Upload folder using huggingface_hub

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_language_model_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_language_model_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_language_model,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_language_model_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_language_model_adapter/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f89f6c01f0072dbe3df59c1ceeaf9d30e39291c8d9232e2edf43d5a6476cf7
+size 4877668032

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_language_model_adapter/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8fef2dc837b22e0ef46ac3b3228a363f3ec80a25f7ef50c9584e078897acec
+size 4932751008

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_language_model_adapter/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae770e2c5d83e64a1cfc553cce90f96e10fa2fe9a4ea69457291ed250874fc4b
+size 4994571904

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_language_model_adapter/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f22f438c3f42d7dcd6253a98c4495bbe35b0f6b8871e9cd7b6a7e1f6bb95f8
+size 1255812224

llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split02_tune_mm_language_model_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_language_model_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_language_model_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_language_model_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": 9.525787471194466,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.5596,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 13.577661133994914,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.8544,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 9.504313053427069,
+      "learning_rate": 2.5e-06,
+      "loss": 0.579,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 10.1558047814326,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6699,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 7.271344157504866,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.481,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.473137771665247,
+      "learning_rate": 5e-06,
+      "loss": 0.3032,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.225786237665924,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.3208,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 11.639924519710787,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3217,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 13.757856228483691,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2966,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 9.845207044239878,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.2406,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 9.536972149961677,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.2531,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.641691208236112,
+      "learning_rate": 1e-05,
+      "loss": 0.2419,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.358208724595953,
+      "learning_rate": 9.999812749151968e-06,
+      "loss": 0.1774,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.299739880329351,
+      "learning_rate": 9.99925101063302e-06,
+      "loss": 0.1501,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.694543891599893,
+      "learning_rate": 9.998314826517564e-06,
+      "loss": 0.1601,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.61216657244483,
+      "learning_rate": 9.997004266926105e-06,
+      "loss": 0.1793,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.112377494051429,
+      "learning_rate": 9.995319430020004e-06,
+      "loss": 0.1461,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.169803794764557,
+      "learning_rate": 9.993260441994116e-06,
+      "loss": 0.1528,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.5539426085038954,
+      "learning_rate": 9.990827457067342e-06,
+      "loss": 0.1703,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.038891724974813,
+      "learning_rate": 9.988020657471078e-06,
+      "loss": 0.1485,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.7546868765424555,
+      "learning_rate": 9.984840253435569e-06,
+      "loss": 0.1482,
+      "step": 21
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.582383481240005,
+      "learning_rate": 9.98128648317415e-06,
+      "loss": 0.1318,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.260395867192864,
+      "learning_rate": 9.977359612865424e-06,
+      "loss": 0.1585,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.6099351110697153,
+      "learning_rate": 9.973059936633308e-06,
+      "loss": 0.1343,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.2243282080736813,
+      "learning_rate": 9.968387776525009e-06,
+      "loss": 0.1378,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.776673258661529,
+      "learning_rate": 9.963343482486907e-06,
+      "loss": 0.1462,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.8204710440207457,
+      "learning_rate": 9.957927432338332e-06,
+      "loss": 0.1236,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.318251398093008,
+      "learning_rate": 9.952140031743282e-06,
+      "loss": 0.116,
+      "step": 28
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.070182199876401,
+      "learning_rate": 9.945981714180021e-06,
+      "loss": 0.1316,
+      "step": 29
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.371337063304912,
+      "learning_rate": 9.939452940908627e-06,
+      "loss": 0.1337,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.8168410746950572,
+      "learning_rate": 9.932554200936428e-06,
+      "loss": 0.1062,
+      "step": 31
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.420970918077943,
+      "learning_rate": 9.925286010981394e-06,
+      "loss": 0.1054,
+      "step": 32
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.8535768596402524,
+      "learning_rate": 9.917648915433413e-06,
+      "loss": 0.1305,
+      "step": 33
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.063893224673226,
+      "learning_rate": 9.909643486313533e-06,
+      "loss": 0.0945,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.207911840353043,
+      "learning_rate": 9.901270323231114e-06,
+      "loss": 0.1256,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.756210285624784,
+      "learning_rate": 9.892530053338909e-06,
+      "loss": 0.151,
+      "step": 36
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.3602317825579266,
+      "learning_rate": 9.883423331286096e-06,
+      "loss": 0.1359,
+      "step": 37
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.8077128348840696,
+      "learning_rate": 9.873950839169248e-06,
+      "loss": 0.1334,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.0662089841896556,
+      "learning_rate": 9.864113286481237e-06,
+      "loss": 0.121,
+      "step": 39
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.0211039087884854,
+      "learning_rate": 9.853911410058097e-06,
+      "loss": 0.1042,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.2110923884782174,
+      "learning_rate": 9.843345974023833e-06,
+      "loss": 0.1184,
+      "step": 41
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.331141233258926,
+      "learning_rate": 9.832417769733185e-06,
+      "loss": 0.1412,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.3274628342660257,
+      "learning_rate": 9.821127615712365e-06,
+      "loss": 0.1117,
+      "step": 43
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.7733515829449136,
+      "learning_rate": 9.809476357597738e-06,
+      "loss": 0.122,
+      "step": 44
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.8153684914162604,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 0.1338,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.3142358772587333,
+      "learning_rate": 9.785094046801256e-06,
+      "loss": 0.1551,
+      "step": 46
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.9090030646334941,
+      "learning_rate": 9.77236482036275e-06,
+      "loss": 0.116,
+      "step": 47
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.2142026505005052,
+      "learning_rate": 9.759278142180348e-06,
+      "loss": 0.1293,
+      "step": 48
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.233514584831996,
+      "learning_rate": 9.745834992450688e-06,
+      "loss": 0.1199,
+      "step": 49
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.9432182852473674,
+      "learning_rate": 9.732036378070243e-06,
+      "loss": 0.1401,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.627864211363688,
+      "learning_rate": 9.717883332559911e-06,
+      "loss": 0.1172,
+      "step": 51
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.6569318244939815,
+      "learning_rate": 9.703376915987601e-06,
+      "loss": 0.1186,
+      "step": 52
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.5130939062894018,
+      "learning_rate": 9.688518214888836e-06,
+      "loss": 0.1065,
+      "step": 53
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.0080004053583884,
+      "learning_rate": 9.673308342185366e-06,
+      "loss": 0.0827,
+      "step": 54
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.5797246859337049,
+      "learning_rate": 9.657748437101819e-06,
+      "loss": 0.1038,
+      "step": 55
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.192639012912126,
+      "learning_rate": 9.641839665080363e-06,
+      "loss": 0.115,
+      "step": 56
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.6613299387190694,
+      "learning_rate": 9.625583217693419e-06,
+      "loss": 0.1287,
+      "step": 57
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.622835316395502,
+      "learning_rate": 9.60898031255441e-06,
+      "loss": 0.1277,
+      "step": 58
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.263701190970214,
+      "learning_rate": 9.592032193226564e-06,
+      "loss": 0.121,
+      "step": 59
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.8393857236106035,
+      "learning_rate": 9.574740129129767e-06,
+      "loss": 0.1372,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.527610747710452,
+      "learning_rate": 9.557105415445485e-06,
+      "loss": 0.1238,
+      "step": 61
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.4706801331734707,
+      "learning_rate": 9.539129373019755e-06,
+      "loss": 0.1112,
+      "step": 62
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.0484040446834957,
+      "learning_rate": 9.520813348264252e-06,
+      "loss": 0.1416,
+      "step": 63
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.0428887789170087,
+      "learning_rate": 9.502158713055444e-06,
+      "loss": 0.1207,
+      "step": 64
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.1115100407848766,
+      "learning_rate": 9.483166864631837e-06,
+      "loss": 0.1031,
+      "step": 65
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.998134909705607,
+      "learning_rate": 9.46383922548932e-06,
+      "loss": 0.1376,
+      "step": 66
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.9056949619057906,
+      "learning_rate": 9.444177243274619e-06,
+      "loss": 0.0907,
+      "step": 67
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.268236057700453,
+      "learning_rate": 9.424182390676872e-06,
+      "loss": 0.1266,
+      "step": 68
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.7390922360422665,
+      "learning_rate": 9.403856165317322e-06,
+      "loss": 0.1356,
+      "step": 69
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.7349600792861224,
+      "learning_rate": 9.383200089637143e-06,
+      "loss": 0.0844,
+      "step": 70
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.735854447343811,
+      "learning_rate": 9.362215710783411e-06,
+      "loss": 0.1043,
+      "step": 71
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.6147812363374454,
+      "learning_rate": 9.34090460049322e-06,
+      "loss": 0.1228,
+      "step": 72
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.6393931610837924,
+      "learning_rate": 9.319268354975958e-06,
+      "loss": 0.1277,
+      "step": 73
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4740517469891852,
+      "learning_rate": 9.297308594793757e-06,
+      "loss": 0.1088,
+      "step": 74
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.767019634612431,
+      "learning_rate": 9.275026964740101e-06,
+      "loss": 0.1136,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.1498021075862725,
+      "learning_rate": 9.252425133716639e-06,
+      "loss": 0.1191,
+      "step": 76
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.7673189701034766,
+      "learning_rate": 9.229504794608182e-06,
+      "loss": 0.1331,
+      "step": 77
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.7249057115816213,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 0.1088,
+      "step": 78
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.6826256963672535,
+      "learning_rate": 9.182715482828764e-06,
+      "loss": 0.1197,
+      "step": 79
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.4995621963808283,
+      "learning_rate": 9.158850014693123e-06,
+      "loss": 0.1159,
+      "step": 80
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.225734409563177,
+      "learning_rate": 9.134673047280644e-06,
+      "loss": 0.1145,
+      "step": 81
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.178869106153866,
+      "learning_rate": 9.110186391454389e-06,
+      "loss": 0.1138,
+      "step": 82
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.7935119809081232,
+      "learning_rate": 9.085391881273182e-06,
+      "loss": 0.1202,
+      "step": 83
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.4131819607398894,
+      "learning_rate": 9.060291373854252e-06,
+      "loss": 0.1168,
+      "step": 84
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.4387452774931535,
+      "learning_rate": 9.034886749234112e-06,
+      "loss": 0.1131,
+      "step": 85
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.8786145682292499,
+      "learning_rate": 9.009179910227767e-06,
+      "loss": 0.1315,
+      "step": 86
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.4835289965471175,
+      "learning_rate": 8.98317278228618e-06,
+      "loss": 0.1057,
+      "step": 87
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.5645732951140703,
+      "learning_rate": 8.956867313352055e-06,
+      "loss": 0.1174,
+      "step": 88
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.7690057177965324,
+      "learning_rate": 8.930265473713939e-06,
+      "loss": 0.1265,
+      "step": 89
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.3090425710387343,
+      "learning_rate": 8.90336925585864e-06,
+      "loss": 0.1257,
+      "step": 90
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.371320893065917,
+      "learning_rate": 8.876180674322006e-06,
+      "loss": 0.1079,
+      "step": 91
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.7940819743067475,
+      "learning_rate": 8.84870176553801e-06,
+      "loss": 0.1128,
+      "step": 92
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3926439612862556,
+      "learning_rate": 8.820934587686247e-06,
+      "loss": 0.0977,
+      "step": 93
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.737237377743936,
+      "learning_rate": 8.792881220537752e-06,
+      "loss": 0.0981,
+      "step": 94
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.899268658488689,
+      "learning_rate": 8.764543765299245e-06,
+      "loss": 0.13,
+      "step": 95
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.688823320546145,
+      "learning_rate": 8.735924344455732e-06,
+      "loss": 0.1179,
+      "step": 96
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.35157630261405,
+      "learning_rate": 8.707025101611546e-06,
+      "loss": 0.1156,
+      "step": 97
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.359119871816434,
+      "learning_rate": 8.677848201329775e-06,
+      "loss": 0.1046,
+      "step": 98
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.271423782440023,
+      "learning_rate": 8.64839582897015e-06,
+      "loss": 0.118,
+      "step": 99
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 2.9184592159863385,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.1163,
+      "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.7491525100963405,
+      "learning_rate": 8.588673512455781e-06,
+      "loss": 0.0997,
+      "step": 101
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 2.2120749398244266,
+      "learning_rate": 8.558408041522801e-06,
+      "loss": 0.1056,
+      "step": 102
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 2.5653511167020215,
+      "learning_rate": 8.527876044620453e-06,
+      "loss": 0.0955,
+      "step": 103
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.2496801798442325,
+      "learning_rate": 8.497079808605659e-06,
+      "loss": 0.114,
+      "step": 104
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.7993365601448135,
+      "learning_rate": 8.466021640126946e-06,
+      "loss": 0.1092,
+      "step": 105
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.0230588860969276,
+      "learning_rate": 8.434703865451666e-06,
+      "loss": 0.0796,
+      "step": 106
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 2.2307605427659114,
+      "learning_rate": 8.403128830291767e-06,
+      "loss": 0.1122,
+      "step": 107
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.6812171495292538,
+      "learning_rate": 8.371298899628091e-06,
+      "loss": 0.1072,
+      "step": 108
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.6381589602464814,
+      "learning_rate": 8.339216457533244e-06,
+      "loss": 0.0951,
+      "step": 109
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.7802439207091867,
+      "learning_rate": 8.306883906993022e-06,
+      "loss": 0.1068,
+      "step": 110
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.0747946716275967,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 0.1166,
+      "step": 111
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.8329161733614794,
+      "learning_rate": 8.24147818600428e-06,
+      "loss": 0.1021,
+      "step": 112
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.5011532868102138,
+      "learning_rate": 8.20840991446645e-06,
+      "loss": 0.0746,
+      "step": 113
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3585139474287726,
+      "learning_rate": 8.175101331937692e-06,
+      "loss": 0.1083,
+      "step": 114
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.0731958994025306,
+      "learning_rate": 8.141554933242135e-06,
+      "loss": 0.1076,
+      "step": 115
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 2.318173470512319,
+      "learning_rate": 8.10777323101642e-06,
+      "loss": 0.0906,
+      "step": 116
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.2700895060798736,
+      "learning_rate": 8.073758755521506e-06,
+      "loss": 0.1042,
+      "step": 117
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.795689783118604,
+      "learning_rate": 8.03951405445314e-06,
+      "loss": 0.0812,
+      "step": 118
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3457044865138106,
+      "learning_rate": 8.005041692751055e-06,
+      "loss": 0.0962,
+      "step": 119
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.5281946694529414,
+      "learning_rate": 7.970344252406832e-06,
+      "loss": 0.106,
+      "step": 120
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.4678785567587775,
+      "learning_rate": 7.935424332270523e-06,
+      "loss": 0.1062,
+      "step": 121
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.396745135738554,
+      "learning_rate": 7.900284547855992e-06,
+      "loss": 0.1208,
+      "step": 122
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.6073489211715066,
+      "learning_rate": 7.864927531145012e-06,
+      "loss": 0.1019,
+      "step": 123
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.6078144270704633,
+      "learning_rate": 7.829355930390126e-06,
+      "loss": 0.1168,
+      "step": 124
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.9435562600383303,
+      "learning_rate": 7.7935724099163e-06,
+      "loss": 0.1047,
+      "step": 125
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.7320744879408487,
+      "learning_rate": 7.757579649921354e-06,
+      "loss": 0.1018,
+      "step": 126
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.816166454632215,
+      "learning_rate": 7.721380346275221e-06,
+      "loss": 0.1032,
+      "step": 127
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.6508731219445392,
+      "learning_rate": 7.684977210318024e-06,
+      "loss": 0.0783,
+      "step": 128
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.838389328103033,
+      "learning_rate": 7.648372968656995e-06,
+      "loss": 0.1201,
+      "step": 129
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.6631347109608936,
+      "learning_rate": 7.611570362962247e-06,
+      "loss": 0.1226,
+      "step": 130
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.8342658893900303,
+      "learning_rate": 7.574572149761437e-06,
+      "loss": 0.1196,
+      "step": 131
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.06691046408365,
+      "learning_rate": 7.5373811002332785e-06,
+      "loss": 0.0929,
+      "step": 132
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.2872097128870155,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.121,
+      "step": 133
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.08594360285207,
+      "learning_rate": 7.462431648918689e-06,
+      "loss": 0.0911,
+      "step": 134
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.6958363625351667,
+      "learning_rate": 7.424678860871584e-06,
+      "loss": 0.0905,
+      "step": 135
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.6226517587117575,
+      "learning_rate": 7.3867444635553165e-06,
+      "loss": 0.1199,
+      "step": 136
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.035656759653299,
+      "learning_rate": 7.3486312982691134e-06,
+      "loss": 0.0985,
+      "step": 137
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.7906647499244968,
+      "learning_rate": 7.310342219701981e-06,
+      "loss": 0.1119,
+      "step": 138
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.6732995195684062,
+      "learning_rate": 7.271880095718895e-06,
+      "loss": 0.1155,
+      "step": 139
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.614107136721527,
+      "learning_rate": 7.233247807145989e-06,
+      "loss": 0.1191,
+      "step": 140
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.4624554596416106,
+      "learning_rate": 7.19444824755478e-06,
+      "loss": 0.0813,
+      "step": 141
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.0012319517798325,
+      "learning_rate": 7.155484323045442e-06,
+      "loss": 0.1136,
+      "step": 142
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.2592162913871308,
+      "learning_rate": 7.11635895202914e-06,
+      "loss": 0.1081,
+      "step": 143
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.6230302280570166,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 0.0998,
+      "step": 144
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.1633372355245533,
+      "learning_rate": 7.037635604362786e-06,
+      "loss": 0.0863,
+      "step": 145
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.5771996295429394,
+      "learning_rate": 6.9980435241181785e-06,
+      "loss": 0.098,
+      "step": 146
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.8859023799191861,
+      "learning_rate": 6.958301789735853e-06,
+      "loss": 0.0924,
+      "step": 147
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.6773850006814912,
+      "learning_rate": 6.918413377885193e-06,
+      "loss": 0.103,
+      "step": 148
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3040377557714922,
+      "learning_rate": 6.878381276221777e-06,
+      "loss": 0.0826,
+      "step": 149
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.6646850091207455,
+      "learning_rate": 6.838208483163601e-06,
+      "loss": 0.1554,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3258441998763089,
+      "learning_rate": 6.797898007666493e-06,
+      "loss": 0.1012,
+      "step": 151
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.1809009985679935,
+      "learning_rate": 6.757452868998737e-06,
+      "loss": 0.1255,
+      "step": 152
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.2097650303007859,
+      "learning_rate": 6.716876096514944e-06,
+      "loss": 0.0898,
+      "step": 153
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.8010961077585854,
+      "learning_rate": 6.676170729429132e-06,
+      "loss": 0.1019,
+      "step": 154
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.282041839459757,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.1048,
+      "step": 155
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.5940022251026889,
+      "learning_rate": 6.594386416238095e-06,
+      "loss": 0.1275,
+      "step": 156
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.2673547783469963,
+      "learning_rate": 6.553313595805666e-06,
+      "loss": 0.1234,
+      "step": 157
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.1494498627143872,
+      "learning_rate": 6.512124431658006e-06,
+      "loss": 0.0935,
+      "step": 158
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.7806740800943994,
+      "learning_rate": 6.470822008877482e-06,
+      "loss": 0.1122,
+      "step": 159
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.7117143529611942,
+      "learning_rate": 6.4294094210295725e-06,
+      "loss": 0.0966,
+      "step": 160
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.8517487155152543,
+      "learning_rate": 6.3878897699311525e-06,
+      "loss": 0.1062,
+      "step": 161
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.3368368916924598,
+      "learning_rate": 6.346266165418173e-06,
+      "loss": 0.0914,
+      "step": 162
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.2601666859073024,
+      "learning_rate": 6.304541725112734e-06,
+      "loss": 0.0947,
+      "step": 163
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.3254854939032,
+      "learning_rate": 6.262719574189564e-06,
+      "loss": 0.105,
+      "step": 164
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.6649263184355307,
+      "learning_rate": 6.2208028451419575e-06,
+      "loss": 0.1077,
+      "step": 165
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.6405940436592243,
+      "learning_rate": 6.178794677547138e-06,
+      "loss": 0.0921,
+      "step": 166
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.2174044436496003,
+      "learning_rate": 6.136698217831106e-06,
+      "loss": 0.106,
+      "step": 167
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1268027015482143,
+      "learning_rate": 6.094516619032975e-06,
+      "loss": 0.1089,
+      "step": 168
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.8227565278270648,
+      "learning_rate": 6.052253040568804e-06,
+      "loss": 0.1116,
+      "step": 169
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.426176514148128,
+      "learning_rate": 6.009910647994956e-06,
+      "loss": 0.1044,
+      "step": 170
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.9640988132893784,
+      "learning_rate": 5.967492612770999e-06,
+      "loss": 0.1329,
+      "step": 171
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.8848868019896607,
+      "learning_rate": 5.925002112022158e-06,
+      "loss": 0.1051,
+      "step": 172
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9617746451294735,
+      "learning_rate": 5.882442328301356e-06,
+      "loss": 0.1106,
+      "step": 173
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.7780923272617215,
+      "learning_rate": 5.839816449350824e-06,
+      "loss": 0.116,
+      "step": 174
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.2399040759444384,
+      "learning_rate": 5.7971276678633625e-06,
+      "loss": 0.0866,
+      "step": 175
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.8454403664078596,
+      "learning_rate": 5.754379181243179e-06,
+      "loss": 0.104,
+      "step": 176
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.721767034004839,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 0.1159,
+      "step": 177
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.5123438813324774,
+      "learning_rate": 5.668715904341365e-06,
+      "loss": 0.097,
+      "step": 178
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.0460217725253567,
+      "learning_rate": 5.62580753026823e-06,
+      "loss": 0.1383,
+      "step": 179
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.0359508980034966,
+      "learning_rate": 5.5828522829987965e-06,
+      "loss": 0.0756,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.5253154319365736,
+      "learning_rate": 5.539853379895656e-06,
+      "loss": 0.124,
+      "step": 181
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 2.952447396295749,
+      "learning_rate": 5.496814041591234e-06,
+      "loss": 0.104,
+      "step": 182
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.3073870851469223,
+      "learning_rate": 5.453737491746572e-06,
+      "loss": 0.101,
+      "step": 183
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.5278161503549679,
+      "learning_rate": 5.410626956809864e-06,
+      "loss": 0.1006,
+      "step": 184
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.496307526434967,
+      "learning_rate": 5.367485665774802e-06,
+      "loss": 0.1048,
+      "step": 185
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.3422122254568056,
+      "learning_rate": 5.324316849938715e-06,
+      "loss": 0.1174,
+      "step": 186
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.4666741747146124,
+      "learning_rate": 5.281123742660558e-06,
+      "loss": 0.1317,
+      "step": 187
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5573860742885797,
+      "learning_rate": 5.237909579118713e-06,
+      "loss": 0.1189,
+      "step": 188
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8701555501879027,
+      "learning_rate": 5.194677596068689e-06,
+      "loss": 0.0965,
+      "step": 189
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.9837060564615407,
+      "learning_rate": 5.1514310316006835e-06,
+      "loss": 0.1071,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.2073231188470195,
+      "learning_rate": 5.1081731248970435e-06,
+      "loss": 0.1047,
+      "step": 191
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.8762827562617891,
+      "learning_rate": 5.064907115989655e-06,
+      "loss": 0.0851,
+      "step": 192
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.3754150944189698,
+      "learning_rate": 5.021636245517261e-06,
+      "loss": 0.0929,
+      "step": 193
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.609003452177782,
+      "learning_rate": 4.978363754482741e-06,
+      "loss": 0.1118,
+      "step": 194
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.145415396710654,
+      "learning_rate": 4.935092884010347e-06,
+      "loss": 0.114,
+      "step": 195
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.5058208083845233,
+      "learning_rate": 4.891826875102958e-06,
+      "loss": 0.1279,
+      "step": 196
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.8090090279962971,
+      "learning_rate": 4.848568968399317e-06,
+      "loss": 0.098,
+      "step": 197
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.0337143776370297,
+      "learning_rate": 4.805322403931312e-06,
+      "loss": 0.0968,
+      "step": 198
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.6778349959876446,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.0868,
+      "step": 199
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.4941432407079094,
+      "learning_rate": 4.718876257339444e-06,
+      "loss": 0.0838,
+      "step": 200
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.7836240702308432,
+      "learning_rate": 4.6756831500612846e-06,
+      "loss": 0.0914,
+      "step": 201
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.4620483971098008,
+      "learning_rate": 4.632514334225201e-06,
+      "loss": 0.102,
+      "step": 202
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.718475618827365,
+      "learning_rate": 4.589373043190137e-06,
+      "loss": 0.0833,
+      "step": 203
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.6346227111857181,
+      "learning_rate": 4.546262508253429e-06,
+      "loss": 0.1029,
+      "step": 204
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.241323700053044,
+      "learning_rate": 4.503185958408767e-06,
+      "loss": 0.087,
+      "step": 205
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.4385327979629616,
+      "learning_rate": 4.460146620104347e-06,
+      "loss": 0.0889,
+      "step": 206
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.0317334482699727,
+      "learning_rate": 4.417147717001205e-06,
+      "loss": 0.086,
+      "step": 207
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.8536859902718168,
+      "learning_rate": 4.374192469731771e-06,
+      "loss": 0.0865,
+      "step": 208
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.4487764403987118,
+      "learning_rate": 4.331284095658637e-06,
+      "loss": 0.0874,
+      "step": 209
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0421900388121277,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.0889,
+      "step": 210
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.6048926156084906,
+      "learning_rate": 4.245620818756822e-06,
+      "loss": 0.0965,
+      "step": 211
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.9422512471586106,
+      "learning_rate": 4.202872332136639e-06,
+      "loss": 0.0795,
+      "step": 212
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.2174631984995927,
+      "learning_rate": 4.160183550649176e-06,
+      "loss": 0.1142,
+      "step": 213
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.4142882187519912,
+      "learning_rate": 4.117557671698648e-06,
+      "loss": 0.0815,
+      "step": 214
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.8121351993382497,
+      "learning_rate": 4.074997887977843e-06,
+      "loss": 0.0741,
+      "step": 215
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.4787570426425294,
+      "learning_rate": 4.032507387229002e-06,
+      "loss": 0.1123,
+      "step": 216
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.1289778347046044,
+      "learning_rate": 3.9900893520050446e-06,
+      "loss": 0.143,
+      "step": 217
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3920527085790346,
+      "learning_rate": 3.9477469594311975e-06,
+      "loss": 0.0857,
+      "step": 218
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.3463608385452561,
+      "learning_rate": 3.905483380967027e-06,
+      "loss": 0.1072,
+      "step": 219
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.5371509847597282,
+      "learning_rate": 3.863301782168896e-06,
+      "loss": 0.1031,
+      "step": 220
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.753717210369209,
+      "learning_rate": 3.821205322452863e-06,
+      "loss": 0.0828,
+      "step": 221
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.074756287227877,
+      "learning_rate": 3.779197154858044e-06,
+      "loss": 0.0973,
+      "step": 222
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.2724948604594926,
+      "learning_rate": 3.7372804258104367e-06,
+      "loss": 0.0895,
+      "step": 223
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.093818703556859,
+      "learning_rate": 3.695458274887268e-06,
+      "loss": 0.1,
+      "step": 224
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.1942131557219615,
+      "learning_rate": 3.6537338345818273e-06,
+      "loss": 0.0792,
+      "step": 225
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1522177170604604,
+      "learning_rate": 3.6121102300688504e-06,
+      "loss": 0.097,
+      "step": 226
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.1482788158692883,
+      "learning_rate": 3.5705905789704296e-06,
+      "loss": 0.1012,
+      "step": 227
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.388676602311021,
+      "learning_rate": 3.529177991122519e-06,
+      "loss": 0.1006,
+      "step": 228
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.4030047564151935,
+      "learning_rate": 3.487875568341995e-06,
+      "loss": 0.1284,
+      "step": 229
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.8976348319210287,
+      "learning_rate": 3.446686404194337e-06,
+      "loss": 0.0927,
+      "step": 230
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.681816592491244,
+      "learning_rate": 3.4056135837619077e-06,
+      "loss": 0.1064,
+      "step": 231
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0021307562865844,
+      "learning_rate": 3.3646601834128924e-06,
+      "loss": 0.1029,
+      "step": 232
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.6623812138571616,
+      "learning_rate": 3.3238292705708675e-06,
+      "loss": 0.1309,
+      "step": 233
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.748214601457332,
+      "learning_rate": 3.2831239034850593e-06,
+      "loss": 0.0852,
+      "step": 234
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.7437893551280836,
+      "learning_rate": 3.2425471310012645e-06,
+      "loss": 0.0751,
+      "step": 235
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.6675853535243832,
+      "learning_rate": 3.2021019923335093e-06,
+      "loss": 0.0916,
+      "step": 236
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.100044651347937,
+      "learning_rate": 3.1617915168363994e-06,
+      "loss": 0.1126,
+      "step": 237
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.6980991571831425,
+      "learning_rate": 3.121618723778225e-06,
+      "loss": 0.114,
+      "step": 238
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.809170392714892,
+      "learning_rate": 3.081586622114809e-06,
+      "loss": 0.0802,
+      "step": 239
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3838776859564594,
+      "learning_rate": 3.041698210264149e-06,
+      "loss": 0.105,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5803152571460155,
+      "learning_rate": 3.001956475881822e-06,
+      "loss": 0.0981,
+      "step": 241
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.067373009416558,
+      "learning_rate": 2.962364395637216e-06,
+      "loss": 0.088,
+      "step": 242
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.92506137356751,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 0.0798,
+      "step": 243
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.696821230185965,
+      "learning_rate": 2.8836410479708625e-06,
+      "loss": 0.1097,
+      "step": 244
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.3695655668106497,
+      "learning_rate": 2.84451567695456e-06,
+      "loss": 0.1074,
+      "step": 245
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.02628207234317,
+      "learning_rate": 2.805551752445222e-06,
+      "loss": 0.0945,
+      "step": 246
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.7890668202069149,
+      "learning_rate": 2.766752192854012e-06,
+      "loss": 0.0962,
+      "step": 247
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.8653309529993138,
+      "learning_rate": 2.728119904281105e-06,
+      "loss": 0.0936,
+      "step": 248
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2556810110616448,
+      "learning_rate": 2.689657780298019e-06,
+      "loss": 0.1015,
+      "step": 249
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.9247017356819199,
+      "learning_rate": 2.651368701730889e-06,
+      "loss": 0.0939,
+      "step": 250
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.7127003953336231,
+      "learning_rate": 2.6132555364446856e-06,
+      "loss": 0.0711,
+      "step": 251
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.1565869125893093,
+      "learning_rate": 2.5753211391284172e-06,
+      "loss": 0.0878,
+      "step": 252
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.8600480673731534,
+      "learning_rate": 2.537568351081311e-06,
+      "loss": 0.0964,
+      "step": 253
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.9185340265693758,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1012,
+      "step": 254
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.1857003942637823,
+      "learning_rate": 2.4626188997667224e-06,
+      "loss": 0.0911,
+      "step": 255
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0308679952818762,
+      "learning_rate": 2.425427850238565e-06,
+      "loss": 0.0831,
+      "step": 256
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.7565226656972092,
+      "learning_rate": 2.388429637037753e-06,
+      "loss": 0.0756,
+      "step": 257
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.9873764687808928,
+      "learning_rate": 2.3516270313430085e-06,
+      "loss": 0.0991,
+      "step": 258
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.7476272594043502,
+      "learning_rate": 2.3150227896819782e-06,
+      "loss": 0.0957,
+      "step": 259
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.1225420059671651,
+      "learning_rate": 2.278619653724781e-06,
+      "loss": 0.0976,
+      "step": 260
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.157051013277684,
+      "learning_rate": 2.2424203500786473e-06,
+      "loss": 0.0834,
+      "step": 261
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.3990824556594672,
+      "learning_rate": 2.206427590083703e-06,
+      "loss": 0.0988,
+      "step": 262
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.3330789487573915,
+      "learning_rate": 2.170644069609876e-06,
+      "loss": 0.0972,
+      "step": 263
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4821281230536878,
+      "learning_rate": 2.1350724688549906e-06,
+      "loss": 0.1144,
+      "step": 264
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.157684636484896,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.1085,
+      "step": 265
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.3256828512756258,
+      "learning_rate": 2.0645756677294788e-06,
+      "loss": 0.1314,
+      "step": 266
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.1702750386243066,
+      "learning_rate": 2.029655747593169e-06,
+      "loss": 0.1014,
+      "step": 267
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.3195913625999418,
+      "learning_rate": 1.9949583072489455e-06,
+      "loss": 0.0901,
+      "step": 268
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3441999161547986,
+      "learning_rate": 1.9604859455468587e-06,
+      "loss": 0.0904,
+      "step": 269
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3870923377648432,
+      "learning_rate": 1.926241244478496e-06,
+      "loss": 0.1032,
+      "step": 270
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3332340713602542,
+      "learning_rate": 1.8922267689835806e-06,
+      "loss": 0.1021,
+      "step": 271
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.1485145375524286,
+      "learning_rate": 1.8584450667578656e-06,
+      "loss": 0.1047,
+      "step": 272
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.7003153327339164,
+      "learning_rate": 1.8248986680623077e-06,
+      "loss": 0.1017,
+      "step": 273
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.1615855994991828,
+      "learning_rate": 1.7915900855335506e-06,
+      "loss": 0.0747,
+      "step": 274
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.3707759394586765,
+      "learning_rate": 1.7585218139957205e-06,
+      "loss": 0.095,
+      "step": 275
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.9601094603046156,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 0.109,
+      "step": 276
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.2840181842732155,
+      "learning_rate": 1.6931160930069789e-06,
+      "loss": 0.0978,
+      "step": 277
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.973388927782162,
+      "learning_rate": 1.6607835424667578e-06,
+      "loss": 0.0705,
+      "step": 278
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.8616502456211874,
+      "learning_rate": 1.6287011003719105e-06,
+      "loss": 0.0997,
+      "step": 279
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.333833632755166,
+      "learning_rate": 1.596871169708235e-06,
+      "loss": 0.0859,
+      "step": 280
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.359618731052767,
+      "learning_rate": 1.5652961345483353e-06,
+      "loss": 0.0912,
+      "step": 281
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.740170889217021,
+      "learning_rate": 1.5339783598730568e-06,
+      "loss": 0.0715,
+      "step": 282
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.3852113409761277,
+      "learning_rate": 1.5029201913943425e-06,
+      "loss": 0.1057,
+      "step": 283
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.2053263094215156,
+      "learning_rate": 1.4721239553795485e-06,
+      "loss": 0.1029,
+      "step": 284
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9024561282066889,
+      "learning_rate": 1.4415919584771999e-06,
+      "loss": 0.076,
+      "step": 285
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.1963038104318369,
+      "learning_rate": 1.4113264875442201e-06,
+      "loss": 0.0958,
+      "step": 286
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.9773063145651026,
+      "learning_rate": 1.3813298094746491e-06,
+      "loss": 0.0947,
+      "step": 287
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.021541672610081,
+      "learning_rate": 1.35160417102985e-06,
+      "loss": 0.084,
+      "step": 288
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.5670442336895052,
+      "learning_rate": 1.3221517986702249e-06,
+      "loss": 0.1005,
+      "step": 289
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.085277060889925,
+      "learning_rate": 1.292974898388456e-06,
+      "loss": 0.0959,
+      "step": 290
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.8890406891437141,
+      "learning_rate": 1.2640756555442684e-06,
+      "loss": 0.088,
+      "step": 291
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.9690837099152053,
+      "learning_rate": 1.235456234700756e-06,
+      "loss": 0.1175,
+      "step": 292
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.3389630748232106,
+      "learning_rate": 1.207118779462248e-06,
+      "loss": 0.0828,
+      "step": 293
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4011538490723006,
+      "learning_rate": 1.1790654123137552e-06,
+      "loss": 0.099,
+      "step": 294
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.9992680354866206,
+      "learning_rate": 1.1512982344619904e-06,
+      "loss": 0.093,
+      "step": 295
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.2851344800723303,
+      "learning_rate": 1.1238193256779955e-06,
+      "loss": 0.1176,
+      "step": 296
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.6910735548211555,
+      "learning_rate": 1.0966307441413598e-06,
+      "loss": 0.0968,
+      "step": 297
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.352666557870654,
+      "learning_rate": 1.0697345262860638e-06,
+      "loss": 0.1099,
+      "step": 298
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5721166661074446,
+      "learning_rate": 1.0431326866479457e-06,
+      "loss": 0.1108,
+      "step": 299
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.121586211029391,
+      "learning_rate": 1.01682721771382e-06,
+      "loss": 0.0806,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9446600346455488,
+      "learning_rate": 9.908200897722332e-07,
+      "loss": 0.0961,
+      "step": 301
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.9114800242476411,
+      "learning_rate": 9.6511325076589e-07,
+      "loss": 0.0801,
+      "step": 302
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.5547982808858901,
+      "learning_rate": 9.397086261457511e-07,
+      "loss": 0.0716,
+      "step": 303
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.0927781521360393,
+      "learning_rate": 9.146081187268185e-07,
+      "loss": 0.1024,
+      "step": 304
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.9577060255176627,
+      "learning_rate": 8.898136085456127e-07,
+      "loss": 0.0773,
+      "step": 305
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.4819631087520413,
+      "learning_rate": 8.65326952719357e-07,
+      "loss": 0.1,
+      "step": 306
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.8006192274937786,
+      "learning_rate": 8.411499853068783e-07,
+      "loss": 0.0984,
+      "step": 307
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0034003640313884,
+      "learning_rate": 8.172845171712379e-07,
+      "loss": 0.0744,
+      "step": 308
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.1967267762077687,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.0738,
+      "step": 309
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.4993037221678234,
+      "learning_rate": 7.70495205391818e-07,
+      "loss": 0.1055,
+      "step": 310
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.1890158669746098,
+      "learning_rate": 7.475748662833615e-07,
+      "loss": 0.0846,
+      "step": 311
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.572385726115481,
+      "learning_rate": 7.249730352599e-07,
+      "loss": 0.1043,
+      "step": 312
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.4378675578144449,
+      "learning_rate": 7.026914052062433e-07,
+      "loss": 0.0767,
+      "step": 313
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2897942508779738,
+      "learning_rate": 6.807316450240425e-07,
+      "loss": 0.0905,
+      "step": 314
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.251144203760798,
+      "learning_rate": 6.590953995067812e-07,
+      "loss": 0.1113,
+      "step": 315
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.6984773583049225,
+      "learning_rate": 6.377842892165892e-07,
+      "loss": 0.0745,
+      "step": 316
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2192657521600931,
+      "learning_rate": 6.167999103628569e-07,
+      "loss": 0.0994,
+      "step": 317
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.286974795623823,
+      "learning_rate": 5.961438346826792e-07,
+      "loss": 0.0896,
+      "step": 318
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.140476983016987,
+      "learning_rate": 5.758176093231294e-07,
+      "loss": 0.0975,
+      "step": 319
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2442083569670794,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.101,
+      "step": 320
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9916854807753926,
+      "learning_rate": 5.361607745106817e-07,
+      "loss": 0.0797,
+      "step": 321
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.8665407482981075,
+      "learning_rate": 5.168331353681643e-07,
+      "loss": 0.0734,
+      "step": 322
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.2248878679412678,
+      "learning_rate": 4.97841286944557e-07,
+      "loss": 0.1122,
+      "step": 323
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.6499953301668673,
+      "learning_rate": 4.791866517357491e-07,
+      "loss": 0.1162,
+      "step": 324
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0973548778211824,
+      "learning_rate": 4.608706269802471e-07,
+      "loss": 0.1064,
+      "step": 325
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0087981189992337,
+      "learning_rate": 4.428945845545168e-07,
+      "loss": 0.0697,
+      "step": 326
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.303611388476217,
+      "learning_rate": 4.2525987087023433e-07,
+      "loss": 0.0959,
+      "step": 327
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.3077016519529772,
+      "learning_rate": 4.0796780677343606e-07,
+      "loss": 0.1029,
+      "step": 328
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.074869389582163,
+      "learning_rate": 3.910196874455896e-07,
+      "loss": 0.1006,
+      "step": 329
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8149984482347605,
+      "learning_rate": 3.744167823065814e-07,
+      "loss": 0.109,
+      "step": 330
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.3141064225973613,
+      "learning_rate": 3.581603349196372e-07,
+      "loss": 0.1117,
+      "step": 331
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.8916445085994008,
+      "learning_rate": 3.4225156289818096e-07,
+      "loss": 0.0899,
+      "step": 332
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.4146065121445264,
+      "learning_rate": 3.26691657814634e-07,
+      "loss": 0.0914,
+      "step": 333
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.2534230135615902,
+      "learning_rate": 3.1148178511116624e-07,
+      "loss": 0.0948,
+      "step": 334
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.2257858603381941,
+      "learning_rate": 2.966230840124007e-07,
+      "loss": 0.0851,
+      "step": 335
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.2284138650051797,
+      "learning_rate": 2.821166674400905e-07,
+      "loss": 0.1002,
+      "step": 336
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.008045250160863,
+      "learning_rate": 2.6796362192975766e-07,
+      "loss": 0.1094,
+      "step": 337
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.112143628767893,
+      "learning_rate": 2.5416500754931294e-07,
+      "loss": 0.0879,
+      "step": 338
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.1320223666663305,
+      "learning_rate": 2.407218578196524e-07,
+      "loss": 0.1138,
+      "step": 339
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.9604117882161444,
+      "learning_rate": 2.2763517963725169e-07,
+      "loss": 0.0724,
+      "step": 340
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.3219255861028065,
+      "learning_rate": 2.1490595319874574e-07,
+      "loss": 0.0762,
+      "step": 341
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0285603853422676,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 0.1003,
+      "step": 342
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0772620699082271,
+      "learning_rate": 1.905236424022633e-07,
+      "loss": 0.0948,
+      "step": 343
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.6500523543411342,
+      "learning_rate": 1.7887238428763553e-07,
+      "loss": 0.0709,
+      "step": 344
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.4427116081080966,
+      "learning_rate": 1.6758223026681507e-07,
+      "loss": 0.0774,
+      "step": 345
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8895261329447393,
+      "learning_rate": 1.5665402597616842e-07,
+      "loss": 0.0844,
+      "step": 346
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.9363814801803447,
+      "learning_rate": 1.4608858994190344e-07,
+      "loss": 0.0637,
+      "step": 347
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.14866157316394,
+      "learning_rate": 1.358867135187636e-07,
+      "loss": 0.1037,
+      "step": 348
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.2115694982924117,
+      "learning_rate": 1.2604916083075236e-07,
+      "loss": 0.102,
+      "step": 349
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.494487106718956,
+      "learning_rate": 1.1657666871390471e-07,
+      "loss": 0.1167,
+      "step": 350
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.5019457011246664,
+      "learning_rate": 1.0746994666109234e-07,
+      "loss": 0.0664,
+      "step": 351
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7230366028390518,
+      "learning_rate": 9.872967676888611e-08,
+      "loss": 0.0917,
+      "step": 352
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.145876850170579,
+      "learning_rate": 9.035651368646647e-08,
+      "loss": 0.0898,
+      "step": 353
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.075956409233676,
+      "learning_rate": 8.235108456658814e-08,
+      "loss": 0.095,
+      "step": 354
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.0728393425730074,
+      "learning_rate": 7.471398901860772e-08,
+      "loss": 0.0866,
+      "step": 355
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.5593106758757171,
+      "learning_rate": 6.744579906357185e-08,
+      "loss": 0.0834,
+      "step": 356
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.8086259248450012,
+      "learning_rate": 6.054705909137426e-08,
+      "loss": 0.0861,
+      "step": 357
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.2906741372150026,
+      "learning_rate": 5.401828581997948e-08,
+      "loss": 0.0967,
+      "step": 358
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8507507736640382,
+      "learning_rate": 4.7859968256719344e-08,
+      "loss": 0.075,
+      "step": 359
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9702062940168862,
+      "learning_rate": 4.207256766166845e-08,
+      "loss": 0.0828,
+      "step": 360
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7967797116313821,
+      "learning_rate": 3.665651751309451e-08,
+      "loss": 0.0911,
+      "step": 361
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.4642009187914857,
+      "learning_rate": 3.16122234749916e-08,
+      "loss": 0.1175,
+      "step": 362
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.7911250417395334,
+      "learning_rate": 2.6940063366693303e-08,
+      "loss": 0.0597,
+      "step": 363
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.0088218718629327,
+      "learning_rate": 2.264038713457706e-08,
+      "loss": 0.1084,
+      "step": 364
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.2314059802507542,
+      "learning_rate": 1.8713516825851207e-08,
+      "loss": 0.0673,
+      "step": 365
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7806704264304777,
+      "learning_rate": 1.51597465644332e-08,
+      "loss": 0.0831,
+      "step": 366
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.3001461471140205,
+      "learning_rate": 1.1979342528922189e-08,
+      "loss": 0.0927,
+      "step": 367
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.7301869685306731,
+      "learning_rate": 9.1725429326589e-09,
+      "loss": 0.0959,
+      "step": 368
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.159763715970489,
+      "learning_rate": 6.739558005884883e-09,
+      "loss": 0.098,
+      "step": 369
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.078763280838958,
+      "learning_rate": 4.6805699799967744e-09,
+      "loss": 0.0911,
+      "step": 370
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.2270429915302712,
+      "learning_rate": 2.995733073895557e-09,
+      "loss": 0.0744,
+      "step": 371
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.792108852154837,
+      "learning_rate": 1.6851734824380184e-09,
+      "loss": 0.0924,
+      "step": 372
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.794409871566622,
+      "learning_rate": 7.48989366980979e-10,
+      "loss": 0.0856,
+      "step": 373
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2148009337214067,
+      "learning_rate": 1.872508480332824e-10,
+      "loss": 0.0913,
+      "step": 374
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8989158063723116,
+      "learning_rate": 0.0,
+      "loss": 0.0646,
+      "step": 375
+    },
+    {
+      "epoch": 1.0,
+      "step": 375,
+      "total_flos": 58465292664832.0,
+      "train_loss": 0.11454790777961413,
+      "train_runtime": 925.98,
+      "train_samples_per_second": 3.24,
+      "train_steps_per_second": 0.405
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 58465292664832.0,
+  "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_language_model_adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2f3284d82bf8c44d0387b1477f898085435b5f300e8a35cd63443ee87360c3
+size 7928