Upload folder using huggingface_hub

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "./checkpoint/llmga-vicuna-7b-v1.5-full-finetune",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "resizesquare",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "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": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2299b6393705074fa6970e67a7ce42a0479ba1ed4155277d44af47906883e6bf
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049092f13d74439a4bd2a3247c75bf02c69eea39259804f97078a3984884effb
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105765a4473f952fbe55eb88cb02ba465c05944c4e4f5ab305ebc5212383bc89
+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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2002 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0035714285714285713,
+      "grad_norm": 1.5478915956248045,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.0625,
+      "step": 1
+    },
+    {
+      "epoch": 0.007142857142857143,
+      "grad_norm": 1.2398301518605641,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.9553,
+      "step": 2
+    },
+    {
+      "epoch": 0.010714285714285714,
+      "grad_norm": 1.4076387212655408,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9978,
+      "step": 3
+    },
+    {
+      "epoch": 0.014285714285714285,
+      "grad_norm": 1.1985949378391438,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.9609,
+      "step": 4
+    },
+    {
+      "epoch": 0.017857142857142856,
+      "grad_norm": 1.0848575200944988,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.8853,
+      "step": 5
+    },
+    {
+      "epoch": 0.02142857142857143,
+      "grad_norm": 1.092467471543203,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8464,
+      "step": 6
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 1.0846562083072122,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.874,
+      "step": 7
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 1.3053964029480514,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.7936,
+      "step": 8
+    },
+    {
+      "epoch": 0.03214285714285714,
+      "grad_norm": 1.1269639729113965,
+      "learning_rate": 2e-05,
+      "loss": 0.759,
+      "step": 9
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 1.0980236614653736,
+      "learning_rate": 1.9999328066483867e-05,
+      "loss": 0.6741,
+      "step": 10
+    },
+    {
+      "epoch": 0.039285714285714285,
+      "grad_norm": 1.0582210049961431,
+      "learning_rate": 1.9997312356234385e-05,
+      "loss": 0.6477,
+      "step": 11
+    },
+    {
+      "epoch": 0.04285714285714286,
+      "grad_norm": 1.0424068026905615,
+      "learning_rate": 1.999395314013622e-05,
+      "loss": 0.5562,
+      "step": 12
+    },
+    {
+      "epoch": 0.04642857142857143,
+      "grad_norm": 0.8719364890870912,
+      "learning_rate": 1.998925086962334e-05,
+      "loss": 0.5305,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9328118755011154,
+      "learning_rate": 1.998320617661839e-05,
+      "loss": 0.4832,
+      "step": 14
+    },
+    {
+      "epoch": 0.05357142857142857,
+      "grad_norm": 0.8896750885959509,
+      "learning_rate": 1.997581987344772e-05,
+      "loss": 0.4814,
+      "step": 15
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 0.9183801340039138,
+      "learning_rate": 1.9967092952732266e-05,
+      "loss": 0.454,
+      "step": 16
+    },
+    {
+      "epoch": 0.060714285714285714,
+      "grad_norm": 0.9241597122472689,
+      "learning_rate": 1.9957026587254136e-05,
+      "loss": 0.435,
+      "step": 17
+    },
+    {
+      "epoch": 0.06428571428571428,
+      "grad_norm": 0.7126203238381043,
+      "learning_rate": 1.9945622129799e-05,
+      "loss": 0.3851,
+      "step": 18
+    },
+    {
+      "epoch": 0.06785714285714285,
+      "grad_norm": 0.7693946450410322,
+      "learning_rate": 1.9932881112974298e-05,
+      "loss": 0.4033,
+      "step": 19
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.705561753707911,
+      "learning_rate": 1.9918805249003272e-05,
+      "loss": 0.3177,
+      "step": 20
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.6571310295289079,
+      "learning_rate": 1.9903396429494882e-05,
+      "loss": 0.3059,
+      "step": 21
+    },
+    {
+      "epoch": 0.07857142857142857,
+      "grad_norm": 0.6584713658862125,
+      "learning_rate": 1.9886656725189575e-05,
+      "loss": 0.2787,
+      "step": 22
+    },
+    {
+      "epoch": 0.08214285714285714,
+      "grad_norm": 0.648454577238481,
+      "learning_rate": 1.9868588385681035e-05,
+      "loss": 0.2697,
+      "step": 23
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.5254043510761319,
+      "learning_rate": 1.9849193839113833e-05,
+      "loss": 0.2226,
+      "step": 24
+    },
+    {
+      "epoch": 0.08928571428571429,
+      "grad_norm": 0.5976203976124158,
+      "learning_rate": 1.9828475691857148e-05,
+      "loss": 0.2385,
+      "step": 25
+    },
+    {
+      "epoch": 0.09285714285714286,
+      "grad_norm": 0.6244066856806556,
+      "learning_rate": 1.9806436728154484e-05,
+      "loss": 0.2964,
+      "step": 26
+    },
+    {
+      "epoch": 0.09642857142857143,
+      "grad_norm": 0.5460606128839673,
+      "learning_rate": 1.9783079909749516e-05,
+      "loss": 0.2288,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5409068847524089,
+      "learning_rate": 1.975840837548807e-05,
+      "loss": 0.2217,
+      "step": 28
+    },
+    {
+      "epoch": 0.10357142857142858,
+      "grad_norm": 0.6639598979647965,
+      "learning_rate": 1.9732425440896298e-05,
+      "loss": 0.2921,
+      "step": 29
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 0.5344411293579373,
+      "learning_rate": 1.9705134597735113e-05,
+      "loss": 0.2367,
+      "step": 30
+    },
+    {
+      "epoch": 0.11071428571428571,
+      "grad_norm": 0.4141908954409791,
+      "learning_rate": 1.9676539513530967e-05,
+      "loss": 0.1812,
+      "step": 31
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 0.49622835670272675,
+      "learning_rate": 1.9646644031082948e-05,
+      "loss": 0.1948,
+      "step": 32
+    },
+    {
+      "epoch": 0.11785714285714285,
+      "grad_norm": 0.5789972585167017,
+      "learning_rate": 1.9615452167946383e-05,
+      "loss": 0.2479,
+      "step": 33
+    },
+    {
+      "epoch": 0.12142857142857143,
+      "grad_norm": 0.5251274398921059,
+      "learning_rate": 1.958296811589293e-05,
+      "loss": 0.2377,
+      "step": 34
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.5521223727466371,
+      "learning_rate": 1.954919624034725e-05,
+      "loss": 0.2499,
+      "step": 35
+    },
+    {
+      "epoch": 0.12857142857142856,
+      "grad_norm": 0.5108768018324138,
+      "learning_rate": 1.951414107980036e-05,
+      "loss": 0.1877,
+      "step": 36
+    },
+    {
+      "epoch": 0.13214285714285715,
+      "grad_norm": 0.5178181270876622,
+      "learning_rate": 1.9477807345199717e-05,
+      "loss": 0.1935,
+      "step": 37
+    },
+    {
+      "epoch": 0.1357142857142857,
+      "grad_norm": 0.47933474414651667,
+      "learning_rate": 1.9440199919316125e-05,
+      "loss": 0.1634,
+      "step": 38
+    },
+    {
+      "epoch": 0.1392857142857143,
+      "grad_norm": 0.5896140031438339,
+      "learning_rate": 1.9401323856087573e-05,
+      "loss": 0.2086,
+      "step": 39
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.6499970611340742,
+      "learning_rate": 1.936118437994003e-05,
+      "loss": 0.2311,
+      "step": 40
+    },
+    {
+      "epoch": 0.14642857142857144,
+      "grad_norm": 0.5503129704249362,
+      "learning_rate": 1.9319786885085366e-05,
+      "loss": 0.2033,
+      "step": 41
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.5337877909960611,
+      "learning_rate": 1.927713693479643e-05,
+      "loss": 0.1645,
+      "step": 42
+    },
+    {
+      "epoch": 0.15357142857142858,
+      "grad_norm": 0.4975309449048533,
+      "learning_rate": 1.923324026065944e-05,
+      "loss": 0.1892,
+      "step": 43
+    },
+    {
+      "epoch": 0.15714285714285714,
+      "grad_norm": 0.4344636172747461,
+      "learning_rate": 1.918810276180372e-05,
+      "loss": 0.139,
+      "step": 44
+    },
+    {
+      "epoch": 0.16071428571428573,
+      "grad_norm": 0.5162539386723686,
+      "learning_rate": 1.9141730504108923e-05,
+      "loss": 0.1752,
+      "step": 45
+    },
+    {
+      "epoch": 0.16428571428571428,
+      "grad_norm": 0.49245919165379515,
+      "learning_rate": 1.9094129719389886e-05,
+      "loss": 0.1968,
+      "step": 46
+    },
+    {
+      "epoch": 0.16785714285714284,
+      "grad_norm": 0.5235680089426945,
+      "learning_rate": 1.904530680455914e-05,
+      "loss": 0.2077,
+      "step": 47
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.5517523916740913,
+      "learning_rate": 1.8995268320767254e-05,
+      "loss": 0.187,
+      "step": 48
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.4519171907644501,
+      "learning_rate": 1.894402099252109e-05,
+      "loss": 0.1827,
+      "step": 49
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 0.6027324398622755,
+      "learning_rate": 1.889157170678015e-05,
+      "loss": 0.2084,
+      "step": 50
+    },
+    {
+      "epoch": 0.18214285714285713,
+      "grad_norm": 0.41117638299222875,
+      "learning_rate": 1.8837927512031022e-05,
+      "loss": 0.1404,
+      "step": 51
+    },
+    {
+      "epoch": 0.18571428571428572,
+      "grad_norm": 0.5026435619169383,
+      "learning_rate": 1.8783095617340193e-05,
+      "loss": 0.1759,
+      "step": 52
+    },
+    {
+      "epoch": 0.18928571428571428,
+      "grad_norm": 0.34112043740605,
+      "learning_rate": 1.872708339138522e-05,
+      "loss": 0.1177,
+      "step": 53
+    },
+    {
+      "epoch": 0.19285714285714287,
+      "grad_norm": 0.3492186764282914,
+      "learning_rate": 1.866989836146449e-05,
+      "loss": 0.1209,
+      "step": 54
+    },
+    {
+      "epoch": 0.19642857142857142,
+      "grad_norm": 0.44324599063346565,
+      "learning_rate": 1.861154821248565e-05,
+      "loss": 0.1446,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.4871710493545156,
+      "learning_rate": 1.8552040785932846e-05,
+      "loss": 0.149,
+      "step": 56
+    },
+    {
+      "epoch": 0.20357142857142857,
+      "grad_norm": 0.4464914558136398,
+      "learning_rate": 1.849138407881296e-05,
+      "loss": 0.183,
+      "step": 57
+    },
+    {
+      "epoch": 0.20714285714285716,
+      "grad_norm": 0.4537236556618241,
+      "learning_rate": 1.8429586242580884e-05,
+      "loss": 0.1592,
+      "step": 58
+    },
+    {
+      "epoch": 0.21071428571428572,
+      "grad_norm": 0.3735622979036519,
+      "learning_rate": 1.8366655582044096e-05,
+      "loss": 0.0911,
+      "step": 59
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.5501752604946842,
+      "learning_rate": 1.83026005542466e-05,
+      "loss": 0.1912,
+      "step": 60
+    },
+    {
+      "epoch": 0.21785714285714286,
+      "grad_norm": 0.3534827565812762,
+      "learning_rate": 1.8237429767332407e-05,
+      "loss": 0.1352,
+      "step": 61
+    },
+    {
+      "epoch": 0.22142857142857142,
+      "grad_norm": 0.3631713691054233,
+      "learning_rate": 1.8171151979388715e-05,
+      "loss": 0.1125,
+      "step": 62
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.4581951469644329,
+      "learning_rate": 1.8103776097268942e-05,
+      "loss": 0.1831,
+      "step": 63
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.29589456760327454,
+      "learning_rate": 1.803531117539577e-05,
+      "loss": 0.1142,
+      "step": 64
+    },
+    {
+      "epoch": 0.23214285714285715,
+      "grad_norm": 0.321656217445022,
+      "learning_rate": 1.7965766414544328e-05,
+      "loss": 0.1071,
+      "step": 65
+    },
+    {
+      "epoch": 0.2357142857142857,
+      "grad_norm": 0.3696948128162081,
+      "learning_rate": 1.7895151160605758e-05,
+      "loss": 0.1645,
+      "step": 66
+    },
+    {
+      "epoch": 0.2392857142857143,
+      "grad_norm": 0.40287093773295857,
+      "learning_rate": 1.782347490333123e-05,
+      "loss": 0.153,
+      "step": 67
+    },
+    {
+      "epoch": 0.24285714285714285,
+      "grad_norm": 0.402551556493297,
+      "learning_rate": 1.775074727505667e-05,
+      "loss": 0.1558,
+      "step": 68
+    },
+    {
+      "epoch": 0.24642857142857144,
+      "grad_norm": 0.36576671510472414,
+      "learning_rate": 1.7676978049408262e-05,
+      "loss": 0.1319,
+      "step": 69
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3910560569712591,
+      "learning_rate": 1.7602177139989046e-05,
+      "loss": 0.1379,
+      "step": 70
+    },
+    {
+      "epoch": 0.25357142857142856,
+      "grad_norm": 0.464138257243692,
+      "learning_rate": 1.7526354599046637e-05,
+      "loss": 0.1772,
+      "step": 71
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.36872626423764915,
+      "learning_rate": 1.7449520616122344e-05,
+      "loss": 0.1453,
+      "step": 72
+    },
+    {
+      "epoch": 0.26071428571428573,
+      "grad_norm": 0.3762147287106459,
+      "learning_rate": 1.7371685516681825e-05,
+      "loss": 0.1238,
+      "step": 73
+    },
+    {
+      "epoch": 0.2642857142857143,
+      "grad_norm": 0.44730344643149733,
+      "learning_rate": 1.7292859760727493e-05,
+      "loss": 0.0905,
+      "step": 74
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 0.31847467886438163,
+      "learning_rate": 1.721305394139282e-05,
+      "loss": 0.0962,
+      "step": 75
+    },
+    {
+      "epoch": 0.2714285714285714,
+      "grad_norm": 0.3172886015603318,
+      "learning_rate": 1.7132278783518756e-05,
+      "loss": 0.1095,
+      "step": 76
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.39833942342886014,
+      "learning_rate": 1.7050545142212483e-05,
+      "loss": 0.146,
+      "step": 77
+    },
+    {
+      "epoch": 0.2785714285714286,
+      "grad_norm": 0.36256098601291475,
+      "learning_rate": 1.696786400138859e-05,
+      "loss": 0.1474,
+      "step": 78
+    },
+    {
+      "epoch": 0.28214285714285714,
+      "grad_norm": 0.5144037485713393,
+      "learning_rate": 1.6884246472293018e-05,
+      "loss": 0.1792,
+      "step": 79
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.35433987050415405,
+      "learning_rate": 1.679970379200983e-05,
+      "loss": 0.1368,
+      "step": 80
+    },
+    {
+      "epoch": 0.2892857142857143,
+      "grad_norm": 0.3775803207062038,
+      "learning_rate": 1.6714247321951106e-05,
+      "loss": 0.1502,
+      "step": 81
+    },
+    {
+      "epoch": 0.29285714285714287,
+      "grad_norm": 0.39879890621433334,
+      "learning_rate": 1.6627888546330136e-05,
+      "loss": 0.1627,
+      "step": 82
+    },
+    {
+      "epoch": 0.29642857142857143,
+      "grad_norm": 0.38927568667509344,
+      "learning_rate": 1.654063907061807e-05,
+      "loss": 0.1336,
+      "step": 83
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.39077723911534096,
+      "learning_rate": 1.64525106199843e-05,
+      "loss": 0.1379,
+      "step": 84
+    },
+    {
+      "epoch": 0.30357142857142855,
+      "grad_norm": 0.3300014890302305,
+      "learning_rate": 1.6363515037720774e-05,
+      "loss": 0.1401,
+      "step": 85
+    },
+    {
+      "epoch": 0.30714285714285716,
+      "grad_norm": 0.3264032400951695,
+      "learning_rate": 1.6273664283650393e-05,
+      "loss": 0.1077,
+      "step": 86
+    },
+    {
+      "epoch": 0.3107142857142857,
+      "grad_norm": 0.28134669681829544,
+      "learning_rate": 1.6182970432519772e-05,
+      "loss": 0.1383,
+      "step": 87
+    },
+    {
+      "epoch": 0.3142857142857143,
+      "grad_norm": 0.39912508407687053,
+      "learning_rate": 1.609144567237658e-05,
+      "loss": 0.134,
+      "step": 88
+    },
+    {
+      "epoch": 0.31785714285714284,
+      "grad_norm": 0.404668324497237,
+      "learning_rate": 1.5999102302931585e-05,
+      "loss": 0.1396,
+      "step": 89
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.5263360190906506,
+      "learning_rate": 1.5905952733905777e-05,
+      "loss": 0.1802,
+      "step": 90
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.4080859243283811,
+      "learning_rate": 1.5812009483362643e-05,
+      "loss": 0.1738,
+      "step": 91
+    },
+    {
+      "epoch": 0.32857142857142857,
+      "grad_norm": 0.44589294219260617,
+      "learning_rate": 1.5717285176025913e-05,
+      "loss": 0.1395,
+      "step": 92
+    },
+    {
+      "epoch": 0.33214285714285713,
+      "grad_norm": 0.48805347667875654,
+      "learning_rate": 1.5621792541582968e-05,
+      "loss": 0.1794,
+      "step": 93
+    },
+    {
+      "epoch": 0.3357142857142857,
+      "grad_norm": 0.31713728426594406,
+      "learning_rate": 1.552554441297413e-05,
+      "loss": 0.1287,
+      "step": 94
+    },
+    {
+      "epoch": 0.3392857142857143,
+      "grad_norm": 0.3997312908073911,
+      "learning_rate": 1.5428553724668103e-05,
+      "loss": 0.1776,
+      "step": 95
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.32512972197402723,
+      "learning_rate": 1.533083351092372e-05,
+      "loss": 0.0987,
+      "step": 96
+    },
+    {
+      "epoch": 0.3464285714285714,
+      "grad_norm": 0.25650097315752696,
+      "learning_rate": 1.5232396904038352e-05,
+      "loss": 0.0963,
+      "step": 97
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.3890103860914231,
+      "learning_rate": 1.5133257132583074e-05,
+      "loss": 0.1899,
+      "step": 98
+    },
+    {
+      "epoch": 0.3535714285714286,
+      "grad_norm": 0.39434451760834605,
+      "learning_rate": 1.503342751962493e-05,
+      "loss": 0.1739,
+      "step": 99
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.4338599110132305,
+      "learning_rate": 1.4932921480936491e-05,
+      "loss": 0.1273,
+      "step": 100
+    },
+    {
+      "epoch": 0.3607142857142857,
+      "grad_norm": 0.41242604208869493,
+      "learning_rate": 1.4831752523192949e-05,
+      "loss": 0.1548,
+      "step": 101
+    },
+    {
+      "epoch": 0.36428571428571427,
+      "grad_norm": 0.3426565228545722,
+      "learning_rate": 1.4729934242157005e-05,
+      "loss": 0.1639,
+      "step": 102
+    },
+    {
+      "epoch": 0.3678571428571429,
+      "grad_norm": 0.4260238384505358,
+      "learning_rate": 1.4627480320851775e-05,
+      "loss": 0.1769,
+      "step": 103
+    },
+    {
+      "epoch": 0.37142857142857144,
+      "grad_norm": 0.33738414849240705,
+      "learning_rate": 1.4524404527721977e-05,
+      "loss": 0.1184,
+      "step": 104
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.377141868162913,
+      "learning_rate": 1.4420720714783635e-05,
+      "loss": 0.1557,
+      "step": 105
+    },
+    {
+      "epoch": 0.37857142857142856,
+      "grad_norm": 0.401113514602946,
+      "learning_rate": 1.4316442815762543e-05,
+      "loss": 0.1646,
+      "step": 106
+    },
+    {
+      "epoch": 0.3821428571428571,
+      "grad_norm": 0.3177971639559263,
+      "learning_rate": 1.4211584844221771e-05,
+      "loss": 0.1075,
+      "step": 107
+    },
+    {
+      "epoch": 0.38571428571428573,
+      "grad_norm": 0.34835754468144986,
+      "learning_rate": 1.4106160891678422e-05,
+      "loss": 0.1335,
+      "step": 108
+    },
+    {
+      "epoch": 0.3892857142857143,
+      "grad_norm": 0.30828103647375366,
+      "learning_rate": 1.4000185125709919e-05,
+      "loss": 0.117,
+      "step": 109
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.32849435123561,
+      "learning_rate": 1.3893671788050073e-05,
+      "loss": 0.1591,
+      "step": 110
+    },
+    {
+      "epoch": 0.3964285714285714,
+      "grad_norm": 0.2709136842488289,
+      "learning_rate": 1.3786635192675184e-05,
+      "loss": 0.1201,
+      "step": 111
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5662239240435536,
+      "learning_rate": 1.3679089723880427e-05,
+      "loss": 0.1811,
+      "step": 112
+    },
+    {
+      "epoch": 0.4035714285714286,
+      "grad_norm": 0.3239753858152088,
+      "learning_rate": 1.35710498343468e-05,
+      "loss": 0.0956,
+      "step": 113
+    },
+    {
+      "epoch": 0.40714285714285714,
+      "grad_norm": 0.4577914787081394,
+      "learning_rate": 1.3462530043198874e-05,
+      "loss": 0.1918,
+      "step": 114
+    },
+    {
+      "epoch": 0.4107142857142857,
+      "grad_norm": 0.28893883723817343,
+      "learning_rate": 1.3353544934053618e-05,
+      "loss": 0.1137,
+      "step": 115
+    },
+    {
+      "epoch": 0.4142857142857143,
+      "grad_norm": 0.3379009547335347,
+      "learning_rate": 1.324410915306055e-05,
+      "loss": 0.1249,
+      "step": 116
+    },
+    {
+      "epoch": 0.41785714285714287,
+      "grad_norm": 0.3197292040926634,
+      "learning_rate": 1.3134237406933493e-05,
+      "loss": 0.1008,
+      "step": 117
+    },
+    {
+      "epoch": 0.42142857142857143,
+      "grad_norm": 0.3392432971976464,
+      "learning_rate": 1.3023944460974183e-05,
+      "loss": 0.121,
+      "step": 118
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.35558554159597894,
+      "learning_rate": 1.2913245137088024e-05,
+      "loss": 0.1471,
+      "step": 119
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.22493336145934734,
+      "learning_rate": 1.2802154311792196e-05,
+      "loss": 0.1002,
+      "step": 120
+    },
+    {
+      "epoch": 0.43214285714285716,
+      "grad_norm": 0.4223106827111893,
+      "learning_rate": 1.2690686914216475e-05,
+      "loss": 0.1566,
+      "step": 121
+    },
+    {
+      "epoch": 0.4357142857142857,
+      "grad_norm": 0.2813621781150817,
+      "learning_rate": 1.2578857924096935e-05,
+      "loss": 0.1098,
+      "step": 122
+    },
+    {
+      "epoch": 0.4392857142857143,
+      "grad_norm": 0.29947686930576417,
+      "learning_rate": 1.2466682369762883e-05,
+      "loss": 0.1129,
+      "step": 123
+    },
+    {
+      "epoch": 0.44285714285714284,
+      "grad_norm": 0.38423327250889927,
+      "learning_rate": 1.2354175326117252e-05,
+      "loss": 0.1674,
+      "step": 124
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": 0.41759411587377016,
+      "learning_rate": 1.2241351912610726e-05,
+      "loss": 0.1823,
+      "step": 125
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3287906320045648,
+      "learning_rate": 1.212822729120989e-05,
+      "loss": 0.1394,
+      "step": 126
+    },
+    {
+      "epoch": 0.45357142857142857,
+      "grad_norm": 0.309937820975526,
+      "learning_rate": 1.2014816664359671e-05,
+      "loss": 0.1252,
+      "step": 127
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.3300093835113784,
+      "learning_rate": 1.190113527294032e-05,
+      "loss": 0.1357,
+      "step": 128
+    },
+    {
+      "epoch": 0.4607142857142857,
+      "grad_norm": 0.3257793959279068,
+      "learning_rate": 1.178719839421925e-05,
+      "loss": 0.1226,
+      "step": 129
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.33056389711570644,
+      "learning_rate": 1.1673021339797967e-05,
+      "loss": 0.1529,
+      "step": 130
+    },
+    {
+      "epoch": 0.46785714285714286,
+      "grad_norm": 0.35534347520612053,
+      "learning_rate": 1.15586194535544e-05,
+      "loss": 0.1064,
+      "step": 131
+    },
+    {
+      "epoch": 0.4714285714285714,
+      "grad_norm": 0.22871074436318123,
+      "learning_rate": 1.1444008109580884e-05,
+      "loss": 0.0955,
+      "step": 132
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.3824987433529803,
+      "learning_rate": 1.1329202710118088e-05,
+      "loss": 0.1612,
+      "step": 133
+    },
+    {
+      "epoch": 0.4785714285714286,
+      "grad_norm": 0.3343360434084649,
+      "learning_rate": 1.1214218683485159e-05,
+      "loss": 0.1187,
+      "step": 134
+    },
+    {
+      "epoch": 0.48214285714285715,
+      "grad_norm": 0.34564099117172165,
+      "learning_rate": 1.1099071482006361e-05,
+      "loss": 0.1485,
+      "step": 135
+    },
+    {
+      "epoch": 0.4857142857142857,
+      "grad_norm": 0.3776437292793847,
+      "learning_rate": 1.0983776579934483e-05,
+      "loss": 0.1381,
+      "step": 136
+    },
+    {
+      "epoch": 0.48928571428571427,
+      "grad_norm": 0.5196891777136812,
+      "learning_rate": 1.0868349471371316e-05,
+      "loss": 0.2327,
+      "step": 137
+    },
+    {
+      "epoch": 0.4928571428571429,
+      "grad_norm": 0.28991752853377784,
+      "learning_rate": 1.0752805668185442e-05,
+      "loss": 0.1068,
+      "step": 138
+    },
+    {
+      "epoch": 0.49642857142857144,
+      "grad_norm": 0.3610469175255664,
+      "learning_rate": 1.0637160697927651e-05,
+      "loss": 0.1483,
+      "step": 139
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.34237987234400713,
+      "learning_rate": 1.0521430101744238e-05,
+      "loss": 0.1327,
+      "step": 140
+    },
+    {
+      "epoch": 0.5035714285714286,
+      "grad_norm": 0.3532653120531725,
+      "learning_rate": 1.040562943228849e-05,
+      "loss": 0.1531,
+      "step": 141
+    },
+    {
+      "epoch": 0.5071428571428571,
+      "grad_norm": 0.2490959381575519,
+      "learning_rate": 1.0289774251630602e-05,
+      "loss": 0.0943,
+      "step": 142
+    },
+    {
+      "epoch": 0.5107142857142857,
+      "grad_norm": 0.3419815025999081,
+      "learning_rate": 1.0173880129166358e-05,
+      "loss": 0.1199,
+      "step": 143
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.27015420390524447,
+      "learning_rate": 1.0057962639524799e-05,
+      "loss": 0.097,
+      "step": 144
+    },
+    {
+      "epoch": 0.5178571428571429,
+      "grad_norm": 0.28947245421874257,
+      "learning_rate": 9.942037360475205e-06,
+      "loss": 0.0992,
+      "step": 145
+    },
+    {
+      "epoch": 0.5214285714285715,
+      "grad_norm": 0.3883015225071508,
+      "learning_rate": 9.826119870833644e-06,
+      "loss": 0.1522,
+      "step": 146
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.8300529149522834,
+      "learning_rate": 9.710225748369402e-06,
+      "loss": 0.1396,
+      "step": 147
+    },
+    {
+      "epoch": 0.5285714285714286,
+      "grad_norm": 0.202016854911906,
+      "learning_rate": 9.594370567711512e-06,
+      "loss": 0.0854,
+      "step": 148
+    },
+    {
+      "epoch": 0.5321428571428571,
+      "grad_norm": 0.36978259812488184,
+      "learning_rate": 9.478569898255765e-06,
+      "loss": 0.1704,
+      "step": 149
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.23665827589903268,
+      "learning_rate": 9.362839302072354e-06,
+      "loss": 0.0948,
+      "step": 150
+    },
+    {
+      "epoch": 0.5392857142857143,
+      "grad_norm": 0.35039135014557515,
+      "learning_rate": 9.247194331814561e-06,
+      "loss": 0.1648,
+      "step": 151
+    },
+    {
+      "epoch": 0.5428571428571428,
+      "grad_norm": 0.32816521513063157,
+      "learning_rate": 9.131650528628688e-06,
+      "loss": 0.1032,
+      "step": 152
+    },
+    {
+      "epoch": 0.5464285714285714,
+      "grad_norm": 0.32264421993745784,
+      "learning_rate": 9.016223420065519e-06,
+      "loss": 0.1248,
+      "step": 153
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.5185778078772257,
+      "learning_rate": 8.900928517993644e-06,
+      "loss": 0.2034,
+      "step": 154
+    },
+    {
+      "epoch": 0.5535714285714286,
+      "grad_norm": 0.33725063318309306,
+      "learning_rate": 8.785781316514841e-06,
+      "loss": 0.1401,
+      "step": 155
+    },
+    {
+      "epoch": 0.5571428571428572,
+      "grad_norm": 0.34767124633241814,
+      "learning_rate": 8.670797289881915e-06,
+      "loss": 0.1564,
+      "step": 156
+    },
+    {
+      "epoch": 0.5607142857142857,
+      "grad_norm": 0.3055450803151196,
+      "learning_rate": 8.555991890419116e-06,
+      "loss": 0.1124,
+      "step": 157
+    },
+    {
+      "epoch": 0.5642857142857143,
+      "grad_norm": 0.25388977773118193,
+      "learning_rate": 8.441380546445603e-06,
+      "loss": 0.1081,
+      "step": 158
+    },
+    {
+      "epoch": 0.5678571428571428,
+      "grad_norm": 0.4455538403435565,
+      "learning_rate": 8.326978660202034e-06,
+      "loss": 0.1676,
+      "step": 159
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.30228248526761664,
+      "learning_rate": 8.212801605780754e-06,
+      "loss": 0.1271,
+      "step": 160
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.2544828612445528,
+      "learning_rate": 8.098864727059685e-06,
+      "loss": 0.1093,
+      "step": 161
+    },
+    {
+      "epoch": 0.5785714285714286,
+      "grad_norm": 0.36913988346664617,
+      "learning_rate": 7.985183335640332e-06,
+      "loss": 0.1516,
+      "step": 162
+    },
+    {
+      "epoch": 0.5821428571428572,
+      "grad_norm": 0.25130653502490885,
+      "learning_rate": 7.871772708790114e-06,
+      "loss": 0.102,
+      "step": 163
+    },
+    {
+      "epoch": 0.5857142857142857,
+      "grad_norm": 0.3482017405768576,
+      "learning_rate": 7.758648087389277e-06,
+      "loss": 0.1439,
+      "step": 164
+    },
+    {
+      "epoch": 0.5892857142857143,
+      "grad_norm": 0.4080868021076819,
+      "learning_rate": 7.64582467388275e-06,
+      "loss": 0.1594,
+      "step": 165
+    },
+    {
+      "epoch": 0.5928571428571429,
+      "grad_norm": 0.22416436168548187,
+      "learning_rate": 7.533317630237117e-06,
+      "loss": 0.0958,
+      "step": 166
+    },
+    {
+      "epoch": 0.5964285714285714,
+      "grad_norm": 0.3548896053394149,
+      "learning_rate": 7.421142075903067e-06,
+      "loss": 0.1805,
+      "step": 167
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3153835017876163,
+      "learning_rate": 7.3093130857835245e-06,
+      "loss": 0.1576,
+      "step": 168
+    },
+    {
+      "epoch": 0.6035714285714285,
+      "grad_norm": 0.37437814298012134,
+      "learning_rate": 7.197845688207805e-06,
+      "loss": 0.1845,
+      "step": 169
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 0.2707210792364402,
+      "learning_rate": 7.086754862911982e-06,
+      "loss": 0.1074,
+      "step": 170
+    },
+    {
+      "epoch": 0.6107142857142858,
+      "grad_norm": 0.38773698909477633,
+      "learning_rate": 6.976055539025819e-06,
+      "loss": 0.1693,
+      "step": 171
+    },
+    {
+      "epoch": 0.6142857142857143,
+      "grad_norm": 0.270791960065858,
+      "learning_rate": 6.865762593066514e-06,
+      "loss": 0.0962,
+      "step": 172
+    },
+    {
+      "epoch": 0.6178571428571429,
+      "grad_norm": 0.33404187296938787,
+      "learning_rate": 6.755890846939454e-06,
+      "loss": 0.1502,
+      "step": 173
+    },
+    {
+      "epoch": 0.6214285714285714,
+      "grad_norm": 0.3169317085587855,
+      "learning_rate": 6.646455065946386e-06,
+      "loss": 0.1535,
+      "step": 174
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.34202948851755516,
+      "learning_rate": 6.537469956801128e-06,
+      "loss": 0.1336,
+      "step": 175
+    },
+    {
+      "epoch": 0.6285714285714286,
+      "grad_norm": 0.22142635555607934,
+      "learning_rate": 6.428950165653204e-06,
+      "loss": 0.089,
+      "step": 176
+    },
+    {
+      "epoch": 0.6321428571428571,
+      "grad_norm": 0.39547548326244164,
+      "learning_rate": 6.320910276119576e-06,
+      "loss": 0.1622,
+      "step": 177
+    },
+    {
+      "epoch": 0.6357142857142857,
+      "grad_norm": 0.34202811717449055,
+      "learning_rate": 6.213364807324817e-06,
+      "loss": 0.1329,
+      "step": 178
+    },
+    {
+      "epoch": 0.6392857142857142,
+      "grad_norm": 0.24984802040484924,
+      "learning_rate": 6.106328211949928e-06,
+      "loss": 0.0978,
+      "step": 179
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.2691895257848114,
+      "learning_rate": 5.999814874290084e-06,
+      "loss": 0.1076,
+      "step": 180
+    },
+    {
+      "epoch": 0.6464285714285715,
+      "grad_norm": 0.35670010783973816,
+      "learning_rate": 5.893839108321584e-06,
+      "loss": 0.1409,
+      "step": 181
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.3063688782891636,
+      "learning_rate": 5.7884151557782305e-06,
+      "loss": 0.1111,
+      "step": 182
+    },
+    {
+      "epoch": 0.6535714285714286,
+      "grad_norm": 0.4478859628471062,
+      "learning_rate": 5.68355718423746e-06,
+      "loss": 0.1582,
+      "step": 183
+    },
+    {
+      "epoch": 0.6571428571428571,
+      "grad_norm": 0.4079013493850928,
+      "learning_rate": 5.579279285216369e-06,
+      "loss": 0.1832,
+      "step": 184
+    },
+    {
+      "epoch": 0.6607142857142857,
+      "grad_norm": 0.36684648196887143,
+      "learning_rate": 5.4755954722780236e-06,
+      "loss": 0.1443,
+      "step": 185
+    },
+    {
+      "epoch": 0.6642857142857143,
+      "grad_norm": 0.4666764433183556,
+      "learning_rate": 5.372519679148227e-06,
+      "loss": 0.1924,
+      "step": 186
+    },
+    {
+      "epoch": 0.6678571428571428,
+      "grad_norm": 0.3679225305422777,
+      "learning_rate": 5.270065757843e-06,
+      "loss": 0.1637,
+      "step": 187
+    },
+    {
+      "epoch": 0.6714285714285714,
+      "grad_norm": 0.5074893835770381,
+      "learning_rate": 5.168247476807054e-06,
+      "loss": 0.1859,
+      "step": 188
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.2996145714991962,
+      "learning_rate": 5.067078519063514e-06,
+      "loss": 0.1343,
+      "step": 189
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.3516548476388983,
+      "learning_rate": 4.966572480375076e-06,
+      "loss": 0.1559,
+      "step": 190
+    },
+    {
+      "epoch": 0.6821428571428572,
+      "grad_norm": 0.356885235057829,
+      "learning_rate": 4.86674286741693e-06,
+      "loss": 0.1475,
+      "step": 191
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.5734359096126976,
+      "learning_rate": 4.767603095961652e-06,
+      "loss": 0.1914,
+      "step": 192
+    },
+    {
+      "epoch": 0.6892857142857143,
+      "grad_norm": 0.40445955460343774,
+      "learning_rate": 4.669166489076283e-06,
+      "loss": 0.1766,
+      "step": 193
+    },
+    {
+      "epoch": 0.6928571428571428,
+      "grad_norm": 0.2800652614843086,
+      "learning_rate": 4.571446275331903e-06,
+      "loss": 0.1188,
+      "step": 194
+    },
+    {
+      "epoch": 0.6964285714285714,
+      "grad_norm": 0.3757570796942492,
+      "learning_rate": 4.47445558702587e-06,
+      "loss": 0.1831,
+      "step": 195
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.32608548991744285,
+      "learning_rate": 4.378207458417035e-06,
+      "loss": 0.1422,
+      "step": 196
+    },
+    {
+      "epoch": 0.7035714285714286,
+      "grad_norm": 0.38378600912734245,
+      "learning_rate": 4.282714823974088e-06,
+      "loss": 0.1512,
+      "step": 197
+    },
+    {
+      "epoch": 0.7071428571428572,
+      "grad_norm": 0.35671347574479906,
+      "learning_rate": 4.187990516637361e-06,
+      "loss": 0.1261,
+      "step": 198
+    },
+    {
+      "epoch": 0.7107142857142857,
+      "grad_norm": 0.30915599350731704,
+      "learning_rate": 4.094047266094225e-06,
+      "loss": 0.1115,
+      "step": 199
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.20400134484541857,
+      "learning_rate": 4.000897697068418e-06,
+      "loss": 0.0755,
+      "step": 200
+    },
+    {
+      "epoch": 0.7178571428571429,
+      "grad_norm": 0.3783702453179056,
+      "learning_rate": 3.908554327623425e-06,
+      "loss": 0.1462,
+      "step": 201
+    },
+    {
+      "epoch": 0.7214285714285714,
+      "grad_norm": 0.39604207952130577,
+      "learning_rate": 3.817029567480228e-06,
+      "loss": 0.1749,
+      "step": 202
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.39751469906997566,
+      "learning_rate": 3.7263357163496118e-06,
+      "loss": 0.1626,
+      "step": 203
+    },
+    {
+      "epoch": 0.7285714285714285,
+      "grad_norm": 0.2879746919882601,
+      "learning_rate": 3.6364849622792262e-06,
+      "loss": 0.1236,
+      "step": 204
+    },
+    {
+      "epoch": 0.7321428571428571,
+      "grad_norm": 0.3656185312372868,
+      "learning_rate": 3.5474893800157005e-06,
+      "loss": 0.1309,
+      "step": 205
+    },
+    {
+      "epoch": 0.7357142857142858,
+      "grad_norm": 0.27352675259784487,
+      "learning_rate": 3.459360929381931e-06,
+      "loss": 0.0926,
+      "step": 206
+    },
+    {
+      "epoch": 0.7392857142857143,
+      "grad_norm": 0.41951631132226436,
+      "learning_rate": 3.372111453669864e-06,
+      "loss": 0.1485,
+      "step": 207
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 0.31261953552147415,
+      "learning_rate": 3.2857526780488925e-06,
+      "loss": 0.151,
+      "step": 208
+    },
+    {
+      "epoch": 0.7464285714285714,
+      "grad_norm": 0.3142527429717002,
+      "learning_rate": 3.2002962079901743e-06,
+      "loss": 0.1286,
+      "step": 209
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.41272553233415865,
+      "learning_rate": 3.115753527706986e-06,
+      "loss": 0.1484,
+      "step": 210
+    },
+    {
+      "epoch": 0.7535714285714286,
+      "grad_norm": 0.2491459925114637,
+      "learning_rate": 3.0321359986114096e-06,
+      "loss": 0.0886,
+      "step": 211
+    },
+    {
+      "epoch": 0.7571428571428571,
+      "grad_norm": 0.383107500116008,
+      "learning_rate": 2.9494548577875195e-06,
+      "loss": 0.1349,
+      "step": 212
+    },
+    {
+      "epoch": 0.7607142857142857,
+      "grad_norm": 0.3719900753257283,
+      "learning_rate": 2.8677212164812464e-06,
+      "loss": 0.1285,
+      "step": 213
+    },
+    {
+      "epoch": 0.7642857142857142,
+      "grad_norm": 0.36185954441920426,
+      "learning_rate": 2.786946058607187e-06,
+      "loss": 0.1728,
+      "step": 214
+    },
+    {
+      "epoch": 0.7678571428571429,
+      "grad_norm": 0.4357674701225695,
+      "learning_rate": 2.70714023927251e-06,
+      "loss": 0.1713,
+      "step": 215
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.32556051670602676,
+      "learning_rate": 2.628314483318178e-06,
+      "loss": 0.1506,
+      "step": 216
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.3447117803793854,
+      "learning_rate": 2.5504793838776585e-06,
+      "loss": 0.1213,
+      "step": 217
+    },
+    {
+      "epoch": 0.7785714285714286,
+      "grad_norm": 0.4342987664730663,
+      "learning_rate": 2.473645400953366e-06,
+      "loss": 0.153,
+      "step": 218
+    },
+    {
+      "epoch": 0.7821428571428571,
+      "grad_norm": 0.3920281781124031,
+      "learning_rate": 2.3978228600109564e-06,
+      "loss": 0.1474,
+      "step": 219
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.37630174801216276,
+      "learning_rate": 2.323021950591743e-06,
+      "loss": 0.1493,
+      "step": 220
+    },
+    {
+      "epoch": 0.7892857142857143,
+      "grad_norm": 0.39066945140138887,
+      "learning_rate": 2.249252724943336e-06,
+      "loss": 0.1576,
+      "step": 221
+    },
+    {
+      "epoch": 0.7928571428571428,
+      "grad_norm": 0.3262711059595468,
+      "learning_rate": 2.176525096668769e-06,
+      "loss": 0.1414,
+      "step": 222
+    },
+    {
+      "epoch": 0.7964285714285714,
+      "grad_norm": 0.33865138896969227,
+      "learning_rate": 2.1048488393942455e-06,
+      "loss": 0.1611,
+      "step": 223
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3379236752698617,
+      "learning_rate": 2.0342335854556738e-06,
+      "loss": 0.1344,
+      "step": 224
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 0.3109450803199544,
+      "learning_rate": 1.964688824604234e-06,
+      "loss": 0.1457,
+      "step": 225
+    },
+    {
+      "epoch": 0.8071428571428572,
+      "grad_norm": 0.2875185632580354,
+      "learning_rate": 1.896223902731058e-06,
+      "loss": 0.0977,
+      "step": 226
+    },
+    {
+      "epoch": 0.8107142857142857,
+      "grad_norm": 0.2347911682820601,
+      "learning_rate": 1.8288480206112879e-06,
+      "loss": 0.0868,
+      "step": 227
+    },
+    {
+      "epoch": 0.8142857142857143,
+      "grad_norm": 0.4121777863518364,
+      "learning_rate": 1.7625702326675952e-06,
+      "loss": 0.1538,
+      "step": 228
+    },
+    {
+      "epoch": 0.8178571428571428,
+      "grad_norm": 0.2912601864031465,
+      "learning_rate": 1.6973994457534026e-06,
+      "loss": 0.1274,
+      "step": 229
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 0.3815620088872596,
+      "learning_rate": 1.6333444179559078e-06,
+      "loss": 0.1042,
+      "step": 230
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.47161502108864845,
+      "learning_rate": 1.5704137574191202e-06,
+      "loss": 0.1571,
+      "step": 231
+    },
+    {
+      "epoch": 0.8285714285714286,
+      "grad_norm": 0.4662370295285976,
+      "learning_rate": 1.5086159211870445e-06,
+      "loss": 0.1984,
+      "step": 232
+    },
+    {
+      "epoch": 0.8321428571428572,
+      "grad_norm": 0.4383207536709599,
+      "learning_rate": 1.447959214067155e-06,
+      "loss": 0.1796,
+      "step": 233
+    },
+    {
+      "epoch": 0.8357142857142857,
+      "grad_norm": 0.31912149691231545,
+      "learning_rate": 1.3884517875143544e-06,
+      "loss": 0.1585,
+      "step": 234
+    },
+    {
+      "epoch": 0.8392857142857143,
+      "grad_norm": 0.40168679552274317,
+      "learning_rate": 1.3301016385355093e-06,
+      "loss": 0.1865,
+      "step": 235
+    },
+    {
+      "epoch": 0.8428571428571429,
+      "grad_norm": 0.2366119414746658,
+      "learning_rate": 1.2729166086147803e-06,
+      "loss": 0.1045,
+      "step": 236
+    },
+    {
+      "epoch": 0.8464285714285714,
+      "grad_norm": 0.34244833431583455,
+      "learning_rate": 1.216904382659806e-06,
+      "loss": 0.1337,
+      "step": 237
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.4468357126703566,
+      "learning_rate": 1.1620724879689793e-06,
+      "loss": 0.1814,
+      "step": 238
+    },
+    {
+      "epoch": 0.8535714285714285,
+      "grad_norm": 0.2949748414048653,
+      "learning_rate": 1.1084282932198543e-06,
+      "loss": 0.1573,
+      "step": 239
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.3478075924736447,
+      "learning_rate": 1.0559790074789134e-06,
+      "loss": 0.1445,
+      "step": 240
+    },
+    {
+      "epoch": 0.8607142857142858,
+      "grad_norm": 0.28328715407169286,
+      "learning_rate": 1.00473167923275e-06,
+      "loss": 0.1063,
+      "step": 241
+    },
+    {
+      "epoch": 0.8642857142857143,
+      "grad_norm": 0.38920844855326037,
+      "learning_rate": 9.546931954408622e-07,
+      "loss": 0.1703,
+      "step": 242
+    },
+    {
+      "epoch": 0.8678571428571429,
+      "grad_norm": 0.5996209968463109,
+      "learning_rate": 9.058702806101172e-07,
+      "loss": 0.1834,
+      "step": 243
+    },
+    {
+      "epoch": 0.8714285714285714,
+      "grad_norm": 0.27975031106611575,
+      "learning_rate": 8.582694958910809e-07,
+      "loss": 0.1356,
+      "step": 244
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.7648856362732316,
+      "learning_rate": 8.118972381962853e-07,
+      "loss": 0.2202,
+      "step": 245
+    },
+    {
+      "epoch": 0.8785714285714286,
+      "grad_norm": 0.3691758708862301,
+      "learning_rate": 7.667597393405602e-07,
+      "loss": 0.1237,
+      "step": 246
+    },
+    {
+      "epoch": 0.8821428571428571,
+      "grad_norm": 0.3178006502647586,
+      "learning_rate": 7.228630652035717e-07,
+      "loss": 0.1178,
+      "step": 247
+    },
+    {
+      "epoch": 0.8857142857142857,
+      "grad_norm": 0.384435688223958,
+      "learning_rate": 6.802131149146374e-07,
+      "loss": 0.1524,
+      "step": 248
+    },
+    {
+      "epoch": 0.8892857142857142,
+      "grad_norm": 0.3068368906735643,
+      "learning_rate": 6.388156200599726e-07,
+      "loss": 0.1247,
+      "step": 249
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.2915652541414803,
+      "learning_rate": 5.986761439124289e-07,
+      "loss": 0.1264,
+      "step": 250
+    },
+    {
+      "epoch": 0.8964285714285715,
+      "grad_norm": 0.4962653014147133,
+      "learning_rate": 5.598000806838766e-07,
+      "loss": 0.2289,
+      "step": 251
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.3105670095756884,
+      "learning_rate": 5.221926548002876e-07,
+      "loss": 0.1692,
+      "step": 252
+    },
+    {
+      "epoch": 0.9035714285714286,
+      "grad_norm": 0.2599346187591853,
+      "learning_rate": 4.858589201996433e-07,
+      "loss": 0.1099,
+      "step": 253
+    },
+    {
+      "epoch": 0.9071428571428571,
+      "grad_norm": 0.37266496166460017,
+      "learning_rate": 4.5080375965275256e-07,
+      "loss": 0.155,
+      "step": 254
+    },
+    {
+      "epoch": 0.9107142857142857,
+      "grad_norm": 0.3523382656079408,
+      "learning_rate": 4.1703188410707087e-07,
+      "loss": 0.1568,
+      "step": 255
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.3139689914742574,
+      "learning_rate": 3.845478320536178e-07,
+      "loss": 0.1442,
+      "step": 256
+    },
+    {
+      "epoch": 0.9178571428571428,
+      "grad_norm": 0.3886010972906401,
+      "learning_rate": 3.5335596891705406e-07,
+      "loss": 0.2008,
+      "step": 257
+    },
+    {
+      "epoch": 0.9214285714285714,
+      "grad_norm": 0.3016440986889294,
+      "learning_rate": 3.2346048646903494e-07,
+      "loss": 0.1743,
+      "step": 258
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.3677684465566086,
+      "learning_rate": 2.9486540226488556e-07,
+      "loss": 0.1359,
+      "step": 259
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.4386983440480599,
+      "learning_rate": 2.6757455910370486e-07,
+      "loss": 0.1479,
+      "step": 260
+    },
+    {
+      "epoch": 0.9321428571428572,
+      "grad_norm": 0.21979803308995374,
+      "learning_rate": 2.41591624511931e-07,
+      "loss": 0.0829,
+      "step": 261
+    },
+    {
+      "epoch": 0.9357142857142857,
+      "grad_norm": 0.33381820914249016,
+      "learning_rate": 2.169200902504842e-07,
+      "loss": 0.1453,
+      "step": 262
+    },
+    {
+      "epoch": 0.9392857142857143,
+      "grad_norm": 0.3320040694348736,
+      "learning_rate": 1.9356327184551716e-07,
+      "loss": 0.1123,
+      "step": 263
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.3412668141144355,
+      "learning_rate": 1.7152430814285303e-07,
+      "loss": 0.13,
+      "step": 264
+    },
+    {
+      "epoch": 0.9464285714285714,
+      "grad_norm": 0.3696237830621812,
+      "learning_rate": 1.5080616088616884e-07,
+      "loss": 0.1907,
+      "step": 265
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.30494316246947967,
+      "learning_rate": 1.3141161431896809e-07,
+      "loss": 0.1555,
+      "step": 266
+    },
+    {
+      "epoch": 0.9535714285714286,
+      "grad_norm": 0.3189572020801009,
+      "learning_rate": 1.1334327481042573e-07,
+      "loss": 0.1219,
+      "step": 267
+    },
+    {
+      "epoch": 0.9571428571428572,
+      "grad_norm": 0.33361495127745605,
+      "learning_rate": 9.660357050512158e-08,
+      "loss": 0.1431,
+      "step": 268
+    },
+    {
+      "epoch": 0.9607142857142857,
+      "grad_norm": 0.48450511535248025,
+      "learning_rate": 8.119475099673035e-08,
+      "loss": 0.1928,
+      "step": 269
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.2906209996194275,
+      "learning_rate": 6.711888702570556e-08,
+      "loss": 0.1028,
+      "step": 270
+    },
+    {
+      "epoch": 0.9678571428571429,
+      "grad_norm": 0.3401517685437452,
+      "learning_rate": 5.437787020100116e-08,
+      "loss": 0.1484,
+      "step": 271
+    },
+    {
+      "epoch": 0.9714285714285714,
+      "grad_norm": 0.4092102841602329,
+      "learning_rate": 4.297341274586475e-08,
+      "loss": 0.1955,
+      "step": 272
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.4364496819852462,
+      "learning_rate": 3.290704726773619e-08,
+      "loss": 0.1753,
+      "step": 273
+    },
+    {
+      "epoch": 0.9785714285714285,
+      "grad_norm": 0.3842525728886007,
+      "learning_rate": 2.4180126552284523e-08,
+      "loss": 0.1609,
+      "step": 274
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "grad_norm": 0.43086325504903594,
+      "learning_rate": 1.6793823381614506e-08,
+      "loss": 0.1804,
+      "step": 275
+    },
+    {
+      "epoch": 0.9857142857142858,
+      "grad_norm": 0.3825806313174142,
+      "learning_rate": 1.0749130376659366e-08,
+      "loss": 0.1329,
+      "step": 276
+    },
+    {
+      "epoch": 0.9892857142857143,
+      "grad_norm": 0.3932695276283175,
+      "learning_rate": 6.046859863781951e-09,
+      "loss": 0.1756,
+      "step": 277
+    },
+    {
+      "epoch": 0.9928571428571429,
+      "grad_norm": 0.4324987338144805,
+      "learning_rate": 2.6876437656153663e-09,
+      "loss": 0.1774,
+      "step": 278
+    },
+    {
+      "epoch": 0.9964285714285714,
+      "grad_norm": 0.2871247824045713,
+      "learning_rate": 6.719335161364804e-10,
+      "loss": 0.1208,
+      "step": 279
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3615603880208619,
+      "learning_rate": 0.0,
+      "loss": 0.1365,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "step": 280,
+      "total_flos": 610370176024576.0,
+      "train_loss": 0.18859978249030454,
+      "train_runtime": 2395.0124,
+      "train_samples_per_second": 14.959,
+      "train_steps_per_second": 0.117
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 610370176024576.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fe4721c7794948c0ffae2571e6cd3c9e8c0992169a25c8bec785c0f0475005
+size 7288