Upload folder using huggingface_hub

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "/vol3/home/ctr/llava-rlhf/models/llava-RLAIF-V-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": "/vol3/home/ctr/llava-rlhf/models/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": 2048,
+  "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 sha256:74897d08330e7af00c14d8d0b358afcbc231f51f7f84f4896903da86b5a8c291
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60d40b6e830db78791aaa5034abd6423eae8e00950af1cedfe98f657b201f73
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de55905dbd3cf41b4e0d3a3c0e440582278e0b7bbe5d02ead15fe3cc8922a944
+size 4239549890

model.safetensors.index.json

@@ -0,0 +1,697 @@
+{
+  "metadata": {
+    "total_size": 14125830146
+  },
+  "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",
+    "score_head.0.bias": "model-00003-of-00003.safetensors",
+    "score_head.0.weight": "model-00003-of-00003.safetensors",
+    "score_head.1.bias": "model-00003-of-00003.safetensors",
+    "score_head.1.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 +1,43 @@
+{
+  "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": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2982 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 492,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.9043,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.7718382013555792e-06,
+      "loss": 5.6328,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.808297106493815e-06,
+      "loss": 5.5723,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.5436764027111585e-06,
+      "loss": 4.5039,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.114080899322211e-06,
+      "loss": 2.3037,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.5801353078493935e-06,
+      "loss": 0.3887,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9741786956652775e-06,
+      "loss": 1.4102,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.315514604066737e-06,
+      "loss": 1.1274,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.61659421298763e-06,
+      "loss": 0.4257,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.885919100677791e-06,
+      "loss": 0.8638,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.1295530968789295e-06,
+      "loss": 2.0259,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.3519735092049725e-06,
+      "loss": 1.3755,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.55658045441586e-06,
+      "loss": 0.3055,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.7460168970208566e-06,
+      "loss": 1.2031,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.922378005816025e-06,
+      "loss": 2.4268,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.087352805422317e-06,
+      "loss": 1.8799,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.242322808748768e-06,
+      "loss": 0.3868,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.388432414343207e-06,
+      "loss": 0.6277,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.52664024490876e-06,
+      "loss": 1.1833,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.657757302033369e-06,
+      "loss": 0.4211,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.782475802159092e-06,
+      "loss": 0.3101,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.90139129823451e-06,
+      "loss": 0.3011,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.015019879940584e-06,
+      "loss": 0.0665,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.123811710560552e-06,
+      "loss": 0.0495,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.228161798644422e-06,
+      "loss": 0.2415,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.328418655771438e-06,
+      "loss": 0.209,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.424891319481442e-06,
+      "loss": 0.0419,
+      "step": 27
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.517855098376436e-06,
+      "loss": 0.0312,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.607556308626424e-06,
+      "loss": 0.1582,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.694216207171605e-06,
+      "loss": 0.1236,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.778034279758329e-06,
+      "loss": 0.0349,
+      "step": 31
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.859191006777897e-06,
+      "loss": 0.0299,
+      "step": 32
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.937850203372744e-06,
+      "loss": 0.0935,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.014161010104347e-06,
+      "loss": 0.0794,
+      "step": 34
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.08825959498749e-06,
+      "loss": 0.0279,
+      "step": 35
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.160270615698787e-06,
+      "loss": 0.0246,
+      "step": 36
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.230308481401767e-06,
+      "loss": 0.0682,
+      "step": 37
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.29847844626434e-06,
+      "loss": 0.0534,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.364877560909674e-06,
+      "loss": 0.0279,
+      "step": 39
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.429595503388948e-06,
+      "loss": 0.0233,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.492715307531484e-06,
+      "loss": 0.049,
+      "step": 41
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.554314003514673e-06,
+      "loss": 0.0448,
+      "step": 42
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.614463183050538e-06,
+      "loss": 0.0261,
+      "step": 43
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.673229499590088e-06,
+      "loss": 0.0196,
+      "step": 44
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.73067511230984e-06,
+      "loss": 0.0553,
+      "step": 45
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.786858081296164e-06,
+      "loss": 0.0488,
+      "step": 46
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.841832720226257e-06,
+      "loss": 0.0203,
+      "step": 47
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.895649911916131e-06,
+      "loss": 0.0192,
+      "step": 48
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.948357391330555e-06,
+      "loss": 0.0512,
+      "step": 49
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1e-05,
+      "loss": 0.0485,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1e-05,
+      "loss": 0.0183,
+      "step": 51
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1e-05,
+      "loss": 0.0146,
+      "step": 52
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1e-05,
+      "loss": 0.0568,
+      "step": 53
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1e-05,
+      "loss": 0.0474,
+      "step": 54
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1e-05,
+      "loss": 0.0148,
+      "step": 55
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1e-05,
+      "loss": 0.0165,
+      "step": 56
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1e-05,
+      "loss": 0.0425,
+      "step": 57
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1e-05,
+      "loss": 0.0416,
+      "step": 58
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1e-05,
+      "loss": 0.0135,
+      "step": 59
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1e-05,
+      "loss": 0.0126,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1e-05,
+      "loss": 0.043,
+      "step": 61
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1e-05,
+      "loss": 0.0319,
+      "step": 62
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1e-05,
+      "loss": 0.0159,
+      "step": 63
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1e-05,
+      "loss": 0.013,
+      "step": 64
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1e-05,
+      "loss": 0.0334,
+      "step": 65
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1e-05,
+      "loss": 0.0356,
+      "step": 66
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1e-05,
+      "loss": 0.0162,
+      "step": 67
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1e-05,
+      "loss": 0.0098,
+      "step": 68
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1e-05,
+      "loss": 0.0288,
+      "step": 69
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1e-05,
+      "loss": 0.0324,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1e-05,
+      "loss": 0.0124,
+      "step": 71
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 0.0121,
+      "step": 72
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 0.0287,
+      "step": 73
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 0.0222,
+      "step": 74
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 0.0138,
+      "step": 75
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 0.0148,
+      "step": 76
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 0.0225,
+      "step": 77
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 0.0202,
+      "step": 78
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 0.0152,
+      "step": 79
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 0.0158,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 0.0229,
+      "step": 81
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1e-05,
+      "loss": 0.0175,
+      "step": 82
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1e-05,
+      "loss": 0.0146,
+      "step": 83
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1e-05,
+      "loss": 0.0155,
+      "step": 84
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1e-05,
+      "loss": 0.017,
+      "step": 85
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1e-05,
+      "loss": 0.0184,
+      "step": 86
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1e-05,
+      "loss": 0.018,
+      "step": 87
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1e-05,
+      "loss": 0.0157,
+      "step": 88
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1e-05,
+      "loss": 0.018,
+      "step": 89
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1e-05,
+      "loss": 0.0147,
+      "step": 90
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1e-05,
+      "loss": 0.0148,
+      "step": 91
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1e-05,
+      "loss": 0.0157,
+      "step": 92
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1e-05,
+      "loss": 0.0173,
+      "step": 93
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1e-05,
+      "loss": 0.015,
+      "step": 94
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1e-05,
+      "loss": 0.0135,
+      "step": 95
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1e-05,
+      "loss": 0.0116,
+      "step": 96
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1e-05,
+      "loss": 0.0152,
+      "step": 97
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1e-05,
+      "loss": 0.0153,
+      "step": 98
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1e-05,
+      "loss": 0.0164,
+      "step": 99
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1e-05,
+      "loss": 0.0162,
+      "step": 100
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1e-05,
+      "loss": 0.0139,
+      "step": 101
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1e-05,
+      "loss": 0.0114,
+      "step": 102
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1e-05,
+      "loss": 0.0154,
+      "step": 103
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1e-05,
+      "loss": 0.0146,
+      "step": 104
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1e-05,
+      "loss": 0.0147,
+      "step": 105
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1e-05,
+      "loss": 0.0129,
+      "step": 106
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1e-05,
+      "loss": 0.0134,
+      "step": 107
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1e-05,
+      "loss": 0.0145,
+      "step": 108
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1e-05,
+      "loss": 0.014,
+      "step": 109
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1e-05,
+      "loss": 0.0126,
+      "step": 110
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1e-05,
+      "loss": 0.013,
+      "step": 111
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1e-05,
+      "loss": 0.0126,
+      "step": 112
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1e-05,
+      "loss": 0.0123,
+      "step": 113
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1e-05,
+      "loss": 0.0103,
+      "step": 114
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1e-05,
+      "loss": 0.0144,
+      "step": 115
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1e-05,
+      "loss": 0.0142,
+      "step": 116
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1e-05,
+      "loss": 0.0117,
+      "step": 117
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "step": 118
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1e-05,
+      "loss": 0.0119,
+      "step": 119
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1e-05,
+      "loss": 0.0135,
+      "step": 120
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1e-05,
+      "loss": 0.0117,
+      "step": 121
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1e-05,
+      "loss": 0.0089,
+      "step": 122
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1e-05,
+      "loss": 0.0137,
+      "step": 123
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1e-05,
+      "loss": 0.0128,
+      "step": 124
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1e-05,
+      "loss": 0.0131,
+      "step": 125
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1e-05,
+      "loss": 0.0133,
+      "step": 126
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "step": 127
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1e-05,
+      "loss": 0.0088,
+      "step": 128
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1e-05,
+      "loss": 0.0153,
+      "step": 129
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1e-05,
+      "loss": 0.0103,
+      "step": 130
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1e-05,
+      "loss": 0.0137,
+      "step": 131
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1e-05,
+      "loss": 0.0112,
+      "step": 132
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1e-05,
+      "loss": 0.0106,
+      "step": 133
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1e-05,
+      "loss": 0.0113,
+      "step": 134
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1e-05,
+      "loss": 0.0098,
+      "step": 135
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1e-05,
+      "loss": 0.0089,
+      "step": 136
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "step": 137
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1e-05,
+      "loss": 0.0119,
+      "step": 138
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1e-05,
+      "loss": 0.0083,
+      "step": 139
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1e-05,
+      "loss": 0.009,
+      "step": 140
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1e-05,
+      "loss": 0.011,
+      "step": 141
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1e-05,
+      "loss": 0.0126,
+      "step": 142
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1e-05,
+      "loss": 0.0095,
+      "step": 143
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1e-05,
+      "loss": 0.0083,
+      "step": 144
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1e-05,
+      "loss": 0.0134,
+      "step": 145
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1e-05,
+      "loss": 0.0112,
+      "step": 146
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "step": 147
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1e-05,
+      "loss": 0.0102,
+      "step": 148
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1e-05,
+      "loss": 0.011,
+      "step": 149
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "step": 150
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1e-05,
+      "loss": 0.0081,
+      "step": 151
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1e-05,
+      "loss": 0.008,
+      "step": 152
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1e-05,
+      "loss": 0.0147,
+      "step": 153
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1e-05,
+      "loss": 0.0117,
+      "step": 154
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 155
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1e-05,
+      "loss": 0.0073,
+      "step": 156
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1e-05,
+      "loss": 0.0123,
+      "step": 157
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1e-05,
+      "loss": 0.0099,
+      "step": 158
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 159
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1e-05,
+      "loss": 0.0064,
+      "step": 160
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1e-05,
+      "loss": 0.0093,
+      "step": 161
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1e-05,
+      "loss": 0.0088,
+      "step": 162
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1e-05,
+      "loss": 0.0097,
+      "step": 163
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1e-05,
+      "loss": 0.0077,
+      "step": 164
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1e-05,
+      "loss": 0.0111,
+      "step": 165
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1e-05,
+      "loss": 0.0114,
+      "step": 166
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1e-05,
+      "loss": 0.0073,
+      "step": 167
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 168
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1e-05,
+      "loss": 0.0105,
+      "step": 169
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1e-05,
+      "loss": 0.0116,
+      "step": 170
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 171
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 172
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1e-05,
+      "loss": 0.012,
+      "step": 173
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 174
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1e-05,
+      "loss": 0.0069,
+      "step": 175
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 176
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "step": 177
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1e-05,
+      "loss": 0.0098,
+      "step": 178
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 179
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 180
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1e-05,
+      "loss": 0.0087,
+      "step": 181
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1e-05,
+      "loss": 0.0106,
+      "step": 182
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 183
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "step": 184
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1e-05,
+      "loss": 0.0106,
+      "step": 185
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 186
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1e-05,
+      "loss": 0.007,
+      "step": 187
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 188
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1e-05,
+      "loss": 0.0105,
+      "step": 189
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1e-05,
+      "loss": 0.008,
+      "step": 190
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1e-05,
+      "loss": 0.0088,
+      "step": 191
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1e-05,
+      "loss": 0.0075,
+      "step": 192
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1e-05,
+      "loss": 0.009,
+      "step": 193
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1e-05,
+      "loss": 0.0097,
+      "step": 194
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 195
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "step": 196
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1e-05,
+      "loss": 0.0095,
+      "step": 197
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1e-05,
+      "loss": 0.0084,
+      "step": 198
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1e-05,
+      "loss": 0.0093,
+      "step": 199
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "step": 200
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1e-05,
+      "loss": 0.0098,
+      "step": 201
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1e-05,
+      "loss": 0.0079,
+      "step": 202
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 203
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1e-05,
+      "loss": 0.0056,
+      "step": 204
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1e-05,
+      "loss": 0.0078,
+      "step": 205
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 206
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1e-05,
+      "loss": 0.0053,
+      "step": 207
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 208
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1e-05,
+      "loss": 0.0093,
+      "step": 209
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.0077,
+      "step": 210
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 211
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 212
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.0102,
+      "step": 213
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.011,
+      "step": 214
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 215
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1e-05,
+      "loss": 0.0078,
+      "step": 216
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1e-05,
+      "loss": 0.0081,
+      "step": 217
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 218
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 219
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0041,
+      "step": 220
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0095,
+      "step": 221
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 222
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 0.0083,
+      "step": 223
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "step": 224
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.0073,
+      "step": 225
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 226
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 227
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.0093,
+      "step": 228
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 0.0089,
+      "step": 229
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 0.0069,
+      "step": 230
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 231
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "step": 232
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 233
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 234
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.006,
+      "step": 235
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 236
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.0082,
+      "step": 237
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 238
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 0.0067,
+      "step": 239
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "step": 240
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 0.0073,
+      "step": 241
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "step": 242
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 0.0093,
+      "step": 243
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.0088,
+      "step": 244
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 245
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.0083,
+      "step": 246
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 247
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 248
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.0069,
+      "step": 249
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 250
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 251
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 252
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.0088,
+      "step": 253
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.0084,
+      "step": 254
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.0087,
+      "step": 255
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.007,
+      "step": 256
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.0075,
+      "step": 257
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 258
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1e-05,
+      "loss": 0.0061,
+      "step": 259
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 260
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "step": 261
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1e-05,
+      "loss": 0.0088,
+      "step": 262
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1e-05,
+      "loss": 0.0042,
+      "step": 263
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.0045,
+      "step": 264
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.0091,
+      "step": 265
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.0084,
+      "step": 266
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 267
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "step": 268
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.0084,
+      "step": 269
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.0117,
+      "step": 270
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.017,
+      "step": 271
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.0101,
+      "step": 272
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.009,
+      "step": 273
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.0092,
+      "step": 274
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "step": 275
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "step": 276
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.0136,
+      "step": 277
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1e-05,
+      "loss": 0.0112,
+      "step": 278
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1e-05,
+      "loss": 0.0104,
+      "step": 279
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1e-05,
+      "loss": 0.0095,
+      "step": 280
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 281
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1e-05,
+      "loss": 0.0079,
+      "step": 282
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 0.0097,
+      "step": 283
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 284
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 0.0069,
+      "step": 285
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "step": 286
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "step": 287
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 288
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 289
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 290
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 291
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "step": 292
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.0053,
+      "step": 293
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 294
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.0082,
+      "step": 295
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.0083,
+      "step": 296
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 297
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "step": 298
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.0091,
+      "step": 299
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 300
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.0067,
+      "step": 301
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "step": 302
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.009,
+      "step": 303
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.0084,
+      "step": 304
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 305
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.0068,
+      "step": 306
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.0085,
+      "step": 307
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.0064,
+      "step": 308
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 309
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 310
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.0077,
+      "step": 311
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.0067,
+      "step": 312
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 0.0075,
+      "step": 313
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 314
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 315
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 0.0045,
+      "step": 316
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 0.0091,
+      "step": 317
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 318
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "step": 319
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1e-05,
+      "loss": 0.0077,
+      "step": 320
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 321
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1e-05,
+      "loss": 0.0061,
+      "step": 322
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 323
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 324
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 325
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1e-05,
+      "loss": 0.0049,
+      "step": 326
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1e-05,
+      "loss": 0.0064,
+      "step": 327
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 328
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1e-05,
+      "loss": 0.0061,
+      "step": 329
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 330
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1e-05,
+      "loss": 0.0049,
+      "step": 331
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 332
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 333
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 334
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 335
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 336
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "step": 337
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 338
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1e-05,
+      "loss": 0.0036,
+      "step": 339
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 340
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1e-05,
+      "loss": 0.007,
+      "step": 341
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 342
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 343
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 0.004,
+      "step": 344
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 0.0061,
+      "step": 345
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 0.0049,
+      "step": 346
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1e-05,
+      "loss": 0.0039,
+      "step": 347
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1e-05,
+      "loss": 0.0049,
+      "step": 348
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 349
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 350
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 351
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 352
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1e-05,
+      "loss": 0.0081,
+      "step": 353
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 354
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 355
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 356
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1e-05,
+      "loss": 0.0073,
+      "step": 357
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 358
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1e-05,
+      "loss": 0.0049,
+      "step": 359
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1e-05,
+      "loss": 0.0049,
+      "step": 360
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1e-05,
+      "loss": 0.0073,
+      "step": 361
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 362
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1e-05,
+      "loss": 0.007,
+      "step": 363
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1e-05,
+      "loss": 0.0044,
+      "step": 364
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1e-05,
+      "loss": 0.0068,
+      "step": 365
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1e-05,
+      "loss": 0.0061,
+      "step": 366
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1e-05,
+      "loss": 0.0041,
+      "step": 367
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 368
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 369
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1e-05,
+      "loss": 0.0084,
+      "step": 370
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1e-05,
+      "loss": 0.0056,
+      "step": 371
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1e-05,
+      "loss": 0.0055,
+      "step": 372
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 373
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1e-05,
+      "loss": 0.0064,
+      "step": 374
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 375
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1e-05,
+      "loss": 0.0039,
+      "step": 376
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 0.0068,
+      "step": 377
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 0.0073,
+      "step": 378
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 379
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 0.0042,
+      "step": 380
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 0.009,
+      "step": 381
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 0.0069,
+      "step": 382
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 383
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 384
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 385
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 386
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 387
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1e-05,
+      "loss": 0.0064,
+      "step": 388
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1e-05,
+      "loss": 0.0143,
+      "step": 389
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1e-05,
+      "loss": 0.0171,
+      "step": 390
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1e-05,
+      "loss": 0.0092,
+      "step": 391
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "step": 392
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0182,
+      "step": 393
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0093,
+      "step": 394
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0092,
+      "step": 395
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0101,
+      "step": 396
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 397
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1e-05,
+      "loss": 0.0116,
+      "step": 398
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1e-05,
+      "loss": 0.0174,
+      "step": 399
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1e-05,
+      "loss": 0.0103,
+      "step": 400
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 401
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1e-05,
+      "loss": 0.0083,
+      "step": 402
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 403
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1e-05,
+      "loss": 0.0121,
+      "step": 404
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1e-05,
+      "loss": 0.0178,
+      "step": 405
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "step": 406
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 407
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 408
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 409
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1e-05,
+      "loss": 0.0044,
+      "step": 410
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 0.005,
+      "step": 411
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 412
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 413
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 0.0036,
+      "step": 414
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "step": 415
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 416
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 417
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1e-05,
+      "loss": 0.0034,
+      "step": 418
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1e-05,
+      "loss": 0.0055,
+      "step": 419
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 420
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1e-05,
+      "loss": 0.0045,
+      "step": 421
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1e-05,
+      "loss": 0.0042,
+      "step": 422
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1e-05,
+      "loss": 0.0045,
+      "step": 423
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 424
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 425
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1e-05,
+      "loss": 0.0061,
+      "step": 426
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 427
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 428
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 429
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 430
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1e-05,
+      "loss": 0.0112,
+      "step": 431
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1e-05,
+      "loss": 0.0121,
+      "step": 432
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1e-05,
+      "loss": 0.0081,
+      "step": 433
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1e-05,
+      "loss": 0.0145,
+      "step": 434
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1e-05,
+      "loss": 0.0304,
+      "step": 435
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1e-05,
+      "loss": 0.0193,
+      "step": 436
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1e-05,
+      "loss": 0.006,
+      "step": 437
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1e-05,
+      "loss": 0.0187,
+      "step": 438
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1e-05,
+      "loss": 0.0374,
+      "step": 439
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1e-05,
+      "loss": 0.0329,
+      "step": 440
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 0.0161,
+      "step": 441
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 0.0078,
+      "step": 442
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 0.0123,
+      "step": 443
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "step": 444
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 445
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1e-05,
+      "loss": 0.0055,
+      "step": 446
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 447
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 448
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1e-05,
+      "loss": 0.0064,
+      "step": 449
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 450
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1e-05,
+      "loss": 0.0042,
+      "step": 451
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1e-05,
+      "loss": 0.0062,
+      "step": 452
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 453
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1e-05,
+      "loss": 0.0108,
+      "step": 454
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1e-05,
+      "loss": 0.0111,
+      "step": 455
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 0.006,
+      "step": 456
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 457
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 0.0147,
+      "step": 458
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 0.0098,
+      "step": 459
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 460
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 461
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1e-05,
+      "loss": 0.0069,
+      "step": 462
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1e-05,
+      "loss": 0.0034,
+      "step": 463
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1e-05,
+      "loss": 0.009,
+      "step": 464
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0111,
+      "step": 465
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 466
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0113,
+      "step": 467
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0174,
+      "step": 468
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1e-05,
+      "loss": 0.0119,
+      "step": 469
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 470
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 471
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1e-05,
+      "loss": 0.0045,
+      "step": 472
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1e-05,
+      "loss": 0.006,
+      "step": 473
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1e-05,
+      "loss": 0.0059,
+      "step": 474
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 0.0055,
+      "step": 475
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 0.0071,
+      "step": 476
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 0.0086,
+      "step": 477
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 478
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 0.0146,
+      "step": 479
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1e-05,
+      "loss": 0.0277,
+      "step": 480
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1e-05,
+      "loss": 0.0163,
+      "step": 481
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 482
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1e-05,
+      "loss": 0.0194,
+      "step": 483
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1e-05,
+      "loss": 0.0394,
+      "step": 484
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1e-05,
+      "loss": 0.0366,
+      "step": 485
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1e-05,
+      "loss": 0.0183,
+      "step": 486
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1e-05,
+      "loss": 0.005,
+      "step": 487
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1e-05,
+      "loss": 0.0266,
+      "step": 488
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1e-05,
+      "loss": 0.0585,
+      "step": 489
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0667,
+      "step": 490
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0379,
+      "step": 491
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0119,
+      "step": 492
+    },
+    {
+      "epoch": 1.0,
+      "step": 492,
+      "total_flos": 1052445427236864.0,
+      "train_loss": 0.08519280441408235,
+      "train_runtime": 16192.5824,
+      "train_samples_per_second": 7.776,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 492,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1052445427236864.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e8133c0395a29145818051bfae4eac15c14501b4d2a4dc1eda4af81e243758
+size 7544