Upload folder using huggingface_hub

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "/mnt/ceph_rbd/mnt_pvc/zbc/llava-v1.5-7b/",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 4096,
+  "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:d785cb8e8b47da8f6f566b1cb15b115b7086773b8cc877c87a006245a2676373
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79ede00e97bc79d8ddea5a9e0de70ef4d4713129309e7d76fd486526e727034
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33d5ab4a12464744cd75c61f22c0a6399f937159ae66df50b4d8ecb79da3a54
+size 4239524944

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,3642 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 602,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 1.307,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 1.2963,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 1.3486,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.2709,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 1.1965,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.31578947368421e-06,
+      "loss": 1.157,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.368421052631579e-06,
+      "loss": 1.0994,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 1.0431,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 0.9693,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.0234,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1578947368421053e-05,
+      "loss": 1.0187,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.263157894736842e-05,
+      "loss": 0.9574,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.3684210526315791e-05,
+      "loss": 0.9403,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4736842105263159e-05,
+      "loss": 0.9109,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.578947368421053e-05,
+      "loss": 0.9802,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 0.8636,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7894736842105264e-05,
+      "loss": 0.8677,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 0.8062,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.9614,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999854811710317e-05,
+      "loss": 0.8499,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.999941925105719e-05,
+      "loss": 0.7738,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9998693330688283e-05,
+      "loss": 0.7737,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997677071682623e-05,
+      "loss": 0.7857,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999637050354999e-05,
+      "loss": 0.739,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9994773664230064e-05,
+      "loss": 0.8261,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9992886600091318e-05,
+      "loss": 0.7056,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9990709365929678e-05,
+      "loss": 0.7581,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9988242024966924e-05,
+      "loss": 0.7024,
+      "step": 28
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9985484648848854e-05,
+      "loss": 0.7209,
+      "step": 29
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9982437317643218e-05,
+      "loss": 0.753,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.997910011983737e-05,
+      "loss": 0.6961,
+      "step": 31
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9975473152335726e-05,
+      "loss": 0.641,
+      "step": 32
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9971556520456928e-05,
+      "loss": 0.6929,
+      "step": 33
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996735033793079e-05,
+      "loss": 0.7563,
+      "step": 34
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9962854726894997e-05,
+      "loss": 0.7009,
+      "step": 35
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.995806981789157e-05,
+      "loss": 0.6801,
+      "step": 36
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.995299574986306e-05,
+      "loss": 0.6669,
+      "step": 37
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9947632670148517e-05,
+      "loss": 0.6949,
+      "step": 38
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9941980734479214e-05,
+      "loss": 0.6194,
+      "step": 39
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9936040106974132e-05,
+      "loss": 0.6486,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.992981096013517e-05,
+      "loss": 0.6008,
+      "step": 41
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9923293474842175e-05,
+      "loss": 0.6155,
+      "step": 42
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9916487840347644e-05,
+      "loss": 0.5991,
+      "step": 43
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.990939425427127e-05,
+      "loss": 0.5591,
+      "step": 44
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9902012922594178e-05,
+      "loss": 0.6447,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9894344059652953e-05,
+      "loss": 0.5531,
+      "step": 46
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9886387888133413e-05,
+      "loss": 0.4996,
+      "step": 47
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9878144639064145e-05,
+      "loss": 0.5111,
+      "step": 48
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9869614551809793e-05,
+      "loss": 0.5318,
+      "step": 49
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9860797874064123e-05,
+      "loss": 0.5139,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9851694861842795e-05,
+      "loss": 0.4108,
+      "step": 51
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.984230577947597e-05,
+      "loss": 0.5292,
+      "step": 52
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9832630899600607e-05,
+      "loss": 0.4453,
+      "step": 53
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9822670503152567e-05,
+      "loss": 0.5731,
+      "step": 54
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9812424879358424e-05,
+      "loss": 0.4626,
+      "step": 55
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9801894325727104e-05,
+      "loss": 0.4679,
+      "step": 56
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.979107914804122e-05,
+      "loss": 0.5613,
+      "step": 57
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.97799796603482e-05,
+      "loss": 0.58,
+      "step": 58
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9768596184951174e-05,
+      "loss": 0.567,
+      "step": 59
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9756929052399606e-05,
+      "loss": 0.4405,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9744978601479693e-05,
+      "loss": 0.4092,
+      "step": 61
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9732745179204553e-05,
+      "loss": 0.5598,
+      "step": 62
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.972022914080411e-05,
+      "loss": 0.4612,
+      "step": 63
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.970743084971481e-05,
+      "loss": 0.4995,
+      "step": 64
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9694350677569043e-05,
+      "loss": 0.4683,
+      "step": 65
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9680989004184383e-05,
+      "loss": 0.5196,
+      "step": 66
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9667346217552528e-05,
+      "loss": 0.3732,
+      "step": 67
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.965342271382805e-05,
+      "loss": 0.455,
+      "step": 68
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9639218897316885e-05,
+      "loss": 0.525,
+      "step": 69
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9624735180464602e-05,
+      "loss": 0.3926,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9609971983844412e-05,
+      "loss": 0.386,
+      "step": 71
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.3632,
+      "step": 72
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.957960887415793e-05,
+      "loss": 0.4412,
+      "step": 73
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9564009842765225e-05,
+      "loss": 0.3838,
+      "step": 74
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9548133094926203e-05,
+      "loss": 0.3078,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.953197909166443e-05,
+      "loss": 0.4856,
+      "step": 76
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9515548302054335e-05,
+      "loss": 0.3373,
+      "step": 77
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.949884120320756e-05,
+      "loss": 0.4282,
+      "step": 78
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.948185828025913e-05,
+      "loss": 0.289,
+      "step": 79
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.946460002635335e-05,
+      "loss": 0.3876,
+      "step": 80
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9447066942629495e-05,
+      "loss": 0.3713,
+      "step": 81
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.942925953820725e-05,
+      "loss": 0.3597,
+      "step": 82
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.941117833017194e-05,
+      "loss": 0.382,
+      "step": 83
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.939282384355949e-05,
+      "loss": 0.3543,
+      "step": 84
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9374196611341212e-05,
+      "loss": 0.3774,
+      "step": 85
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9355297174408298e-05,
+      "loss": 0.306,
+      "step": 86
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9336126081556134e-05,
+      "loss": 0.4041,
+      "step": 87
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.931668388946836e-05,
+      "loss": 0.3839,
+      "step": 88
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9296971162700696e-05,
+      "loss": 0.392,
+      "step": 89
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9276988473664557e-05,
+      "loss": 0.4527,
+      "step": 90
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9256736402610437e-05,
+      "loss": 0.3799,
+      "step": 91
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9236215537611044e-05,
+      "loss": 0.2356,
+      "step": 92
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9215426474544242e-05,
+      "loss": 0.3679,
+      "step": 93
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9194369817075725e-05,
+      "loss": 0.313,
+      "step": 94
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9173046176641515e-05,
+      "loss": 0.3142,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9151456172430186e-05,
+      "loss": 0.2715,
+      "step": 96
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.91296004313649e-05,
+      "loss": 0.2938,
+      "step": 97
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9107479588085182e-05,
+      "loss": 0.3277,
+      "step": 98
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.908509428492852e-05,
+      "loss": 0.2161,
+      "step": 99
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9062445171911688e-05,
+      "loss": 0.314,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.903953290671188e-05,
+      "loss": 0.295,
+      "step": 101
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9016358154647618e-05,
+      "loss": 0.5739,
+      "step": 102
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8992921588659424e-05,
+      "loss": 0.3509,
+      "step": 103
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8969223889290283e-05,
+      "loss": 0.358,
+      "step": 104
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8945265744665886e-05,
+      "loss": 0.2689,
+      "step": 105
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8921047850474645e-05,
+      "loss": 0.2367,
+      "step": 106
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8896570909947477e-05,
+      "loss": 0.2676,
+      "step": 107
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.887183563383741e-05,
+      "loss": 0.3266,
+      "step": 108
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.884684274039894e-05,
+      "loss": 0.43,
+      "step": 109
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8821592955367154e-05,
+      "loss": 0.2942,
+      "step": 110
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8796087011936665e-05,
+      "loss": 0.4012,
+      "step": 111
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8770325650740347e-05,
+      "loss": 0.2977,
+      "step": 112
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.874430961982778e-05,
+      "loss": 0.3367,
+      "step": 113
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.871803967464358e-05,
+      "loss": 0.2307,
+      "step": 114
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8691516578005426e-05,
+      "loss": 0.2784,
+      "step": 115
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.866474110008193e-05,
+      "loss": 0.2833,
+      "step": 116
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8637714018370255e-05,
+      "loss": 0.2318,
+      "step": 117
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8610436117673557e-05,
+      "loss": 0.1993,
+      "step": 118
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8582908190078184e-05,
+      "loss": 0.2124,
+      "step": 119
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8555131034930686e-05,
+      "loss": 0.2767,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.852710545881459e-05,
+      "loss": 0.283,
+      "step": 121
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8498832275526988e-05,
+      "loss": 0.3091,
+      "step": 122
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8470312306054903e-05,
+      "loss": 0.2807,
+      "step": 123
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8441546378551457e-05,
+      "loss": 0.2986,
+      "step": 124
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.2228,
+      "step": 125
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.838327999774892e-05,
+      "loss": 0.1954,
+      "step": 126
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8353781236369065e-05,
+      "loss": 0.2095,
+      "step": 127
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.832403990074719e-05,
+      "loss": 0.1852,
+      "step": 128
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.829405685450202e-05,
+      "loss": 0.2725,
+      "step": 129
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8263832968271e-05,
+      "loss": 0.2307,
+      "step": 130
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8233369119685e-05,
+      "loss": 0.2215,
+      "step": 131
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8202666193342834e-05,
+      "loss": 0.1862,
+      "step": 132
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.817172508078557e-05,
+      "loss": 0.2139,
+      "step": 133
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.814054668047066e-05,
+      "loss": 0.2186,
+      "step": 134
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8109131897745823e-05,
+      "loss": 0.1616,
+      "step": 135
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.807748164482277e-05,
+      "loss": 0.2289,
+      "step": 136
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8045596840750722e-05,
+      "loss": 0.2641,
+      "step": 137
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.801347841138972e-05,
+      "loss": 0.2647,
+      "step": 138
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7981127289383718e-05,
+      "loss": 0.2312,
+      "step": 139
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7948544414133534e-05,
+      "loss": 0.2072,
+      "step": 140
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7915730731769558e-05,
+      "loss": 0.2107,
+      "step": 141
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.788268719512427e-05,
+      "loss": 0.2489,
+      "step": 142
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7849414763704587e-05,
+      "loss": 0.2391,
+      "step": 143
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.781591440366399e-05,
+      "loss": 0.2666,
+      "step": 144
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.778218708777448e-05,
+      "loss": 0.1389,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7748233795398308e-05,
+      "loss": 0.1709,
+      "step": 146
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.771405551245957e-05,
+      "loss": 0.2138,
+      "step": 147
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.767965323141555e-05,
+      "loss": 0.15,
+      "step": 148
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.764502795122793e-05,
+      "loss": 0.2135,
+      "step": 149
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.761018067733374e-05,
+      "loss": 0.2029,
+      "step": 150
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7575112421616203e-05,
+      "loss": 0.2023,
+      "step": 151
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.753982420237533e-05,
+      "loss": 0.2309,
+      "step": 152
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.750431704429837e-05,
+      "loss": 0.1989,
+      "step": 153
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7468591978430024e-05,
+      "loss": 0.129,
+      "step": 154
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7432650042142535e-05,
+      "loss": 0.2014,
+      "step": 155
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7396492279105562e-05,
+      "loss": 0.1654,
+      "step": 156
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.736011973925585e-05,
+      "loss": 0.2262,
+      "step": 157
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7323533478766777e-05,
+      "loss": 0.0958,
+      "step": 158
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.728673456001766e-05,
+      "loss": 0.1716,
+      "step": 159
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7249724051562905e-05,
+      "loss": 0.2305,
+      "step": 160
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7212503028101012e-05,
+      "loss": 0.1722,
+      "step": 161
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.717507257044331e-05,
+      "loss": 0.2655,
+      "step": 162
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7137433765482644e-05,
+      "loss": 0.207,
+      "step": 163
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.709958770616174e-05,
+      "loss": 0.1939,
+      "step": 164
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7061535491441538e-05,
+      "loss": 0.1811,
+      "step": 165
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7023278226269222e-05,
+      "loss": 0.1917,
+      "step": 166
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6984817021546177e-05,
+      "loss": 0.1318,
+      "step": 167
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6946152994095705e-05,
+      "loss": 0.1629,
+      "step": 168
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6907287266630614e-05,
+      "loss": 0.1278,
+      "step": 169
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6868220967720604e-05,
+      "loss": 0.2071,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6828955231759495e-05,
+      "loss": 0.1586,
+      "step": 171
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6789491198932302e-05,
+      "loss": 0.1866,
+      "step": 172
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6749830015182106e-05,
+      "loss": 0.2368,
+      "step": 173
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6709972832176797e-05,
+      "loss": 0.1126,
+      "step": 174
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6669920807275622e-05,
+      "loss": 0.1073,
+      "step": 175
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.662967510349558e-05,
+      "loss": 0.2808,
+      "step": 176
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.658923688947765e-05,
+      "loss": 0.1124,
+      "step": 177
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.1828,
+      "step": 178
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6507787633208173e-05,
+      "loss": 0.1617,
+      "step": 179
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.646677895605227e-05,
+      "loss": 0.1273,
+      "step": 180
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.642558249878109e-05,
+      "loss": 0.1125,
+      "step": 181
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6384199457643264e-05,
+      "loss": 0.1044,
+      "step": 182
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6342631034305386e-05,
+      "loss": 0.0849,
+      "step": 183
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6300878435817115e-05,
+      "loss": 0.1717,
+      "step": 184
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6258942874576117e-05,
+      "loss": 0.1175,
+      "step": 185
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6216825568292885e-05,
+      "loss": 0.0555,
+      "step": 186
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6174527739955345e-05,
+      "loss": 0.0661,
+      "step": 187
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.613205061779337e-05,
+      "loss": 0.0863,
+      "step": 188
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6089395435243105e-05,
+      "loss": 0.0906,
+      "step": 189
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6046563430911148e-05,
+      "loss": 0.1801,
+      "step": 190
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6003555848538586e-05,
+      "loss": 0.1413,
+      "step": 191
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.596037393696489e-05,
+      "loss": 0.1435,
+      "step": 192
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5917018950091642e-05,
+      "loss": 0.1245,
+      "step": 193
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.587349214684611e-05,
+      "loss": 0.1001,
+      "step": 194
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5829794791144723e-05,
+      "loss": 0.0853,
+      "step": 195
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5785928151856345e-05,
+      "loss": 0.1143,
+      "step": 196
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5741893502765452e-05,
+      "loss": 0.1728,
+      "step": 197
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.569769212253511e-05,
+      "loss": 0.1025,
+      "step": 198
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5653325294669884e-05,
+      "loss": 0.1428,
+      "step": 199
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5608794307478546e-05,
+      "loss": 0.1358,
+      "step": 200
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.556410045403667e-05,
+      "loss": 0.1497,
+      "step": 201
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5519245032149083e-05,
+      "loss": 0.1081,
+      "step": 202
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.547422934431218e-05,
+      "loss": 0.1102,
+      "step": 203
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.542905469767611e-05,
+      "loss": 0.0643,
+      "step": 204
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5383722404006808e-05,
+      "loss": 0.0768,
+      "step": 205
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.533823377964791e-05,
+      "loss": 0.1066,
+      "step": 206
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.529259014548253e-05,
+      "loss": 0.2044,
+      "step": 207
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5246792826894906e-05,
+      "loss": 0.0805,
+      "step": 208
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5200843153731905e-05,
+      "loss": 0.0828,
+      "step": 209
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5154742460264426e-05,
+      "loss": 0.0747,
+      "step": 210
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5108492085148632e-05,
+      "loss": 0.1062,
+      "step": 211
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5062093371387097e-05,
+      "loss": 0.1254,
+      "step": 212
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5015547666289798e-05,
+      "loss": 0.0915,
+      "step": 213
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4968856321434997e-05,
+      "loss": 0.0975,
+      "step": 214
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.492202069263e-05,
+      "loss": 0.069,
+      "step": 215
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4875042139871768e-05,
+      "loss": 0.1409,
+      "step": 216
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.482792202730745e-05,
+      "loss": 0.1101,
+      "step": 217
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4780661723194757e-05,
+      "loss": 0.1218,
+      "step": 218
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4733262599862234e-05,
+      "loss": 0.0761,
+      "step": 219
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4685726033669412e-05,
+      "loss": 0.0954,
+      "step": 220
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4638053404966836e-05,
+      "loss": 0.0573,
+      "step": 221
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4590246098055995e-05,
+      "loss": 0.2068,
+      "step": 222
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.454230550114911e-05,
+      "loss": 0.077,
+      "step": 223
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4494233006328837e-05,
+      "loss": 0.0696,
+      "step": 224
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.444603000950784e-05,
+      "loss": 0.1436,
+      "step": 225
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4397697910388248e-05,
+      "loss": 0.0723,
+      "step": 226
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4349238112421025e-05,
+      "loss": 0.1255,
+      "step": 227
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4300652022765207e-05,
+      "loss": 0.1388,
+      "step": 228
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4251941052247044e-05,
+      "loss": 0.1412,
+      "step": 229
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.420310661531904e-05,
+      "loss": 0.091,
+      "step": 230
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 0.153,
+      "step": 231
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4105073017928199e-05,
+      "loss": 0.1109,
+      "step": 232
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.405587670413143e-05,
+      "loss": 0.0831,
+      "step": 233
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4006562617174292e-05,
+      "loss": 0.0567,
+      "step": 234
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3957132189022373e-05,
+      "loss": 0.1013,
+      "step": 235
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3907586855019538e-05,
+      "loss": 0.0524,
+      "step": 236
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.385792805384625e-05,
+      "loss": 0.0659,
+      "step": 237
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3808157227477788e-05,
+      "loss": 0.0683,
+      "step": 238
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3758275821142382e-05,
+      "loss": 0.0898,
+      "step": 239
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3708285283279252e-05,
+      "loss": 0.1448,
+      "step": 240
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3658187065496533e-05,
+      "loss": 0.1463,
+      "step": 241
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3607982622529135e-05,
+      "loss": 0.0451,
+      "step": 242
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3557673412196504e-05,
+      "loss": 0.0497,
+      "step": 243
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3507260895360274e-05,
+      "loss": 0.0486,
+      "step": 244
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3456746535881872e-05,
+      "loss": 0.0408,
+      "step": 245
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3406131800579985e-05,
+      "loss": 0.0695,
+      "step": 246
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3355418159187988e-05,
+      "loss": 0.0736,
+      "step": 247
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3304607084311246e-05,
+      "loss": 0.0561,
+      "step": 248
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3253700051384371e-05,
+      "loss": 0.0547,
+      "step": 249
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3202698538628376e-05,
+      "loss": 0.0944,
+      "step": 250
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3151604027007744e-05,
+      "loss": 0.0512,
+      "step": 251
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.310041800018742e-05,
+      "loss": 0.174,
+      "step": 252
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.304914194448975e-05,
+      "loss": 0.0536,
+      "step": 253
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2997777348851288e-05,
+      "loss": 0.0666,
+      "step": 254
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2946325704779602e-05,
+      "loss": 0.096,
+      "step": 255
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.289478850630993e-05,
+      "loss": 0.1043,
+      "step": 256
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.284316724996181e-05,
+      "loss": 0.0378,
+      "step": 257
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.279146343469563e-05,
+      "loss": 0.1041,
+      "step": 258
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.273967856186909e-05,
+      "loss": 0.0893,
+      "step": 259
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2687814135193613e-05,
+      "loss": 0.0678,
+      "step": 260
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2635871660690677e-05,
+      "loss": 0.0293,
+      "step": 261
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2583852646648097e-05,
+      "loss": 0.0582,
+      "step": 262
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.25317586035762e-05,
+      "loss": 0.1079,
+      "step": 263
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2479591044163997e-05,
+      "loss": 0.0557,
+      "step": 264
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2427351483235224e-05,
+      "loss": 0.0785,
+      "step": 265
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2375041437704394e-05,
+      "loss": 0.1013,
+      "step": 266
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.232266242653271e-05,
+      "loss": 0.0538,
+      "step": 267
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2270215970683977e-05,
+      "loss": 0.0429,
+      "step": 268
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2217703593080445e-05,
+      "loss": 0.0351,
+      "step": 269
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2165126818558572e-05,
+      "loss": 0.0409,
+      "step": 270
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2112487173824755e-05,
+      "loss": 0.0611,
+      "step": 271
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2059786187410984e-05,
+      "loss": 0.0939,
+      "step": 272
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2007025389630484e-05,
+      "loss": 0.0413,
+      "step": 273
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1954206312533246e-05,
+      "loss": 0.0238,
+      "step": 274
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1901330489861564e-05,
+      "loss": 0.0813,
+      "step": 275
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1848399457005496e-05,
+      "loss": 0.0986,
+      "step": 276
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1795414750958265e-05,
+      "loss": 0.1239,
+      "step": 277
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1742377910271638e-05,
+      "loss": 0.114,
+      "step": 278
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1689290475011258e-05,
+      "loss": 0.0431,
+      "step": 279
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1636153986711906e-05,
+      "loss": 0.0429,
+      "step": 280
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1582969988332757e-05,
+      "loss": 0.0504,
+      "step": 281
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1529740024212566e-05,
+      "loss": 0.0668,
+      "step": 282
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1476465640024814e-05,
+      "loss": 0.0454,
+      "step": 283
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.0444,
+      "step": 284
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.136978980054496e-05,
+      "loss": 0.0573,
+      "step": 285
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1316391442869394e-05,
+      "loss": 0.0746,
+      "step": 286
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.12629548602694e-05,
+      "loss": 0.0407,
+      "step": 287
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1209481604418182e-05,
+      "loss": 0.0394,
+      "step": 288
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1155973228053854e-05,
+      "loss": 0.0395,
+      "step": 289
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1102431284934345e-05,
+      "loss": 0.1865,
+      "step": 290
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1048857329792284e-05,
+      "loss": 0.0954,
+      "step": 291
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.099525291828986e-05,
+      "loss": 0.0577,
+      "step": 292
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0941619606973633e-05,
+      "loss": 0.0789,
+      "step": 293
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0887958953229349e-05,
+      "loss": 0.0879,
+      "step": 294
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.083427251523672e-05,
+      "loss": 0.0613,
+      "step": 295
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0780561851924168e-05,
+      "loss": 0.0868,
+      "step": 296
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0726828522923563e-05,
+      "loss": 0.0441,
+      "step": 297
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0673074088524926e-05,
+      "loss": 0.0601,
+      "step": 298
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0619300109631146e-05,
+      "loss": 0.1636,
+      "step": 299
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0565508147712618e-05,
+      "loss": 0.0363,
+      "step": 300
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0511699764761935e-05,
+      "loss": 0.036,
+      "step": 301
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0457876523248518e-05,
+      "loss": 0.0752,
+      "step": 302
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0404039986073244e-05,
+      "loss": 0.0707,
+      "step": 303
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.035019171652306e-05,
+      "loss": 0.0607,
+      "step": 304
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0296333278225599e-05,
+      "loss": 0.0562,
+      "step": 305
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.024246623510377e-05,
+      "loss": 0.0699,
+      "step": 306
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0188592151330343e-05,
+      "loss": 0.1047,
+      "step": 307
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0134712591282539e-05,
+      "loss": 0.0383,
+      "step": 308
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0080829119496587e-05,
+      "loss": 0.0102,
+      "step": 309
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0026943300622313e-05,
+      "loss": 0.0833,
+      "step": 310
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.973056699377692e-06,
+      "loss": 0.0263,
+      "step": 311
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.919170880503416e-06,
+      "loss": 0.0665,
+      "step": 312
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.865287408717464e-06,
+      "loss": 0.0773,
+      "step": 313
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.811407848669657e-06,
+      "loss": 0.0483,
+      "step": 314
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.757533764896235e-06,
+      "loss": 0.0828,
+      "step": 315
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.703666721774403e-06,
+      "loss": 0.0338,
+      "step": 316
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.64980828347694e-06,
+      "loss": 0.0311,
+      "step": 317
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.595960013926761e-06,
+      "loss": 0.0704,
+      "step": 318
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.542123476751484e-06,
+      "loss": 0.0459,
+      "step": 319
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.488300235238067e-06,
+      "loss": 0.0283,
+      "step": 320
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.434491852287385e-06,
+      "loss": 0.0671,
+      "step": 321
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.38069989036886e-06,
+      "loss": 0.0623,
+      "step": 322
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.326925911475075e-06,
+      "loss": 0.0937,
+      "step": 323
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.27317147707644e-06,
+      "loss": 0.0534,
+      "step": 324
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.219438148075834e-06,
+      "loss": 0.07,
+      "step": 325
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.165727484763283e-06,
+      "loss": 0.043,
+      "step": 326
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.112041046770653e-06,
+      "loss": 0.0094,
+      "step": 327
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.058380393026369e-06,
+      "loss": 0.033,
+      "step": 328
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.00474708171014e-06,
+      "loss": 0.0547,
+      "step": 329
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.951142670207718e-06,
+      "loss": 0.0513,
+      "step": 330
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.897568715065658e-06,
+      "loss": 0.0324,
+      "step": 331
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.844026771946148e-06,
+      "loss": 0.0238,
+      "step": 332
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.790518395581823e-06,
+      "loss": 0.0381,
+      "step": 333
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.737045139730605e-06,
+      "loss": 0.042,
+      "step": 334
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.683608557130608e-06,
+      "loss": 0.033,
+      "step": 335
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.63021019945504e-06,
+      "loss": 0.02,
+      "step": 336
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 0.0499,
+      "step": 337
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.52353435997519e-06,
+      "loss": 0.0498,
+      "step": 338
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.470259975787438e-06,
+      "loss": 0.0284,
+      "step": 339
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.417030011667241e-06,
+      "loss": 0.0664,
+      "step": 340
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.363846013288096e-06,
+      "loss": 0.0607,
+      "step": 341
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.310709524988743e-06,
+      "loss": 0.0507,
+      "step": 342
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.257622089728362e-06,
+      "loss": 0.0144,
+      "step": 343
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.20458524904174e-06,
+      "loss": 0.0363,
+      "step": 344
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.151600542994506e-06,
+      "loss": 0.0904,
+      "step": 345
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.098669510138438e-06,
+      "loss": 0.1086,
+      "step": 346
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.045793687466757e-06,
+      "loss": 0.0527,
+      "step": 347
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.992974610369521e-06,
+      "loss": 0.0334,
+      "step": 348
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.940213812589018e-06,
+      "loss": 0.0337,
+      "step": 349
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.887512826175247e-06,
+      "loss": 0.0243,
+      "step": 350
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.834873181441426e-06,
+      "loss": 0.0385,
+      "step": 351
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.782296406919557e-06,
+      "loss": 0.041,
+      "step": 352
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.729784029316025e-06,
+      "loss": 0.0667,
+      "step": 353
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.677337573467294e-06,
+      "loss": 0.0196,
+      "step": 354
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.624958562295607e-06,
+      "loss": 0.0547,
+      "step": 355
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.572648516764778e-06,
+      "loss": 0.0105,
+      "step": 356
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.5204089558360076e-06,
+      "loss": 0.0339,
+      "step": 357
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.468241396423801e-06,
+      "loss": 0.0207,
+      "step": 358
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.416147353351909e-06,
+      "loss": 0.0121,
+      "step": 359
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.364128339309326e-06,
+      "loss": 0.0531,
+      "step": 360
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.312185864806391e-06,
+      "loss": 0.0109,
+      "step": 361
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.260321438130913e-06,
+      "loss": 0.0371,
+      "step": 362
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.208536565304374e-06,
+      "loss": 0.0088,
+      "step": 363
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.156832750038192e-06,
+      "loss": 0.0907,
+      "step": 364
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.105211493690073e-06,
+      "loss": 0.0105,
+      "step": 365
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.053674295220399e-06,
+      "loss": 0.0757,
+      "step": 366
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.002222651148714e-06,
+      "loss": 0.0065,
+      "step": 367
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.950858055510254e-06,
+      "loss": 0.049,
+      "step": 368
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.89958199981258e-06,
+      "loss": 0.0258,
+      "step": 369
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.848395972992261e-06,
+      "loss": 0.0608,
+      "step": 370
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.797301461371626e-06,
+      "loss": 0.0246,
+      "step": 371
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.7462999486156315e-06,
+      "loss": 0.024,
+      "step": 372
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.695392915688759e-06,
+      "loss": 0.0104,
+      "step": 373
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.644581840812019e-06,
+      "loss": 0.0269,
+      "step": 374
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.593868199420017e-06,
+      "loss": 0.0535,
+      "step": 375
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.543253464118131e-06,
+      "loss": 0.0638,
+      "step": 376
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.492739104639727e-06,
+      "loss": 0.0919,
+      "step": 377
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.4423265878035015e-06,
+      "loss": 0.0064,
+      "step": 378
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.392017377470867e-06,
+      "loss": 0.0357,
+      "step": 379
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.341812934503469e-06,
+      "loss": 0.0275,
+      "step": 380
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.2917147167207495e-06,
+      "loss": 0.0455,
+      "step": 381
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.241724178857621e-06,
+      "loss": 0.0407,
+      "step": 382
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.191842772522214e-06,
+      "loss": 0.0185,
+      "step": 383
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.142071946153751e-06,
+      "loss": 0.0253,
+      "step": 384
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.092413144980465e-06,
+      "loss": 0.0123,
+      "step": 385
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.04286781097763e-06,
+      "loss": 0.0555,
+      "step": 386
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.993437382825711e-06,
+      "loss": 0.0201,
+      "step": 387
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.944123295868574e-06,
+      "loss": 0.0063,
+      "step": 388
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.894926982071805e-06,
+      "loss": 0.0251,
+      "step": 389
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.0193,
+      "step": 390
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.796893384680964e-06,
+      "loss": 0.0114,
+      "step": 391
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.748058947752955e-06,
+      "loss": 0.0145,
+      "step": 392
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.699347977234799e-06,
+      "loss": 0.0283,
+      "step": 393
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.650761887578977e-06,
+      "loss": 0.0178,
+      "step": 394
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.602302089611755e-06,
+      "loss": 0.0493,
+      "step": 395
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.553969990492164e-06,
+      "loss": 0.0211,
+      "step": 396
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5057669936711625e-06,
+      "loss": 0.0238,
+      "step": 397
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.457694498850892e-06,
+      "loss": 0.0745,
+      "step": 398
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.409753901944006e-06,
+      "loss": 0.0235,
+      "step": 399
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.361946595033165e-06,
+      "loss": 0.0487,
+      "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.314273966330591e-06,
+      "loss": 0.0258,
+      "step": 401
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.266737400137765e-06,
+      "loss": 0.0067,
+      "step": 402
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.219338276805243e-06,
+      "loss": 0.0053,
+      "step": 403
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.172077972692553e-06,
+      "loss": 0.0271,
+      "step": 404
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.124957860128237e-06,
+      "loss": 0.0347,
+      "step": 405
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.077979307370004e-06,
+      "loss": 0.0604,
+      "step": 406
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.031143678565005e-06,
+      "loss": 0.0106,
+      "step": 407
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.984452333710207e-06,
+      "loss": 0.0316,
+      "step": 408
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.937906628612905e-06,
+      "loss": 0.0122,
+      "step": 409
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.89150791485137e-06,
+      "loss": 0.0158,
+      "step": 410
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.845257539735577e-06,
+      "loss": 0.0353,
+      "step": 411
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.7991568462680945e-06,
+      "loss": 0.0628,
+      "step": 412
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7532071731050975e-06,
+      "loss": 0.0078,
+      "step": 413
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.707409854517471e-06,
+      "loss": 0.013,
+      "step": 414
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.661766220352098e-06,
+      "loss": 0.0148,
+      "step": 415
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.616277595993196e-06,
+      "loss": 0.0274,
+      "step": 416
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.57094530232389e-06,
+      "loss": 0.0108,
+      "step": 417
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.525770655687821e-06,
+      "loss": 0.0159,
+      "step": 418
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.48075496785092e-06,
+      "loss": 0.0476,
+      "step": 419
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.435899545963333e-06,
+      "loss": 0.0312,
+      "step": 420
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.391205692521453e-06,
+      "loss": 0.038,
+      "step": 421
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.346674705330117e-06,
+      "loss": 0.0168,
+      "step": 422
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.302307877464893e-06,
+      "loss": 0.0138,
+      "step": 423
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.258106497234551e-06,
+      "loss": 0.0288,
+      "step": 424
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.214071848143655e-06,
+      "loss": 0.0306,
+      "step": 425
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.170205208855281e-06,
+      "loss": 0.015,
+      "step": 426
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.126507853153891e-06,
+      "loss": 0.0047,
+      "step": 427
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.082981049908362e-06,
+      "loss": 0.0046,
+      "step": 428
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.039626063035107e-06,
+      "loss": 0.0455,
+      "step": 429
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.996444151461417e-06,
+      "loss": 0.0152,
+      "step": 430
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.953436569088856e-06,
+      "loss": 0.0123,
+      "step": 431
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.9106045647569005e-06,
+      "loss": 0.0026,
+      "step": 432
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.867949382206632e-06,
+      "loss": 0.0021,
+      "step": 433
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.825472260044658e-06,
+      "loss": 0.0646,
+      "step": 434
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7831744317071194e-06,
+      "loss": 0.0378,
+      "step": 435
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7410571254238835e-06,
+      "loss": 0.0164,
+      "step": 436
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6991215641828903e-06,
+      "loss": 0.0312,
+      "step": 437
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6573689656946177e-06,
+      "loss": 0.055,
+      "step": 438
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.615800542356738e-06,
+      "loss": 0.03,
+      "step": 439
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.574417501218913e-06,
+      "loss": 0.0162,
+      "step": 440
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5332210439477334e-06,
+      "loss": 0.0435,
+      "step": 441
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4922123667918305e-06,
+      "loss": 0.0106,
+      "step": 442
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 0.0031,
+      "step": 443
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4107631105223528e-06,
+      "loss": 0.0076,
+      "step": 444
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3703248965044253e-06,
+      "loss": 0.0107,
+      "step": 445
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.330079192724379e-06,
+      "loss": 0.0257,
+      "step": 446
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2900271678232045e-06,
+      "loss": 0.0343,
+      "step": 447
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.250169984817897e-06,
+      "loss": 0.0358,
+      "step": 448
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.2105088010677e-06,
+      "loss": 0.023,
+      "step": 449
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.171044768240508e-06,
+      "loss": 0.0323,
+      "step": 450
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.131779032279397e-06,
+      "loss": 0.0099,
+      "step": 451
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0927127333693872e-06,
+      "loss": 0.0051,
+      "step": 452
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.053847005904298e-06,
+      "loss": 0.0036,
+      "step": 453
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0151829784538257e-06,
+      "loss": 0.015,
+      "step": 454
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9767217737307805e-06,
+      "loss": 0.0138,
+      "step": 455
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.938464508558466e-06,
+      "loss": 0.0209,
+      "step": 456
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9004122938382617e-06,
+      "loss": 0.0062,
+      "step": 457
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.86256623451736e-06,
+      "loss": 0.0118,
+      "step": 458
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8249274295566863e-06,
+      "loss": 0.0613,
+      "step": 459
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7874969718989943e-06,
+      "loss": 0.0254,
+      "step": 460
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7502759484370946e-06,
+      "loss": 0.0173,
+      "step": 461
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7132654399823444e-06,
+      "loss": 0.0414,
+      "step": 462
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.676466521233225e-06,
+      "loss": 0.0249,
+      "step": 463
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.639880260744151e-06,
+      "loss": 0.0093,
+      "step": 464
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6035077208944416e-06,
+      "loss": 0.0106,
+      "step": 465
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5673499578574644e-06,
+      "loss": 0.0975,
+      "step": 466
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.5314080215699822e-06,
+      "loss": 0.0128,
+      "step": 467
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4956829557016336e-06,
+      "loss": 0.0111,
+      "step": 468
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4601757976246685e-06,
+      "loss": 0.016,
+      "step": 469
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.424887578383799e-06,
+      "loss": 0.0368,
+      "step": 470
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.389819322666264e-06,
+      "loss": 0.0084,
+      "step": 471
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.354972048772074e-06,
+      "loss": 0.0663,
+      "step": 472
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.320346768584449e-06,
+      "loss": 0.0793,
+      "step": 473
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2859444875404347e-06,
+      "loss": 0.0439,
+      "step": 474
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2517662046016975e-06,
+      "loss": 0.0058,
+      "step": 475
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2178129122255255e-06,
+      "loss": 0.0016,
+      "step": 476
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.184085596336011e-06,
+      "loss": 0.0211,
+      "step": 477
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.150585236295415e-06,
+      "loss": 0.0207,
+      "step": 478
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.1173128048757307e-06,
+      "loss": 0.0177,
+      "step": 479
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0842692682304442e-06,
+      "loss": 0.01,
+      "step": 480
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0514555858664663e-06,
+      "loss": 0.0214,
+      "step": 481
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0188727106162874e-06,
+      "loss": 0.0046,
+      "step": 482
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.986521588610285e-06,
+      "loss": 0.0094,
+      "step": 483
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9544031592492763e-06,
+      "loss": 0.0372,
+      "step": 484
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.922518355177232e-06,
+      "loss": 0.0088,
+      "step": 485
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.890868102254182e-06,
+      "loss": 0.0047,
+      "step": 486
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.859453319529343e-06,
+      "loss": 0.0228,
+      "step": 487
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.82827491921443e-06,
+      "loss": 0.0127,
+      "step": 488
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.797333806657171e-06,
+      "loss": 0.0224,
+      "step": 489
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7666308803150045e-06,
+      "loss": 0.0224,
+      "step": 490
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7361670317290014e-06,
+      "loss": 0.0067,
+      "step": 491
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7059431454979825e-06,
+      "loss": 0.0046,
+      "step": 492
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6759600992528147e-06,
+      "loss": 0.0226,
+      "step": 493
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6462187636309345e-06,
+      "loss": 0.0054,
+      "step": 494
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6167200022510799e-06,
+      "loss": 0.0198,
+      "step": 495
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 0.0114,
+      "step": 496
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5584536214485457e-06,
+      "loss": 0.0043,
+      "step": 497
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5296876939450978e-06,
+      "loss": 0.012,
+      "step": 498
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.501167724473016e-06,
+      "loss": 0.0063,
+      "step": 499
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4728945411854135e-06,
+      "loss": 0.0172,
+      "step": 500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.444868965069315e-06,
+      "loss": 0.0301,
+      "step": 501
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4170918099218166e-06,
+      "loss": 0.0452,
+      "step": 502
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3895638823264447e-06,
+      "loss": 0.0029,
+      "step": 503
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3622859816297473e-06,
+      "loss": 0.0445,
+      "step": 504
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3352588999180726e-06,
+      "loss": 0.028,
+      "step": 505
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3084834219945731e-06,
+      "loss": 0.0053,
+      "step": 506
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2819603253564206e-06,
+      "loss": 0.0026,
+      "step": 507
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.255690380172222e-06,
+      "loss": 0.0282,
+      "step": 508
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2296743492596587e-06,
+      "loss": 0.048,
+      "step": 509
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.203912988063335e-06,
+      "loss": 0.0357,
+      "step": 510
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1784070446328477e-06,
+      "loss": 0.0105,
+      "step": 511
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.153157259601062e-06,
+      "loss": 0.0035,
+      "step": 512
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1281643661625896e-06,
+      "loss": 0.0157,
+      "step": 513
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1034290900525279e-06,
+      "loss": 0.014,
+      "step": 514
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.078952149525362e-06,
+      "loss": 0.0095,
+      "step": 515
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0547342553341144e-06,
+      "loss": 0.01,
+      "step": 516
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.030776110709718e-06,
+      "loss": 0.007,
+      "step": 517
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0070784113405763e-06,
+      "loss": 0.0397,
+      "step": 518
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.836418453523833e-07,
+      "loss": 0.0035,
+      "step": 519
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.604670932881211e-07,
+      "loss": 0.0135,
+      "step": 520
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.375548280883129e-07,
+      "loss": 0.022,
+      "step": 521
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.149057150714802e-07,
+      "loss": 0.0062,
+      "step": 522
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.925204119148189e-07,
+      "loss": 0.0022,
+      "step": 523
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.703995686351041e-07,
+      "loss": 0.0544,
+      "step": 524
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.485438275698154e-07,
+      "loss": 0.0116,
+      "step": 525
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.269538233584884e-07,
+      "loss": 0.0145,
+      "step": 526
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.056301829242785e-07,
+      "loss": 0.0231,
+      "step": 527
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.845735254557608e-07,
+      "loss": 0.0161,
+      "step": 528
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.637844623889557e-07,
+      "loss": 0.0062,
+      "step": 529
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.432635973895652e-07,
+      "loss": 0.0026,
+      "step": 530
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.230115263354431e-07,
+      "loss": 0.0011,
+      "step": 531
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.030288372993066e-07,
+      "loss": 0.0079,
+      "step": 532
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.833161105316421e-07,
+      "loss": 0.0031,
+      "step": 533
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.638739184438681e-07,
+      "loss": 0.0039,
+      "step": 534
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.447028255917054e-07,
+      "loss": 0.0092,
+      "step": 535
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.258033886587911e-07,
+      "loss": 0.0309,
+      "step": 536
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.071761564405121e-07,
+      "loss": 0.0053,
+      "step": 537
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.888216698280646e-07,
+      "loss": 0.0036,
+      "step": 538
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.707404617927526e-07,
+      "loss": 0.014,
+      "step": 539
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.529330573705083e-07,
+      "loss": 0.0062,
+      "step": 540
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.353999736466531e-07,
+      "loss": 0.0072,
+      "step": 541
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.181417197408733e-07,
+      "loss": 0.0025,
+      "step": 542
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.011587967924414e-07,
+      "loss": 0.0046,
+      "step": 543
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.844516979456671e-07,
+      "loss": 0.0544,
+      "step": 544
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.6802090833557136e-07,
+      "loss": 0.0264,
+      "step": 545
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.5186690507379894e-07,
+      "loss": 0.0232,
+      "step": 546
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.359901572347758e-07,
+      "loss": 0.0053,
+      "step": 547
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.203911258420712e-07,
+      "loss": 0.0159,
+      "step": 548
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.0328,
+      "step": 549
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.9002801615558805e-07,
+      "loss": 0.0303,
+      "step": 550
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.7526481953539915e-07,
+      "loss": 0.0437,
+      "step": 551
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.607811026831176e-07,
+      "loss": 0.0425,
+      "step": 552
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.4657728617195295e-07,
+      "loss": 0.0255,
+      "step": 553
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.32653782447474e-07,
+      "loss": 0.0064,
+      "step": 554
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1901099581561846e-07,
+      "loss": 0.0158,
+      "step": 555
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.056493224309587e-07,
+      "loss": 0.0443,
+      "step": 556
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.9256915028519575e-07,
+      "loss": 0.0289,
+      "step": 557
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.7977085919589253e-07,
+      "loss": 0.0154,
+      "step": 558
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.672548207954495e-07,
+      "loss": 0.008,
+      "step": 559
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.550213985203076e-07,
+      "loss": 0.0431,
+      "step": 560
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.430709476003978e-07,
+      "loss": 0.015,
+      "step": 561
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.3140381504882736e-07,
+      "loss": 0.0074,
+      "step": 562
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.200203396517997e-07,
+      "loss": 0.0338,
+      "step": 563
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0892085195878154e-07,
+      "loss": 0.0086,
+      "step": 564
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9810567427289596e-07,
+      "loss": 0.017,
+      "step": 565
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8757512064157658e-07,
+      "loss": 0.0929,
+      "step": 566
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7732949684743593e-07,
+      "loss": 0.0096,
+      "step": 567
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6736910039939159e-07,
+      "loss": 0.0467,
+      "step": 568
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5769422052403172e-07,
+      "loss": 0.0203,
+      "step": 569
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.483051381572076e-07,
+      "loss": 0.0152,
+      "step": 570
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3920212593588113e-07,
+      "loss": 0.0088,
+      "step": 571
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.303854481902067e-07,
+      "loss": 0.0193,
+      "step": 572
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.218553609358575e-07,
+      "loss": 0.0061,
+      "step": 573
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1361211186658893e-07,
+      "loss": 0.0037,
+      "step": 574
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0565594034704918e-07,
+      "loss": 0.0443,
+      "step": 575
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.798707740582447e-08,
+      "loss": 0.0024,
+      "step": 576
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.060574572873238e-08,
+      "loss": 0.0042,
+      "step": 577
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.351215965235915e-08,
+      "loss": 0.0049,
+      "step": 578
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.670652515782917e-08,
+      "loss": 0.0213,
+      "step": 579
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.018903986483083e-08,
+      "loss": 0.0328,
+      "step": 580
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.395989302587113e-08,
+      "loss": 0.0049,
+      "step": 581
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.801926552078563e-08,
+      "loss": 0.0169,
+      "step": 582
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.236732985148374e-08,
+      "loss": 0.0025,
+      "step": 583
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.7004250136940547e-08,
+      "loss": 0.0351,
+      "step": 584
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.1930182108430584e-08,
+      "loss": 0.0151,
+      "step": 585
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.714527310500371e-08,
+      "loss": 0.0023,
+      "step": 586
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.264966206921294e-08,
+      "loss": 0.0057,
+      "step": 587
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.8443479543073248e-08,
+      "loss": 0.0288,
+      "step": 588
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.4526847664273488e-08,
+      "loss": 0.002,
+      "step": 589
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.0899880162630336e-08,
+      "loss": 0.0287,
+      "step": 590
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.7562682356786488e-08,
+      "loss": 0.0111,
+      "step": 591
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.451535115114866e-08,
+      "loss": 0.0261,
+      "step": 592
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.175797503307874e-08,
+      "loss": 0.0166,
+      "step": 593
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.290634070322491e-09,
+      "loss": 0.0026,
+      "step": 594
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.113399908681429e-09,
+      "loss": 0.0093,
+      "step": 595
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.226335769936697e-09,
+      "loss": 0.0216,
+      "step": 596
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.6294964500116492e-09,
+      "loss": 0.004,
+      "step": 597
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.322928317378681e-09,
+      "loss": 0.0167,
+      "step": 598
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3066693117191886e-09,
+      "loss": 0.0035,
+      "step": 599
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.807489428111268e-10,
+      "loss": 0.0016,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4518828968523857e-10,
+      "loss": 0.0174,
+      "step": 601
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.0652,
+      "step": 602
+    },
+    {
+      "epoch": 1.0,
+      "step": 602,
+      "total_flos": 58586457047040.0,
+      "train_loss": 0.16352578145691637,
+      "train_runtime": 4452.054,
+      "train_samples_per_second": 4.325,
+      "train_steps_per_second": 0.135
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 602,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "total_flos": 58586457047040.0,
+  "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 sha256:929cf28a2dc381baf2426d7a0acd8e9d7b8b1e7631be8cd4a4d137a0288b73bb
+size 6776