765353,
+      "grad_norm": 1.9466096395859314,
+      "learning_rate": 2.431564265566781e-06,
+      "loss": 0.9998,
+      "step": 570
+    },
+    {
+      "epoch": 0.5676535356006851,
+      "grad_norm": 2.487288664151329,
+      "learning_rate": 2.346097734665143e-06,
+      "loss": 0.9871,
+      "step": 580
+    },
+    {
+      "epoch": 0.5774406655248349,
+      "grad_norm": 1.816928462189231,
+      "learning_rate": 2.2608114295832053e-06,
+      "loss": 0.9979,
+      "step": 590
+    },
+    {
+      "epoch": 0.5872277954489846,
+      "grad_norm": 1.75653406126234,
+      "learning_rate": 2.175805224057129e-06,
+      "loss": 0.9724,
+      "step": 600
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 1.7976791598972546,
+      "learning_rate": 2.0911786638150873e-06,
+      "loss": 0.9937,
+      "step": 610
+    },
+    {
+      "epoch": 0.606802055297284,
+      "grad_norm": 1.9243691484831966,
+      "learning_rate": 2.0070308500051715e-06,
+      "loss": 0.9859,
+      "step": 620
+    },
+    {
+      "epoch": 0.6165891852214338,
+      "grad_norm": 2.7481202060087835,
+      "learning_rate": 1.9234603231439e-06,
+      "loss": 0.9841,
+      "step": 630
+    },
+    {
+      "epoch": 0.6263763151455836,
+      "grad_norm": 2.003686173024267,
+      "learning_rate": 1.84056494772127e-06,
+      "loss": 0.9749,
+      "step": 640
+    },
+    {
+      "epoch": 0.6361634450697333,
+      "grad_norm": 1.6161005997468445,
+      "learning_rate": 1.7584417975974535e-06,
+      "loss": 0.985,
+      "step": 650
+    },
+    {
+      "epoch": 0.6459505749938831,
+      "grad_norm": 1.5994212448277128,
+      "learning_rate": 1.6771870423253473e-06,
+      "loss": 0.9823,
+      "step": 660
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 2.947926766692084,
+      "learning_rate": 1.5968958345321178e-06,
+      "loss": 0.9905,
+      "step": 670
+    },
+    {
+      "epoch": 0.6655248348421825,
+      "grad_norm": 2.496926900199072,
+      "learning_rate": 1.517662198491599e-06,
+      "loss": 0.9802,
+      "step": 680
+    },
+    {
+      "epoch": 0.6753119647663323,
+      "grad_norm": 2.50313272426719,
+      "learning_rate": 1.4395789200180343e-06,
+      "loss": 0.9839,
+      "step": 690
+    },
+    {
+      "epoch": 0.685099094690482,
+      "grad_norm": 3.162725883476327,
+      "learning_rate": 1.362737437810114e-06,
+      "loss": 0.9746,
+      "step": 700
+    },
+    {
+      "epoch": 0.6948862246146318,
+      "grad_norm": 2.5094677251656696,
+      "learning_rate": 1.287227736372538e-06,
+      "loss": 0.9662,
+      "step": 710
+    },
+    {
+      "epoch": 0.7046733545387815,
+      "grad_norm": 1.7194609557385765,
+      "learning_rate": 1.2131382406404866e-06,
+      "loss": 0.9654,
+      "step": 720
+    },
+    {
+      "epoch": 0.7144604844629312,
+      "grad_norm": 2.088741834771206,
+      "learning_rate": 1.1405557124304338e-06,
+      "loss": 0.9687,
+      "step": 730
+    },
+    {
+      "epoch": 0.724247614387081,
+      "grad_norm": 2.3589729813581637,
+      "learning_rate": 1.0695651488385168e-06,
+      "loss": 0.9764,
+      "step": 740
+    },
+    {
+      "epoch": 0.7340347443112307,
+      "grad_norm": 1.4080735212450242,
+      "learning_rate": 1.0002496827054806e-06,
+      "loss": 0.9734,
+      "step": 750
+    },
+    {
+      "epoch": 0.7438218742353805,
+      "grad_norm": 2.028266231817523,
+      "learning_rate": 9.326904852647345e-07,
+      "loss": 0.9731,
+      "step": 760
+    },
+    {
+      "epoch": 0.7536090041595302,
+      "grad_norm": 1.9325878087268091,
+      "learning_rate": 8.669666710875319e-07,
+      "loss": 0.9717,
+      "step": 770
+    },
+    {
+      "epoch": 0.76339613408368,
+      "grad_norm": 2.6471850221409583,
+      "learning_rate": 8.031552054365905e-07,
+      "loss": 0.9721,
+      "step": 780
+    },
+    {
+      "epoch": 0.7731832640078297,
+      "grad_norm": 1.8267904470848466,
+      "learning_rate": 7.413308141366254e-07,
+      "loss": 0.9925,
+      "step": 790
+    },
+    {
+      "epoch": 0.7829703939319794,
+      "grad_norm": 1.7349835377240377,
+      "learning_rate": 6.815658960673782e-07,
+      "loss": 0.9581,
+      "step": 800
+    },
+    {
+      "epoch": 0.7927575238561292,
+      "grad_norm": 2.037859066803747,
+      "learning_rate": 6.239304383815706e-07,
+      "loss": 0.9699,
+      "step": 810
+    },
+    {
+      "epoch": 0.802544653780279,
+      "grad_norm": 2.1130579933367257,
+      "learning_rate": 5.684919345471029e-07,
+      "loss": 0.9905,
+      "step": 820
+    },
+    {
+      "epoch": 0.8123317837044287,
+      "grad_norm": 1.946465156584691,
+      "learning_rate": 5.15315305309455e-07,
+      "loss": 0.973,
+      "step": 830
+    },
+    {
+      "epoch": 0.8221189136285785,
+      "grad_norm": 2.5768060337551972,
+      "learning_rate": 4.644628226668485e-07,
+      "loss": 0.9582,
+      "step": 840
+    },
+    {
+      "epoch": 0.8319060435527281,
+      "grad_norm": 2.173860689008899,
+      "learning_rate": 4.159940369472015e-07,
+      "loss": 0.9729,
+      "step": 850
+    },
+    {
+      "epoch": 0.8416931734768779,
+      "grad_norm": 2.291543898620316,
+      "learning_rate": 3.699657070722698e-07,
+      "loss": 0.9761,
+      "step": 860
+    },
+    {
+      "epoch": 0.8514803034010276,
+      "grad_norm": 2.088024718750774,
+      "learning_rate": 3.2643173409063976e-07,
+      "loss": 0.9818,
+      "step": 870
+    },
+    {
+      "epoch": 0.8612674333251774,
+      "grad_norm": 1.8060057642166407,
+      "learning_rate": 2.854430980574002e-07,
+      "loss": 0.9636,
+      "step": 880
+    },
+    {
+      "epoch": 0.8710545632493272,
+      "grad_norm": 1.749866063660457,
+      "learning_rate": 2.4704779833442993e-07,
+      "loss": 0.9636,
+      "step": 890
+    },
+    {
+      "epoch": 0.8808416931734768,
+      "grad_norm": 2.0741463604546913,
+      "learning_rate": 2.1129079738118424e-07,
+      "loss": 0.963,
+      "step": 900
+    },
+    {
+      "epoch": 0.8906288230976266,
+      "grad_norm": 1.4388364613303446,
+      "learning_rate": 1.782139681018244e-07,
+      "loss": 0.9757,
+      "step": 910
+    },
+    {
+      "epoch": 0.9004159530217763,
+      "grad_norm": 2.3114929534129343,
+      "learning_rate": 1.4785604481034639e-07,
+      "loss": 0.9678,
+      "step": 920
+    },
+    {
+      "epoch": 0.9102030829459261,
+      "grad_norm": 2.0415525131838432,
+      "learning_rate": 1.202525778711172e-07,
+      "loss": 0.9595,
+      "step": 930
+    },
+    {
+      "epoch": 0.9199902128700759,
+      "grad_norm": 2.3293806080394104,
+      "learning_rate": 9.54358920679524e-08,
+      "loss": 0.98,
+      "step": 940
+    },
+    {
+      "epoch": 0.9297773427942256,
+      "grad_norm": 2.0830083897095406,
+      "learning_rate": 7.343504875047814e-08,
+      "loss": 0.964,
+      "step": 950
+    },
+    {
+      "epoch": 0.9395644727183753,
+      "grad_norm": 2.218326205399271,
+      "learning_rate": 5.427581180210639e-08,
+      "loss": 0.979,
+      "step": 960
+    },
+    {
+      "epoch": 0.949351602642525,
+      "grad_norm": 2.153253403337433,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 0.9578,
+      "step": 970
+    },
+    {
+      "epoch": 0.9591387325666748,
+      "grad_norm": 1.611398342662154,
+      "learning_rate": 2.456854808871201e-08,
+      "loss": 0.9759,
+      "step": 980
+    },
+    {
+      "epoch": 0.9689258624908246,
+      "grad_norm": 2.2214603407537883,
+      "learning_rate": 1.4055309739195166e-08,
+      "loss": 0.9691,
+      "step": 990
+    },
+    {
+      "epoch": 0.9787129924149743,
+      "grad_norm": 1.8872382897952824,
+      "learning_rate": 6.453213851142226e-09,
+      "loss": 0.9866,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9885001223391241,
+      "grad_norm": 3.466854317296078,
+      "learning_rate": 1.7711627883998383e-09,
+      "loss": 0.9735,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9982872522632737,
+      "grad_norm": 1.8136326675400594,
+      "learning_rate": 1.463942341850544e-11,
+      "loss": 0.9689,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9992659652556888,
+      "step": 1021,
+      "total_flos": 1.136081069573931e+18,
+      "train_loss": 1.019411426333092,
+      "train_runtime": 37962.3304,
+      "train_samples_per_second": 3.444,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1021,
+  "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": 1.136081069573931e+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 sha256:32516dbf62a7806e0e5eecf916316db253834675250f4f576021b09b3e6ab3ff
+size 7160