Upload 11 files

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,191 @@
+{
+  "_name_or_path": "./model/LLaVA-Med-Phi-finetune",
+  "architectures": [
+    "LlavaPhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "freeze_vision_tower": false,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "mm_projector_lr": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "model_type": "llava_phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "tune_mm_mlp_adapter": true,
+  "use_cache": true,
+  "vision_config": {
+    "mm_projector": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "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_size": 2560,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "mm_hidden_size": 1024,
+      "mm_projector_type": "mlp2x_gelu",
+      "model_type": "llava_phi_projector",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "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,
+      "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": null,
+      "torchscript": false,
+      "transformers_version": "4.36.2",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "vision_tower": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "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,
+      "dropout": 0.0,
+      "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": "quick_gelu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 336,
+      "initializer_factor": 1.0,
+      "initializer_range": 0.02,
+      "intermediate_size": 4096,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-05,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "mm_vision_select_feature": "patch",
+      "mm_vision_select_layer": -2,
+      "model_type": "llava_phi_clip_vision_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_hidden_layers": 24,
+      "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,
+      "projection_dim": 768,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "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": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.36.2",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    }
+  },
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.36.2"
+}

model.safetensors.index.json

@@ -0,0 +1,727 @@
+{
+  "metadata": {
+    "total_size": 6184742912
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 336,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 336
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,327 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,1920 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.1016,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.1211,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-06,
+      "loss": 3.2852,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.0801,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 2.9102,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2e-05,
+      "loss": 2.7852,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4e-05,
+      "loss": 2.7852,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.9199,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8e-05,
+      "loss": 2.7734,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 2.8418,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999469523400122e-05,
+      "loss": 2.7402,
+      "step": 11
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997878149881576e-05,
+      "loss": 2.834,
+      "step": 12
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999522604828164e-05,
+      "loss": 2.7441,
+      "step": 13
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9991513499975883e-05,
+      "loss": 2.8438,
+      "step": 14
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9986740898848306e-05,
+      "loss": 2.7539,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9980908751249556e-05,
+      "loss": 2.582,
+      "step": 16
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.997401767594319e-05,
+      "loss": 2.6973,
+      "step": 17
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996606840404006e-05,
+      "loss": 2.7734,
+      "step": 18
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9957061778920703e-05,
+      "loss": 2.7227,
+      "step": 19
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9946998756145894e-05,
+      "loss": 2.6445,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9935880403355255e-05,
+      "loss": 2.4629,
+      "step": 21
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9923707900153984e-05,
+      "loss": 2.6074,
+      "step": 22
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9910482537987704e-05,
+      "loss": 2.6328,
+      "step": 23
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.989620572000544e-05,
+      "loss": 2.6055,
+      "step": 24
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9880878960910772e-05,
+      "loss": 2.7031,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9864503886801108e-05,
+      "loss": 2.6191,
+      "step": 26
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9847082234995172e-05,
+      "loss": 2.5859,
+      "step": 27
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.982861585384869e-05,
+      "loss": 2.5078,
+      "step": 28
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9809106702558277e-05,
+      "loss": 2.4648,
+      "step": 29
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.978855685095358e-05,
+      "loss": 2.5371,
+      "step": 30
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9766968479277684e-05,
+      "loss": 2.6172,
+      "step": 31
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.974434387795579e-05,
+      "loss": 2.5449,
+      "step": 32
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.972068544735221e-05,
+      "loss": 2.3799,
+      "step": 33
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.969599569751571e-05,
+      "loss": 2.2725,
+      "step": 34
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9670277247913205e-05,
+      "loss": 2.4512,
+      "step": 35
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.964353282715183e-05,
+      "loss": 2.4785,
+      "step": 36
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.961576527268946e-05,
+      "loss": 2.3672,
+      "step": 37
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9586977530533677e-05,
+      "loss": 2.375,
+      "step": 38
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.95571726549292e-05,
+      "loss": 2.3008,
+      "step": 39
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9526353808033827e-05,
+      "loss": 2.4326,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9494524259582994e-05,
+      "loss": 2.4062,
+      "step": 41
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9461687386542826e-05,
+      "loss": 2.4414,
+      "step": 42
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9427846672751873e-05,
+      "loss": 2.3223,
+      "step": 43
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.93930057085515e-05,
+      "loss": 2.2812,
+      "step": 44
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9357168190404937e-05,
+      "loss": 2.167,
+      "step": 45
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.932033792050515e-05,
+      "loss": 2.4902,
+      "step": 46
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.928251880637141e-05,
+      "loss": 2.4883,
+      "step": 47
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.924371486043473e-05,
+      "loss": 2.3662,
+      "step": 48
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.920393019961217e-05,
+      "loss": 2.3066,
+      "step": 49
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.916316904487005e-05,
+      "loss": 2.2275,
+      "step": 50
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9121435720776122e-05,
+      "loss": 2.2197,
+      "step": 51
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9078734655040763e-05,
+      "loss": 2.3467,
+      "step": 52
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9035070378047204e-05,
+      "loss": 2.1914,
+      "step": 53
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8990447522370886e-05,
+      "loss": 2.3965,
+      "step": 54
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8944870822287957e-05,
+      "loss": 2.4883,
+      "step": 55
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8898345113273e-05,
+      "loss": 2.3955,
+      "step": 56
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8850875331485996e-05,
+      "loss": 2.5859,
+      "step": 57
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8802466513248635e-05,
+      "loss": 2.2754,
+      "step": 58
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8753123794509974e-05,
+      "loss": 2.2451,
+      "step": 59
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8702852410301556e-05,
+      "loss": 2.3584,
+      "step": 60
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.865165769418196e-05,
+      "loss": 2.3281,
+      "step": 61
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8599545077670983e-05,
+      "loss": 2.2256,
+      "step": 62
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.854652008967335e-05,
+      "loss": 2.3828,
+      "step": 63
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8492588355892125e-05,
+      "loss": 2.126,
+      "step": 64
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8437755598231857e-05,
+      "loss": 2.3516,
+      "step": 65
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8382027634191523e-05,
+      "loss": 2.1816,
+      "step": 66
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8325410376247295e-05,
+      "loss": 2.29,
+      "step": 67
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.826790983122527e-05,
+      "loss": 2.2529,
+      "step": 68
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8209532099664177e-05,
+      "loss": 1.96,
+      "step": 69
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8150283375168112e-05,
+      "loss": 2.0742,
+      "step": 70
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 2.2773,
+      "step": 71
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8029198183162e-05,
+      "loss": 2.3135,
+      "step": 72
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.796737456222413e-05,
+      "loss": 2.4082,
+      "step": 73
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7904705640132717e-05,
+      "loss": 2.3262,
+      "step": 74
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7841198065767107e-05,
+      "loss": 2.1162,
+      "step": 75
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7776858576983713e-05,
+      "loss": 2.2832,
+      "step": 76
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.771169399990119e-05,
+      "loss": 2.125,
+      "step": 77
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7645711248176198e-05,
+      "loss": 2.1611,
+      "step": 78
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7578917322269885e-05,
+      "loss": 2.1689,
+      "step": 79
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7511319308705198e-05,
+      "loss": 2.1641,
+      "step": 80
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.744292437931502e-05,
+      "loss": 2.2217,
+      "step": 81
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7373739790481263e-05,
+      "loss": 2.2656,
+      "step": 82
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7303772882365018e-05,
+      "loss": 2.0977,
+      "step": 83
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.723303107812779e-05,
+      "loss": 2.1602,
+      "step": 84
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7161521883143936e-05,
+      "loss": 2.1045,
+      "step": 85
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7089252884204376e-05,
+      "loss": 2.2949,
+      "step": 86
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.701623174871168e-05,
+      "loss": 2.124,
+      "step": 87
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6942466223866582e-05,
+      "loss": 2.2051,
+      "step": 88
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6867964135846043e-05,
+      "loss": 2.0146,
+      "step": 89
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.679273338897293e-05,
+      "loss": 2.1816,
+      "step": 90
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6716781964877413e-05,
+      "loss": 2.2002,
+      "step": 91
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.664011792165012e-05,
+      "loss": 2.0781,
+      "step": 92
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6562749392987255e-05,
+      "loss": 2.2031,
+      "step": 93
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.648468458732762e-05,
+      "loss": 2.1719,
+      "step": 94
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6405931786981753e-05,
+      "loss": 2.2246,
+      "step": 95
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6326499347253206e-05,
+      "loss": 2.2852,
+      "step": 96
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6246395695552086e-05,
+      "loss": 2.1357,
+      "step": 97
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6165629330500952e-05,
+      "loss": 2.2148,
+      "step": 98
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6084208821033152e-05,
+      "loss": 2.0781,
+      "step": 99
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6002142805483686e-05,
+      "loss": 2.2197,
+      "step": 100
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.591943999067273e-05,
+      "loss": 2.0957,
+      "step": 101
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5836109150981885e-05,
+      "loss": 2.0645,
+      "step": 102
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5752159127423262e-05,
+      "loss": 2.4609,
+      "step": 103
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5667598826701463e-05,
+      "loss": 2.3008,
+      "step": 104
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5582437220268648e-05,
+      "loss": 2.0254,
+      "step": 105
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.549668334337271e-05,
+      "loss": 2.0322,
+      "step": 106
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.541034629409865e-05,
+      "loss": 1.9941,
+      "step": 107
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.532343523240334e-05,
+      "loss": 1.9033,
+      "step": 108
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.523595937914368e-05,
+      "loss": 1.8633,
+      "step": 109
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5147928015098309e-05,
+      "loss": 2.043,
+      "step": 110
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5059350479982966e-05,
+      "loss": 2.0029,
+      "step": 111
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.497023617145958e-05,
+      "loss": 1.9092,
+      "step": 112
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.488059454413923e-05,
+      "loss": 1.8877,
+      "step": 113
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4790435108579048e-05,
+      "loss": 2.0322,
+      "step": 114
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4699767430273202e-05,
+      "loss": 1.9189,
+      "step": 115
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4608601128638027e-05,
+      "loss": 1.8535,
+      "step": 116
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4516945875991472e-05,
+      "loss": 1.8447,
+      "step": 117
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4424811396526892e-05,
+      "loss": 1.916,
+      "step": 118
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4332207465281365e-05,
+      "loss": 1.8838,
+      "step": 119
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.423914390709861e-05,
+      "loss": 2.0352,
+      "step": 120
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4145630595586607e-05,
+      "loss": 1.9609,
+      "step": 121
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4051677452070064e-05,
+      "loss": 2.0049,
+      "step": 122
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3957294444537808e-05,
+      "loss": 1.8584,
+      "step": 123
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.386249158658522e-05,
+      "loss": 1.7842,
+      "step": 124
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3767278936351853e-05,
+      "loss": 1.9111,
+      "step": 125
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3671666595454296e-05,
+      "loss": 1.8887,
+      "step": 126
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.357566470791445e-05,
+      "loss": 1.917,
+      "step": 127
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.347928345908329e-05,
+      "loss": 1.959,
+      "step": 128
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3382533074560256e-05,
+      "loss": 1.8545,
+      "step": 129
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3285423819108349e-05,
+      "loss": 2.0332,
+      "step": 130
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3187965995565098e-05,
+      "loss": 2.0068,
+      "step": 131
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 2.0713,
+      "step": 132
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2992046039364893e-05,
+      "loss": 1.8516,
+      "step": 133
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2893604692898381e-05,
+      "loss": 1.8965,
+      "step": 134
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2794856348516095e-05,
+      "loss": 1.9531,
+      "step": 135
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2695811482955227e-05,
+      "loss": 1.8584,
+      "step": 136
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2596480604412485e-05,
+      "loss": 1.873,
+      "step": 137
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.24968742514292e-05,
+      "loss": 2.0059,
+      "step": 138
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2397002991773277e-05,
+      "loss": 1.9492,
+      "step": 139
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2296877421317958e-05,
+      "loss": 2.0479,
+      "step": 140
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2196508162917678e-05,
+      "loss": 1.8369,
+      "step": 141
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2095905865281026e-05,
+      "loss": 2.0,
+      "step": 142
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1995081201840958e-05,
+      "loss": 1.8086,
+      "step": 143
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1894044869622403e-05,
+      "loss": 1.9092,
+      "step": 144
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1792807588107358e-05,
+      "loss": 1.8643,
+      "step": 145
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1691380098097598e-05,
+      "loss": 1.9043,
+      "step": 146
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.158977316057513e-05,
+      "loss": 1.8506,
+      "step": 147
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1487997555560503e-05,
+      "loss": 1.7197,
+      "step": 148
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1386064080969095e-05,
+      "loss": 1.9434,
+      "step": 149
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1283983551465512e-05,
+      "loss": 1.9307,
+      "step": 150
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.118176679731619e-05,
+      "loss": 1.915,
+      "step": 151
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1079424663240372e-05,
+      "loss": 1.8701,
+      "step": 152
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0976968007259519e-05,
+      "loss": 1.9004,
+      "step": 153
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0874407699545329e-05,
+      "loss": 1.9346,
+      "step": 154
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0771754621266466e-05,
+      "loss": 1.9727,
+      "step": 155
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0669019663434117e-05,
+      "loss": 2.0176,
+      "step": 156
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0566213725746506e-05,
+      "loss": 1.9346,
+      "step": 157
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0463347715432488e-05,
+      "loss": 1.8779,
+      "step": 158
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0360432546094341e-05,
+      "loss": 1.8389,
+      "step": 159
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0257479136549889e-05,
+      "loss": 2.0264,
+      "step": 160
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0154498409674051e-05,
+      "loss": 1.9092,
+      "step": 161
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0051501291240008e-05,
+      "loss": 1.9785,
+      "step": 162
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.948498708759993e-06,
+      "loss": 1.8594,
+      "step": 163
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.845501590325949e-06,
+      "loss": 1.9746,
+      "step": 164
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.742520863450116e-06,
+      "loss": 1.9082,
+      "step": 165
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.639567453905662e-06,
+      "loss": 1.9717,
+      "step": 166
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.536652284567514e-06,
+      "loss": 1.8242,
+      "step": 167
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.433786274253496e-06,
+      "loss": 1.8867,
+      "step": 168
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.330980336565887e-06,
+      "loss": 1.9629,
+      "step": 169
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.228245378733537e-06,
+      "loss": 1.8652,
+      "step": 170
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.125592300454675e-06,
+      "loss": 1.7227,
+      "step": 171
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.023031992740488e-06,
+      "loss": 1.8809,
+      "step": 172
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.92057533675963e-06,
+      "loss": 2.0039,
+      "step": 173
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.818233202683815e-06,
+      "loss": 1.9102,
+      "step": 174
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.71601644853449e-06,
+      "loss": 2.0049,
+      "step": 175
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.613935919030908e-06,
+      "loss": 1.9795,
+      "step": 176
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.512002444439502e-06,
+      "loss": 1.8223,
+      "step": 177
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.410226839424871e-06,
+      "loss": 1.9092,
+      "step": 178
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.308619901902406e-06,
+      "loss": 1.8193,
+      "step": 179
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.207192411892645e-06,
+      "loss": 1.7246,
+      "step": 180
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.1059551303776e-06,
+      "loss": 1.7344,
+      "step": 181
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.004918798159046e-06,
+      "loss": 1.957,
+      "step": 182
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.904094134718975e-06,
+      "loss": 1.8555,
+      "step": 183
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.803491837082324e-06,
+      "loss": 1.8994,
+      "step": 184
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.703122578682047e-06,
+      "loss": 1.9053,
+      "step": 185
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.602997008226725e-06,
+      "loss": 1.8857,
+      "step": 186
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.503125748570801e-06,
+      "loss": 1.8555,
+      "step": 187
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.403519395587522e-06,
+      "loss": 1.8174,
+      "step": 188
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.304188517044774e-06,
+      "loss": 1.8281,
+      "step": 189
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.2051436514839064e-06,
+      "loss": 1.7969,
+      "step": 190
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.106395307101621e-06,
+      "loss": 2.0137,
+      "step": 191
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.007953960635109e-06,
+      "loss": 1.8184,
+      "step": 192
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 2.0029,
+      "step": 193
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.812034004434904e-06,
+      "loss": 1.8242,
+      "step": 194
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.714576180891653e-06,
+      "loss": 1.9043,
+      "step": 195
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.617466925439746e-06,
+      "loss": 1.9297,
+      "step": 196
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.520716540916709e-06,
+      "loss": 1.8525,
+      "step": 197
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.424335292085553e-06,
+      "loss": 1.8643,
+      "step": 198
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.32833340454571e-06,
+      "loss": 1.915,
+      "step": 199
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.232721063648148e-06,
+      "loss": 1.8682,
+      "step": 200
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.137508413414784e-06,
+      "loss": 1.7812,
+      "step": 201
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.042705555462192e-06,
+      "loss": 1.8555,
+      "step": 202
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.948322547929939e-06,
+      "loss": 1.8301,
+      "step": 203
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.8543694044133984e-06,
+      "loss": 1.8125,
+      "step": 204
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.760856092901394e-06,
+      "loss": 1.8857,
+      "step": 205
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.667792534718639e-06,
+      "loss": 1.7637,
+      "step": 206
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.575188603473112e-06,
+      "loss": 1.8281,
+      "step": 207
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.483054124008528e-06,
+      "loss": 1.7715,
+      "step": 208
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.391398871361972e-06,
+      "loss": 1.8154,
+      "step": 209
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.300232569726805e-06,
+      "loss": 1.8232,
+      "step": 210
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.209564891420953e-06,
+      "loss": 1.5811,
+      "step": 211
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.119405455860772e-06,
+      "loss": 1.7432,
+      "step": 212
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.029763828540419e-06,
+      "loss": 1.7061,
+      "step": 213
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.9406495200170345e-06,
+      "loss": 1.6689,
+      "step": 214
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.852071984901696e-06,
+      "loss": 1.8164,
+      "step": 215
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.764040620856323e-06,
+      "loss": 1.6289,
+      "step": 216
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.676564767596663e-06,
+      "loss": 1.7148,
+      "step": 217
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.5896537059013536e-06,
+      "loss": 1.79,
+      "step": 218
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.503316656627295e-06,
+      "loss": 1.6221,
+      "step": 219
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.417562779731355e-06,
+      "loss": 1.71,
+      "step": 220
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.332401173298544e-06,
+      "loss": 1.5859,
+      "step": 221
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.24784087257674e-06,
+      "loss": 1.6191,
+      "step": 222
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.163890849018114e-06,
+      "loss": 1.7393,
+      "step": 223
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.080560009327274e-06,
+      "loss": 1.7051,
+      "step": 224
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.997857194516319e-06,
+      "loss": 1.6621,
+      "step": 225
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.915791178966852e-06,
+      "loss": 1.6973,
+      "step": 226
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.834370669499047e-06,
+      "loss": 1.7031,
+      "step": 227
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.753604304447915e-06,
+      "loss": 1.7021,
+      "step": 228
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.6735006527467967e-06,
+      "loss": 1.7051,
+      "step": 229
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.594068213018249e-06,
+      "loss": 1.7451,
+      "step": 230
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.515315412672384e-06,
+      "loss": 1.7207,
+      "step": 231
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.4372506070127476e-06,
+      "loss": 1.6436,
+      "step": 232
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.3598820783498833e-06,
+      "loss": 1.667,
+      "step": 233
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.2832180351225916e-06,
+      "loss": 1.7021,
+      "step": 234
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.207266611027069e-06,
+      "loss": 1.7061,
+      "step": 235
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.1320358641539583e-06,
+      "loss": 1.6035,
+      "step": 236
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.0575337761334213e-06,
+      "loss": 1.6094,
+      "step": 237
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9837682512883205e-06,
+      "loss": 1.707,
+      "step": 238
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.910747115795628e-06,
+      "loss": 1.6982,
+      "step": 239
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.8384781168560693e-06,
+      "loss": 1.5889,
+      "step": 240
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.766968921872213e-06,
+      "loss": 1.7129,
+      "step": 241
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.696227117634985e-06,
+      "loss": 1.6025,
+      "step": 242
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.626260209518737e-06,
+      "loss": 1.7686,
+      "step": 243
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.5570756206849834e-06,
+      "loss": 1.6543,
+      "step": 244
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.4886806912948034e-06,
+      "loss": 1.627,
+      "step": 245
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4210826777301154e-06,
+      "loss": 1.7227,
+      "step": 246
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3542887518238056e-06,
+      "loss": 1.7588,
+      "step": 247
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.288306000098811e-06,
+      "loss": 1.7256,
+      "step": 248
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.2231414230162897e-06,
+      "loss": 1.5625,
+      "step": 249
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.158801934232897e-06,
+      "loss": 1.7207,
+      "step": 250
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.0952943598672847e-06,
+      "loss": 1.8096,
+      "step": 251
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0326254377758704e-06,
+      "loss": 1.6533,
+      "step": 252
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.970801816838004e-06,
+      "loss": 1.7139,
+      "step": 253
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.6504,
+      "step": 254
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8497166248318876e-06,
+      "loss": 1.585,
+      "step": 255
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7904679003358283e-06,
+      "loss": 1.6641,
+      "step": 256
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7320901687747294e-06,
+      "loss": 1.7246,
+      "step": 257
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6745896237527071e-06,
+      "loss": 1.6484,
+      "step": 258
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.6179723658084811e-06,
+      "loss": 1.8076,
+      "step": 259
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5622444017681438e-06,
+      "loss": 1.748,
+      "step": 260
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.507411644107879e-06,
+      "loss": 1.5947,
+      "step": 261
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.4534799103266505e-06,
+      "loss": 1.667,
+      "step": 262
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.4004549223290165e-06,
+      "loss": 1.6357,
+      "step": 263
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3483423058180423e-06,
+      "loss": 1.5732,
+      "step": 264
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.2971475896984475e-06,
+      "loss": 1.6221,
+      "step": 265
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2468762054900264e-06,
+      "loss": 1.7861,
+      "step": 266
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.1975334867513687e-06,
+      "loss": 1.6611,
+      "step": 267
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1491246685140078e-06,
+      "loss": 1.4912,
+      "step": 268
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.1016548867270037e-06,
+      "loss": 1.6748,
+      "step": 269
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.0551291777120465e-06,
+      "loss": 1.8672,
+      "step": 270
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0095524776291165e-06,
+      "loss": 1.7246,
+      "step": 271
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.649296219527982e-07,
+      "loss": 1.6426,
+      "step": 272
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.21265344959239e-07,
+      "loss": 1.6289,
+      "step": 273
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.785642792238814e-07,
+      "loss": 1.6562,
+      "step": 274
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.368309551299536e-07,
+      "loss": 1.7344,
+      "step": 275
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.960698003878309e-07,
+      "loss": 1.7451,
+      "step": 276
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.562851395652693e-07,
+      "loss": 1.6445,
+      "step": 277
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.174811936285886e-07,
+      "loss": 1.792,
+      "step": 278
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.796620794948483e-07,
+      "loss": 1.6738,
+      "step": 279
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.428318095950648e-07,
+      "loss": 1.5811,
+      "step": 280
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.06994291448505e-07,
+      "loss": 1.7129,
+      "step": 281
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.721533272481272e-07,
+      "loss": 1.5957,
+      "step": 282
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.383126134571748e-07,
+      "loss": 1.7637,
+      "step": 283
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.054757404170074e-07,
+      "loss": 1.7734,
+      "step": 284
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.73646191966175e-07,
+      "loss": 1.5537,
+      "step": 285
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.428273450708065e-07,
+      "loss": 1.666,
+      "step": 286
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.1302246946632206e-07,
+      "loss": 1.6973,
+      "step": 287
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.842347273105396e-07,
+      "loss": 1.7041,
+      "step": 288
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.564671728481739e-07,
+      "loss": 1.7529,
+      "step": 289
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.2972275208679625e-07,
+      "loss": 1.667,
+      "step": 290
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.0400430248428983e-07,
+      "loss": 1.7051,
+      "step": 291
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.793145526477914e-07,
+      "loss": 1.7529,
+      "step": 292
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.556561220442144e-07,
+      "loss": 1.5752,
+      "step": 293
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.3303152072231883e-07,
+      "loss": 1.7285,
+      "step": 294
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.1144314904642194e-07,
+      "loss": 1.7803,
+      "step": 295
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.9089329744172658e-07,
+      "loss": 1.6621,
+      "step": 296
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.7138414615131327e-07,
+      "loss": 1.6738,
+      "step": 297
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.529177650048297e-07,
+      "loss": 1.6641,
+      "step": 298
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.3549611319889522e-07,
+      "loss": 1.6367,
+      "step": 299
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.1912103908922945e-07,
+      "loss": 1.6582,
+      "step": 300
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.0379427999456015e-07,
+      "loss": 1.6406,
+      "step": 301
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.951746201229961e-08,
+      "loss": 1.709,
+      "step": 302
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.629209984601816e-08,
+      "loss": 1.6416,
+      "step": 303
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.411959664474832e-08,
+      "loss": 1.7266,
+      "step": 304
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.300124385410943e-08,
+      "loss": 1.6006,
+      "step": 305
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.2938221079300566e-08,
+      "loss": 1.707,
+      "step": 306
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.3931595959942885e-08,
+      "loss": 1.6123,
+      "step": 307
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.5982324056810227e-08,
+      "loss": 1.6455,
+      "step": 308
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.9091248750446877e-08,
+      "loss": 1.7812,
+      "step": 309
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.325910115169471e-08,
+      "loss": 1.6172,
+      "step": 310
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.48650002411855e-09,
+      "loss": 1.6328,
+      "step": 311
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 4.773951718362035e-09,
+      "loss": 1.6768,
+      "step": 312
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.1218501184261385e-09,
+      "loss": 1.6006,
+      "step": 313
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.304765998781491e-10,
+      "loss": 1.5791,
+      "step": 314
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 1.4365,
+      "step": 315
+    },
+    {
+      "epoch": 3.0,
+      "step": 315,
+      "total_flos": 19095171661824.0,
+      "train_loss": 1.9948753720238095,
+      "train_runtime": 5108.9216,
+      "train_samples_per_second": 1.957,
+      "train_steps_per_second": 0.062
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 158,
+  "total_flos": 19095171661824.0,
+  "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 sha256:109b42a783f5a28deaec95c0529e41e62fc80aadbf4833beaf1f1be64fe52daf
+size 6203