Upload folder using huggingface_hub

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<image>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/config.json

@@ -0,0 +1,221 @@
+{
+  "_name_or_path": "lmms-lab/llava-onevision-qwen2-7b-si",
+  "add_faster_video": false,
+  "add_time_instruction": true,
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": true,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "ignore_index": -100,
+  "image_aspect_ratio": "anyres_max_9",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      768,
+      1920
+    ],
+    [
+      768,
+      2304
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      1152,
+      1152
+    ],
+    [
+      1152,
+      1536
+    ],
+    [
+      1152,
+      1920
+    ],
+    [
+      1152,
+      2304
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      1536,
+      1152
+    ],
+    [
+      1536,
+      1536
+    ],
+    [
+      1536,
+      1920
+    ],
+    [
+      1536,
+      2304
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      1920,
+      768
+    ],
+    [
+      1920,
+      1152
+    ],
+    [
+      1920,
+      1536
+    ],
+    [
+      1920,
+      1920
+    ],
+    [
+      1920,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      2304,
+      768
+    ],
+    [
+      2304,
+      1152
+    ],
+    [
+      2304,
+      1536
+    ],
+    [
+      2304,
+      1920
+    ],
+    [
+      2304,
+      2304
+    ]
+  ],
+  "image_split_resolution": null,
+  "image_token_index": 151646,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_spatial_pool_stride": 2,
+  "mm_tunable_parts": "mm_vision_tower",
+  "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": "google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llava",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pos_skipping_range": 4096,
+  "projector_hidden_act": "gelu",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "text_config": {
+    "model_type": "llama"
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 32768,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vision_tower_pretrained": null
+}

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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": "4.40.0.dev0"
+}

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e55e199d7279d35dbe3f81bd92d122ea70cda8e73217d2c12333b288fccaf05
+size 4877668032

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea026bd3efa2621af6b14d0f47795663986b264c6d2965bdf195253f3f9a300
+size 4932751008

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4161e6f6a4be71a3d8b08f453f8e6d5fa411621f42a3a8fe6c55e533483619
+size 4994571904

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29bb1695c809ae1ec1a8b3a239b6b27d3176f6bf2b2b9f03f8427d9399cd8e57
+size 1255812224

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/model.safetensors.index.json

@@ -0,0 +1,772 @@
+{
+  "metadata": {
+    "total_size": 16060697664
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.image_newline": "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-00004-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "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-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
+  }
+}

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/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
+  }
+}

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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
+    },
+    "151646": {
+      "content": "<image>",
+      "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/trainer_state.json

@@ -0,0 +1,2655 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.6711267187562766,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.5596,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.3669321871979832,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.8544,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.9109019132590702,
+      "learning_rate": 2.5e-06,
+      "loss": 0.5811,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.0184062682776156,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.696,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.7175661136324879,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.5641,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.7092872300252631,
+      "learning_rate": 5e-06,
+      "loss": 0.4397,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.6973252905091321,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.5948,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2243332689054096,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7624,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.152317296431991,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7317,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.6743241498314535,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.596,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.0078100147956144,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.5015,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.2392639814445237,
+      "learning_rate": 1e-05,
+      "loss": 0.7438,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.9853750523720064,
+      "learning_rate": 9.999812749151968e-06,
+      "loss": 0.7353,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.1066049251921286,
+      "learning_rate": 9.99925101063302e-06,
+      "loss": 0.6318,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.003746386844725,
+      "learning_rate": 9.998314826517564e-06,
+      "loss": 0.6023,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2771224646488821,
+      "learning_rate": 9.997004266926105e-06,
+      "loss": 0.7657,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.7200246465223197,
+      "learning_rate": 9.995319430020004e-06,
+      "loss": 0.6033,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9199228489518354,
+      "learning_rate": 9.993260441994116e-06,
+      "loss": 0.5058,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9737034069620627,
+      "learning_rate": 9.990827457067342e-06,
+      "loss": 0.5832,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.2457613299929884,
+      "learning_rate": 9.988020657471078e-06,
+      "loss": 0.6205,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.6838077541975052,
+      "learning_rate": 9.984840253435569e-06,
+      "loss": 0.6321,
+      "step": 21
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.2688711243064799,
+      "learning_rate": 9.98128648317415e-06,
+      "loss": 0.4966,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.2075301405016,
+      "learning_rate": 9.977359612865424e-06,
+      "loss": 0.5672,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.3954003921464848,
+      "learning_rate": 9.973059936633308e-06,
+      "loss": 0.5425,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.6031726137588147,
+      "learning_rate": 9.968387776525009e-06,
+      "loss": 0.5863,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.359474076859349,
+      "learning_rate": 9.963343482486907e-06,
+      "loss": 0.6257,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.3129249414637645,
+      "learning_rate": 9.957927432338332e-06,
+      "loss": 0.5115,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.5580716032886142,
+      "learning_rate": 9.952140031743282e-06,
+      "loss": 0.5134,
+      "step": 28
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2693596277201307,
+      "learning_rate": 9.945981714180021e-06,
+      "loss": 0.5353,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.8105625079146115,
+      "learning_rate": 9.939452940908627e-06,
+      "loss": 0.6146,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0298529692729361,
+      "learning_rate": 9.932554200936428e-06,
+      "loss": 0.4504,
+      "step": 31
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.255856527068645,
+      "learning_rate": 9.925286010981394e-06,
+      "loss": 0.3659,
+      "step": 32
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.1273193754187087,
+      "learning_rate": 9.917648915433413e-06,
+      "loss": 0.4852,
+      "step": 33
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.9690305443581672,
+      "learning_rate": 9.909643486313533e-06,
+      "loss": 0.3931,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.2546625381149885,
+      "learning_rate": 9.901270323231114e-06,
+      "loss": 0.5204,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.677861692623221,
+      "learning_rate": 9.892530053338909e-06,
+      "loss": 0.763,
+      "step": 36
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.2367429869788005,
+      "learning_rate": 9.883423331286096e-06,
+      "loss": 0.5453,
+      "step": 37
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.819639818634355,
+      "learning_rate": 9.873950839169248e-06,
+      "loss": 0.4237,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.73776336639331,
+      "learning_rate": 9.864113286481237e-06,
+      "loss": 0.4741,
+      "step": 39
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.2074050938830103,
+      "learning_rate": 9.853911410058097e-06,
+      "loss": 0.3968,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.217258191607437,
+      "learning_rate": 9.843345974023833e-06,
+      "loss": 0.4297,
+      "step": 41
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.7420139975012436,
+      "learning_rate": 9.832417769733185e-06,
+      "loss": 0.5065,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.8982245227023504,
+      "learning_rate": 9.821127615712365e-06,
+      "loss": 0.4307,
+      "step": 43
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.2823585090798764,
+      "learning_rate": 9.809476357597738e-06,
+      "loss": 0.5852,
+      "step": 44
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.5892120080631182,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 0.5499,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.415033892017002,
+      "learning_rate": 9.785094046801256e-06,
+      "loss": 0.6176,
+      "step": 46
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.1959978768664865,
+      "learning_rate": 9.77236482036275e-06,
+      "loss": 0.4928,
+      "step": 47
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.0485951107661133,
+      "learning_rate": 9.759278142180348e-06,
+      "loss": 0.5798,
+      "step": 48
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.781509897090649,
+      "learning_rate": 9.745834992450688e-06,
+      "loss": 0.4542,
+      "step": 49
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.7380254605988925,
+      "learning_rate": 9.732036378070243e-06,
+      "loss": 0.6785,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.096213930662671,
+      "learning_rate": 9.717883332559911e-06,
+      "loss": 0.467,
+      "step": 51
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.4317850994189496,
+      "learning_rate": 9.703376915987601e-06,
+      "loss": 0.5226,
+      "step": 52
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.7801405061281884,
+      "learning_rate": 9.688518214888836e-06,
+      "loss": 0.3703,
+      "step": 53
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8576713778874969,
+      "learning_rate": 9.673308342185366e-06,
+      "loss": 0.3825,
+      "step": 54
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.3014234469188866,
+      "learning_rate": 9.657748437101819e-06,
+      "loss": 0.4878,
+      "step": 55
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.2097090016520846,
+      "learning_rate": 9.641839665080363e-06,
+      "loss": 0.4109,
+      "step": 56
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.9761366785932536,
+      "learning_rate": 9.625583217693419e-06,
+      "loss": 0.4912,
+      "step": 57
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.7165005735527354,
+      "learning_rate": 9.60898031255441e-06,
+      "loss": 0.6785,
+      "step": 58
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9806213357736829,
+      "learning_rate": 9.592032193226564e-06,
+      "loss": 0.4339,
+      "step": 59
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.4589182949335622,
+      "learning_rate": 9.574740129129767e-06,
+      "loss": 0.6235,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.4568175593538273,
+      "learning_rate": 9.557105415445485e-06,
+      "loss": 0.5636,
+      "step": 61
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.2579234055293798,
+      "learning_rate": 9.539129373019755e-06,
+      "loss": 0.514,
+      "step": 62
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.0830690806330578,
+      "learning_rate": 9.520813348264252e-06,
+      "loss": 0.5787,
+      "step": 63
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.6927828619147741,
+      "learning_rate": 9.502158713055444e-06,
+      "loss": 0.3934,
+      "step": 64
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.2159192154689418,
+      "learning_rate": 9.483166864631837e-06,
+      "loss": 0.4235,
+      "step": 65
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.1365635420329332,
+      "learning_rate": 9.46383922548932e-06,
+      "loss": 0.588,
+      "step": 66
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.9581318368685685,
+      "learning_rate": 9.444177243274619e-06,
+      "loss": 0.3413,
+      "step": 67
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.1187661169539564,
+      "learning_rate": 9.424182390676872e-06,
+      "loss": 0.4884,
+      "step": 68
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.682885559803617,
+      "learning_rate": 9.403856165317322e-06,
+      "loss": 0.585,
+      "step": 69
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.1023071688691886,
+      "learning_rate": 9.383200089637143e-06,
+      "loss": 0.3684,
+      "step": 70
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.8801077023553932,
+      "learning_rate": 9.362215710783411e-06,
+      "loss": 0.3807,
+      "step": 71
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.6344636928833465,
+      "learning_rate": 9.34090460049322e-06,
+      "loss": 0.4829,
+      "step": 72
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.1370024945494468,
+      "learning_rate": 9.319268354975958e-06,
+      "loss": 0.4865,
+      "step": 73
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.505384534129854,
+      "learning_rate": 9.297308594793757e-06,
+      "loss": 0.4341,
+      "step": 74
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7115604185943166,
+      "learning_rate": 9.275026964740101e-06,
+      "loss": 0.3789,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9150052018114226,
+      "learning_rate": 9.252425133716639e-06,
+      "loss": 0.4014,
+      "step": 76
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.5962704856896133,
+      "learning_rate": 9.229504794608182e-06,
+      "loss": 0.5954,
+      "step": 77
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.9734643443866443,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 0.4349,
+      "step": 78
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.7010965100066101,
+      "learning_rate": 9.182715482828764e-06,
+      "loss": 0.3799,
+      "step": 79
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.4280669887966977,
+      "learning_rate": 9.158850014693123e-06,
+      "loss": 0.4953,
+      "step": 80
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.668306940053885,
+      "learning_rate": 9.134673047280644e-06,
+      "loss": 0.5568,
+      "step": 81
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.396095562786626,
+      "learning_rate": 9.110186391454389e-06,
+      "loss": 0.3713,
+      "step": 82
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.2888502453064903,
+      "learning_rate": 9.085391881273182e-06,
+      "loss": 0.4109,
+      "step": 83
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.264357366842386,
+      "learning_rate": 9.060291373854252e-06,
+      "loss": 0.4019,
+      "step": 84
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.9690457112167321,
+      "learning_rate": 9.034886749234112e-06,
+      "loss": 0.3809,
+      "step": 85
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.2568163860173298,
+      "learning_rate": 9.009179910227767e-06,
+      "loss": 0.4765,
+      "step": 86
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.3290469887551444,
+      "learning_rate": 8.98317278228618e-06,
+      "loss": 0.4596,
+      "step": 87
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.973036312115464,
+      "learning_rate": 8.956867313352055e-06,
+      "loss": 0.3799,
+      "step": 88
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.242958762266794,
+      "learning_rate": 8.930265473713939e-06,
+      "loss": 0.5409,
+      "step": 89
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.9301428706071964,
+      "learning_rate": 8.90336925585864e-06,
+      "loss": 0.4584,
+      "step": 90
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.4944960022992793,
+      "learning_rate": 8.876180674322006e-06,
+      "loss": 0.4012,
+      "step": 91
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.6839226978552402,
+      "learning_rate": 8.84870176553801e-06,
+      "loss": 0.4674,
+      "step": 92
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3947319874721409,
+      "learning_rate": 8.820934587686247e-06,
+      "loss": 0.3818,
+      "step": 93
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3269960931803961,
+      "learning_rate": 8.792881220537752e-06,
+      "loss": 0.3954,
+      "step": 94
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.073715268413767,
+      "learning_rate": 8.764543765299245e-06,
+      "loss": 0.3544,
+      "step": 95
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.0691872907802231,
+      "learning_rate": 8.735924344455732e-06,
+      "loss": 0.3358,
+      "step": 96
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1392988873956975,
+      "learning_rate": 8.707025101611546e-06,
+      "loss": 0.3736,
+      "step": 97
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1276502307277065,
+      "learning_rate": 8.677848201329775e-06,
+      "loss": 0.2964,
+      "step": 98
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.0843270251298762,
+      "learning_rate": 8.64839582897015e-06,
+      "loss": 0.3143,
+      "step": 99
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.3703330926510682,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.3358,
+      "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.7367372933251561,
+      "learning_rate": 8.588673512455781e-06,
+      "loss": 0.3486,
+      "step": 101
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.990606804443138,
+      "learning_rate": 8.558408041522801e-06,
+      "loss": 0.3472,
+      "step": 102
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.3773026858144821,
+      "learning_rate": 8.527876044620453e-06,
+      "loss": 0.3524,
+      "step": 103
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.5431869329106156,
+      "learning_rate": 8.497079808605659e-06,
+      "loss": 0.3878,
+      "step": 104
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.151204763217006,
+      "learning_rate": 8.466021640126946e-06,
+      "loss": 0.3697,
+      "step": 105
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.7968092185914961,
+      "learning_rate": 8.434703865451666e-06,
+      "loss": 0.3228,
+      "step": 106
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 2.284296398717193,
+      "learning_rate": 8.403128830291767e-06,
+      "loss": 0.4377,
+      "step": 107
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.2785866437780706,
+      "learning_rate": 8.371298899628091e-06,
+      "loss": 0.3555,
+      "step": 108
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.2789734680874216,
+      "learning_rate": 8.339216457533244e-06,
+      "loss": 0.3305,
+      "step": 109
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.3473939547007117,
+      "learning_rate": 8.306883906993022e-06,
+      "loss": 0.3163,
+      "step": 110
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.238511738328111,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 0.3763,
+      "step": 111
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.4219666789106928,
+      "learning_rate": 8.24147818600428e-06,
+      "loss": 0.3168,
+      "step": 112
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2488987632377448,
+      "learning_rate": 8.20840991446645e-06,
+      "loss": 0.2877,
+      "step": 113
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.9045610282392258,
+      "learning_rate": 8.175101331937692e-06,
+      "loss": 0.3078,
+      "step": 114
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 2.7250332387681713,
+      "learning_rate": 8.141554933242135e-06,
+      "loss": 0.3584,
+      "step": 115
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.0724368393129782,
+      "learning_rate": 8.10777323101642e-06,
+      "loss": 0.2842,
+      "step": 116
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.4207729424332025,
+      "learning_rate": 8.073758755521506e-06,
+      "loss": 0.373,
+      "step": 117
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.8791837241326725,
+      "learning_rate": 8.03951405445314e-06,
+      "loss": 0.2401,
+      "step": 118
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.167152168531044,
+      "learning_rate": 8.005041692751055e-06,
+      "loss": 0.302,
+      "step": 119
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3202159063987837,
+      "learning_rate": 7.970344252406832e-06,
+      "loss": 0.3239,
+      "step": 120
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.14441333716959,
+      "learning_rate": 7.935424332270523e-06,
+      "loss": 0.3154,
+      "step": 121
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1221115336765681,
+      "learning_rate": 7.900284547855992e-06,
+      "loss": 0.3298,
+      "step": 122
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.0025343179423416,
+      "learning_rate": 7.864927531145012e-06,
+      "loss": 0.3774,
+      "step": 123
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.7308036028190243,
+      "learning_rate": 7.829355930390126e-06,
+      "loss": 0.3743,
+      "step": 124
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2505392456229392,
+      "learning_rate": 7.7935724099163e-06,
+      "loss": 0.304,
+      "step": 125
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.7292798832662777,
+      "learning_rate": 7.757579649921354e-06,
+      "loss": 0.3015,
+      "step": 126
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.3998222514085483,
+      "learning_rate": 7.721380346275221e-06,
+      "loss": 0.2618,
+      "step": 127
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.8754223056184315,
+      "learning_rate": 7.684977210318024e-06,
+      "loss": 0.2246,
+      "step": 128
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.6543501493416324,
+      "learning_rate": 7.648372968656995e-06,
+      "loss": 0.3435,
+      "step": 129
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.598494111407793,
+      "learning_rate": 7.611570362962247e-06,
+      "loss": 0.333,
+      "step": 130
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.001776814196774,
+      "learning_rate": 7.574572149761437e-06,
+      "loss": 0.3597,
+      "step": 131
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.5269042263534056,
+      "learning_rate": 7.5373811002332785e-06,
+      "loss": 0.2788,
+      "step": 132
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.3845817660815585,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2798,
+      "step": 133
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1095331739120862,
+      "learning_rate": 7.462431648918689e-06,
+      "loss": 0.2507,
+      "step": 134
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.971959954883552,
+      "learning_rate": 7.424678860871584e-06,
+      "loss": 0.2611,
+      "step": 135
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.7307715841355622,
+      "learning_rate": 7.3867444635553165e-06,
+      "loss": 0.3228,
+      "step": 136
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.5294650029664811,
+      "learning_rate": 7.3486312982691134e-06,
+      "loss": 0.2883,
+      "step": 137
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.4823781102997002,
+      "learning_rate": 7.310342219701981e-06,
+      "loss": 0.3574,
+      "step": 138
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.8917100975212073,
+      "learning_rate": 7.271880095718895e-06,
+      "loss": 0.3337,
+      "step": 139
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.874543622498554,
+      "learning_rate": 7.233247807145989e-06,
+      "loss": 0.3349,
+      "step": 140
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.3117302146814291,
+      "learning_rate": 7.19444824755478e-06,
+      "loss": 0.2148,
+      "step": 141
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.5371546554383115,
+      "learning_rate": 7.155484323045442e-06,
+      "loss": 0.3045,
+      "step": 142
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.7716248014455815,
+      "learning_rate": 7.11635895202914e-06,
+      "loss": 0.2607,
+      "step": 143
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.6783205748207581,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 0.2533,
+      "step": 144
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.260990403403975,
+      "learning_rate": 7.037635604362786e-06,
+      "loss": 0.2353,
+      "step": 145
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.164244577831506,
+      "learning_rate": 6.9980435241181785e-06,
+      "loss": 0.2519,
+      "step": 146
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.4799726455867968,
+      "learning_rate": 6.958301789735853e-06,
+      "loss": 0.2234,
+      "step": 147
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.600275860191559,
+      "learning_rate": 6.918413377885193e-06,
+      "loss": 0.2597,
+      "step": 148
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1781203286518527,
+      "learning_rate": 6.878381276221777e-06,
+      "loss": 0.1988,
+      "step": 149
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.905547897145102,
+      "learning_rate": 6.838208483163601e-06,
+      "loss": 0.3296,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.1990202911101893,
+      "learning_rate": 6.797898007666493e-06,
+      "loss": 0.2252,
+      "step": 151
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.455920439458587,
+      "learning_rate": 6.757452868998737e-06,
+      "loss": 0.2968,
+      "step": 152
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.5747748150207377,
+      "learning_rate": 6.716876096514944e-06,
+      "loss": 0.2171,
+      "step": 153
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.6459032306720125,
+      "learning_rate": 6.676170729429132e-06,
+      "loss": 0.2285,
+      "step": 154
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.061441007052434,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.2317,
+      "step": 155
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.9858771872403316,
+      "learning_rate": 6.594386416238095e-06,
+      "loss": 0.2821,
+      "step": 156
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.01267315011427,
+      "learning_rate": 6.553313595805666e-06,
+      "loss": 0.2569,
+      "step": 157
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.4672048965301339,
+      "learning_rate": 6.512124431658006e-06,
+      "loss": 0.2198,
+      "step": 158
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.4901032442839597,
+      "learning_rate": 6.470822008877482e-06,
+      "loss": 0.2314,
+      "step": 159
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.4454501030382882,
+      "learning_rate": 6.4294094210295725e-06,
+      "loss": 0.2283,
+      "step": 160
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 6.516845523649235,
+      "learning_rate": 6.3878897699311525e-06,
+      "loss": 0.2526,
+      "step": 161
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.2093600534449003,
+      "learning_rate": 6.346266165418173e-06,
+      "loss": 0.2035,
+      "step": 162
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.276483290162287,
+      "learning_rate": 6.304541725112734e-06,
+      "loss": 0.1966,
+      "step": 163
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.3796393100896127,
+      "learning_rate": 6.262719574189564e-06,
+      "loss": 0.2054,
+      "step": 164
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6845618659747361,
+      "learning_rate": 6.2208028451419575e-06,
+      "loss": 0.2182,
+      "step": 165
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6898751610013216,
+      "learning_rate": 6.178794677547138e-06,
+      "loss": 0.1938,
+      "step": 166
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.7912564112448242,
+      "learning_rate": 6.136698217831106e-06,
+      "loss": 0.2239,
+      "step": 167
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.0316103794465614,
+      "learning_rate": 6.094516619032975e-06,
+      "loss": 0.2393,
+      "step": 168
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.3588139795898466,
+      "learning_rate": 6.052253040568804e-06,
+      "loss": 0.2265,
+      "step": 169
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.731395194988873,
+      "learning_rate": 6.009910647994956e-06,
+      "loss": 0.2387,
+      "step": 170
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.2798608365532833,
+      "learning_rate": 5.967492612770999e-06,
+      "loss": 0.293,
+      "step": 171
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6697082303577055,
+      "learning_rate": 5.925002112022158e-06,
+      "loss": 0.2115,
+      "step": 172
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.2971719234336436,
+      "learning_rate": 5.882442328301356e-06,
+      "loss": 0.2427,
+      "step": 173
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.1838203808378158,
+      "learning_rate": 5.839816449350824e-06,
+      "loss": 0.231,
+      "step": 174
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.9528745373450809,
+      "learning_rate": 5.7971276678633625e-06,
+      "loss": 0.2172,
+      "step": 175
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.5576690576607024,
+      "learning_rate": 5.754379181243179e-06,
+      "loss": 0.2273,
+      "step": 176
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.5052221197653346,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 0.2564,
+      "step": 177
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.0545021051200707,
+      "learning_rate": 5.668715904341365e-06,
+      "loss": 0.2173,
+      "step": 178
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.4156406626487668,
+      "learning_rate": 5.62580753026823e-06,
+      "loss": 0.2585,
+      "step": 179
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3544621765194202,
+      "learning_rate": 5.5828522829987965e-06,
+      "loss": 0.197,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.7307249887468672,
+      "learning_rate": 5.539853379895656e-06,
+      "loss": 0.2484,
+      "step": 181
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.5742742862788535,
+      "learning_rate": 5.496814041591234e-06,
+      "loss": 0.2111,
+      "step": 182
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 2.1237818250734892,
+      "learning_rate": 5.453737491746572e-06,
+      "loss": 0.2076,
+      "step": 183
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.6808557868966725,
+      "learning_rate": 5.410626956809864e-06,
+      "loss": 0.2075,
+      "step": 184
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.7783926541749946,
+      "learning_rate": 5.367485665774802e-06,
+      "loss": 0.2175,
+      "step": 185
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.0403325243543136,
+      "learning_rate": 5.324316849938715e-06,
+      "loss": 0.2546,
+      "step": 186
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8981213500870242,
+      "learning_rate": 5.281123742660558e-06,
+      "loss": 0.2969,
+      "step": 187
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8024578255203776,
+      "learning_rate": 5.237909579118713e-06,
+      "loss": 0.2617,
+      "step": 188
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0970881848132787,
+      "learning_rate": 5.194677596068689e-06,
+      "loss": 0.2196,
+      "step": 189
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 2.6982531221174875,
+      "learning_rate": 5.1514310316006835e-06,
+      "loss": 0.2513,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.7272262251972244,
+      "learning_rate": 5.1081731248970435e-06,
+      "loss": 0.2113,
+      "step": 191
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.0101065698469625,
+      "learning_rate": 5.064907115989655e-06,
+      "loss": 0.181,
+      "step": 192
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.5791632339006783,
+      "learning_rate": 5.021636245517261e-06,
+      "loss": 0.2044,
+      "step": 193
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.4304884175735106,
+      "learning_rate": 4.978363754482741e-06,
+      "loss": 0.2502,
+      "step": 194
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.4391730942143188,
+      "learning_rate": 4.935092884010347e-06,
+      "loss": 0.2447,
+      "step": 195
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.976760247516797,
+      "learning_rate": 4.891826875102958e-06,
+      "loss": 0.2453,
+      "step": 196
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.340462410275216,
+      "learning_rate": 4.848568968399317e-06,
+      "loss": 0.1846,
+      "step": 197
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.0353383484319085,
+      "learning_rate": 4.805322403931312e-06,
+      "loss": 0.2,
+      "step": 198
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.7448321752506524,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.2016,
+      "step": 199
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.022124752419934,
+      "learning_rate": 4.718876257339444e-06,
+      "loss": 0.1809,
+      "step": 200
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.0534761374666912,
+      "learning_rate": 4.6756831500612846e-06,
+      "loss": 0.1984,
+      "step": 201
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1214718709551037,
+      "learning_rate": 4.632514334225201e-06,
+      "loss": 0.2058,
+      "step": 202
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.102478510487434,
+      "learning_rate": 4.589373043190137e-06,
+      "loss": 0.1788,
+      "step": 203
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.003339696533222,
+      "learning_rate": 4.546262508253429e-06,
+      "loss": 0.2138,
+      "step": 204
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.2631193102660385,
+      "learning_rate": 4.503185958408767e-06,
+      "loss": 0.1873,
+      "step": 205
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.1329459627426175,
+      "learning_rate": 4.460146620104347e-06,
+      "loss": 0.1859,
+      "step": 206
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.7623718436501588,
+      "learning_rate": 4.417147717001205e-06,
+      "loss": 0.1778,
+      "step": 207
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.360897561153888,
+      "learning_rate": 4.374192469731771e-06,
+      "loss": 0.2144,
+      "step": 208
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.719481299673356,
+      "learning_rate": 4.331284095658637e-06,
+      "loss": 0.1782,
+      "step": 209
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.3323810842155317,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.1843,
+      "step": 210
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.3445572161334918,
+      "learning_rate": 4.245620818756822e-06,
+      "loss": 0.2135,
+      "step": 211
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 2.5433301647077835,
+      "learning_rate": 4.202872332136639e-06,
+      "loss": 0.1716,
+      "step": 212
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.8590988667451764,
+      "learning_rate": 4.160183550649176e-06,
+      "loss": 0.2379,
+      "step": 213
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.7486923849602685,
+      "learning_rate": 4.117557671698648e-06,
+      "loss": 0.1763,
+      "step": 214
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.8418916232196894,
+      "learning_rate": 4.074997887977843e-06,
+      "loss": 0.1711,
+      "step": 215
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.235610990820909,
+      "learning_rate": 4.032507387229002e-06,
+      "loss": 0.2319,
+      "step": 216
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.7643425154320762,
+      "learning_rate": 3.9900893520050446e-06,
+      "loss": 0.2592,
+      "step": 217
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.381913734496923,
+      "learning_rate": 3.9477469594311975e-06,
+      "loss": 0.1856,
+      "step": 218
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.7091959750645167,
+      "learning_rate": 3.905483380967027e-06,
+      "loss": 0.2211,
+      "step": 219
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.4966367560394092,
+      "learning_rate": 3.863301782168896e-06,
+      "loss": 0.2159,
+      "step": 220
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.7652861024341437,
+      "learning_rate": 3.821205322452863e-06,
+      "loss": 0.1851,
+      "step": 221
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.4167707436739405,
+      "learning_rate": 3.779197154858044e-06,
+      "loss": 0.1947,
+      "step": 222
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.613815918227562,
+      "learning_rate": 3.7372804258104367e-06,
+      "loss": 0.2119,
+      "step": 223
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.293929971018336,
+      "learning_rate": 3.695458274887268e-06,
+      "loss": 0.2112,
+      "step": 224
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.7929854440612267,
+      "learning_rate": 3.6537338345818273e-06,
+      "loss": 0.1907,
+      "step": 225
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.3966747957732302,
+      "learning_rate": 3.6121102300688504e-06,
+      "loss": 0.2011,
+      "step": 226
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 2.028526319678531,
+      "learning_rate": 3.5705905789704296e-06,
+      "loss": 0.2194,
+      "step": 227
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.0247798038098892,
+      "learning_rate": 3.529177991122519e-06,
+      "loss": 0.193,
+      "step": 228
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 2.4449023632136915,
+      "learning_rate": 3.487875568341995e-06,
+      "loss": 0.2684,
+      "step": 229
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.3957752861316721,
+      "learning_rate": 3.446686404194337e-06,
+      "loss": 0.2043,
+      "step": 230
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.0041975596630217,
+      "learning_rate": 3.4056135837619077e-06,
+      "loss": 0.2357,
+      "step": 231
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.424008111001868,
+      "learning_rate": 3.3646601834128924e-06,
+      "loss": 0.2114,
+      "step": 232
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.7851200794790578,
+      "learning_rate": 3.3238292705708675e-06,
+      "loss": 0.2527,
+      "step": 233
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9781714837023094,
+      "learning_rate": 3.2831239034850593e-06,
+      "loss": 0.1743,
+      "step": 234
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.8496452019635998,
+      "learning_rate": 3.2425471310012645e-06,
+      "loss": 0.1656,
+      "step": 235
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.8109204979985765,
+      "learning_rate": 3.2021019923335093e-06,
+      "loss": 0.1815,
+      "step": 236
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.1630126935696823,
+      "learning_rate": 3.1617915168363994e-06,
+      "loss": 0.2126,
+      "step": 237
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.892359990650481,
+      "learning_rate": 3.121618723778225e-06,
+      "loss": 0.2284,
+      "step": 238
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.144770490883956,
+      "learning_rate": 3.081586622114809e-06,
+      "loss": 0.166,
+      "step": 239
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3033242624563122,
+      "learning_rate": 3.041698210264149e-06,
+      "loss": 0.2239,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.4688215894012941,
+      "learning_rate": 3.001956475881822e-06,
+      "loss": 0.1935,
+      "step": 241
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.2971556376599849,
+      "learning_rate": 2.962364395637216e-06,
+      "loss": 0.1756,
+      "step": 242
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.3581783462277541,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 0.1853,
+      "step": 243
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.2428268166914216,
+      "learning_rate": 2.8836410479708625e-06,
+      "loss": 0.2495,
+      "step": 244
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.47585286789941,
+      "learning_rate": 2.84451567695456e-06,
+      "loss": 0.2192,
+      "step": 245
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.9852844773610605,
+      "learning_rate": 2.805551752445222e-06,
+      "loss": 0.2455,
+      "step": 246
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.240444492715871,
+      "learning_rate": 2.766752192854012e-06,
+      "loss": 0.1994,
+      "step": 247
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.7994151976357682,
+      "learning_rate": 2.728119904281105e-06,
+      "loss": 0.2021,
+      "step": 248
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.417781075170001,
+      "learning_rate": 2.689657780298019e-06,
+      "loss": 0.1907,
+      "step": 249
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.2212820850498616,
+      "learning_rate": 2.651368701730889e-06,
+      "loss": 0.1693,
+      "step": 250
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.9619524388329801,
+      "learning_rate": 2.6132555364446856e-06,
+      "loss": 0.1567,
+      "step": 251
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0205076026788809,
+      "learning_rate": 2.5753211391284172e-06,
+      "loss": 0.157,
+      "step": 252
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.3181036995239204,
+      "learning_rate": 2.537568351081311e-06,
+      "loss": 0.1933,
+      "step": 253
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.8352517699362205,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1866,
+      "step": 254
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0362931790772913,
+      "learning_rate": 2.4626188997667224e-06,
+      "loss": 0.18,
+      "step": 255
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.297358908221885,
+      "learning_rate": 2.425427850238565e-06,
+      "loss": 0.184,
+      "step": 256
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.944034748569574,
+      "learning_rate": 2.388429637037753e-06,
+      "loss": 0.158,
+      "step": 257
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.385137248795438,
+      "learning_rate": 2.3516270313430085e-06,
+      "loss": 0.2079,
+      "step": 258
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.1437540625000946,
+      "learning_rate": 2.3150227896819782e-06,
+      "loss": 0.1963,
+      "step": 259
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.5628709634248554,
+      "learning_rate": 2.278619653724781e-06,
+      "loss": 0.1881,
+      "step": 260
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.6145185337247683,
+      "learning_rate": 2.2424203500786473e-06,
+      "loss": 0.1818,
+      "step": 261
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4267807831596866,
+      "learning_rate": 2.206427590083703e-06,
+      "loss": 0.1935,
+      "step": 262
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.769421488052719,
+      "learning_rate": 2.170644069609876e-06,
+      "loss": 0.2216,
+      "step": 263
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.8967760746254942,
+      "learning_rate": 2.1350724688549906e-06,
+      "loss": 0.2347,
+      "step": 264
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.8198202980708036,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.2508,
+      "step": 265
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.862448043832358,
+      "learning_rate": 2.0645756677294788e-06,
+      "loss": 0.2759,
+      "step": 266
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.2356865814926912,
+      "learning_rate": 2.029655747593169e-06,
+      "loss": 0.1913,
+      "step": 267
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.0654404028361557,
+      "learning_rate": 1.9949583072489455e-06,
+      "loss": 0.1865,
+      "step": 268
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.237405792893722,
+      "learning_rate": 1.9604859455468587e-06,
+      "loss": 0.1907,
+      "step": 269
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3018469753474626,
+      "learning_rate": 1.926241244478496e-06,
+      "loss": 0.2018,
+      "step": 270
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0890680773126107,
+      "learning_rate": 1.8922267689835806e-06,
+      "loss": 0.2105,
+      "step": 271
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.495048003334895,
+      "learning_rate": 1.8584450667578656e-06,
+      "loss": 0.2293,
+      "step": 272
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 2.1448614464501916,
+      "learning_rate": 1.8248986680623077e-06,
+      "loss": 0.2021,
+      "step": 273
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.3822593620590728,
+      "learning_rate": 1.7915900855335506e-06,
+      "loss": 0.1701,
+      "step": 274
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.1422794678348713,
+      "learning_rate": 1.7585218139957205e-06,
+      "loss": 0.188,
+      "step": 275
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.114109258975923,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 0.2025,
+      "step": 276
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.306403990082721,
+      "learning_rate": 1.6931160930069789e-06,
+      "loss": 0.2113,
+      "step": 277
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.142528386777687,
+      "learning_rate": 1.6607835424667578e-06,
+      "loss": 0.1536,
+      "step": 278
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.5947577491310232,
+      "learning_rate": 1.6287011003719105e-06,
+      "loss": 0.2268,
+      "step": 279
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.2113068151573663,
+      "learning_rate": 1.596871169708235e-06,
+      "loss": 0.1735,
+      "step": 280
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.65611841120046,
+      "learning_rate": 1.5652961345483353e-06,
+      "loss": 0.2082,
+      "step": 281
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.3764804014648153,
+      "learning_rate": 1.5339783598730568e-06,
+      "loss": 0.1419,
+      "step": 282
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.1412185414875824,
+      "learning_rate": 1.5029201913943425e-06,
+      "loss": 0.2135,
+      "step": 283
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.9752929301730582,
+      "learning_rate": 1.4721239553795485e-06,
+      "loss": 0.2136,
+      "step": 284
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.1884720258868442,
+      "learning_rate": 1.4415919584771999e-06,
+      "loss": 0.1652,
+      "step": 285
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.3431031815080743,
+      "learning_rate": 1.4113264875442201e-06,
+      "loss": 0.1933,
+      "step": 286
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9921362477179113,
+      "learning_rate": 1.3813298094746491e-06,
+      "loss": 0.1812,
+      "step": 287
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.1564038041392914,
+      "learning_rate": 1.35160417102985e-06,
+      "loss": 0.1754,
+      "step": 288
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.9678664884973698,
+      "learning_rate": 1.3221517986702249e-06,
+      "loss": 0.2056,
+      "step": 289
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.3025616408354987,
+      "learning_rate": 1.292974898388456e-06,
+      "loss": 0.1895,
+      "step": 290
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0994757496219993,
+      "learning_rate": 1.2640756555442684e-06,
+      "loss": 0.183,
+      "step": 291
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.3399046076527112,
+      "learning_rate": 1.235456234700756e-06,
+      "loss": 0.236,
+      "step": 292
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.487877632249796,
+      "learning_rate": 1.207118779462248e-06,
+      "loss": 0.1639,
+      "step": 293
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4397785185953393,
+      "learning_rate": 1.1790654123137552e-06,
+      "loss": 0.2139,
+      "step": 294
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.4383244508954862,
+      "learning_rate": 1.1512982344619904e-06,
+      "loss": 0.2061,
+      "step": 295
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.4666229958659296,
+      "learning_rate": 1.1238193256779955e-06,
+      "loss": 0.2233,
+      "step": 296
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 5.649925229654807,
+      "learning_rate": 1.0966307441413598e-06,
+      "loss": 0.2208,
+      "step": 297
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.2835956283557763,
+      "learning_rate": 1.0697345262860638e-06,
+      "loss": 0.2139,
+      "step": 298
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.2085842558871347,
+      "learning_rate": 1.0431326866479457e-06,
+      "loss": 0.2224,
+      "step": 299
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.4693550530262014,
+      "learning_rate": 1.01682721771382e-06,
+      "loss": 0.1908,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1516694186482015,
+      "learning_rate": 9.908200897722332e-07,
+      "loss": 0.1891,
+      "step": 301
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.7168235578284265,
+      "learning_rate": 9.6511325076589e-07,
+      "loss": 0.1748,
+      "step": 302
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.3219496350198179,
+      "learning_rate": 9.397086261457511e-07,
+      "loss": 0.1572,
+      "step": 303
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 2.56786959760664,
+      "learning_rate": 9.146081187268185e-07,
+      "loss": 0.2013,
+      "step": 304
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.8437429040002822,
+      "learning_rate": 8.898136085456127e-07,
+      "loss": 0.1621,
+      "step": 305
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.6011151676064899,
+      "learning_rate": 8.65326952719357e-07,
+      "loss": 0.2,
+      "step": 306
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.473297431622754,
+      "learning_rate": 8.411499853068783e-07,
+      "loss": 0.2119,
+      "step": 307
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.5191303355576082,
+      "learning_rate": 8.172845171712379e-07,
+      "loss": 0.1599,
+      "step": 308
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 5.358809732505781,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.1802,
+      "step": 309
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.4655232399177145,
+      "learning_rate": 7.70495205391818e-07,
+      "loss": 0.2149,
+      "step": 310
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.1213558383066429,
+      "learning_rate": 7.475748662833615e-07,
+      "loss": 0.1551,
+      "step": 311
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.034808469859055,
+      "learning_rate": 7.249730352599e-07,
+      "loss": 0.2101,
+      "step": 312
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.1667195801457733,
+      "learning_rate": 7.026914052062433e-07,
+      "loss": 0.1719,
+      "step": 313
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.3017393361679748,
+      "learning_rate": 6.807316450240425e-07,
+      "loss": 0.1824,
+      "step": 314
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.4637494927419403,
+      "learning_rate": 6.590953995067812e-07,
+      "loss": 0.2217,
+      "step": 315
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.0734222217533145,
+      "learning_rate": 6.377842892165892e-07,
+      "loss": 0.173,
+      "step": 316
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.3554263871603187,
+      "learning_rate": 6.167999103628569e-07,
+      "loss": 0.2164,
+      "step": 317
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.063934037321115,
+      "learning_rate": 5.961438346826792e-07,
+      "loss": 0.2134,
+      "step": 318
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2103613565807279,
+      "learning_rate": 5.758176093231294e-07,
+      "loss": 0.2059,
+      "step": 319
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2005522755435272,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.1953,
+      "step": 320
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.845403285368735,
+      "learning_rate": 5.361607745106817e-07,
+      "loss": 0.1457,
+      "step": 321
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.261693404740118,
+      "learning_rate": 5.168331353681643e-07,
+      "loss": 0.1683,
+      "step": 322
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.5851984906569154,
+      "learning_rate": 4.97841286944557e-07,
+      "loss": 0.2124,
+      "step": 323
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.523726785060755,
+      "learning_rate": 4.791866517357491e-07,
+      "loss": 0.2361,
+      "step": 324
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.2363751164140784,
+      "learning_rate": 4.608706269802471e-07,
+      "loss": 0.2043,
+      "step": 325
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.8257851756752632,
+      "learning_rate": 4.428945845545168e-07,
+      "loss": 0.1723,
+      "step": 326
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0704313301096995,
+      "learning_rate": 4.2525987087023433e-07,
+      "loss": 0.1793,
+      "step": 327
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.7345294945747147,
+      "learning_rate": 4.0796780677343606e-07,
+      "loss": 0.1894,
+      "step": 328
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2793601238653005,
+      "learning_rate": 3.910196874455896e-07,
+      "loss": 0.2147,
+      "step": 329
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.1248339116099797,
+      "learning_rate": 3.744167823065814e-07,
+      "loss": 0.2218,
+      "step": 330
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.7887733554762244,
+      "learning_rate": 3.581603349196372e-07,
+      "loss": 0.2267,
+      "step": 331
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.4084446197492118,
+      "learning_rate": 3.4225156289818096e-07,
+      "loss": 0.1788,
+      "step": 332
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.899622912182613,
+      "learning_rate": 3.26691657814634e-07,
+      "loss": 0.1939,
+      "step": 333
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.7446464340796515,
+      "learning_rate": 3.1148178511116624e-07,
+      "loss": 0.1924,
+      "step": 334
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 2.3439206542252093,
+      "learning_rate": 2.966230840124007e-07,
+      "loss": 0.1817,
+      "step": 335
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.385153703610484,
+      "learning_rate": 2.821166674400905e-07,
+      "loss": 0.1684,
+      "step": 336
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.3699902368661212,
+      "learning_rate": 2.6796362192975766e-07,
+      "loss": 0.2186,
+      "step": 337
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.5671721780951213,
+      "learning_rate": 2.5416500754931294e-07,
+      "loss": 0.1615,
+      "step": 338
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2442561018528566,
+      "learning_rate": 2.407218578196524e-07,
+      "loss": 0.204,
+      "step": 339
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.3245163553556882,
+      "learning_rate": 2.2763517963725169e-07,
+      "loss": 0.1508,
+      "step": 340
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.4443125484817598,
+      "learning_rate": 2.1490595319874574e-07,
+      "loss": 0.1468,
+      "step": 341
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0080028863026755,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 0.1884,
+      "step": 342
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.1153585325990107,
+      "learning_rate": 1.905236424022633e-07,
+      "loss": 0.1859,
+      "step": 343
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.8865584670667468,
+      "learning_rate": 1.7887238428763553e-07,
+      "loss": 0.1546,
+      "step": 344
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.230506462806752,
+      "learning_rate": 1.6758223026681507e-07,
+      "loss": 0.1685,
+      "step": 345
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0880739757634574,
+      "learning_rate": 1.5665402597616842e-07,
+      "loss": 0.1914,
+      "step": 346
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.6690615352515796,
+      "learning_rate": 1.4608858994190344e-07,
+      "loss": 0.1619,
+      "step": 347
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.566667309205433,
+      "learning_rate": 1.358867135187636e-07,
+      "loss": 0.2008,
+      "step": 348
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.4810073106116959,
+      "learning_rate": 1.2604916083075236e-07,
+      "loss": 0.1948,
+      "step": 349
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 2.3780456607386116,
+      "learning_rate": 1.1657666871390471e-07,
+      "loss": 0.2333,
+      "step": 350
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.132800666627968,
+      "learning_rate": 1.0746994666109234e-07,
+      "loss": 0.1349,
+      "step": 351
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.335987755289687,
+      "learning_rate": 9.872967676888611e-08,
+      "loss": 0.1881,
+      "step": 352
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.5722809053335216,
+      "learning_rate": 9.035651368646647e-08,
+      "loss": 0.1772,
+      "step": 353
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.4322959166671239,
+      "learning_rate": 8.235108456658814e-08,
+      "loss": 0.1746,
+      "step": 354
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.827103850452774,
+      "learning_rate": 7.471398901860772e-08,
+      "loss": 0.1796,
+      "step": 355
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.0901159204868605,
+      "learning_rate": 6.744579906357185e-08,
+      "loss": 0.2001,
+      "step": 356
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.264725784348664,
+      "learning_rate": 6.054705909137426e-08,
+      "loss": 0.1969,
+      "step": 357
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.790275117341466,
+      "learning_rate": 5.401828581997948e-08,
+      "loss": 0.2149,
+      "step": 358
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.4371061562729375,
+      "learning_rate": 4.7859968256719344e-08,
+      "loss": 0.149,
+      "step": 359
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0820259934611336,
+      "learning_rate": 4.207256766166845e-08,
+      "loss": 0.1739,
+      "step": 360
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.464196014988727,
+      "learning_rate": 3.665651751309451e-08,
+      "loss": 0.1833,
+      "step": 361
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.9110118488670174,
+      "learning_rate": 3.16122234749916e-08,
+      "loss": 0.2256,
+      "step": 362
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.1849306893196245,
+      "learning_rate": 2.6940063366693303e-08,
+      "loss": 0.1185,
+      "step": 363
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.056217532084132,
+      "learning_rate": 2.264038713457706e-08,
+      "loss": 0.1977,
+      "step": 364
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.3555937053199987,
+      "learning_rate": 1.8713516825851207e-08,
+      "loss": 0.1518,
+      "step": 365
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.3241310217180846,
+      "learning_rate": 1.51597465644332e-08,
+      "loss": 0.1724,
+      "step": 366
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.5056988463601566,
+      "learning_rate": 1.1979342528922189e-08,
+      "loss": 0.1858,
+      "step": 367
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.1775425039811125,
+      "learning_rate": 9.1725429326589e-09,
+      "loss": 0.1928,
+      "step": 368
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.4669192580620838,
+      "learning_rate": 6.739558005884883e-09,
+      "loss": 0.1999,
+      "step": 369
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.3080333239549076,
+      "learning_rate": 4.6805699799967744e-09,
+      "loss": 0.1879,
+      "step": 370
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.0356683078795677,
+      "learning_rate": 2.995733073895557e-09,
+      "loss": 0.1496,
+      "step": 371
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.2200749316804114,
+      "learning_rate": 1.6851734824380184e-09,
+      "loss": 0.1744,
+      "step": 372
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.255017826002363,
+      "learning_rate": 7.48989366980979e-10,
+      "loss": 0.1972,
+      "step": 373
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.8563634005979386,
+      "learning_rate": 1.872508480332824e-10,
+      "loss": 0.1978,
+      "step": 374
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0362522869355721,
+      "learning_rate": 0.0,
+      "loss": 0.1574,
+      "step": 375
+    },
+    {
+      "epoch": 1.0,
+      "step": 375,
+      "total_flos": 20962186485760.0,
+      "train_loss": 0.2976814561287562,
+      "train_runtime": 919.5329,
+      "train_samples_per_second": 3.263,
+      "train_steps_per_second": 0.408
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 20962186485760.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49685b9bdc02c9e9a4f38038219df7fb1d4caf6c9c6e6ee48cd16dd3fbebf222
+size 7864