Upload folder using huggingface_hub

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower_adapter/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_adapter/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_mlp_adapter",
+  "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_adapter/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_adapter/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_adapter/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_adapter/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c980b4dc729f6c4c83e165eb467ed581fa99eeb8f40e3f97d5b395fcc4021938
+size 4994571904

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower_adapter/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449a972e00fc514764a996d6907490ef4a11dc254492a8afe1c6075d7ac780c9
+size 1255812224

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_vision_tower_adapter/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_adapter/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_adapter/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_adapter/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": 0.6734368278111681,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.5596,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.3681512091683838,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.8544,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.1691410618641844,
+      "learning_rate": 2.5e-06,
+      "loss": 0.5807,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.8190502445516818,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6955,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.7999623221686807,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.5644,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8294349725607431,
+      "learning_rate": 5e-06,
+      "loss": 0.4395,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.7430462678130991,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.5957,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2683693398256872,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7639,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.4859451547407603,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7318,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.718809696829822,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5966,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.9577671353532506,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.5033,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.2100216527415733,
+      "learning_rate": 1e-05,
+      "loss": 0.7475,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.014413292835487,
+      "learning_rate": 9.999812749151968e-06,
+      "loss": 0.7392,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0305963261346556,
+      "learning_rate": 9.99925101063302e-06,
+      "loss": 0.6364,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0011261115709251,
+      "learning_rate": 9.998314826517564e-06,
+      "loss": 0.6071,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.4278800616224594,
+      "learning_rate": 9.997004266926105e-06,
+      "loss": 0.7718,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9853199498425232,
+      "learning_rate": 9.995319430020004e-06,
+      "loss": 0.6125,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.7103568218429488,
+      "learning_rate": 9.993260441994116e-06,
+      "loss": 0.5138,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.112546545106814,
+      "learning_rate": 9.990827457067342e-06,
+      "loss": 0.5963,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9029565498486303,
+      "learning_rate": 9.988020657471078e-06,
+      "loss": 0.6366,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0505442442169013,
+      "learning_rate": 9.984840253435569e-06,
+      "loss": 0.6479,
+      "step": 21
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.136303529620716,
+      "learning_rate": 9.98128648317415e-06,
+      "loss": 0.5168,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.5325978440477437,
+      "learning_rate": 9.977359612865424e-06,
+      "loss": 0.5889,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9559200885278366,
+      "learning_rate": 9.973059936633308e-06,
+      "loss": 0.5669,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.1459217871764056,
+      "learning_rate": 9.968387776525009e-06,
+      "loss": 0.6144,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.9017717832380352,
+      "learning_rate": 9.963343482486907e-06,
+      "loss": 0.6623,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8314344459499121,
+      "learning_rate": 9.957927432338332e-06,
+      "loss": 0.532,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.7710438275198986,
+      "learning_rate": 9.952140031743282e-06,
+      "loss": 0.5517,
+      "step": 28
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.8541010876918343,
+      "learning_rate": 9.945981714180021e-06,
+      "loss": 0.5762,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2069726554063132,
+      "learning_rate": 9.939452940908627e-06,
+      "loss": 0.6641,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.9478895430546033,
+      "learning_rate": 9.932554200936428e-06,
+      "loss": 0.4817,
+      "step": 31
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.552485153377028,
+      "learning_rate": 9.925286010981394e-06,
+      "loss": 0.3834,
+      "step": 32
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.7950262043910397,
+      "learning_rate": 9.917648915433413e-06,
+      "loss": 0.5204,
+      "step": 33
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.842504329927148,
+      "learning_rate": 9.909643486313533e-06,
+      "loss": 0.4205,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.0342375181071488,
+      "learning_rate": 9.901270323231114e-06,
+      "loss": 0.5613,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.8702779537556573,
+      "learning_rate": 9.892530053338909e-06,
+      "loss": 0.8368,
+      "step": 36
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.1510577979925192,
+      "learning_rate": 9.883423331286096e-06,
+      "loss": 0.5972,
+      "step": 37
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6147760482696417,
+      "learning_rate": 9.873950839169248e-06,
+      "loss": 0.4527,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.7682313684989804,
+      "learning_rate": 9.864113286481237e-06,
+      "loss": 0.5136,
+      "step": 39
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.8299542802673553,
+      "learning_rate": 9.853911410058097e-06,
+      "loss": 0.4264,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.011515090950018,
+      "learning_rate": 9.843345974023833e-06,
+      "loss": 0.4637,
+      "step": 41
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.1951561888907094,
+      "learning_rate": 9.832417769733185e-06,
+      "loss": 0.5517,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.8950296718567703,
+      "learning_rate": 9.821127615712365e-06,
+      "loss": 0.4612,
+      "step": 43
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3773952253176274,
+      "learning_rate": 9.809476357597738e-06,
+      "loss": 0.638,
+      "step": 44
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3603528992773917,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 0.5994,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.3694601207835229,
+      "learning_rate": 9.785094046801256e-06,
+      "loss": 0.6725,
+      "step": 46
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.942131300475299,
+      "learning_rate": 9.77236482036275e-06,
+      "loss": 0.5493,
+      "step": 47
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.4686035406401314,
+      "learning_rate": 9.759278142180348e-06,
+      "loss": 0.6433,
+      "step": 48
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.145865373950894,
+      "learning_rate": 9.745834992450688e-06,
+      "loss": 0.4918,
+      "step": 49
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.129386787672922,
+      "learning_rate": 9.732036378070243e-06,
+      "loss": 0.7314,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.5098544590873433,
+      "learning_rate": 9.717883332559911e-06,
+      "loss": 0.5109,
+      "step": 51
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.333152463546811,
+      "learning_rate": 9.703376915987601e-06,
+      "loss": 0.5686,
+      "step": 52
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8917776841281857,
+      "learning_rate": 9.688518214888836e-06,
+      "loss": 0.3997,
+      "step": 53
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.339334384195638,
+      "learning_rate": 9.673308342185366e-06,
+      "loss": 0.4168,
+      "step": 54
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.507399287878121,
+      "learning_rate": 9.657748437101819e-06,
+      "loss": 0.5282,
+      "step": 55
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.6981113717761291,
+      "learning_rate": 9.641839665080363e-06,
+      "loss": 0.4468,
+      "step": 56
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.38055826612265,
+      "learning_rate": 9.625583217693419e-06,
+      "loss": 0.5371,
+      "step": 57
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 9.348645008868207,
+      "learning_rate": 9.60898031255441e-06,
+      "loss": 0.7308,
+      "step": 58
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2019910717805047,
+      "learning_rate": 9.592032193226564e-06,
+      "loss": 0.4752,
+      "step": 59
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.4887854352700587,
+      "learning_rate": 9.574740129129767e-06,
+      "loss": 0.6862,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.9319051352732766,
+      "learning_rate": 9.557105415445485e-06,
+      "loss": 0.6227,
+      "step": 61
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.5874440182070515,
+      "learning_rate": 9.539129373019755e-06,
+      "loss": 0.5659,
+      "step": 62
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 5.413501663953093,
+      "learning_rate": 9.520813348264252e-06,
+      "loss": 0.6358,
+      "step": 63
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.9913745215827112,
+      "learning_rate": 9.502158713055444e-06,
+      "loss": 0.4333,
+      "step": 64
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.7968110926668184,
+      "learning_rate": 9.483166864631837e-06,
+      "loss": 0.4674,
+      "step": 65
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.2507534918337786,
+      "learning_rate": 9.46383922548932e-06,
+      "loss": 0.6458,
+      "step": 66
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.7822664966861084,
+      "learning_rate": 9.444177243274619e-06,
+      "loss": 0.367,
+      "step": 67
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.959266071962443,
+      "learning_rate": 9.424182390676872e-06,
+      "loss": 0.5351,
+      "step": 68
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.5097168439607733,
+      "learning_rate": 9.403856165317322e-06,
+      "loss": 0.6444,
+      "step": 69
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.1304676082761889,
+      "learning_rate": 9.383200089637143e-06,
+      "loss": 0.4068,
+      "step": 70
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.0220587501496923,
+      "learning_rate": 9.362215710783411e-06,
+      "loss": 0.4156,
+      "step": 71
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.203919494407004,
+      "learning_rate": 9.34090460049322e-06,
+      "loss": 0.5414,
+      "step": 72
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.5531085816730719,
+      "learning_rate": 9.319268354975958e-06,
+      "loss": 0.5357,
+      "step": 73
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.1867847937117226,
+      "learning_rate": 9.297308594793757e-06,
+      "loss": 0.4832,
+      "step": 74
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9311374520514676,
+      "learning_rate": 9.275026964740101e-06,
+      "loss": 0.4151,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.1816922494583428,
+      "learning_rate": 9.252425133716639e-06,
+      "loss": 0.4546,
+      "step": 76
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.9259460387589804,
+      "learning_rate": 9.229504794608182e-06,
+      "loss": 0.6645,
+      "step": 77
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.063284357545532,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 0.4934,
+      "step": 78
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.0127820329278427,
+      "learning_rate": 9.182715482828764e-06,
+      "loss": 0.4182,
+      "step": 79
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.2356168483096375,
+      "learning_rate": 9.158850014693123e-06,
+      "loss": 0.5537,
+      "step": 80
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.7374711912946172,
+      "learning_rate": 9.134673047280644e-06,
+      "loss": 0.6472,
+      "step": 81
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7801033674425297,
+      "learning_rate": 9.110186391454389e-06,
+      "loss": 0.4123,
+      "step": 82
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.1212457852788764,
+      "learning_rate": 9.085391881273182e-06,
+      "loss": 0.458,
+      "step": 83
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.9839792831965357,
+      "learning_rate": 9.060291373854252e-06,
+      "loss": 0.4534,
+      "step": 84
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8610577034347635,
+      "learning_rate": 9.034886749234112e-06,
+      "loss": 0.4303,
+      "step": 85
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.3361753084307515,
+      "learning_rate": 9.009179910227767e-06,
+      "loss": 0.5346,
+      "step": 86
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.341638391099747,
+      "learning_rate": 8.98317278228618e-06,
+      "loss": 0.546,
+      "step": 87
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.7202669871814353,
+      "learning_rate": 8.956867313352055e-06,
+      "loss": 0.4353,
+      "step": 88
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.7790494409545357,
+      "learning_rate": 8.930265473713939e-06,
+      "loss": 0.631,
+      "step": 89
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.4631461164344992,
+      "learning_rate": 8.90336925585864e-06,
+      "loss": 0.5452,
+      "step": 90
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.554813675100113,
+      "learning_rate": 8.876180674322006e-06,
+      "loss": 0.4791,
+      "step": 91
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.2020430285908648,
+      "learning_rate": 8.84870176553801e-06,
+      "loss": 0.5607,
+      "step": 92
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.647901189250044,
+      "learning_rate": 8.820934587686247e-06,
+      "loss": 0.4471,
+      "step": 93
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.1737903059586954,
+      "learning_rate": 8.792881220537752e-06,
+      "loss": 0.4941,
+      "step": 94
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.9249812097667618,
+      "learning_rate": 8.764543765299245e-06,
+      "loss": 0.4267,
+      "step": 95
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1313797376231975,
+      "learning_rate": 8.735924344455732e-06,
+      "loss": 0.4062,
+      "step": 96
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.0322836878191592,
+      "learning_rate": 8.707025101611546e-06,
+      "loss": 0.4548,
+      "step": 97
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.7634694976216791,
+      "learning_rate": 8.677848201329775e-06,
+      "loss": 0.3704,
+      "step": 98
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.299471635536299,
+      "learning_rate": 8.64839582897015e-06,
+      "loss": 0.3776,
+      "step": 99
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.1442105523959114,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.4046,
+      "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.747136085505563,
+      "learning_rate": 8.588673512455781e-06,
+      "loss": 0.4392,
+      "step": 101
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.8771369273695218,
+      "learning_rate": 8.558408041522801e-06,
+      "loss": 0.4227,
+      "step": 102
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.9890411638445165,
+      "learning_rate": 8.527876044620453e-06,
+      "loss": 0.4397,
+      "step": 103
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.1971260642633375,
+      "learning_rate": 8.497079808605659e-06,
+      "loss": 0.4766,
+      "step": 104
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.0533846028537168,
+      "learning_rate": 8.466021640126946e-06,
+      "loss": 0.4573,
+      "step": 105
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.9694262553939589,
+      "learning_rate": 8.434703865451666e-06,
+      "loss": 0.4135,
+      "step": 106
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 2.300475262510013,
+      "learning_rate": 8.403128830291767e-06,
+      "loss": 0.5504,
+      "step": 107
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.1722181434150782,
+      "learning_rate": 8.371298899628091e-06,
+      "loss": 0.4406,
+      "step": 108
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.3738187778062096,
+      "learning_rate": 8.339216457533244e-06,
+      "loss": 0.4227,
+      "step": 109
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.3787756102577409,
+      "learning_rate": 8.306883906993022e-06,
+      "loss": 0.3959,
+      "step": 110
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3673269500923275,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 0.4687,
+      "step": 111
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.8575508743259427,
+      "learning_rate": 8.24147818600428e-06,
+      "loss": 0.3933,
+      "step": 112
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2716921510246182,
+      "learning_rate": 8.20840991446645e-06,
+      "loss": 0.3781,
+      "step": 113
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.119598891096802,
+      "learning_rate": 8.175101331937692e-06,
+      "loss": 0.3712,
+      "step": 114
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.431335944733643,
+      "learning_rate": 8.141554933242135e-06,
+      "loss": 0.4492,
+      "step": 115
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.8591322914111644,
+      "learning_rate": 8.10777323101642e-06,
+      "loss": 0.3625,
+      "step": 116
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.2872576874185022,
+      "learning_rate": 8.073758755521506e-06,
+      "loss": 0.4831,
+      "step": 117
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.4070370913922001,
+      "learning_rate": 8.03951405445314e-06,
+      "loss": 0.2976,
+      "step": 118
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0951748266289887,
+      "learning_rate": 8.005041692751055e-06,
+      "loss": 0.3713,
+      "step": 119
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0226748521539821,
+      "learning_rate": 7.970344252406832e-06,
+      "loss": 0.4041,
+      "step": 120
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3279448026530023,
+      "learning_rate": 7.935424332270523e-06,
+      "loss": 0.3968,
+      "step": 121
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.9238327744400439,
+      "learning_rate": 7.900284547855992e-06,
+      "loss": 0.389,
+      "step": 122
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.998635070462261,
+      "learning_rate": 7.864927531145012e-06,
+      "loss": 0.4712,
+      "step": 123
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.6390077851246356,
+      "learning_rate": 7.829355930390126e-06,
+      "loss": 0.4933,
+      "step": 124
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.9687860776834304,
+      "learning_rate": 7.7935724099163e-06,
+      "loss": 0.3697,
+      "step": 125
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.6476512986882939,
+      "learning_rate": 7.757579649921354e-06,
+      "loss": 0.3805,
+      "step": 126
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.9549730281111898,
+      "learning_rate": 7.721380346275221e-06,
+      "loss": 0.3188,
+      "step": 127
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.7436308222608589,
+      "learning_rate": 7.684977210318024e-06,
+      "loss": 0.2718,
+      "step": 128
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1359322180885196,
+      "learning_rate": 7.648372968656995e-06,
+      "loss": 0.4368,
+      "step": 129
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1524856601723423,
+      "learning_rate": 7.611570362962247e-06,
+      "loss": 0.415,
+      "step": 130
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1296824656704323,
+      "learning_rate": 7.574572149761437e-06,
+      "loss": 0.4342,
+      "step": 131
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1421467509149192,
+      "learning_rate": 7.5373811002332785e-06,
+      "loss": 0.3442,
+      "step": 132
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.196007824748958,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3436,
+      "step": 133
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.0893090279685598,
+      "learning_rate": 7.462431648918689e-06,
+      "loss": 0.2981,
+      "step": 134
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1409621100405718,
+      "learning_rate": 7.424678860871584e-06,
+      "loss": 0.3148,
+      "step": 135
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.3725280230244188,
+      "learning_rate": 7.3867444635553165e-06,
+      "loss": 0.4035,
+      "step": 136
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.0240448653771859,
+      "learning_rate": 7.3486312982691134e-06,
+      "loss": 0.3544,
+      "step": 137
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.8507075073838535,
+      "learning_rate": 7.310342219701981e-06,
+      "loss": 0.4482,
+      "step": 138
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.0688420047382605,
+      "learning_rate": 7.271880095718895e-06,
+      "loss": 0.4217,
+      "step": 139
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.3770115885083798,
+      "learning_rate": 7.233247807145989e-06,
+      "loss": 0.4195,
+      "step": 140
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.9411411230756633,
+      "learning_rate": 7.19444824755478e-06,
+      "loss": 0.2642,
+      "step": 141
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.1682534220599694,
+      "learning_rate": 7.155484323045442e-06,
+      "loss": 0.358,
+      "step": 142
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.4541700046379986,
+      "learning_rate": 7.11635895202914e-06,
+      "loss": 0.333,
+      "step": 143
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.1379470274423935,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 0.3096,
+      "step": 144
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.9071743227869266,
+      "learning_rate": 7.037635604362786e-06,
+      "loss": 0.2811,
+      "step": 145
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.8064071122337786,
+      "learning_rate": 6.9980435241181785e-06,
+      "loss": 0.2931,
+      "step": 146
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.8535076620997424,
+      "learning_rate": 6.958301789735853e-06,
+      "loss": 0.2719,
+      "step": 147
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.9482269649906224,
+      "learning_rate": 6.918413377885193e-06,
+      "loss": 0.3124,
+      "step": 148
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.8549102591179385,
+      "learning_rate": 6.878381276221777e-06,
+      "loss": 0.2363,
+      "step": 149
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.326812886368985,
+      "learning_rate": 6.838208483163601e-06,
+      "loss": 0.4042,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0498555616829353,
+      "learning_rate": 6.797898007666493e-06,
+      "loss": 0.2739,
+      "step": 151
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.4136292981677538,
+      "learning_rate": 6.757452868998737e-06,
+      "loss": 0.3669,
+      "step": 152
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.9366212163762664,
+      "learning_rate": 6.716876096514944e-06,
+      "loss": 0.2767,
+      "step": 153
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.1702906017394328,
+      "learning_rate": 6.676170729429132e-06,
+      "loss": 0.2969,
+      "step": 154
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.0097924982069597,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.2694,
+      "step": 155
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.6055611708010118,
+      "learning_rate": 6.594386416238095e-06,
+      "loss": 0.3534,
+      "step": 156
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.4286056067744608,
+      "learning_rate": 6.553313595805666e-06,
+      "loss": 0.3429,
+      "step": 157
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.180110551453183,
+      "learning_rate": 6.512124431658006e-06,
+      "loss": 0.2795,
+      "step": 158
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.1682226845118089,
+      "learning_rate": 6.470822008877482e-06,
+      "loss": 0.2891,
+      "step": 159
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.6598172034370966,
+      "learning_rate": 6.4294094210295725e-06,
+      "loss": 0.2771,
+      "step": 160
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.7361490591633932,
+      "learning_rate": 6.3878897699311525e-06,
+      "loss": 0.3215,
+      "step": 161
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.7682369558837525,
+      "learning_rate": 6.346266165418173e-06,
+      "loss": 0.2411,
+      "step": 162
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.0772012049306992,
+      "learning_rate": 6.304541725112734e-06,
+      "loss": 0.2415,
+      "step": 163
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.1221481117462984,
+      "learning_rate": 6.262719574189564e-06,
+      "loss": 0.2537,
+      "step": 164
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.5032624604418883,
+      "learning_rate": 6.2208028451419575e-06,
+      "loss": 0.2729,
+      "step": 165
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6689916375066,
+      "learning_rate": 6.178794677547138e-06,
+      "loss": 0.2528,
+      "step": 166
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.1357922890367247,
+      "learning_rate": 6.136698217831106e-06,
+      "loss": 0.2668,
+      "step": 167
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.314949314093478,
+      "learning_rate": 6.094516619032975e-06,
+      "loss": 0.2893,
+      "step": 168
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.0266530029925238,
+      "learning_rate": 6.052253040568804e-06,
+      "loss": 0.2667,
+      "step": 169
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.583588057365036,
+      "learning_rate": 6.009910647994956e-06,
+      "loss": 0.2944,
+      "step": 170
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.498262539761988,
+      "learning_rate": 5.967492612770999e-06,
+      "loss": 0.3443,
+      "step": 171
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.9355403870833707,
+      "learning_rate": 5.925002112022158e-06,
+      "loss": 0.2355,
+      "step": 172
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.4077110218022293,
+      "learning_rate": 5.882442328301356e-06,
+      "loss": 0.2836,
+      "step": 173
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.1387948169298059,
+      "learning_rate": 5.839816449350824e-06,
+      "loss": 0.2643,
+      "step": 174
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.3815050582816581,
+      "learning_rate": 5.7971276678633625e-06,
+      "loss": 0.2507,
+      "step": 175
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.0719106157280966,
+      "learning_rate": 5.754379181243179e-06,
+      "loss": 0.2539,
+      "step": 176
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.343580319642491,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 0.2849,
+      "step": 177
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.2450640252076939,
+      "learning_rate": 5.668715904341365e-06,
+      "loss": 0.2572,
+      "step": 178
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.71008037153349,
+      "learning_rate": 5.62580753026823e-06,
+      "loss": 0.2879,
+      "step": 179
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.941050896790882,
+      "learning_rate": 5.5828522829987965e-06,
+      "loss": 0.2631,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.2318592507566635,
+      "learning_rate": 5.539853379895656e-06,
+      "loss": 0.2907,
+      "step": 181
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.5646985786418,
+      "learning_rate": 5.496814041591234e-06,
+      "loss": 0.2445,
+      "step": 182
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.983861108306878,
+      "learning_rate": 5.453737491746572e-06,
+      "loss": 0.2446,
+      "step": 183
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.2699136222789564,
+      "learning_rate": 5.410626956809864e-06,
+      "loss": 0.234,
+      "step": 184
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.2621053931581894,
+      "learning_rate": 5.367485665774802e-06,
+      "loss": 0.2336,
+      "step": 185
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.456445321628872,
+      "learning_rate": 5.324316849938715e-06,
+      "loss": 0.2822,
+      "step": 186
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.509917287616566,
+      "learning_rate": 5.281123742660558e-06,
+      "loss": 0.3326,
+      "step": 187
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.788137580165615,
+      "learning_rate": 5.237909579118713e-06,
+      "loss": 0.2769,
+      "step": 188
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0699465563284762,
+      "learning_rate": 5.194677596068689e-06,
+      "loss": 0.2464,
+      "step": 189
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.8561845760424909,
+      "learning_rate": 5.1514310316006835e-06,
+      "loss": 0.2641,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.6560368575142284,
+      "learning_rate": 5.1081731248970435e-06,
+      "loss": 0.232,
+      "step": 191
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.5236834645966364,
+      "learning_rate": 5.064907115989655e-06,
+      "loss": 0.2001,
+      "step": 192
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.1316470393518598,
+      "learning_rate": 5.021636245517261e-06,
+      "loss": 0.211,
+      "step": 193
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.259620314614562,
+      "learning_rate": 4.978363754482741e-06,
+      "loss": 0.2767,
+      "step": 194
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0719669076835106,
+      "learning_rate": 4.935092884010347e-06,
+      "loss": 0.2598,
+      "step": 195
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.419514625670958,
+      "learning_rate": 4.891826875102958e-06,
+      "loss": 0.2741,
+      "step": 196
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.294128958628265,
+      "learning_rate": 4.848568968399317e-06,
+      "loss": 0.1985,
+      "step": 197
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.0141453964527885,
+      "learning_rate": 4.805322403931312e-06,
+      "loss": 0.2152,
+      "step": 198
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.1171370251069463,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.209,
+      "step": 199
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.1527449050966676,
+      "learning_rate": 4.718876257339444e-06,
+      "loss": 0.1925,
+      "step": 200
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.7561489437595508,
+      "learning_rate": 4.6756831500612846e-06,
+      "loss": 0.2034,
+      "step": 201
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1247423548271078,
+      "learning_rate": 4.632514334225201e-06,
+      "loss": 0.2233,
+      "step": 202
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.7489622321071914,
+      "learning_rate": 4.589373043190137e-06,
+      "loss": 0.2066,
+      "step": 203
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.3651046530273716,
+      "learning_rate": 4.546262508253429e-06,
+      "loss": 0.231,
+      "step": 204
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.7728027125479735,
+      "learning_rate": 4.503185958408767e-06,
+      "loss": 0.1885,
+      "step": 205
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.668916632050167,
+      "learning_rate": 4.460146620104347e-06,
+      "loss": 0.1833,
+      "step": 206
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.1479652087851935,
+      "learning_rate": 4.417147717001205e-06,
+      "loss": 0.1923,
+      "step": 207
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.7870823477207927,
+      "learning_rate": 4.374192469731771e-06,
+      "loss": 0.2281,
+      "step": 208
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.615945653965678,
+      "learning_rate": 4.331284095658637e-06,
+      "loss": 0.1925,
+      "step": 209
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.8518109937831446,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.196,
+      "step": 210
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0009490949889857,
+      "learning_rate": 4.245620818756822e-06,
+      "loss": 0.2166,
+      "step": 211
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 2.5049197633812317,
+      "learning_rate": 4.202872332136639e-06,
+      "loss": 0.2114,
+      "step": 212
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.2973151558230087,
+      "learning_rate": 4.160183550649176e-06,
+      "loss": 0.2492,
+      "step": 213
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.0055520844002497,
+      "learning_rate": 4.117557671698648e-06,
+      "loss": 0.1868,
+      "step": 214
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 4.536828791334527,
+      "learning_rate": 4.074997887977843e-06,
+      "loss": 0.2226,
+      "step": 215
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.0131826874338583,
+      "learning_rate": 4.032507387229002e-06,
+      "loss": 0.2439,
+      "step": 216
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.2664865469399766,
+      "learning_rate": 3.9900893520050446e-06,
+      "loss": 0.2638,
+      "step": 217
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.0088860564777202,
+      "learning_rate": 3.9477469594311975e-06,
+      "loss": 0.1892,
+      "step": 218
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.1652920355938632,
+      "learning_rate": 3.905483380967027e-06,
+      "loss": 0.2324,
+      "step": 219
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 2.8884929652462645,
+      "learning_rate": 3.863301782168896e-06,
+      "loss": 0.2445,
+      "step": 220
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.1165124110225142,
+      "learning_rate": 3.821205322452863e-06,
+      "loss": 0.192,
+      "step": 221
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.3924319521466968,
+      "learning_rate": 3.779197154858044e-06,
+      "loss": 0.2032,
+      "step": 222
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.435559214552163,
+      "learning_rate": 3.7372804258104367e-06,
+      "loss": 0.221,
+      "step": 223
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.0286892139496182,
+      "learning_rate": 3.695458274887268e-06,
+      "loss": 0.2133,
+      "step": 224
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.9416238210318837,
+      "learning_rate": 3.6537338345818273e-06,
+      "loss": 0.227,
+      "step": 225
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.0208486915655237,
+      "learning_rate": 3.6121102300688504e-06,
+      "loss": 0.2113,
+      "step": 226
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.5392466747643556,
+      "learning_rate": 3.5705905789704296e-06,
+      "loss": 0.2301,
+      "step": 227
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.8292131446212958,
+      "learning_rate": 3.529177991122519e-06,
+      "loss": 0.196,
+      "step": 228
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.3519017573584804,
+      "learning_rate": 3.487875568341995e-06,
+      "loss": 0.2637,
+      "step": 229
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9568471391977225,
+      "learning_rate": 3.446686404194337e-06,
+      "loss": 0.2056,
+      "step": 230
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.5967712182397447,
+      "learning_rate": 3.4056135837619077e-06,
+      "loss": 0.241,
+      "step": 231
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9875722123937978,
+      "learning_rate": 3.3646601834128924e-06,
+      "loss": 0.2103,
+      "step": 232
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.3156241014697734,
+      "learning_rate": 3.3238292705708675e-06,
+      "loss": 0.2559,
+      "step": 233
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9583948477933737,
+      "learning_rate": 3.2831239034850593e-06,
+      "loss": 0.1841,
+      "step": 234
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.6623355925604687,
+      "learning_rate": 3.2425471310012645e-06,
+      "loss": 0.1736,
+      "step": 235
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.304934915624425,
+      "learning_rate": 3.2021019923335093e-06,
+      "loss": 0.218,
+      "step": 236
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.095700628908178,
+      "learning_rate": 3.1617915168363994e-06,
+      "loss": 0.2317,
+      "step": 237
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.4376828881849366,
+      "learning_rate": 3.121618723778225e-06,
+      "loss": 0.2422,
+      "step": 238
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1487002431162434,
+      "learning_rate": 3.081586622114809e-06,
+      "loss": 0.1747,
+      "step": 239
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0390092539425828,
+      "learning_rate": 3.041698210264149e-06,
+      "loss": 0.2298,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8425241798233793,
+      "learning_rate": 3.001956475881822e-06,
+      "loss": 0.1973,
+      "step": 241
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8843779947738756,
+      "learning_rate": 2.962364395637216e-06,
+      "loss": 0.1775,
+      "step": 242
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.165689883276365,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 0.1878,
+      "step": 243
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.8617909136981146,
+      "learning_rate": 2.8836410479708625e-06,
+      "loss": 0.2705,
+      "step": 244
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.2725720812455874,
+      "learning_rate": 2.84451567695456e-06,
+      "loss": 0.2277,
+      "step": 245
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.190062444782164,
+      "learning_rate": 2.805551752445222e-06,
+      "loss": 0.2442,
+      "step": 246
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.7735306208588132,
+      "learning_rate": 2.766752192854012e-06,
+      "loss": 0.2069,
+      "step": 247
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.9836421057453275,
+      "learning_rate": 2.728119904281105e-06,
+      "loss": 0.2085,
+      "step": 248
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.9257316824367812,
+      "learning_rate": 2.689657780298019e-06,
+      "loss": 0.1866,
+      "step": 249
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0357194391176094,
+      "learning_rate": 2.651368701730889e-06,
+      "loss": 0.1756,
+      "step": 250
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.7986810582564121,
+      "learning_rate": 2.6132555364446856e-06,
+      "loss": 0.1615,
+      "step": 251
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.8592249880783868,
+      "learning_rate": 2.5753211391284172e-06,
+      "loss": 0.1643,
+      "step": 252
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0235299222662588,
+      "learning_rate": 2.537568351081311e-06,
+      "loss": 0.1923,
+      "step": 253
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.2999235904539277,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1948,
+      "step": 254
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6457603543162468,
+      "learning_rate": 2.4626188997667224e-06,
+      "loss": 0.1819,
+      "step": 255
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.2926694326856092,
+      "learning_rate": 2.425427850238565e-06,
+      "loss": 0.1955,
+      "step": 256
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.7141332989842546,
+      "learning_rate": 2.388429637037753e-06,
+      "loss": 0.1613,
+      "step": 257
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.8934250309338756,
+      "learning_rate": 2.3516270313430085e-06,
+      "loss": 0.2023,
+      "step": 258
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.8160378695917272,
+      "learning_rate": 2.3150227896819782e-06,
+      "loss": 0.1939,
+      "step": 259
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.9420598556403198,
+      "learning_rate": 2.278619653724781e-06,
+      "loss": 0.1851,
+      "step": 260
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.1334957223710067,
+      "learning_rate": 2.2424203500786473e-06,
+      "loss": 0.1899,
+      "step": 261
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.3969384560319473,
+      "learning_rate": 2.206427590083703e-06,
+      "loss": 0.2018,
+      "step": 262
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.2979638085285385,
+      "learning_rate": 2.170644069609876e-06,
+      "loss": 0.2209,
+      "step": 263
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.1341344477894943,
+      "learning_rate": 2.1350724688549906e-06,
+      "loss": 0.2506,
+      "step": 264
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.505962420051243,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.2544,
+      "step": 265
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.511809643082286,
+      "learning_rate": 2.0645756677294788e-06,
+      "loss": 0.2965,
+      "step": 266
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.6443629471499115,
+      "learning_rate": 2.029655747593169e-06,
+      "loss": 0.1906,
+      "step": 267
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.7536871845510098,
+      "learning_rate": 1.9949583072489455e-06,
+      "loss": 0.1936,
+      "step": 268
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.9161074827777862,
+      "learning_rate": 1.9604859455468587e-06,
+      "loss": 0.1912,
+      "step": 269
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0969167751901923,
+      "learning_rate": 1.926241244478496e-06,
+      "loss": 0.2107,
+      "step": 270
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.9659245535161112,
+      "learning_rate": 1.8922267689835806e-06,
+      "loss": 0.2165,
+      "step": 271
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.173589662046032,
+      "learning_rate": 1.8584450667578656e-06,
+      "loss": 0.2401,
+      "step": 272
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.1959928398399948,
+      "learning_rate": 1.8248986680623077e-06,
+      "loss": 0.2075,
+      "step": 273
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9472842845266933,
+      "learning_rate": 1.7915900855335506e-06,
+      "loss": 0.1701,
+      "step": 274
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9777100393095655,
+      "learning_rate": 1.7585218139957205e-06,
+      "loss": 0.1996,
+      "step": 275
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.4597546225589537,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 0.2034,
+      "step": 276
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0295705900486563,
+      "learning_rate": 1.6931160930069789e-06,
+      "loss": 0.2129,
+      "step": 277
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7429356481152557,
+      "learning_rate": 1.6607835424667578e-06,
+      "loss": 0.1535,
+      "step": 278
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.2815961274954903,
+      "learning_rate": 1.6287011003719105e-06,
+      "loss": 0.2403,
+      "step": 279
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.0206240990901747,
+      "learning_rate": 1.596871169708235e-06,
+      "loss": 0.1858,
+      "step": 280
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.6856440750208912,
+      "learning_rate": 1.5652961345483353e-06,
+      "loss": 0.204,
+      "step": 281
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.7652934595039215,
+      "learning_rate": 1.5339783598730568e-06,
+      "loss": 0.141,
+      "step": 282
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.2432597598371389,
+      "learning_rate": 1.5029201913943425e-06,
+      "loss": 0.2189,
+      "step": 283
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9792339514531253,
+      "learning_rate": 1.4721239553795485e-06,
+      "loss": 0.2163,
+      "step": 284
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7810824523129147,
+      "learning_rate": 1.4415919584771999e-06,
+      "loss": 0.1656,
+      "step": 285
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8934890216214316,
+      "learning_rate": 1.4113264875442201e-06,
+      "loss": 0.19,
+      "step": 286
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.8685042798744403,
+      "learning_rate": 1.3813298094746491e-06,
+      "loss": 0.1869,
+      "step": 287
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9600448799971761,
+      "learning_rate": 1.35160417102985e-06,
+      "loss": 0.1753,
+      "step": 288
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.5575394515678607,
+      "learning_rate": 1.3221517986702249e-06,
+      "loss": 0.2213,
+      "step": 289
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.0321008597314612,
+      "learning_rate": 1.292974898388456e-06,
+      "loss": 0.1915,
+      "step": 290
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9037028216806072,
+      "learning_rate": 1.2640756555442684e-06,
+      "loss": 0.1803,
+      "step": 291
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0707840349871238,
+      "learning_rate": 1.235456234700756e-06,
+      "loss": 0.2387,
+      "step": 292
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.8451841229884565,
+      "learning_rate": 1.207118779462248e-06,
+      "loss": 0.168,
+      "step": 293
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0269508194303216,
+      "learning_rate": 1.1790654123137552e-06,
+      "loss": 0.2165,
+      "step": 294
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.9461917746452349,
+      "learning_rate": 1.1512982344619904e-06,
+      "loss": 0.2098,
+      "step": 295
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.4147781409520923,
+      "learning_rate": 1.1238193256779955e-06,
+      "loss": 0.2196,
+      "step": 296
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.56084132809559,
+      "learning_rate": 1.0966307441413598e-06,
+      "loss": 0.2132,
+      "step": 297
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.0161735584257976,
+      "learning_rate": 1.0697345262860638e-06,
+      "loss": 0.2232,
+      "step": 298
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6742153593334117,
+      "learning_rate": 1.0431326866479457e-06,
+      "loss": 0.2136,
+      "step": 299
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.144823746869992,
+      "learning_rate": 1.01682721771382e-06,
+      "loss": 0.216,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2651620873455793,
+      "learning_rate": 9.908200897722332e-07,
+      "loss": 0.1949,
+      "step": 301
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.775539527000076,
+      "learning_rate": 9.6511325076589e-07,
+      "loss": 0.18,
+      "step": 302
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.8566223976377377,
+      "learning_rate": 9.397086261457511e-07,
+      "loss": 0.1609,
+      "step": 303
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.4641240145262817,
+      "learning_rate": 9.146081187268185e-07,
+      "loss": 0.2048,
+      "step": 304
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.6540588118605503,
+      "learning_rate": 8.898136085456127e-07,
+      "loss": 0.1659,
+      "step": 305
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0913890916917088,
+      "learning_rate": 8.65326952719357e-07,
+      "loss": 0.2152,
+      "step": 306
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0344184572118216,
+      "learning_rate": 8.411499853068783e-07,
+      "loss": 0.2183,
+      "step": 307
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.1848888867240643,
+      "learning_rate": 8.172845171712379e-07,
+      "loss": 0.1685,
+      "step": 308
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.4568876835036333,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.1877,
+      "step": 309
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.1997044752508947,
+      "learning_rate": 7.70495205391818e-07,
+      "loss": 0.2102,
+      "step": 310
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.055582444042227,
+      "learning_rate": 7.475748662833615e-07,
+      "loss": 0.1662,
+      "step": 311
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 2.6662177592798817,
+      "learning_rate": 7.249730352599e-07,
+      "loss": 0.2225,
+      "step": 312
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.8540722123505368,
+      "learning_rate": 7.026914052062433e-07,
+      "loss": 0.1686,
+      "step": 313
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.164196309426519,
+      "learning_rate": 6.807316450240425e-07,
+      "loss": 0.1877,
+      "step": 314
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.1475160221361378,
+      "learning_rate": 6.590953995067812e-07,
+      "loss": 0.2272,
+      "step": 315
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8085276468949238,
+      "learning_rate": 6.377842892165892e-07,
+      "loss": 0.177,
+      "step": 316
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.9783392259539228,
+      "learning_rate": 6.167999103628569e-07,
+      "loss": 0.2171,
+      "step": 317
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 2.264417641622648,
+      "learning_rate": 5.961438346826792e-07,
+      "loss": 0.2343,
+      "step": 318
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.8386980689323554,
+      "learning_rate": 5.758176093231294e-07,
+      "loss": 0.2079,
+      "step": 319
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2117820640884065,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.1937,
+      "step": 320
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.7088819848375714,
+      "learning_rate": 5.361607745106817e-07,
+      "loss": 0.1526,
+      "step": 321
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.0561579670044179,
+      "learning_rate": 5.168331353681643e-07,
+      "loss": 0.1773,
+      "step": 322
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.0124996437916134,
+      "learning_rate": 4.97841286944557e-07,
+      "loss": 0.2151,
+      "step": 323
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.3488264048007867,
+      "learning_rate": 4.791866517357491e-07,
+      "loss": 0.2361,
+      "step": 324
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.9503210346910481,
+      "learning_rate": 4.608706269802471e-07,
+      "loss": 0.2032,
+      "step": 325
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0775130418414676,
+      "learning_rate": 4.428945845545168e-07,
+      "loss": 0.1688,
+      "step": 326
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.8892158871500606,
+      "learning_rate": 4.2525987087023433e-07,
+      "loss": 0.1784,
+      "step": 327
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.5250799592751716,
+      "learning_rate": 4.0796780677343606e-07,
+      "loss": 0.2012,
+      "step": 328
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2002308387725682,
+      "learning_rate": 3.910196874455896e-07,
+      "loss": 0.2197,
+      "step": 329
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.7832717273950531,
+      "learning_rate": 3.744167823065814e-07,
+      "loss": 0.2267,
+      "step": 330
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.4443931054038313,
+      "learning_rate": 3.581603349196372e-07,
+      "loss": 0.2291,
+      "step": 331
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.8575087569323027,
+      "learning_rate": 3.4225156289818096e-07,
+      "loss": 0.1922,
+      "step": 332
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.0015853171272124,
+      "learning_rate": 3.26691657814634e-07,
+      "loss": 0.1956,
+      "step": 333
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.4408590110349573,
+      "learning_rate": 3.1148178511116624e-07,
+      "loss": 0.2019,
+      "step": 334
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.3629351147560047,
+      "learning_rate": 2.966230840124007e-07,
+      "loss": 0.1901,
+      "step": 335
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9672147122577578,
+      "learning_rate": 2.821166674400905e-07,
+      "loss": 0.1817,
+      "step": 336
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.1382075239943934,
+      "learning_rate": 2.6796362192975766e-07,
+      "loss": 0.2216,
+      "step": 337
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9386055088719938,
+      "learning_rate": 2.5416500754931294e-07,
+      "loss": 0.1642,
+      "step": 338
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.1082965446712723,
+      "learning_rate": 2.407218578196524e-07,
+      "loss": 0.2113,
+      "step": 339
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.8604705317919309,
+      "learning_rate": 2.2763517963725169e-07,
+      "loss": 0.1593,
+      "step": 340
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.2697105840508078,
+      "learning_rate": 2.1490595319874574e-07,
+      "loss": 0.1525,
+      "step": 341
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0766804959458083,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 0.1957,
+      "step": 342
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.8671741152259191,
+      "learning_rate": 1.905236424022633e-07,
+      "loss": 0.1978,
+      "step": 343
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.3844811683571667,
+      "learning_rate": 1.7887238428763553e-07,
+      "loss": 0.1561,
+      "step": 344
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.526716851084662,
+      "learning_rate": 1.6758223026681507e-07,
+      "loss": 0.1706,
+      "step": 345
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.918215159118574,
+      "learning_rate": 1.5665402597616842e-07,
+      "loss": 0.1861,
+      "step": 346
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.255208384109814,
+      "learning_rate": 1.4608858994190344e-07,
+      "loss": 0.155,
+      "step": 347
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.9696426069386889,
+      "learning_rate": 1.358867135187636e-07,
+      "loss": 0.2159,
+      "step": 348
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.9392727009606353,
+      "learning_rate": 1.2604916083075236e-07,
+      "loss": 0.2102,
+      "step": 349
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.056544505555531,
+      "learning_rate": 1.1657666871390471e-07,
+      "loss": 0.2298,
+      "step": 350
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.4138822544214522,
+      "learning_rate": 1.0746994666109234e-07,
+      "loss": 0.1373,
+      "step": 351
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.0639971581032015,
+      "learning_rate": 9.872967676888611e-08,
+      "loss": 0.191,
+      "step": 352
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7033027987135066,
+      "learning_rate": 9.035651368646647e-08,
+      "loss": 0.1786,
+      "step": 353
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.2567643527023928,
+      "learning_rate": 8.235108456658814e-08,
+      "loss": 0.1913,
+      "step": 354
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.7030518826228479,
+      "learning_rate": 7.471398901860772e-08,
+      "loss": 0.1715,
+      "step": 355
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.0788061065039583,
+      "learning_rate": 6.744579906357185e-08,
+      "loss": 0.2076,
+      "step": 356
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.8457909524158602,
+      "learning_rate": 6.054705909137426e-08,
+      "loss": 0.2153,
+      "step": 357
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.0819298321885193,
+      "learning_rate": 5.401828581997948e-08,
+      "loss": 0.2084,
+      "step": 358
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.3313164307665812,
+      "learning_rate": 4.7859968256719344e-08,
+      "loss": 0.1534,
+      "step": 359
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9541364087042156,
+      "learning_rate": 4.207256766166845e-08,
+      "loss": 0.1772,
+      "step": 360
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.0274591464057286,
+      "learning_rate": 3.665651751309451e-08,
+      "loss": 0.1865,
+      "step": 361
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.2836775792842172,
+      "learning_rate": 3.16122234749916e-08,
+      "loss": 0.2195,
+      "step": 362
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9350601072633269,
+      "learning_rate": 2.6940063366693303e-08,
+      "loss": 0.1225,
+      "step": 363
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.6741410342291686,
+      "learning_rate": 2.264038713457706e-08,
+      "loss": 0.2001,
+      "step": 364
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.113136729446253,
+      "learning_rate": 1.8713516825851207e-08,
+      "loss": 0.1468,
+      "step": 365
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.0177166078743458,
+      "learning_rate": 1.51597465644332e-08,
+      "loss": 0.1722,
+      "step": 366
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.3978046284035448,
+      "learning_rate": 1.1979342528922189e-08,
+      "loss": 0.1879,
+      "step": 367
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7480278975483311,
+      "learning_rate": 9.1725429326589e-09,
+      "loss": 0.2032,
+      "step": 368
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.2771884250719052,
+      "learning_rate": 6.739558005884883e-09,
+      "loss": 0.2167,
+      "step": 369
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.8682323897000702,
+      "learning_rate": 4.6805699799967744e-09,
+      "loss": 0.1923,
+      "step": 370
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.3344533873272757,
+      "learning_rate": 2.995733073895557e-09,
+      "loss": 0.1508,
+      "step": 371
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.7608860560649859,
+      "learning_rate": 1.6851734824380184e-09,
+      "loss": 0.1796,
+      "step": 372
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 2.1117745028421475,
+      "learning_rate": 7.48989366980979e-10,
+      "loss": 0.1961,
+      "step": 373
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2276219202479637,
+      "learning_rate": 1.872508480332824e-10,
+      "loss": 0.1978,
+      "step": 374
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7085984121892608,
+      "learning_rate": 0.0,
+      "loss": 0.1596,
+      "step": 375
+    },
+    {
+      "epoch": 1.0,
+      "step": 375,
+      "total_flos": 20962186485760.0,
+      "train_loss": 0.3264745690425237,
+      "train_runtime": 917.1419,
+      "train_samples_per_second": 3.271,
+      "train_steps_per_second": 0.409
+    }
+  ],
+  "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_adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0afa32d43f18acf8c160be86dfa666481964a05940c55d215a86fc1c87ac2c06
+size 7928