Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "./checkpoint/llmga-Qwen2-7B-full-finetune",
+  "architectures": [
+    "LlavaQwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_aspect_ratio": "resizesquare",
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "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_Qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "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,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53284486ca8e2cfbb0131d2294c14cf234df0fe66996ee897754f449f7eb20d0
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67fe238efaf621b6529495bb68af8380e60c9a8293cee0bedb874ec15e2b04b
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed8a88d501d12557fac9af03f153bcb597020aa423b39248ff6c215ab334580
+size 4970986384

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9960d5d89adfb5909ff9577343076d0f59b3f3ee40baa8902945e755e333cf6d
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,741 @@
+{
+  "metadata": {
+    "total_size": 15871292416
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2408 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9983385637806904,
+  "eval_steps": 500,
+  "global_step": 338,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029536643898836995,
+      "grad_norm": 1.9736734572153813,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.0332,
+      "step": 1
+    },
+    {
+      "epoch": 0.005907328779767399,
+      "grad_norm": 1.89466674300729,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.0858,
+      "step": 2
+    },
+    {
+      "epoch": 0.008860993169651098,
+      "grad_norm": 2.0586700988484337,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.1422,
+      "step": 3
+    },
+    {
+      "epoch": 0.011814657559534798,
+      "grad_norm": 1.8769825182011597,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.1113,
+      "step": 4
+    },
+    {
+      "epoch": 0.014768321949418498,
+      "grad_norm": 1.683377634890378,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0089,
+      "step": 5
+    },
+    {
+      "epoch": 0.017721986339302196,
+      "grad_norm": 1.6814695051713617,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.9674,
+      "step": 6
+    },
+    {
+      "epoch": 0.020675650729185896,
+      "grad_norm": 1.9017119730121659,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.9005,
+      "step": 7
+    },
+    {
+      "epoch": 0.023629315119069596,
+      "grad_norm": 1.603735219060158,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.9265,
+      "step": 8
+    },
+    {
+      "epoch": 0.026582979508953296,
+      "grad_norm": 1.8288678360919526,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.8121,
+      "step": 9
+    },
+    {
+      "epoch": 0.029536643898836996,
+      "grad_norm": 1.5570221294659097,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.7292,
+      "step": 10
+    },
+    {
+      "epoch": 0.032490308288720696,
+      "grad_norm": 2.5250052299606964,
+      "learning_rate": 2e-05,
+      "loss": 0.8079,
+      "step": 11
+    },
+    {
+      "epoch": 0.03544397267860439,
+      "grad_norm": 1.7266275987207245,
+      "learning_rate": 1.9999538500851633e-05,
+      "loss": 0.6159,
+      "step": 12
+    },
+    {
+      "epoch": 0.038397637068488095,
+      "grad_norm": 1.687733702161376,
+      "learning_rate": 1.9998154046002822e-05,
+      "loss": 0.5926,
+      "step": 13
+    },
+    {
+      "epoch": 0.04135130145837179,
+      "grad_norm": 1.4681611793409828,
+      "learning_rate": 1.9995846763238514e-05,
+      "loss": 0.5179,
+      "step": 14
+    },
+    {
+      "epoch": 0.044304965848255495,
+      "grad_norm": 1.661603577794359,
+      "learning_rate": 1.9992616865520515e-05,
+      "loss": 0.6002,
+      "step": 15
+    },
+    {
+      "epoch": 0.04725863023813919,
+      "grad_norm": 1.5757267480206656,
+      "learning_rate": 1.9988464650967834e-05,
+      "loss": 0.548,
+      "step": 16
+    },
+    {
+      "epoch": 0.05021229462802289,
+      "grad_norm": 1.443516459043832,
+      "learning_rate": 1.9983390502829168e-05,
+      "loss": 0.4763,
+      "step": 17
+    },
+    {
+      "epoch": 0.05316595901790659,
+      "grad_norm": 1.9356317236988005,
+      "learning_rate": 1.9977394889447526e-05,
+      "loss": 0.4841,
+      "step": 18
+    },
+    {
+      "epoch": 0.05611962340779029,
+      "grad_norm": 1.5992738201782284,
+      "learning_rate": 1.9970478364217e-05,
+      "loss": 0.4163,
+      "step": 19
+    },
+    {
+      "epoch": 0.05907328779767399,
+      "grad_norm": 2.933784967885916,
+      "learning_rate": 1.9962641565531694e-05,
+      "loss": 0.4842,
+      "step": 20
+    },
+    {
+      "epoch": 0.06202695218755769,
+      "grad_norm": 1.2537224524788972,
+      "learning_rate": 1.9953885216726788e-05,
+      "loss": 0.3521,
+      "step": 21
+    },
+    {
+      "epoch": 0.06498061657744139,
+      "grad_norm": 1.6032713497627293,
+      "learning_rate": 1.994421012601179e-05,
+      "loss": 0.3752,
+      "step": 22
+    },
+    {
+      "epoch": 0.06793428096732508,
+      "grad_norm": 1.9257499786171195,
+      "learning_rate": 1.9933617186395917e-05,
+      "loss": 0.427,
+      "step": 23
+    },
+    {
+      "epoch": 0.07088794535720878,
+      "grad_norm": 1.585551383595158,
+      "learning_rate": 1.99221073756057e-05,
+      "loss": 0.3391,
+      "step": 24
+    },
+    {
+      "epoch": 0.07384160974709249,
+      "grad_norm": 1.4395031762291213,
+      "learning_rate": 1.990968175599471e-05,
+      "loss": 0.3681,
+      "step": 25
+    },
+    {
+      "epoch": 0.07679527413697619,
+      "grad_norm": 1.8379758969132987,
+      "learning_rate": 1.9896341474445526e-05,
+      "loss": 0.3644,
+      "step": 26
+    },
+    {
+      "epoch": 0.07974893852685988,
+      "grad_norm": 2.536047764684934,
+      "learning_rate": 1.9882087762263857e-05,
+      "loss": 0.3729,
+      "step": 27
+    },
+    {
+      "epoch": 0.08270260291674358,
+      "grad_norm": 1.7401811118309274,
+      "learning_rate": 1.9866921935064907e-05,
+      "loss": 0.3652,
+      "step": 28
+    },
+    {
+      "epoch": 0.08565626730662729,
+      "grad_norm": 1.6279552899997376,
+      "learning_rate": 1.985084539265195e-05,
+      "loss": 0.3381,
+      "step": 29
+    },
+    {
+      "epoch": 0.08860993169651099,
+      "grad_norm": 1.2722212246169622,
+      "learning_rate": 1.983385961888711e-05,
+      "loss": 0.3051,
+      "step": 30
+    },
+    {
+      "epoch": 0.09156359608639468,
+      "grad_norm": 1.4978048532104433,
+      "learning_rate": 1.9815966181554412e-05,
+      "loss": 0.3502,
+      "step": 31
+    },
+    {
+      "epoch": 0.09451726047627838,
+      "grad_norm": 1.7582762904526588,
+      "learning_rate": 1.9797166732215078e-05,
+      "loss": 0.4365,
+      "step": 32
+    },
+    {
+      "epoch": 0.09747092486616209,
+      "grad_norm": 1.1718400265178528,
+      "learning_rate": 1.977746300605507e-05,
+      "loss": 0.3054,
+      "step": 33
+    },
+    {
+      "epoch": 0.10042458925604578,
+      "grad_norm": 1.8293028625760361,
+      "learning_rate": 1.975685682172497e-05,
+      "loss": 0.2785,
+      "step": 34
+    },
+    {
+      "epoch": 0.10337825364592948,
+      "grad_norm": 1.0440735267994106,
+      "learning_rate": 1.973535008117207e-05,
+      "loss": 0.3104,
+      "step": 35
+    },
+    {
+      "epoch": 0.10633191803581318,
+      "grad_norm": 1.6728007851360074,
+      "learning_rate": 1.9712944769464864e-05,
+      "loss": 0.2799,
+      "step": 36
+    },
+    {
+      "epoch": 0.10928558242569689,
+      "grad_norm": 1.405904514520795,
+      "learning_rate": 1.9689642954609808e-05,
+      "loss": 0.2881,
+      "step": 37
+    },
+    {
+      "epoch": 0.11223924681558058,
+      "grad_norm": 1.7016870737912315,
+      "learning_rate": 1.9665446787360444e-05,
+      "loss": 0.3062,
+      "step": 38
+    },
+    {
+      "epoch": 0.11519291120546428,
+      "grad_norm": 1.1987401007424765,
+      "learning_rate": 1.9640358501018885e-05,
+      "loss": 0.2892,
+      "step": 39
+    },
+    {
+      "epoch": 0.11814657559534798,
+      "grad_norm": 1.5149380484224841,
+      "learning_rate": 1.9614380411229693e-05,
+      "loss": 0.308,
+      "step": 40
+    },
+    {
+      "epoch": 0.12110023998523167,
+      "grad_norm": 1.1620416606100095,
+      "learning_rate": 1.9587514915766124e-05,
+      "loss": 0.2722,
+      "step": 41
+    },
+    {
+      "epoch": 0.12405390437511538,
+      "grad_norm": 1.534285242480307,
+      "learning_rate": 1.9559764494308838e-05,
+      "loss": 0.2446,
+      "step": 42
+    },
+    {
+      "epoch": 0.12700756876499908,
+      "grad_norm": 1.117214762293682,
+      "learning_rate": 1.9531131708217005e-05,
+      "loss": 0.2565,
+      "step": 43
+    },
+    {
+      "epoch": 0.12996123315488278,
+      "grad_norm": 1.8690417660104388,
+      "learning_rate": 1.950161920029191e-05,
+      "loss": 0.2991,
+      "step": 44
+    },
+    {
+      "epoch": 0.13291489754476649,
+      "grad_norm": 1.2823815577983428,
+      "learning_rate": 1.9471229694533003e-05,
+      "loss": 0.3053,
+      "step": 45
+    },
+    {
+      "epoch": 0.13586856193465016,
+      "grad_norm": 1.0457394301123093,
+      "learning_rate": 1.943996599588649e-05,
+      "loss": 0.2692,
+      "step": 46
+    },
+    {
+      "epoch": 0.13882222632453387,
+      "grad_norm": 1.6582540556983663,
+      "learning_rate": 1.940783098998643e-05,
+      "loss": 0.3117,
+      "step": 47
+    },
+    {
+      "epoch": 0.14177589071441757,
+      "grad_norm": 2.8122374846048093,
+      "learning_rate": 1.93748276428884e-05,
+      "loss": 0.2413,
+      "step": 48
+    },
+    {
+      "epoch": 0.14472955510430127,
+      "grad_norm": 1.06858926462545,
+      "learning_rate": 1.9340959000795707e-05,
+      "loss": 0.251,
+      "step": 49
+    },
+    {
+      "epoch": 0.14768321949418498,
+      "grad_norm": 1.784288703961607,
+      "learning_rate": 1.9306228189778255e-05,
+      "loss": 0.3198,
+      "step": 50
+    },
+    {
+      "epoch": 0.15063688388406868,
+      "grad_norm": 1.0358042162583945,
+      "learning_rate": 1.927063841548398e-05,
+      "loss": 0.2155,
+      "step": 51
+    },
+    {
+      "epoch": 0.15359054827395238,
+      "grad_norm": 1.1257663919037064,
+      "learning_rate": 1.9234192962842996e-05,
+      "loss": 0.265,
+      "step": 52
+    },
+    {
+      "epoch": 0.15654421266383609,
+      "grad_norm": 1.8812981570071463,
+      "learning_rate": 1.9196895195764363e-05,
+      "loss": 0.2678,
+      "step": 53
+    },
+    {
+      "epoch": 0.15949787705371976,
+      "grad_norm": 1.0219311054009077,
+      "learning_rate": 1.9158748556825637e-05,
+      "loss": 0.2619,
+      "step": 54
+    },
+    {
+      "epoch": 0.16245154144360346,
+      "grad_norm": 0.8757775200019958,
+      "learning_rate": 1.9119756566955092e-05,
+      "loss": 0.2153,
+      "step": 55
+    },
+    {
+      "epoch": 0.16540520583348717,
+      "grad_norm": 1.2257972336982437,
+      "learning_rate": 1.907992282510675e-05,
+      "loss": 0.2621,
+      "step": 56
+    },
+    {
+      "epoch": 0.16835887022337087,
+      "grad_norm": 1.1235673530163361,
+      "learning_rate": 1.90392510079282e-05,
+      "loss": 0.2597,
+      "step": 57
+    },
+    {
+      "epoch": 0.17131253461325457,
+      "grad_norm": 1.1981603118820592,
+      "learning_rate": 1.8997744869421248e-05,
+      "loss": 0.2267,
+      "step": 58
+    },
+    {
+      "epoch": 0.17426619900313828,
+      "grad_norm": 1.2580175658104467,
+      "learning_rate": 1.8955408240595396e-05,
+      "loss": 0.2157,
+      "step": 59
+    },
+    {
+      "epoch": 0.17721986339302198,
+      "grad_norm": 1.4994807395260425,
+      "learning_rate": 1.891224502911428e-05,
+      "loss": 0.3247,
+      "step": 60
+    },
+    {
+      "epoch": 0.18017352778290566,
+      "grad_norm": 1.084157032960403,
+      "learning_rate": 1.886825921893497e-05,
+      "loss": 0.2657,
+      "step": 61
+    },
+    {
+      "epoch": 0.18312719217278936,
+      "grad_norm": 1.4470552854446672,
+      "learning_rate": 1.8823454869940243e-05,
+      "loss": 0.3487,
+      "step": 62
+    },
+    {
+      "epoch": 0.18608085656267306,
+      "grad_norm": 2.0068879631177334,
+      "learning_rate": 1.8777836117563894e-05,
+      "loss": 0.2727,
+      "step": 63
+    },
+    {
+      "epoch": 0.18903452095255677,
+      "grad_norm": 1.1466460571800723,
+      "learning_rate": 1.873140717240899e-05,
+      "loss": 0.2913,
+      "step": 64
+    },
+    {
+      "epoch": 0.19198818534244047,
+      "grad_norm": 1.8682852110070804,
+      "learning_rate": 1.8684172319859258e-05,
+      "loss": 0.2383,
+      "step": 65
+    },
+    {
+      "epoch": 0.19494184973232417,
+      "grad_norm": 1.2843394680645717,
+      "learning_rate": 1.863613591968355e-05,
+      "loss": 0.2472,
+      "step": 66
+    },
+    {
+      "epoch": 0.19789551412220788,
+      "grad_norm": 1.017809753190489,
+      "learning_rate": 1.858730240563342e-05,
+      "loss": 0.2485,
+      "step": 67
+    },
+    {
+      "epoch": 0.20084917851209155,
+      "grad_norm": 2.2205775400272505,
+      "learning_rate": 1.8537676285033886e-05,
+      "loss": 0.2493,
+      "step": 68
+    },
+    {
+      "epoch": 0.20380284290197526,
+      "grad_norm": 1.235929269519101,
+      "learning_rate": 1.848726213836744e-05,
+      "loss": 0.2565,
+      "step": 69
+    },
+    {
+      "epoch": 0.20675650729185896,
+      "grad_norm": 1.8604954040590647,
+      "learning_rate": 1.8436064618851225e-05,
+      "loss": 0.3199,
+      "step": 70
+    },
+    {
+      "epoch": 0.20971017168174266,
+      "grad_norm": 2.0980254275510446,
+      "learning_rate": 1.838408845200758e-05,
+      "loss": 0.3298,
+      "step": 71
+    },
+    {
+      "epoch": 0.21266383607162637,
+      "grad_norm": 1.1425880293706356,
+      "learning_rate": 1.8331338435227838e-05,
+      "loss": 0.2163,
+      "step": 72
+    },
+    {
+      "epoch": 0.21561750046151007,
+      "grad_norm": 1.4113107349066654,
+      "learning_rate": 1.8277819437329577e-05,
+      "loss": 0.2598,
+      "step": 73
+    },
+    {
+      "epoch": 0.21857116485139377,
+      "grad_norm": 1.9224862314097175,
+      "learning_rate": 1.8223536398107177e-05,
+      "loss": 0.3132,
+      "step": 74
+    },
+    {
+      "epoch": 0.22152482924127745,
+      "grad_norm": 1.06320772052325,
+      "learning_rate": 1.8168494327875918e-05,
+      "loss": 0.2937,
+      "step": 75
+    },
+    {
+      "epoch": 0.22447849363116115,
+      "grad_norm": 1.2174257014009797,
+      "learning_rate": 1.8112698307009506e-05,
+      "loss": 0.238,
+      "step": 76
+    },
+    {
+      "epoch": 0.22743215802104486,
+      "grad_norm": 1.5162497230780494,
+      "learning_rate": 1.8056153485471167e-05,
+      "loss": 0.1991,
+      "step": 77
+    },
+    {
+      "epoch": 0.23038582241092856,
+      "grad_norm": 1.18750715957012,
+      "learning_rate": 1.799886508233829e-05,
+      "loss": 0.2978,
+      "step": 78
+    },
+    {
+      "epoch": 0.23333948680081226,
+      "grad_norm": 2.973457653034149,
+      "learning_rate": 1.7940838385320732e-05,
+      "loss": 0.2601,
+      "step": 79
+    },
+    {
+      "epoch": 0.23629315119069597,
+      "grad_norm": 1.4297439267822007,
+      "learning_rate": 1.788207875027274e-05,
+      "loss": 0.3164,
+      "step": 80
+    },
+    {
+      "epoch": 0.23924681558057967,
+      "grad_norm": 1.6564928680332287,
+      "learning_rate": 1.7822591600698632e-05,
+      "loss": 0.237,
+      "step": 81
+    },
+    {
+      "epoch": 0.24220047997046334,
+      "grad_norm": 1.2481653938902246,
+      "learning_rate": 1.776238242725217e-05,
+      "loss": 0.2825,
+      "step": 82
+    },
+    {
+      "epoch": 0.24515414436034705,
+      "grad_norm": 1.4622528270629795,
+      "learning_rate": 1.7701456787229805e-05,
+      "loss": 0.2967,
+      "step": 83
+    },
+    {
+      "epoch": 0.24810780875023075,
+      "grad_norm": 1.1364730949104225,
+      "learning_rate": 1.7639820304057745e-05,
+      "loss": 0.2693,
+      "step": 84
+    },
+    {
+      "epoch": 0.25106147314011446,
+      "grad_norm": 1.0844100740250735,
+      "learning_rate": 1.7577478666772886e-05,
+      "loss": 0.2929,
+      "step": 85
+    },
+    {
+      "epoch": 0.25401513752999816,
+      "grad_norm": 1.0265123142436297,
+      "learning_rate": 1.751443762949772e-05,
+      "loss": 0.2386,
+      "step": 86
+    },
+    {
+      "epoch": 0.25696880191988186,
+      "grad_norm": 1.8332595816906205,
+      "learning_rate": 1.7450703010909263e-05,
+      "loss": 0.2268,
+      "step": 87
+    },
+    {
+      "epoch": 0.25992246630976557,
+      "grad_norm": 1.2274642417045811,
+      "learning_rate": 1.738628069370195e-05,
+      "loss": 0.1997,
+      "step": 88
+    },
+    {
+      "epoch": 0.26287613069964927,
+      "grad_norm": 1.8440511370248884,
+      "learning_rate": 1.732117662404469e-05,
+      "loss": 0.3254,
+      "step": 89
+    },
+    {
+      "epoch": 0.26582979508953297,
+      "grad_norm": 1.7570589127181166,
+      "learning_rate": 1.7255396811032014e-05,
+      "loss": 0.2358,
+      "step": 90
+    },
+    {
+      "epoch": 0.2687834594794167,
+      "grad_norm": 1.5694781679384842,
+      "learning_rate": 1.718894732612947e-05,
+      "loss": 0.253,
+      "step": 91
+    },
+    {
+      "epoch": 0.2717371238693003,
+      "grad_norm": 1.0385463235337,
+      "learning_rate": 1.712183430261319e-05,
+      "loss": 0.2717,
+      "step": 92
+    },
+    {
+      "epoch": 0.274690788259184,
+      "grad_norm": 1.4412499710422237,
+      "learning_rate": 1.7054063935003813e-05,
+      "loss": 0.2302,
+      "step": 93
+    },
+    {
+      "epoch": 0.27764445264906773,
+      "grad_norm": 3.529966786893214,
+      "learning_rate": 1.698564247849473e-05,
+      "loss": 0.2867,
+      "step": 94
+    },
+    {
+      "epoch": 0.28059811703895143,
+      "grad_norm": 1.2672492658805385,
+      "learning_rate": 1.691657624837472e-05,
+      "loss": 0.2045,
+      "step": 95
+    },
+    {
+      "epoch": 0.28355178142883514,
+      "grad_norm": 0.9176767851503596,
+      "learning_rate": 1.684687161944506e-05,
+      "loss": 0.2509,
+      "step": 96
+    },
+    {
+      "epoch": 0.28650544581871884,
+      "grad_norm": 1.161604448718551,
+      "learning_rate": 1.677653502543113e-05,
+      "loss": 0.2474,
+      "step": 97
+    },
+    {
+      "epoch": 0.28945911020860254,
+      "grad_norm": 1.1883037859108712,
+      "learning_rate": 1.6705572958388576e-05,
+      "loss": 0.2825,
+      "step": 98
+    },
+    {
+      "epoch": 0.29241277459848625,
+      "grad_norm": 1.3916922978511344,
+      "learning_rate": 1.6633991968104095e-05,
+      "loss": 0.2935,
+      "step": 99
+    },
+    {
+      "epoch": 0.29536643898836995,
+      "grad_norm": 1.1724380392159808,
+      "learning_rate": 1.6561798661490904e-05,
+      "loss": 0.2165,
+      "step": 100
+    },
+    {
+      "epoch": 0.29832010337825365,
+      "grad_norm": 1.3803456662831326,
+      "learning_rate": 1.6488999701978905e-05,
+      "loss": 0.272,
+      "step": 101
+    },
+    {
+      "epoch": 0.30127376776813736,
+      "grad_norm": 1.2576499318824381,
+      "learning_rate": 1.6415601808899658e-05,
+      "loss": 0.2234,
+      "step": 102
+    },
+    {
+      "epoch": 0.30422743215802106,
+      "grad_norm": 1.1279853492268177,
+      "learning_rate": 1.63416117568662e-05,
+      "loss": 0.2501,
+      "step": 103
+    },
+    {
+      "epoch": 0.30718109654790476,
+      "grad_norm": 2.1142008653949533,
+      "learning_rate": 1.6267036375147728e-05,
+      "loss": 0.231,
+      "step": 104
+    },
+    {
+      "epoch": 0.31013476093778847,
+      "grad_norm": 1.5354148204855673,
+      "learning_rate": 1.619188254703927e-05,
+      "loss": 0.2572,
+      "step": 105
+    },
+    {
+      "epoch": 0.31308842532767217,
+      "grad_norm": 1.8111259417638643,
+      "learning_rate": 1.6116157209226356e-05,
+      "loss": 0.2485,
+      "step": 106
+    },
+    {
+      "epoch": 0.3160420897175558,
+      "grad_norm": 1.6621307355421575,
+      "learning_rate": 1.6039867351144778e-05,
+      "loss": 0.2292,
+      "step": 107
+    },
+    {
+      "epoch": 0.3189957541074395,
+      "grad_norm": 3.3263259030038843,
+      "learning_rate": 1.5963020014335437e-05,
+      "loss": 0.2319,
+      "step": 108
+    },
+    {
+      "epoch": 0.3219494184973232,
+      "grad_norm": 2.052088135053435,
+      "learning_rate": 1.588562229179443e-05,
+      "loss": 0.2785,
+      "step": 109
+    },
+    {
+      "epoch": 0.32490308288720693,
+      "grad_norm": 1.7457872664375444,
+      "learning_rate": 1.5807681327318372e-05,
+      "loss": 0.2375,
+      "step": 110
+    },
+    {
+      "epoch": 0.32785674727709063,
+      "grad_norm": 2.1656130103223292,
+      "learning_rate": 1.5729204314845002e-05,
+      "loss": 0.3204,
+      "step": 111
+    },
+    {
+      "epoch": 0.33081041166697434,
+      "grad_norm": 1.4347887292208887,
+      "learning_rate": 1.56501984977892e-05,
+      "loss": 0.1912,
+      "step": 112
+    },
+    {
+      "epoch": 0.33376407605685804,
+      "grad_norm": 1.7457376826745783,
+      "learning_rate": 1.557067116837444e-05,
+      "loss": 0.1869,
+      "step": 113
+    },
+    {
+      "epoch": 0.33671774044674174,
+      "grad_norm": 1.279310426755318,
+      "learning_rate": 1.5490629666959668e-05,
+      "loss": 0.2515,
+      "step": 114
+    },
+    {
+      "epoch": 0.33967140483662545,
+      "grad_norm": 1.2398989051076739,
+      "learning_rate": 1.541008138136183e-05,
+      "loss": 0.276,
+      "step": 115
+    },
+    {
+      "epoch": 0.34262506922650915,
+      "grad_norm": 0.8931524769308568,
+      "learning_rate": 1.5329033746173975e-05,
+      "loss": 0.1926,
+      "step": 116
+    },
+    {
+      "epoch": 0.34557873361639285,
+      "grad_norm": 0.9382290625981602,
+      "learning_rate": 1.5247494242079024e-05,
+      "loss": 0.1994,
+      "step": 117
+    },
+    {
+      "epoch": 0.34853239800627656,
+      "grad_norm": 1.6152374848968118,
+      "learning_rate": 1.5165470395159314e-05,
+      "loss": 0.2737,
+      "step": 118
+    },
+    {
+      "epoch": 0.35148606239616026,
+      "grad_norm": 0.7437908075523608,
+      "learning_rate": 1.5082969776201948e-05,
+      "loss": 0.2452,
+      "step": 119
+    },
+    {
+      "epoch": 0.35443972678604396,
+      "grad_norm": 1.433187333629193,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2928,
+      "step": 120
+    },
+    {
+      "epoch": 0.3573933911759276,
+      "grad_norm": 1.1151731420543107,
+      "learning_rate": 1.4916568724649688e-05,
+      "loss": 0.2469,
+      "step": 121
+    },
+    {
+      "epoch": 0.3603470555658113,
+      "grad_norm": 1.628208821537734,
+      "learning_rate": 1.483268365084351e-05,
+      "loss": 0.2672,
+      "step": 122
+    },
+    {
+      "epoch": 0.363300719955695,
+      "grad_norm": 1.655636248263217,
+      "learning_rate": 1.4748352521159492e-05,
+      "loss": 0.2558,
+      "step": 123
+    },
+    {
+      "epoch": 0.3662543843455787,
+      "grad_norm": 1.1190196781911896,
+      "learning_rate": 1.466358311934654e-05,
+      "loss": 0.2424,
+      "step": 124
+    },
+    {
+      "epoch": 0.3692080487354624,
+      "grad_norm": 1.5683734426508247,
+      "learning_rate": 1.4578383269606004e-05,
+      "loss": 0.2078,
+      "step": 125
+    },
+    {
+      "epoch": 0.3721617131253461,
+      "grad_norm": 2.1959742679571392,
+      "learning_rate": 1.4492760835869504e-05,
+      "loss": 0.1833,
+      "step": 126
+    },
+    {
+      "epoch": 0.37511537751522983,
+      "grad_norm": 1.8629992032442229,
+      "learning_rate": 1.4406723721073088e-05,
+      "loss": 0.2172,
+      "step": 127
+    },
+    {
+      "epoch": 0.37806904190511353,
+      "grad_norm": 1.3715247051576143,
+      "learning_rate": 1.4320279866427798e-05,
+      "loss": 0.2275,
+      "step": 128
+    },
+    {
+      "epoch": 0.38102270629499724,
+      "grad_norm": 1.9490061377077916,
+      "learning_rate": 1.4233437250686695e-05,
+      "loss": 0.2788,
+      "step": 129
+    },
+    {
+      "epoch": 0.38397637068488094,
+      "grad_norm": 2.5933766685145283,
+      "learning_rate": 1.4146203889408418e-05,
+      "loss": 0.2166,
+      "step": 130
+    },
+    {
+      "epoch": 0.38693003507476464,
+      "grad_norm": 1.2370288412958634,
+      "learning_rate": 1.4058587834217356e-05,
+      "loss": 0.2072,
+      "step": 131
+    },
+    {
+      "epoch": 0.38988369946464835,
+      "grad_norm": 1.1081749176693048,
+      "learning_rate": 1.3970597172060482e-05,
+      "loss": 0.1989,
+      "step": 132
+    },
+    {
+      "epoch": 0.39283736385453205,
+      "grad_norm": 1.4828838112332934,
+      "learning_rate": 1.3882240024460928e-05,
+      "loss": 0.3022,
+      "step": 133
+    },
+    {
+      "epoch": 0.39579102824441575,
+      "grad_norm": 1.1733959356793078,
+      "learning_rate": 1.3793524546768358e-05,
+      "loss": 0.2889,
+      "step": 134
+    },
+    {
+      "epoch": 0.3987446926342994,
+      "grad_norm": 0.8750941794002657,
+      "learning_rate": 1.3704458927406261e-05,
+      "loss": 0.2043,
+      "step": 135
+    },
+    {
+      "epoch": 0.4016983570241831,
+      "grad_norm": 0.9229984145111342,
+      "learning_rate": 1.3615051387116131e-05,
+      "loss": 0.1931,
+      "step": 136
+    },
+    {
+      "epoch": 0.4046520214140668,
+      "grad_norm": 0.9607360356833068,
+      "learning_rate": 1.3525310178198707e-05,
+      "loss": 0.2502,
+      "step": 137
+    },
+    {
+      "epoch": 0.4076056858039505,
+      "grad_norm": 1.267256607998377,
+      "learning_rate": 1.3435243583752294e-05,
+      "loss": 0.2551,
+      "step": 138
+    },
+    {
+      "epoch": 0.4105593501938342,
+      "grad_norm": 1.1535151890824327,
+      "learning_rate": 1.3344859916908206e-05,
+      "loss": 0.2519,
+      "step": 139
+    },
+    {
+      "epoch": 0.4135130145837179,
+      "grad_norm": 1.2308120883855471,
+      "learning_rate": 1.325416752006351e-05,
+      "loss": 0.2028,
+      "step": 140
+    },
+    {
+      "epoch": 0.4164666789736016,
+      "grad_norm": 1.1261523707817411,
+      "learning_rate": 1.3163174764110985e-05,
+      "loss": 0.2891,
+      "step": 141
+    },
+    {
+      "epoch": 0.4194203433634853,
+      "grad_norm": 1.0484777228642377,
+      "learning_rate": 1.3071890047666498e-05,
+      "loss": 0.2847,
+      "step": 142
+    },
+    {
+      "epoch": 0.42237400775336903,
+      "grad_norm": 1.3574789457653618,
+      "learning_rate": 1.2980321796293838e-05,
+      "loss": 0.2313,
+      "step": 143
+    },
+    {
+      "epoch": 0.42532767214325273,
+      "grad_norm": 1.6359214874264179,
+      "learning_rate": 1.288847846172701e-05,
+      "loss": 0.2613,
+      "step": 144
+    },
+    {
+      "epoch": 0.42828133653313644,
+      "grad_norm": 1.4849630914722172,
+      "learning_rate": 1.2796368521090143e-05,
+      "loss": 0.2497,
+      "step": 145
+    },
+    {
+      "epoch": 0.43123500092302014,
+      "grad_norm": 0.9672458928556958,
+      "learning_rate": 1.2704000476115079e-05,
+      "loss": 0.2125,
+      "step": 146
+    },
+    {
+      "epoch": 0.43418866531290384,
+      "grad_norm": 1.3631344827108736,
+      "learning_rate": 1.2611382852356632e-05,
+      "loss": 0.2102,
+      "step": 147
+    },
+    {
+      "epoch": 0.43714232970278755,
+      "grad_norm": 1.081373449791384,
+      "learning_rate": 1.2518524198405699e-05,
+      "loss": 0.1994,
+      "step": 148
+    },
+    {
+      "epoch": 0.4400959940926712,
+      "grad_norm": 3.031111169053163,
+      "learning_rate": 1.2425433085100224e-05,
+      "loss": 0.251,
+      "step": 149
+    },
+    {
+      "epoch": 0.4430496584825549,
+      "grad_norm": 1.109367118461991,
+      "learning_rate": 1.233211810473411e-05,
+      "loss": 0.2145,
+      "step": 150
+    },
+    {
+      "epoch": 0.4460033228724386,
+      "grad_norm": 1.8019223476694273,
+      "learning_rate": 1.2238587870264152e-05,
+      "loss": 0.2416,
+      "step": 151
+    },
+    {
+      "epoch": 0.4489569872623223,
+      "grad_norm": 0.9740173075655284,
+      "learning_rate": 1.2144851014515055e-05,
+      "loss": 0.2483,
+      "step": 152
+    },
+    {
+      "epoch": 0.451910651652206,
+      "grad_norm": 2.103510651583566,
+      "learning_rate": 1.2050916189382646e-05,
+      "loss": 0.2503,
+      "step": 153
+    },
+    {
+      "epoch": 0.4548643160420897,
+      "grad_norm": 0.9776576320454566,
+      "learning_rate": 1.1956792065035281e-05,
+      "loss": 0.2097,
+      "step": 154
+    },
+    {
+      "epoch": 0.4578179804319734,
+      "grad_norm": 0.9661788560533139,
+      "learning_rate": 1.1862487329113606e-05,
+      "loss": 0.2307,
+      "step": 155
+    },
+    {
+      "epoch": 0.4607716448218571,
+      "grad_norm": 1.089240042431727,
+      "learning_rate": 1.1768010685928686e-05,
+      "loss": 0.2716,
+      "step": 156
+    },
+    {
+      "epoch": 0.4637253092117408,
+      "grad_norm": 1.8188209063972023,
+      "learning_rate": 1.1673370855658592e-05,
+      "loss": 0.2543,
+      "step": 157
+    },
+    {
+      "epoch": 0.4666789736016245,
+      "grad_norm": 0.9268264783045698,
+      "learning_rate": 1.1578576573543541e-05,
+      "loss": 0.1993,
+      "step": 158
+    },
+    {
+      "epoch": 0.46963263799150823,
+      "grad_norm": 2.8113037410793633,
+      "learning_rate": 1.1483636589079627e-05,
+      "loss": 0.2359,
+      "step": 159
+    },
+    {
+      "epoch": 0.47258630238139193,
+      "grad_norm": 1.1434071278207998,
+      "learning_rate": 1.1388559665211241e-05,
+      "loss": 0.2429,
+      "step": 160
+    },
+    {
+      "epoch": 0.47553996677127564,
+      "grad_norm": 1.7302412316542266,
+      "learning_rate": 1.1293354577522264e-05,
+      "loss": 0.2826,
+      "step": 161
+    },
+    {
+      "epoch": 0.47849363116115934,
+      "grad_norm": 2.0316255286578735,
+      "learning_rate": 1.1198030113426074e-05,
+      "loss": 0.2273,
+      "step": 162
+    },
+    {
+      "epoch": 0.481447295551043,
+      "grad_norm": 0.8326584843590035,
+      "learning_rate": 1.1102595071354471e-05,
+      "loss": 0.2394,
+      "step": 163
+    },
+    {
+      "epoch": 0.4844009599409267,
+      "grad_norm": 1.317424629649938,
+      "learning_rate": 1.1007058259945584e-05,
+      "loss": 0.2339,
+      "step": 164
+    },
+    {
+      "epoch": 0.4873546243308104,
+      "grad_norm": 1.021243726388158,
+      "learning_rate": 1.0911428497230834e-05,
+      "loss": 0.2483,
+      "step": 165
+    },
+    {
+      "epoch": 0.4903082887206941,
+      "grad_norm": 0.9876546362231726,
+      "learning_rate": 1.0815714609821027e-05,
+      "loss": 0.3242,
+      "step": 166
+    },
+    {
+      "epoch": 0.4932619531105778,
+      "grad_norm": 0.8098325451574229,
+      "learning_rate": 1.0719925432091671e-05,
+      "loss": 0.2444,
+      "step": 167
+    },
+    {
+      "epoch": 0.4962156175004615,
+      "grad_norm": 2.17413162626723,
+      "learning_rate": 1.0624069805367558e-05,
+      "loss": 0.3416,
+      "step": 168
+    },
+    {
+      "epoch": 0.4991692818903452,
+      "grad_norm": 1.8720289242626653,
+      "learning_rate": 1.0528156577106703e-05,
+      "loss": 0.2682,
+      "step": 169
+    },
+    {
+      "epoch": 0.5021229462802289,
+      "grad_norm": 0.8874485016784218,
+      "learning_rate": 1.043219460008374e-05,
+      "loss": 0.2733,
+      "step": 170
+    },
+    {
+      "epoch": 0.5050766106701126,
+      "grad_norm": 1.0480044654604301,
+      "learning_rate": 1.0336192731572805e-05,
+      "loss": 0.2298,
+      "step": 171
+    },
+    {
+      "epoch": 0.5080302750599963,
+      "grad_norm": 1.181818854385163,
+      "learning_rate": 1.0240159832530007e-05,
+      "loss": 0.2572,
+      "step": 172
+    },
+    {
+      "epoch": 0.51098393944988,
+      "grad_norm": 0.98648646319354,
+      "learning_rate": 1.0144104766775574e-05,
+      "loss": 0.2495,
+      "step": 173
+    },
+    {
+      "epoch": 0.5139376038397637,
+      "grad_norm": 1.0277098370436357,
+      "learning_rate": 1.004803640017571e-05,
+      "loss": 0.2619,
+      "step": 174
+    },
+    {
+      "epoch": 0.5168912682296474,
+      "grad_norm": 1.1062050987306524,
+      "learning_rate": 9.951963599824294e-06,
+      "loss": 0.2238,
+      "step": 175
+    },
+    {
+      "epoch": 0.5198449326195311,
+      "grad_norm": 1.2488436891812305,
+      "learning_rate": 9.855895233224431e-06,
+      "loss": 0.2372,
+      "step": 176
+    },
+    {
+      "epoch": 0.5227985970094148,
+      "grad_norm": 1.3481996131119136,
+      "learning_rate": 9.759840167469995e-06,
+      "loss": 0.2746,
+      "step": 177
+    },
+    {
+      "epoch": 0.5257522613992985,
+      "grad_norm": 0.8826183612671726,
+      "learning_rate": 9.663807268427197e-06,
+      "loss": 0.2335,
+      "step": 178
+    },
+    {
+      "epoch": 0.5287059257891822,
+      "grad_norm": 0.9244242887212063,
+      "learning_rate": 9.56780539991626e-06,
+      "loss": 0.2178,
+      "step": 179
+    },
+    {
+      "epoch": 0.5316595901790659,
+      "grad_norm": 1.4163564901321666,
+      "learning_rate": 9.471843422893299e-06,
+      "loss": 0.2747,
+      "step": 180
+    },
+    {
+      "epoch": 0.5346132545689496,
+      "grad_norm": 1.009293146826116,
+      "learning_rate": 9.375930194632447e-06,
+      "loss": 0.2688,
+      "step": 181
+    },
+    {
+      "epoch": 0.5375669189588334,
+      "grad_norm": 1.1818455803606223,
+      "learning_rate": 9.28007456790833e-06,
+      "loss": 0.2621,
+      "step": 182
+    },
+    {
+      "epoch": 0.540520583348717,
+      "grad_norm": 1.0611769717320774,
+      "learning_rate": 9.184285390178978e-06,
+      "loss": 0.2437,
+      "step": 183
+    },
+    {
+      "epoch": 0.5434742477386006,
+      "grad_norm": 1.2390997213154737,
+      "learning_rate": 9.08857150276917e-06,
+      "loss": 0.2952,
+      "step": 184
+    },
+    {
+      "epoch": 0.5464279121284844,
+      "grad_norm": 1.835044765816236,
+      "learning_rate": 8.992941740054418e-06,
+      "loss": 0.3033,
+      "step": 185
+    },
+    {
+      "epoch": 0.549381576518368,
+      "grad_norm": 0.8704926207718849,
+      "learning_rate": 8.897404928645529e-06,
+      "loss": 0.2365,
+      "step": 186
+    },
+    {
+      "epoch": 0.5523352409082518,
+      "grad_norm": 1.4546396972602982,
+      "learning_rate": 8.80196988657393e-06,
+      "loss": 0.2468,
+      "step": 187
+    },
+    {
+      "epoch": 0.5552889052981355,
+      "grad_norm": 1.1497614503627624,
+      "learning_rate": 8.706645422477739e-06,
+      "loss": 0.2231,
+      "step": 188
+    },
+    {
+      "epoch": 0.5582425696880192,
+      "grad_norm": 1.898082986482141,
+      "learning_rate": 8.611440334788762e-06,
+      "loss": 0.2955,
+      "step": 189
+    },
+    {
+      "epoch": 0.5611962340779029,
+      "grad_norm": 1.732309153229397,
+      "learning_rate": 8.516363410920376e-06,
+      "loss": 0.2623,
+      "step": 190
+    },
+    {
+      "epoch": 0.5641498984677866,
+      "grad_norm": 1.3066685408925918,
+      "learning_rate": 8.42142342645646e-06,
+      "loss": 0.2101,
+      "step": 191
+    },
+    {
+      "epoch": 0.5671035628576703,
+      "grad_norm": 1.162748592458113,
+      "learning_rate": 8.326629144341408e-06,
+      "loss": 0.2041,
+      "step": 192
+    },
+    {
+      "epoch": 0.570057227247554,
+      "grad_norm": 1.29586252973902,
+      "learning_rate": 8.231989314071318e-06,
+      "loss": 0.2386,
+      "step": 193
+    },
+    {
+      "epoch": 0.5730108916374377,
+      "grad_norm": 1.5953660392118898,
+      "learning_rate": 8.137512670886397e-06,
+      "loss": 0.3249,
+      "step": 194
+    },
+    {
+      "epoch": 0.5759645560273214,
+      "grad_norm": 1.1905039053627462,
+      "learning_rate": 8.043207934964722e-06,
+      "loss": 0.2688,
+      "step": 195
+    },
+    {
+      "epoch": 0.5789182204172051,
+      "grad_norm": 1.1837724923413109,
+      "learning_rate": 7.949083810617358e-06,
+      "loss": 0.2218,
+      "step": 196
+    },
+    {
+      "epoch": 0.5818718848070888,
+      "grad_norm": 1.0337142264120576,
+      "learning_rate": 7.855148985484946e-06,
+      "loss": 0.2313,
+      "step": 197
+    },
+    {
+      "epoch": 0.5848255491969725,
+      "grad_norm": 1.023527322376044,
+      "learning_rate": 7.761412129735853e-06,
+      "loss": 0.2546,
+      "step": 198
+    },
+    {
+      "epoch": 0.5877792135868561,
+      "grad_norm": 1.9398516606289615,
+      "learning_rate": 7.667881895265895e-06,
+      "loss": 0.2541,
+      "step": 199
+    },
+    {
+      "epoch": 0.5907328779767399,
+      "grad_norm": 1.2286452090124362,
+      "learning_rate": 7.574566914899779e-06,
+      "loss": 0.2435,
+      "step": 200
+    },
+    {
+      "epoch": 0.5936865423666235,
+      "grad_norm": 1.9724170175167155,
+      "learning_rate": 7.481475801594302e-06,
+      "loss": 0.2256,
+      "step": 201
+    },
+    {
+      "epoch": 0.5966402067565073,
+      "grad_norm": 0.9322838897748312,
+      "learning_rate": 7.388617147643371e-06,
+      "loss": 0.2217,
+      "step": 202
+    },
+    {
+      "epoch": 0.599593871146391,
+      "grad_norm": 1.4987943471159813,
+      "learning_rate": 7.295999523884921e-06,
+      "loss": 0.2415,
+      "step": 203
+    },
+    {
+      "epoch": 0.6025475355362747,
+      "grad_norm": 2.3935521553878902,
+      "learning_rate": 7.203631478909857e-06,
+      "loss": 0.2644,
+      "step": 204
+    },
+    {
+      "epoch": 0.6055011999261584,
+      "grad_norm": 1.0320215273603501,
+      "learning_rate": 7.111521538272997e-06,
+      "loss": 0.2676,
+      "step": 205
+    },
+    {
+      "epoch": 0.6084548643160421,
+      "grad_norm": 0.7108542636852405,
+      "learning_rate": 7.019678203706164e-06,
+      "loss": 0.2172,
+      "step": 206
+    },
+    {
+      "epoch": 0.6114085287059258,
+      "grad_norm": 0.9743452858582518,
+      "learning_rate": 6.928109952333506e-06,
+      "loss": 0.1604,
+      "step": 207
+    },
+    {
+      "epoch": 0.6143621930958095,
+      "grad_norm": 1.031069019097842,
+      "learning_rate": 6.83682523588902e-06,
+      "loss": 0.2489,
+      "step": 208
+    },
+    {
+      "epoch": 0.6173158574856932,
+      "grad_norm": 1.1126940698355048,
+      "learning_rate": 6.745832479936492e-06,
+      "loss": 0.2271,
+      "step": 209
+    },
+    {
+      "epoch": 0.6202695218755769,
+      "grad_norm": 1.0020460027427114,
+      "learning_rate": 6.655140083091794e-06,
+      "loss": 0.209,
+      "step": 210
+    },
+    {
+      "epoch": 0.6232231862654606,
+      "grad_norm": 0.8970125803197203,
+      "learning_rate": 6.564756416247712e-06,
+      "loss": 0.2583,
+      "step": 211
+    },
+    {
+      "epoch": 0.6261768506553443,
+      "grad_norm": 1.0568957445259135,
+      "learning_rate": 6.474689821801295e-06,
+      "loss": 0.2324,
+      "step": 212
+    },
+    {
+      "epoch": 0.629130515045228,
+      "grad_norm": 1.051239767211671,
+      "learning_rate": 6.384948612883872e-06,
+      "loss": 0.2223,
+      "step": 213
+    },
+    {
+      "epoch": 0.6320841794351116,
+      "grad_norm": 1.3654867580389307,
+      "learning_rate": 6.2955410725937405e-06,
+      "loss": 0.3261,
+      "step": 214
+    },
+    {
+      "epoch": 0.6350378438249954,
+      "grad_norm": 1.5940508984964765,
+      "learning_rate": 6.206475453231644e-06,
+      "loss": 0.3056,
+      "step": 215
+    },
+    {
+      "epoch": 0.637991508214879,
+      "grad_norm": 1.6484237300537123,
+      "learning_rate": 6.117759975539075e-06,
+      "loss": 0.2511,
+      "step": 216
+    },
+    {
+      "epoch": 0.6409451726047628,
+      "grad_norm": 0.9783636169511857,
+      "learning_rate": 6.029402827939519e-06,
+      "loss": 0.1926,
+      "step": 217
+    },
+    {
+      "epoch": 0.6438988369946465,
+      "grad_norm": 1.2177544643933664,
+      "learning_rate": 5.941412165782645e-06,
+      "loss": 0.2448,
+      "step": 218
+    },
+    {
+      "epoch": 0.6468525013845302,
+      "grad_norm": 1.3485731634469964,
+      "learning_rate": 5.853796110591583e-06,
+      "loss": 0.3118,
+      "step": 219
+    },
+    {
+      "epoch": 0.6498061657744139,
+      "grad_norm": 1.0074910225979905,
+      "learning_rate": 5.766562749313309e-06,
+      "loss": 0.2329,
+      "step": 220
+    },
+    {
+      "epoch": 0.6527598301642976,
+      "grad_norm": 1.9631275122537244,
+      "learning_rate": 5.6797201335722064e-06,
+      "loss": 0.2364,
+      "step": 221
+    },
+    {
+      "epoch": 0.6557134945541813,
+      "grad_norm": 1.062222369251804,
+      "learning_rate": 5.593276278926912e-06,
+      "loss": 0.2315,
+      "step": 222
+    },
+    {
+      "epoch": 0.658667158944065,
+      "grad_norm": 1.07696139078638,
+      "learning_rate": 5.507239164130501e-06,
+      "loss": 0.1934,
+      "step": 223
+    },
+    {
+      "epoch": 0.6616208233339487,
+      "grad_norm": 1.0422028056726698,
+      "learning_rate": 5.421616730394e-06,
+      "loss": 0.2931,
+      "step": 224
+    },
+    {
+      "epoch": 0.6645744877238324,
+      "grad_norm": 1.1093276167484338,
+      "learning_rate": 5.336416880653461e-06,
+      "loss": 0.2677,
+      "step": 225
+    },
+    {
+      "epoch": 0.6675281521137161,
+      "grad_norm": 1.0629629635370519,
+      "learning_rate": 5.251647478840511e-06,
+      "loss": 0.207,
+      "step": 226
+    },
+    {
+      "epoch": 0.6704818165035997,
+      "grad_norm": 0.779645708058216,
+      "learning_rate": 5.167316349156495e-06,
+      "loss": 0.2009,
+      "step": 227
+    },
+    {
+      "epoch": 0.6734354808934835,
+      "grad_norm": 0.8926314737189482,
+      "learning_rate": 5.083431275350312e-06,
+      "loss": 0.19,
+      "step": 228
+    },
+    {
+      "epoch": 0.6763891452833671,
+      "grad_norm": 1.376351113952889,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.2771,
+      "step": 229
+    },
+    {
+      "epoch": 0.6793428096732509,
+      "grad_norm": 0.7572945693080168,
+      "learning_rate": 4.917030223798057e-06,
+      "loss": 0.191,
+      "step": 230
+    },
+    {
+      "epoch": 0.6822964740631345,
+      "grad_norm": 1.2668574548219917,
+      "learning_rate": 4.834529604840686e-06,
+      "loss": 0.2342,
+      "step": 231
+    },
+    {
+      "epoch": 0.6852501384530183,
+      "grad_norm": 0.9504831876512666,
+      "learning_rate": 4.7525057579209775e-06,
+      "loss": 0.2033,
+      "step": 232
+    },
+    {
+      "epoch": 0.688203802842902,
+      "grad_norm": 1.2471827348726847,
+      "learning_rate": 4.670966253826027e-06,
+      "loss": 0.2503,
+      "step": 233
+    },
+    {
+      "epoch": 0.6911574672327857,
+      "grad_norm": 1.2316083853653141,
+      "learning_rate": 4.589918618638173e-06,
+      "loss": 0.2345,
+      "step": 234
+    },
+    {
+      "epoch": 0.6941111316226694,
+      "grad_norm": 1.233920943028571,
+      "learning_rate": 4.5093703330403385e-06,
+      "loss": 0.2549,
+      "step": 235
+    },
+    {
+      "epoch": 0.6970647960125531,
+      "grad_norm": 1.2774449733259186,
+      "learning_rate": 4.429328831625565e-06,
+      "loss": 0.2747,
+      "step": 236
+    },
+    {
+      "epoch": 0.7000184604024368,
+      "grad_norm": 1.151879743444661,
+      "learning_rate": 4.349801502210801e-06,
+      "loss": 0.211,
+      "step": 237
+    },
+    {
+      "epoch": 0.7029721247923205,
+      "grad_norm": 1.0883996040038033,
+      "learning_rate": 4.270795685155001e-06,
+      "loss": 0.225,
+      "step": 238
+    },
+    {
+      "epoch": 0.7059257891822042,
+      "grad_norm": 0.8330598619298225,
+      "learning_rate": 4.192318672681631e-06,
+      "loss": 0.2428,
+      "step": 239
+    },
+    {
+      "epoch": 0.7088794535720879,
+      "grad_norm": 1.743882855971486,
+      "learning_rate": 4.1143777082055715e-06,
+      "loss": 0.3097,
+      "step": 240
+    },
+    {
+      "epoch": 0.7118331179619716,
+      "grad_norm": 0.8382109254728533,
+      "learning_rate": 4.036979985664566e-06,
+      "loss": 0.1831,
+      "step": 241
+    },
+    {
+      "epoch": 0.7147867823518552,
+      "grad_norm": 1.3270682727089078,
+      "learning_rate": 3.960132648855226e-06,
+      "loss": 0.2422,
+      "step": 242
+    },
+    {
+      "epoch": 0.717740446741739,
+      "grad_norm": 1.240272547956328,
+      "learning_rate": 3.883842790773647e-06,
+      "loss": 0.2562,
+      "step": 243
+    },
+    {
+      "epoch": 0.7206941111316226,
+      "grad_norm": 1.2319353987670736,
+      "learning_rate": 3.8081174529607346e-06,
+      "loss": 0.281,
+      "step": 244
+    },
+    {
+      "epoch": 0.7236477755215064,
+      "grad_norm": 1.1603454653088285,
+      "learning_rate": 3.732963624852275e-06,
+      "loss": 0.2749,
+      "step": 245
+    },
+    {
+      "epoch": 0.72660143991139,
+      "grad_norm": 1.0523508127263002,
+      "learning_rate": 3.6583882431338047e-06,
+      "loss": 0.201,
+      "step": 246
+    },
+    {
+      "epoch": 0.7295551043012738,
+      "grad_norm": 1.5484575857761667,
+      "learning_rate": 3.584398191100341e-06,
+      "loss": 0.1748,
+      "step": 247
+    },
+    {
+      "epoch": 0.7325087686911574,
+      "grad_norm": 0.927816740497892,
+      "learning_rate": 3.511000298021098e-06,
+      "loss": 0.2038,
+      "step": 248
+    },
+    {
+      "epoch": 0.7354624330810412,
+      "grad_norm": 1.281465915405747,
+      "learning_rate": 3.4382013385090985e-06,
+      "loss": 0.1967,
+      "step": 249
+    },
+    {
+      "epoch": 0.7384160974709248,
+      "grad_norm": 0.8383135259558974,
+      "learning_rate": 3.3660080318959043e-06,
+      "loss": 0.3009,
+      "step": 250
+    },
+    {
+      "epoch": 0.7413697618608086,
+      "grad_norm": 0.9034285090369809,
+      "learning_rate": 3.2944270416114256e-06,
+      "loss": 0.2712,
+      "step": 251
+    },
+    {
+      "epoch": 0.7443234262506923,
+      "grad_norm": 1.7330918162831006,
+      "learning_rate": 3.223464974568874e-06,
+      "loss": 0.3026,
+      "step": 252
+    },
+    {
+      "epoch": 0.747277090640576,
+      "grad_norm": 2.278797836193121,
+      "learning_rate": 3.153128380554941e-06,
+      "loss": 0.2026,
+      "step": 253
+    },
+    {
+      "epoch": 0.7502307550304597,
+      "grad_norm": 1.6530429628004708,
+      "learning_rate": 3.0834237516252817e-06,
+      "loss": 0.3184,
+      "step": 254
+    },
+    {
+      "epoch": 0.7531844194203433,
+      "grad_norm": 1.014176332937703,
+      "learning_rate": 3.0143575215052732e-06,
+      "loss": 0.2137,
+      "step": 255
+    },
+    {
+      "epoch": 0.7561380838102271,
+      "grad_norm": 1.3834895222118382,
+      "learning_rate": 2.94593606499619e-06,
+      "loss": 0.2532,
+      "step": 256
+    },
+    {
+      "epoch": 0.7590917482001107,
+      "grad_norm": 0.9517980209975256,
+      "learning_rate": 2.878165697386812e-06,
+      "loss": 0.223,
+      "step": 257
+    },
+    {
+      "epoch": 0.7620454125899945,
+      "grad_norm": 1.4826707785316666,
+      "learning_rate": 2.8110526738705345e-06,
+      "loss": 0.2331,
+      "step": 258
+    },
+    {
+      "epoch": 0.7649990769798781,
+      "grad_norm": 0.9535584029950059,
+      "learning_rate": 2.7446031889679893e-06,
+      "loss": 0.2252,
+      "step": 259
+    },
+    {
+      "epoch": 0.7679527413697619,
+      "grad_norm": 1.1476536352431068,
+      "learning_rate": 2.678823375955314e-06,
+      "loss": 0.2673,
+      "step": 260
+    },
+    {
+      "epoch": 0.7709064057596455,
+      "grad_norm": 1.443599601569734,
+      "learning_rate": 2.6137193062980506e-06,
+      "loss": 0.2148,
+      "step": 261
+    },
+    {
+      "epoch": 0.7738600701495293,
+      "grad_norm": 1.0031835343451487,
+      "learning_rate": 2.5492969890907383e-06,
+      "loss": 0.2404,
+      "step": 262
+    },
+    {
+      "epoch": 0.7768137345394129,
+      "grad_norm": 1.5720112441700467,
+      "learning_rate": 2.485562370502279e-06,
+      "loss": 0.2102,
+      "step": 263
+    },
+    {
+      "epoch": 0.7797673989292967,
+      "grad_norm": 1.515634223478538,
+      "learning_rate": 2.4225213332271203e-06,
+      "loss": 0.2801,
+      "step": 264
+    },
+    {
+      "epoch": 0.7827210633191803,
+      "grad_norm": 1.6679133246539453,
+      "learning_rate": 2.3601796959422585e-06,
+      "loss": 0.2728,
+      "step": 265
+    },
+    {
+      "epoch": 0.7856747277090641,
+      "grad_norm": 1.140587687664246,
+      "learning_rate": 2.2985432127701945e-06,
+      "loss": 0.2343,
+      "step": 266
+    },
+    {
+      "epoch": 0.7886283920989478,
+      "grad_norm": 1.6372470878039884,
+      "learning_rate": 2.2376175727478346e-06,
+      "loss": 0.3012,
+      "step": 267
+    },
+    {
+      "epoch": 0.7915820564888315,
+      "grad_norm": 1.0418170981548798,
+      "learning_rate": 2.1774083993013715e-06,
+      "loss": 0.2903,
+      "step": 268
+    },
+    {
+      "epoch": 0.7945357208787152,
+      "grad_norm": 0.9841407460639144,
+      "learning_rate": 2.1179212497272582e-06,
+      "loss": 0.2021,
+      "step": 269
+    },
+    {
+      "epoch": 0.7974893852685988,
+      "grad_norm": 3.3040280272424076,
+      "learning_rate": 2.0591616146792705e-06,
+      "loss": 0.2567,
+      "step": 270
+    },
+    {
+      "epoch": 0.8004430496584826,
+      "grad_norm": 1.0889363962398735,
+      "learning_rate": 2.0011349176617133e-06,
+      "loss": 0.2387,
+      "step": 271
+    },
+    {
+      "epoch": 0.8033967140483662,
+      "grad_norm": 1.1052353260085468,
+      "learning_rate": 1.9438465145288377e-06,
+      "loss": 0.2549,
+      "step": 272
+    },
+    {
+      "epoch": 0.80635037843825,
+      "grad_norm": 1.0811411366280128,
+      "learning_rate": 1.8873016929904942e-06,
+      "loss": 0.2245,
+      "step": 273
+    },
+    {
+      "epoch": 0.8093040428281336,
+      "grad_norm": 1.5617796782808597,
+      "learning_rate": 1.8315056721240831e-06,
+      "loss": 0.2689,
+      "step": 274
+    },
+    {
+      "epoch": 0.8122577072180174,
+      "grad_norm": 0.9419563951986655,
+      "learning_rate": 1.7764636018928249e-06,
+      "loss": 0.2274,
+      "step": 275
+    },
+    {
+      "epoch": 0.815211371607901,
+      "grad_norm": 1.0888276242305772,
+      "learning_rate": 1.722180562670428e-06,
+      "loss": 0.2137,
+      "step": 276
+    },
+    {
+      "epoch": 0.8181650359977848,
+      "grad_norm": 1.3638497191830405,
+      "learning_rate": 1.6686615647721638e-06,
+      "loss": 0.2936,
+      "step": 277
+    },
+    {
+      "epoch": 0.8211187003876684,
+      "grad_norm": 1.1621534586524414,
+      "learning_rate": 1.6159115479924259e-06,
+      "loss": 0.2835,
+      "step": 278
+    },
+    {
+      "epoch": 0.8240723647775522,
+      "grad_norm": 1.5160217377536473,
+      "learning_rate": 1.5639353811487744e-06,
+      "loss": 0.2013,
+      "step": 279
+    },
+    {
+      "epoch": 0.8270260291674358,
+      "grad_norm": 1.0562241070452318,
+      "learning_rate": 1.5127378616325606e-06,
+      "loss": 0.2387,
+      "step": 280
+    },
+    {
+      "epoch": 0.8299796935573196,
+      "grad_norm": 0.9587608909012787,
+      "learning_rate": 1.462323714966114e-06,
+      "loss": 0.2439,
+      "step": 281
+    },
+    {
+      "epoch": 0.8329333579472032,
+      "grad_norm": 1.6757197295398196,
+      "learning_rate": 1.4126975943665844e-06,
+      "loss": 0.2315,
+      "step": 282
+    },
+    {
+      "epoch": 0.8358870223370869,
+      "grad_norm": 1.3676443709621444,
+      "learning_rate": 1.3638640803164516e-06,
+      "loss": 0.2285,
+      "step": 283
+    },
+    {
+      "epoch": 0.8388406867269707,
+      "grad_norm": 1.1179995558525562,
+      "learning_rate": 1.3158276801407432e-06,
+      "loss": 0.2649,
+      "step": 284
+    },
+    {
+      "epoch": 0.8417943511168543,
+      "grad_norm": 1.042657568622807,
+      "learning_rate": 1.2685928275910142e-06,
+      "loss": 0.2123,
+      "step": 285
+    },
+    {
+      "epoch": 0.8447480155067381,
+      "grad_norm": 1.5556578514626542,
+      "learning_rate": 1.222163882436107e-06,
+      "loss": 0.2612,
+      "step": 286
+    },
+    {
+      "epoch": 0.8477016798966217,
+      "grad_norm": 1.430426782366678,
+      "learning_rate": 1.1765451300597574e-06,
+      "loss": 0.2679,
+      "step": 287
+    },
+    {
+      "epoch": 0.8506553442865055,
+      "grad_norm": 1.346297948811944,
+      "learning_rate": 1.1317407810650372e-06,
+      "loss": 0.3629,
+      "step": 288
+    },
+    {
+      "epoch": 0.8536090086763891,
+      "grad_norm": 0.903041997125672,
+      "learning_rate": 1.0877549708857228e-06,
+      "loss": 0.232,
+      "step": 289
+    },
+    {
+      "epoch": 0.8565626730662729,
+      "grad_norm": 1.0773880128337658,
+      "learning_rate": 1.0445917594046073e-06,
+      "loss": 0.1946,
+      "step": 290
+    },
+    {
+      "epoch": 0.8595163374561565,
+      "grad_norm": 1.1827269325419392,
+      "learning_rate": 1.0022551305787564e-06,
+      "loss": 0.274,
+      "step": 291
+    },
+    {
+      "epoch": 0.8624700018460403,
+      "grad_norm": 1.2938978043172173,
+      "learning_rate": 9.607489920717983e-07,
+      "loss": 0.2568,
+      "step": 292
+    },
+    {
+      "epoch": 0.8654236662359239,
+      "grad_norm": 0.8777587732368793,
+      "learning_rate": 9.200771748932513e-07,
+      "loss": 0.195,
+      "step": 293
+    },
+    {
+      "epoch": 0.8683773306258077,
+      "grad_norm": 1.0574272517036634,
+      "learning_rate": 8.802434330449128e-07,
+      "loss": 0.2284,
+      "step": 294
+    },
+    {
+      "epoch": 0.8713309950156913,
+      "grad_norm": 0.9462220870406266,
+      "learning_rate": 8.412514431743657e-07,
+      "loss": 0.2023,
+      "step": 295
+    },
+    {
+      "epoch": 0.8742846594055751,
+      "grad_norm": 1.3664321425766135,
+      "learning_rate": 8.031048042356393e-07,
+      "loss": 0.2713,
+      "step": 296
+    },
+    {
+      "epoch": 0.8772383237954587,
+      "grad_norm": 2.196437108751979,
+      "learning_rate": 7.65807037157007e-07,
+      "loss": 0.2231,
+      "step": 297
+    },
+    {
+      "epoch": 0.8801919881853424,
+      "grad_norm": 1.0022132609661685,
+      "learning_rate": 7.293615845160196e-07,
+      "loss": 0.2272,
+      "step": 298
+    },
+    {
+      "epoch": 0.8831456525752261,
+      "grad_norm": 0.8691720804489206,
+      "learning_rate": 6.937718102217461e-07,
+      "loss": 0.2079,
+      "step": 299
+    },
+    {
+      "epoch": 0.8860993169651098,
+      "grad_norm": 1.2735957834600269,
+      "learning_rate": 6.590409992042957e-07,
+      "loss": 0.3447,
+      "step": 300
+    },
+    {
+      "epoch": 0.8890529813549936,
+      "grad_norm": 0.9596393088771338,
+      "learning_rate": 6.251723571116031e-07,
+      "loss": 0.2269,
+      "step": 301
+    },
+    {
+      "epoch": 0.8920066457448772,
+      "grad_norm": 0.9568122348658286,
+      "learning_rate": 5.921690100135713e-07,
+      "loss": 0.2327,
+      "step": 302
+    },
+    {
+      "epoch": 0.894960310134761,
+      "grad_norm": 0.9463458760012983,
+      "learning_rate": 5.600340041135133e-07,
+      "loss": 0.2629,
+      "step": 303
+    },
+    {
+      "epoch": 0.8979139745246446,
+      "grad_norm": 1.1532749148406225,
+      "learning_rate": 5.287703054670012e-07,
+      "loss": 0.2508,
+      "step": 304
+    },
+    {
+      "epoch": 0.9008676389145284,
+      "grad_norm": 1.0281277964315167,
+      "learning_rate": 4.983807997080925e-07,
+      "loss": 0.2212,
+      "step": 305
+    },
+    {
+      "epoch": 0.903821303304412,
+      "grad_norm": 0.8750621395665438,
+      "learning_rate": 4.6886829178299676e-07,
+      "loss": 0.2405,
+      "step": 306
+    },
+    {
+      "epoch": 0.9067749676942958,
+      "grad_norm": 1.1195160374002207,
+      "learning_rate": 4.402355056911656e-07,
+      "loss": 0.2042,
+      "step": 307
+    },
+    {
+      "epoch": 0.9097286320841794,
+      "grad_norm": 1.2073055574446565,
+      "learning_rate": 4.124850842338779e-07,
+      "loss": 0.3165,
+      "step": 308
+    },
+    {
+      "epoch": 0.9126822964740632,
+      "grad_norm": 0.9971547949248887,
+      "learning_rate": 3.8561958877030957e-07,
+      "loss": 0.2248,
+      "step": 309
+    },
+    {
+      "epoch": 0.9156359608639468,
+      "grad_norm": 1.2258045934933872,
+      "learning_rate": 3.5964149898111587e-07,
+      "loss": 0.261,
+      "step": 310
+    },
+    {
+      "epoch": 0.9185896252538306,
+      "grad_norm": 1.2822010085661448,
+      "learning_rate": 3.345532126395579e-07,
+      "loss": 0.2145,
+      "step": 311
+    },
+    {
+      "epoch": 0.9215432896437142,
+      "grad_norm": 1.197892649344162,
+      "learning_rate": 3.1035704539019384e-07,
+      "loss": 0.2274,
+      "step": 312
+    },
+    {
+      "epoch": 0.9244969540335979,
+      "grad_norm": 1.3780412739693457,
+      "learning_rate": 2.870552305351382e-07,
+      "loss": 0.2529,
+      "step": 313
+    },
+    {
+      "epoch": 0.9274506184234816,
+      "grad_norm": 1.2245421854784801,
+      "learning_rate": 2.646499188279328e-07,
+      "loss": 0.2578,
+      "step": 314
+    },
+    {
+      "epoch": 0.9304042828133653,
+      "grad_norm": 0.8725967365032492,
+      "learning_rate": 2.4314317827503375e-07,
+      "loss": 0.1964,
+      "step": 315
+    },
+    {
+      "epoch": 0.933357947203249,
+      "grad_norm": 1.0171829897640234,
+      "learning_rate": 2.2253699394493066e-07,
+      "loss": 0.192,
+      "step": 316
+    },
+    {
+      "epoch": 0.9363116115931327,
+      "grad_norm": 1.5120721916483608,
+      "learning_rate": 2.028332677849254e-07,
+      "loss": 0.2038,
+      "step": 317
+    },
+    {
+      "epoch": 0.9392652759830165,
+      "grad_norm": 0.9364220238859826,
+      "learning_rate": 1.840338184455881e-07,
+      "loss": 0.302,
+      "step": 318
+    },
+    {
+      "epoch": 0.9422189403729001,
+      "grad_norm": 1.048113515822863,
+      "learning_rate": 1.6614038111289034e-07,
+      "loss": 0.2429,
+      "step": 319
+    },
+    {
+      "epoch": 0.9451726047627839,
+      "grad_norm": 1.650208720659303,
+      "learning_rate": 1.49154607348051e-07,
+      "loss": 0.273,
+      "step": 320
+    },
+    {
+      "epoch": 0.9481262691526675,
+      "grad_norm": 0.8862126425841627,
+      "learning_rate": 1.330780649350938e-07,
+      "loss": 0.229,
+      "step": 321
+    },
+    {
+      "epoch": 0.9510799335425513,
+      "grad_norm": 1.3008396761106353,
+      "learning_rate": 1.1791223773614635e-07,
+      "loss": 0.2084,
+      "step": 322
+    },
+    {
+      "epoch": 0.9540335979324349,
+      "grad_norm": 1.2411283844792398,
+      "learning_rate": 1.0365852555447642e-07,
+      "loss": 0.2308,
+      "step": 323
+    },
+    {
+      "epoch": 0.9569872623223187,
+      "grad_norm": 2.1540616271945563,
+      "learning_rate": 9.031824400528854e-08,
+      "loss": 0.2664,
+      "step": 324
+    },
+    {
+      "epoch": 0.9599409267122023,
+      "grad_norm": 0.9623032655438389,
+      "learning_rate": 7.789262439430012e-08,
+      "loss": 0.253,
+      "step": 325
+    },
+    {
+      "epoch": 0.962894591102086,
+      "grad_norm": 1.5329453334978849,
+      "learning_rate": 6.638281360408339e-08,
+      "loss": 0.2565,
+      "step": 326
+    },
+    {
+      "epoch": 0.9658482554919697,
+      "grad_norm": 1.8116742792949059,
+      "learning_rate": 5.578987398821345e-08,
+      "loss": 0.1815,
+      "step": 327
+    },
+    {
+      "epoch": 0.9688019198818534,
+      "grad_norm": 1.1469022052933218,
+      "learning_rate": 4.6114783273213395e-08,
+      "loss": 0.1761,
+      "step": 328
+    },
+    {
+      "epoch": 0.9717555842717371,
+      "grad_norm": 1.3429884598164736,
+      "learning_rate": 3.735843446830867e-08,
+      "loss": 0.2152,
+      "step": 329
+    },
+    {
+      "epoch": 0.9747092486616208,
+      "grad_norm": 1.06929888763052,
+      "learning_rate": 2.9521635783001932e-08,
+      "loss": 0.3005,
+      "step": 330
+    },
+    {
+      "epoch": 0.9776629130515045,
+      "grad_norm": 0.94720389771271,
+      "learning_rate": 2.2605110552477162e-08,
+      "loss": 0.2281,
+      "step": 331
+    },
+    {
+      "epoch": 0.9806165774413882,
+      "grad_norm": 1.4632786705472418,
+      "learning_rate": 1.6609497170834154e-08,
+      "loss": 0.2023,
+      "step": 332
+    },
+    {
+      "epoch": 0.983570241831272,
+      "grad_norm": 0.920915062499091,
+      "learning_rate": 1.1535349032167908e-08,
+      "loss": 0.2609,
+      "step": 333
+    },
+    {
+      "epoch": 0.9865239062211556,
+      "grad_norm": 0.9150221985245088,
+      "learning_rate": 7.3831344794872415e-09,
+      "loss": 0.2174,
+      "step": 334
+    },
+    {
+      "epoch": 0.9894775706110394,
+      "grad_norm": 1.4231218123910203,
+      "learning_rate": 4.153236761488266e-09,
+      "loss": 0.2448,
+      "step": 335
+    },
+    {
+      "epoch": 0.992431235000923,
+      "grad_norm": 1.4419487005726424,
+      "learning_rate": 1.8459539971804608e-09,
+      "loss": 0.247,
+      "step": 336
+    },
+    {
+      "epoch": 0.9953848993908068,
+      "grad_norm": 1.5776000940081785,
+      "learning_rate": 4.614991483686826e-10,
+      "loss": 0.2729,
+      "step": 337
+    },
+    {
+      "epoch": 0.9983385637806904,
+      "grad_norm": 1.218373936040361,
+      "learning_rate": 0.0,
+      "loss": 0.2897,
+      "step": 338
+    },
+    {
+      "epoch": 0.9983385637806904,
+      "step": 338,
+      "total_flos": 405222433030144.0,
+      "train_loss": 0.2837119762449575,
+      "train_runtime": 5278.9341,
+      "train_samples_per_second": 8.209,
+      "train_steps_per_second": 0.064
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 338,
+  "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": 405222433030144.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7079d683dca335b320de12eddf2246b247abba44c0a0529902b2abc271ca265d
+size 7224