Upload folder using huggingface_hub

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "liuhaotian/llava-v1.5-7b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 1024,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd2fda21cd3579aa11d52af662d3f8001ac144bbc3fae3ef8c73449e67457d8
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4ebc1df5c9def5b8a4cec67e633ab48854ecadf6c69aff1680d7b108387618
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae6da654b1aa93e49f46d90ae11cce4286b03c7c807310de957111d6de5d3f3
+size 4239524944

model.safetensors.index.json

@@ -0,0 +1,693 @@
+{
+  "metadata": {
+    "total_size": 14125805568
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.mm_projector.0.bias": "model-00003-of-00003.safetensors",
+    "model.mm_projector.0.weight": "model-00003-of-00003.safetensors",
+    "model.mm_projector.2.bias": "model-00003-of-00003.safetensors",
+    "model.mm_projector.2.weight": "model-00003-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1770 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9982788296041308,
+  "eval_steps": 500,
+  "global_step": 290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.0458,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.0521,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9549,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.7315,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.6335,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.0116,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.5621,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.7761,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.7048,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999375039475278e-05,
+      "loss": 0.6919,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997500236016233e-05,
+      "loss": 0.6744,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9994375823958504e-05,
+      "loss": 0.571,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9990002193828923e-05,
+      "loss": 0.5849,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998437989229673e-05,
+      "loss": 0.5264,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9977509622105233e-05,
+      "loss": 0.5171,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9969392241983957e-05,
+      "loss": 0.6064,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9960028766541336e-05,
+      "loss": 1.419,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.994942036613787e-05,
+      "loss": 0.605,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9937568366739858e-05,
+      "loss": 0.6079,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9924474249753656e-05,
+      "loss": 0.6545,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9910139651840497e-05,
+      "loss": 0.5648,
+      "step": 21
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9894566364711965e-05,
+      "loss": 0.4007,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9877756334905983e-05,
+      "loss": 0.3545,
+      "step": 23
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9859711663543573e-05,
+      "loss": 0.3676,
+      "step": 24
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9840434606066182e-05,
+      "loss": 0.3657,
+      "step": 25
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9819927571953804e-05,
+      "loss": 0.2507,
+      "step": 26
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9798193124423804e-05,
+      "loss": 0.1892,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9775233980110524e-05,
+      "loss": 0.2312,
+      "step": 28
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9751053008725736e-05,
+      "loss": 0.13,
+      "step": 29
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9725653232699962e-05,
+      "loss": 0.2087,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.969903782680467e-05,
+      "loss": 0.1707,
+      "step": 31
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.967121011775546e-05,
+      "loss": 0.1929,
+      "step": 32
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9642173583796265e-05,
+      "loss": 0.7225,
+      "step": 33
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.961193185426459e-05,
+      "loss": 0.1488,
+      "step": 34
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.958048870913786e-05,
+      "loss": 0.2369,
+      "step": 35
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9547848078560975e-05,
+      "loss": 0.2356,
+      "step": 36
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9514014042355057e-05,
+      "loss": 0.3123,
+      "step": 37
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9478990829507507e-05,
+      "loss": 0.2355,
+      "step": 38
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9442782817643425e-05,
+      "loss": 0.2231,
+      "step": 39
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9405394532478422e-05,
+      "loss": 0.158,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9366830647252974e-05,
+      "loss": 0.2163,
+      "step": 41
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9327095982148258e-05,
+      "loss": 0.2184,
+      "step": 42
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.928619550368371e-05,
+      "loss": 0.1329,
+      "step": 43
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9244134324096223e-05,
+      "loss": 0.0903,
+      "step": 44
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9200917700701176e-05,
+      "loss": 0.134,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.915655103523529e-05,
+      "loss": 0.1293,
+      "step": 46
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9111039873181478e-05,
+      "loss": 0.0764,
+      "step": 47
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9064389903075676e-05,
+      "loss": 0.0527,
+      "step": 48
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.901660695579585e-05,
+      "loss": 0.0677,
+      "step": 49
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8967697003833156e-05,
+      "loss": 0.0862,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8917666160545446e-05,
+      "loss": 0.0737,
+      "step": 51
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8866520679393127e-05,
+      "loss": 0.028,
+      "step": 52
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8814266953157557e-05,
+      "loss": 0.0202,
+      "step": 53
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.876091151314196e-05,
+      "loss": 0.0498,
+      "step": 54
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8706461028355107e-05,
+      "loss": 0.0222,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.865092230467769e-05,
+      "loss": 0.0122,
+      "step": 56
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8594302284011704e-05,
+      "loss": 0.0364,
+      "step": 57
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.85366080434127e-05,
+      "loss": 0.0184,
+      "step": 58
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8477846794205258e-05,
+      "loss": 0.0379,
+      "step": 59
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8418025881081612e-05,
+      "loss": 0.0095,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8357152781183606e-05,
+      "loss": 0.0144,
+      "step": 61
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.829523510316813e-05,
+      "loss": 0.0103,
+      "step": 62
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.82322805862561e-05,
+      "loss": 0.019,
+      "step": 63
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8168297099265094e-05,
+      "loss": 0.0846,
+      "step": 64
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.810329263962584e-05,
+      "loss": 0.027,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.803727533238257e-05,
+      "loss": 0.0468,
+      "step": 66
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7970253429177477e-05,
+      "loss": 0.0446,
+      "step": 67
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7902235307219333e-05,
+      "loss": 0.0086,
+      "step": 68
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7833229468236367e-05,
+      "loss": 0.0284,
+      "step": 69
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.776324453741365e-05,
+      "loss": 0.0302,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7692289262315e-05,
+      "loss": 0.0113,
+      "step": 71
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7620372511789607e-05,
+      "loss": 0.0043,
+      "step": 72
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.75475032748635e-05,
+      "loss": 0.0113,
+      "step": 73
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.747369065961599e-05,
+      "loss": 0.0051,
+      "step": 74
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7398943892041223e-05,
+      "loss": 0.0087,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7323272314895022e-05,
+      "loss": 0.0135,
+      "step": 76
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7246685386527098e-05,
+      "loss": 0.0077,
+      "step": 77
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7169192679698837e-05,
+      "loss": 0.0173,
+      "step": 78
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7090803880386784e-05,
+      "loss": 0.0023,
+      "step": 79
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.701152878657197e-05,
+      "loss": 0.0216,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.693137730701524e-05,
+      "loss": 0.0072,
+      "step": 81
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6850359460018737e-05,
+      "loss": 0.0078,
+      "step": 82
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6768485372173696e-05,
+      "loss": 0.0146,
+      "step": 83
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6685765277094702e-05,
+      "loss": 0.0039,
+      "step": 84
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6602209514140552e-05,
+      "loss": 0.0218,
+      "step": 85
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6517828527121942e-05,
+      "loss": 0.0135,
+      "step": 86
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6432632862996056e-05,
+      "loss": 0.0046,
+      "step": 87
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.634663317054829e-05,
+      "loss": 0.0108,
+      "step": 88
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6259840199061215e-05,
+      "loss": 0.0207,
+      "step": 89
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.617226479697105e-05,
+      "loss": 0.0337,
+      "step": 90
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.608391791051163e-05,
+      "loss": 0.0125,
+      "step": 91
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.599481058234626e-05,
+      "loss": 0.01,
+      "step": 92
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5904953950187458e-05,
+      "loss": 0.0128,
+      "step": 93
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5814359245404818e-05,
+      "loss": 0.0059,
+      "step": 94
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5723037791621193e-05,
+      "loss": 0.0134,
+      "step": 95
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.563100100329731e-05,
+      "loss": 0.0104,
+      "step": 96
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5538260384305076e-05,
+      "loss": 0.0145,
+      "step": 97
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5444827526489675e-05,
+      "loss": 0.0104,
+      "step": 98
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5350714108220673e-05,
+      "loss": 0.0105,
+      "step": 99
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5255931892932333e-05,
+      "loss": 0.0128,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5160492727653241e-05,
+      "loss": 0.0093,
+      "step": 101
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5064408541525573e-05,
+      "loss": 0.0226,
+      "step": 102
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4967691344313995e-05,
+      "loss": 0.0089,
+      "step": 103
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4870353224904572e-05,
+      "loss": 0.0259,
+      "step": 104
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4772406349793744e-05,
+      "loss": 0.0189,
+      "step": 105
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4673862961567602e-05,
+      "loss": 0.0119,
+      "step": 106
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.457473537737167e-05,
+      "loss": 0.0115,
+      "step": 107
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4475035987371355e-05,
+      "loss": 0.0027,
+      "step": 108
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4374777253203273e-05,
+      "loss": 0.008,
+      "step": 109
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4273971706417648e-05,
+      "loss": 0.0108,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4172631946911964e-05,
+      "loss": 0.0054,
+      "step": 111
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.407077064135607e-05,
+      "loss": 0.0064,
+      "step": 112
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3968400521608969e-05,
+      "loss": 0.0042,
+      "step": 113
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3865534383127406e-05,
+      "loss": 0.0101,
+      "step": 114
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3762185083366557e-05,
+      "loss": 0.0121,
+      "step": 115
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3658365540172948e-05,
+      "loss": 0.0021,
+      "step": 116
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3554088730169814e-05,
+      "loss": 0.0067,
+      "step": 117
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3449367687135134e-05,
+      "loss": 0.0303,
+      "step": 118
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.334421550037251e-05,
+      "loss": 0.0012,
+      "step": 119
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3238645313075104e-05,
+      "loss": 0.0014,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.313267032068285e-05,
+      "loss": 0.0087,
+      "step": 121
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3026303769233112e-05,
+      "loss": 0.0086,
+      "step": 122
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2919558953705055e-05,
+      "loss": 0.0008,
+      "step": 123
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2812449216357863e-05,
+      "loss": 0.0064,
+      "step": 124
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.270498794506307e-05,
+      "loss": 0.0101,
+      "step": 125
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.259718857163117e-05,
+      "loss": 0.0168,
+      "step": 126
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2489064570132764e-05,
+      "loss": 0.013,
+      "step": 127
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2380629455214392e-05,
+      "loss": 0.0308,
+      "step": 128
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2271896780409321e-05,
+      "loss": 0.0053,
+      "step": 129
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2162880136443447e-05,
+      "loss": 0.0038,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2053593149536576e-05,
+      "loss": 0.0014,
+      "step": 131
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1944049479699244e-05,
+      "loss": 0.0046,
+      "step": 132
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1834262819025326e-05,
+      "loss": 0.0309,
+      "step": 133
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1724246889980638e-05,
+      "loss": 0.0022,
+      "step": 134
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1614015443687723e-05,
+      "loss": 0.0189,
+      "step": 135
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.150358225820709e-05,
+      "loss": 0.0115,
+      "step": 136
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1392961136815046e-05,
+      "loss": 0.0218,
+      "step": 137
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1282165906278402e-05,
+      "loss": 0.0017,
+      "step": 138
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1171210415126248e-05,
+      "loss": 0.0144,
+      "step": 139
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1060108531918972e-05,
+      "loss": 0.0081,
+      "step": 140
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.094887414351482e-05,
+      "loss": 0.0043,
+      "step": 141
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0837521153334143e-05,
+      "loss": 0.0025,
+      "step": 142
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0726063479621574e-05,
+      "loss": 0.0041,
+      "step": 143
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0614515053706367e-05,
+      "loss": 0.002,
+      "step": 144
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0502889818261075e-05,
+      "loss": 0.0018,
+      "step": 145
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0391201725558842e-05,
+      "loss": 0.0008,
+      "step": 146
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0279464735729472e-05,
+      "loss": 0.0027,
+      "step": 147
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0167692815014527e-05,
+      "loss": 0.0062,
+      "step": 148
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0055899934021649e-05,
+      "loss": 0.0018,
+      "step": 149
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.944100065978351e-06,
+      "loss": 0.001,
+      "step": 150
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.832307184985475e-06,
+      "loss": 0.0033,
+      "step": 151
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.720535264270529e-06,
+      "loss": 0.0048,
+      "step": 152
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.60879827444116e-06,
+      "loss": 0.0244,
+      "step": 153
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.497110181738928e-06,
+      "loss": 0.0004,
+      "step": 154
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.385484946293636e-06,
+      "loss": 0.0018,
+      "step": 155
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.273936520378428e-06,
+      "loss": 0.0015,
+      "step": 156
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.16247884666586e-06,
+      "loss": 0.0008,
+      "step": 157
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.051125856485183e-06,
+      "loss": 0.0049,
+      "step": 158
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.939891468081033e-06,
+      "loss": 0.0224,
+      "step": 159
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.828789584873754e-06,
+      "loss": 0.0282,
+      "step": 160
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.717834093721598e-06,
+      "loss": 0.0015,
+      "step": 161
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.607038863184957e-06,
+      "loss": 0.0009,
+      "step": 162
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.496417741792912e-06,
+      "loss": 0.0034,
+      "step": 163
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.385984556312282e-06,
+      "loss": 0.0103,
+      "step": 164
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.275753110019367e-06,
+      "loss": 0.0058,
+      "step": 165
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.165737180974678e-06,
+      "loss": 0.0177,
+      "step": 166
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.05595052030076e-06,
+      "loss": 0.002,
+      "step": 167
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.94640685046343e-06,
+      "loss": 0.0269,
+      "step": 168
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.837119863556554e-06,
+      "loss": 0.0048,
+      "step": 169
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.72810321959068e-06,
+      "loss": 0.0125,
+      "step": 170
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.619370544785608e-06,
+      "loss": 0.0032,
+      "step": 171
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.510935429867237e-06,
+      "loss": 0.0079,
+      "step": 172
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.402811428368832e-06,
+      "loss": 0.0154,
+      "step": 173
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.295012054936934e-06,
+      "loss": 0.0036,
+      "step": 174
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.187550783642141e-06,
+      "loss": 0.0063,
+      "step": 175
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.080441046294948e-06,
+      "loss": 0.0119,
+      "step": 176
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.973696230766891e-06,
+      "loss": 0.0015,
+      "step": 177
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.8673296793171555e-06,
+      "loss": 0.003,
+      "step": 178
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.761354686924895e-06,
+      "loss": 0.0065,
+      "step": 179
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.655784499627491e-06,
+      "loss": 0.0034,
+      "step": 180
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.550632312864869e-06,
+      "loss": 0.0031,
+      "step": 181
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.445911269830189e-06,
+      "loss": 0.0023,
+      "step": 182
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.341634459827053e-06,
+      "loss": 0.0009,
+      "step": 183
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.237814916633444e-06,
+      "loss": 0.003,
+      "step": 184
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.134465616872598e-06,
+      "loss": 0.0036,
+      "step": 185
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.0315994783910345e-06,
+      "loss": 0.0005,
+      "step": 186
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.929229358643932e-06,
+      "loss": 0.0005,
+      "step": 187
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.827368053088043e-06,
+      "loss": 0.0036,
+      "step": 188
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.726028293582355e-06,
+      "loss": 0.0098,
+      "step": 189
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.62522274679673e-06,
+      "loss": 0.0005,
+      "step": 190
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.524964012628648e-06,
+      "loss": 0.0207,
+      "step": 191
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.42526462262833e-06,
+      "loss": 0.0015,
+      "step": 192
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.326137038432399e-06,
+      "loss": 0.0024,
+      "step": 193
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.227593650206258e-06,
+      "loss": 0.0059,
+      "step": 194
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.129646775095432e-06,
+      "loss": 0.0188,
+      "step": 195
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.032308655686011e-06,
+      "loss": 0.0007,
+      "step": 196
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.935591458474433e-06,
+      "loss": 0.0056,
+      "step": 197
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.8395072723467585e-06,
+      "loss": 0.019,
+      "step": 198
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.74406810706767e-06,
+      "loss": 0.0081,
+      "step": 199
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.649285891779327e-06,
+      "loss": 0.0308,
+      "step": 200
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.5551724735103285e-06,
+      "loss": 0.0108,
+      "step": 201
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.461739615694929e-06,
+      "loss": 0.0028,
+      "step": 202
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.368998996702694e-06,
+      "loss": 0.0044,
+      "step": 203
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.276962208378811e-06,
+      "loss": 0.0014,
+      "step": 204
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.185640754595183e-06,
+      "loss": 0.004,
+      "step": 205
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.095046049812545e-06,
+      "loss": 0.0007,
+      "step": 206
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.005189417653743e-06,
+      "loss": 0.0236,
+      "step": 207
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.916082089488372e-06,
+      "loss": 0.0132,
+      "step": 208
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.827735203028953e-06,
+      "loss": 0.0031,
+      "step": 209
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.740159800938784e-06,
+      "loss": 0.01,
+      "step": 210
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6533668294517154e-06,
+      "loss": 0.0053,
+      "step": 211
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5673671370039464e-06,
+      "loss": 0.0009,
+      "step": 212
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.482171472878062e-06,
+      "loss": 0.0005,
+      "step": 213
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.39779048585945e-06,
+      "loss": 0.0075,
+      "step": 214
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.314234722905302e-06,
+      "loss": 0.0083,
+      "step": 215
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2315146278263053e-06,
+      "loss": 0.0097,
+      "step": 216
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.149640539981267e-06,
+      "loss": 0.0015,
+      "step": 217
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0686226929847617e-06,
+      "loss": 0.0013,
+      "step": 218
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.9884712134280324e-06,
+      "loss": 0.0046,
+      "step": 219
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.909196119613218e-06,
+      "loss": 0.0017,
+      "step": 220
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8308073203011667e-06,
+      "loss": 0.0015,
+      "step": 221
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.753314613472906e-06,
+      "loss": 0.0005,
+      "step": 222
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6767276851049818e-06,
+      "loss": 0.0006,
+      "step": 223
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6010561079587817e-06,
+      "loss": 0.0037,
+      "step": 224
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5263093403840145e-06,
+      "loss": 0.0051,
+      "step": 225
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.452496725136503e-06,
+      "loss": 0.0045,
+      "step": 226
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3796274882103964e-06,
+      "loss": 0.0006,
+      "step": 227
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3077107376850005e-06,
+      "loss": 0.0014,
+      "step": 228
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2367554625863496e-06,
+      "loss": 0.0024,
+      "step": 229
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1667705317636333e-06,
+      "loss": 0.0036,
+      "step": 230
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0977646927806682e-06,
+      "loss": 0.0096,
+      "step": 231
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.029746570822524e-06,
+      "loss": 0.0004,
+      "step": 232
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9627246676174363e-06,
+      "loss": 0.0075,
+      "step": 233
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.896707360374167e-06,
+      "loss": 0.0008,
+      "step": 234
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8317029007349086e-06,
+      "loss": 0.0009,
+      "step": 235
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7677194137439036e-06,
+      "loss": 0.0005,
+      "step": 236
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7047648968318697e-06,
+      "loss": 0.0123,
+      "step": 237
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.642847218816398e-06,
+      "loss": 0.0054,
+      "step": 238
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5819741189183902e-06,
+      "loss": 0.0005,
+      "step": 239
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.522153205794742e-06,
+      "loss": 0.0075,
+      "step": 240
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4633919565873033e-06,
+      "loss": 0.011,
+      "step": 241
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4056977159883011e-06,
+      "loss": 0.0016,
+      "step": 242
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3490776953223107e-06,
+      "loss": 0.0046,
+      "step": 243
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2935389716448976e-06,
+      "loss": 0.0002,
+      "step": 244
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.23908848685804e-06,
+      "loss": 0.0036,
+      "step": 245
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1857330468424466e-06,
+      "loss": 0.0028,
+      "step": 246
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1334793206068739e-06,
+      "loss": 0.0011,
+      "step": 247
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.082333839454559e-06,
+      "loss": 0.0013,
+      "step": 248
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0323029961668463e-06,
+      "loss": 0.0005,
+      "step": 249
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.833930442041506e-07,
+      "loss": 0.0089,
+      "step": 250
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.356100969243231e-07,
+      "loss": 0.0011,
+      "step": 251
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.889601268185233e-07,
+      "loss": 0.0014,
+      "step": 252
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.434489647647093e-07,
+      "loss": 0.0003,
+      "step": 253
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.990822992988267e-07,
+      "loss": 0.0011,
+      "step": 254
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.558656759037796e-07,
+      "loss": 0.0039,
+      "step": 255
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.13804496316296e-07,
+      "loss": 0.0037,
+      "step": 256
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.729040178517454e-07,
+      "loss": 0.0031,
+      "step": 257
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.331693527470306e-07,
+      "loss": 0.0006,
+      "step": 258
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.946054675215785e-07,
+      "loss": 0.0036,
+      "step": 259
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.572171823565797e-07,
+      "loss": 0.0011,
+      "step": 260
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.210091704924947e-07,
+      "loss": 0.001,
+      "step": 261
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.859859576449444e-07,
+      "loss": 0.0005,
+      "step": 262
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.5215192143902577e-07,
+      "loss": 0.0012,
+      "step": 263
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1951129086214015e-07,
+      "loss": 0.0016,
+      "step": 264
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.8806814573541185e-07,
+      "loss": 0.0038,
+      "step": 265
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.578264162037348e-07,
+      "loss": 0.0019,
+      "step": 266
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.2878988224454346e-07,
+      "loss": 0.0059,
+      "step": 267
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0096217319533386e-07,
+      "loss": 0.0044,
+      "step": 268
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7434676730003886e-07,
+      "loss": 0.0026,
+      "step": 269
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.489469912742637e-07,
+      "loss": 0.0052,
+      "step": 270
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.2476601988947965e-07,
+      "loss": 0.0029,
+      "step": 271
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0180687557619816e-07,
+      "loss": 0.0003,
+      "step": 272
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.800724280461963e-07,
+      "loss": 0.0038,
+      "step": 273
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5956539393382043e-07,
+      "loss": 0.0036,
+      "step": 274
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4028833645643113e-07,
+      "loss": 0.0029,
+      "step": 275
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2224366509401732e-07,
+      "loss": 0.0004,
+      "step": 276
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0543363528803696e-07,
+      "loss": 0.0007,
+      "step": 277
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.986034815950173e-08,
+      "loss": 0.0004,
+      "step": 278
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.55257502463469e-08,
+      "loss": 0.0021,
+      "step": 279
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.243163326014268e-08,
+      "loss": 0.0017,
+      "step": 280
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.057963386213116e-08,
+      "loss": 0.0013,
+      "step": 281
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.9971233458665495e-08,
+      "loss": 0.0029,
+      "step": 282
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.0607758016043546e-08,
+      "loss": 0.0016,
+      "step": 283
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.2490377894768266e-08,
+      "loss": 0.0022,
+      "step": 284
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.562010770326916e-08,
+      "loss": 0.0044,
+      "step": 285
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.99780617107815e-09,
+      "loss": 0.0093,
+      "step": 286
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.6241760414987856e-09,
+      "loss": 0.0016,
+      "step": 287
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.4997639837687217e-09,
+      "loss": 0.0003,
+      "step": 288
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.24960524725493e-10,
+      "loss": 0.0004,
+      "step": 289
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.0017,
+      "step": 290
+    },
+    {
+      "epoch": 1.0,
+      "step": 290,
+      "total_flos": 135956826390528.0,
+      "train_loss": 0.0826369430505518,
+      "train_runtime": 7100.2656,
+      "train_samples_per_second": 5.237,
+      "train_steps_per_second": 0.041
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 290,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 135956826390528.0,
+  "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 sha256:401b045a78ca7514e53b2e8df6f3a166601f571706428e362254caaa61a6d37b
+size 6712