Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "./checkpoint/llmga-gemma-2b-it-full-finetune",
+  "architectures": [
+    "LlavaGemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "freeze_mm_mlp_adapter": false,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "resizesquare",
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef92e70b360ff5ebfee578c50108278620c3c3fd638979f49a11a456a8b73e4a
+size 4945242264

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18812ca688fdcfb0b408926571f15642266c7292ccb867672efd861b4e562712
+size 686788592

model.safetensors.index.json

@@ -0,0 +1,566 @@
+{
+  "metadata": {
+    "total_size": 5631950848
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a91ce4908a747435938ec27fe0f811551fdc89a64222b539f8de528b7fd81b
+size 17477957

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2002 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0035714285714285713,
+      "grad_norm": 3.8463999080701567,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.4306,
+      "step": 1
+    },
+    {
+      "epoch": 0.007142857142857143,
+      "grad_norm": 4.501409614652374,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.389,
+      "step": 2
+    },
+    {
+      "epoch": 0.010714285714285714,
+      "grad_norm": 3.111210623412801,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.3317,
+      "step": 3
+    },
+    {
+      "epoch": 0.014285714285714285,
+      "grad_norm": 2.5775839680049404,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.2209,
+      "step": 4
+    },
+    {
+      "epoch": 0.017857142857142856,
+      "grad_norm": 4.018440125184394,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.1069,
+      "step": 5
+    },
+    {
+      "epoch": 0.02142857142857143,
+      "grad_norm": 3.638348466019723,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.0509,
+      "step": 6
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 3.0034037196084795,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 1.0702,
+      "step": 7
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 4.791530764509695,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.9702,
+      "step": 8
+    },
+    {
+      "epoch": 0.03214285714285714,
+      "grad_norm": 9.699715397578693,
+      "learning_rate": 2e-05,
+      "loss": 0.9043,
+      "step": 9
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 5.607992651212428,
+      "learning_rate": 1.9999328066483867e-05,
+      "loss": 0.8379,
+      "step": 10
+    },
+    {
+      "epoch": 0.039285714285714285,
+      "grad_norm": 5.954953700526873,
+      "learning_rate": 1.9997312356234385e-05,
+      "loss": 0.826,
+      "step": 11
+    },
+    {
+      "epoch": 0.04285714285714286,
+      "grad_norm": 3.8312931320435766,
+      "learning_rate": 1.999395314013622e-05,
+      "loss": 0.7208,
+      "step": 12
+    },
+    {
+      "epoch": 0.04642857142857143,
+      "grad_norm": 4.907697587217522,
+      "learning_rate": 1.998925086962334e-05,
+      "loss": 0.7129,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.8606079819969548,
+      "learning_rate": 1.998320617661839e-05,
+      "loss": 0.6455,
+      "step": 14
+    },
+    {
+      "epoch": 0.05357142857142857,
+      "grad_norm": 3.4257199397634324,
+      "learning_rate": 1.997581987344772e-05,
+      "loss": 0.6201,
+      "step": 15
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 2.771129704941321,
+      "learning_rate": 1.9967092952732266e-05,
+      "loss": 0.6003,
+      "step": 16
+    },
+    {
+      "epoch": 0.060714285714285714,
+      "grad_norm": 3.5019346172505625,
+      "learning_rate": 1.9957026587254136e-05,
+      "loss": 0.603,
+      "step": 17
+    },
+    {
+      "epoch": 0.06428571428571428,
+      "grad_norm": 2.535377938583749,
+      "learning_rate": 1.9945622129799e-05,
+      "loss": 0.5821,
+      "step": 18
+    },
+    {
+      "epoch": 0.06785714285714285,
+      "grad_norm": 2.885735932770747,
+      "learning_rate": 1.9932881112974298e-05,
+      "loss": 0.5753,
+      "step": 19
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 1.895147639236987,
+      "learning_rate": 1.9918805249003272e-05,
+      "loss": 0.4513,
+      "step": 20
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 2.2424998503694624,
+      "learning_rate": 1.9903396429494882e-05,
+      "loss": 0.4331,
+      "step": 21
+    },
+    {
+      "epoch": 0.07857142857142857,
+      "grad_norm": 2.913523442452943,
+      "learning_rate": 1.9886656725189575e-05,
+      "loss": 0.4266,
+      "step": 22
+    },
+    {
+      "epoch": 0.08214285714285714,
+      "grad_norm": 2.0251214408422005,
+      "learning_rate": 1.9868588385681035e-05,
+      "loss": 0.3957,
+      "step": 23
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 1.8849371078735193,
+      "learning_rate": 1.9849193839113833e-05,
+      "loss": 0.3361,
+      "step": 24
+    },
+    {
+      "epoch": 0.08928571428571429,
+      "grad_norm": 1.6308189938610342,
+      "learning_rate": 1.9828475691857148e-05,
+      "loss": 0.3394,
+      "step": 25
+    },
+    {
+      "epoch": 0.09285714285714286,
+      "grad_norm": 1.8883916767324196,
+      "learning_rate": 1.9806436728154484e-05,
+      "loss": 0.4039,
+      "step": 26
+    },
+    {
+      "epoch": 0.09642857142857143,
+      "grad_norm": 2.0063005720849842,
+      "learning_rate": 1.9783079909749516e-05,
+      "loss": 0.3558,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.6567074932208588,
+      "learning_rate": 1.975840837548807e-05,
+      "loss": 0.3188,
+      "step": 28
+    },
+    {
+      "epoch": 0.10357142857142858,
+      "grad_norm": 2.0465722029487603,
+      "learning_rate": 1.9732425440896298e-05,
+      "loss": 0.4368,
+      "step": 29
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 1.6849076670981753,
+      "learning_rate": 1.9705134597735113e-05,
+      "loss": 0.3544,
+      "step": 30
+    },
+    {
+      "epoch": 0.11071428571428571,
+      "grad_norm": 1.57618074931163,
+      "learning_rate": 1.9676539513530967e-05,
+      "loss": 0.334,
+      "step": 31
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.6690393305302673,
+      "learning_rate": 1.9646644031082948e-05,
+      "loss": 0.3321,
+      "step": 32
+    },
+    {
+      "epoch": 0.11785714285714285,
+      "grad_norm": 2.0879061826066048,
+      "learning_rate": 1.9615452167946383e-05,
+      "loss": 0.3857,
+      "step": 33
+    },
+    {
+      "epoch": 0.12142857142857143,
+      "grad_norm": 1.7235580572135418,
+      "learning_rate": 1.958296811589293e-05,
+      "loss": 0.3363,
+      "step": 34
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 1.7300478556647807,
+      "learning_rate": 1.954919624034725e-05,
+      "loss": 0.3739,
+      "step": 35
+    },
+    {
+      "epoch": 0.12857142857142856,
+      "grad_norm": 1.5130257554839706,
+      "learning_rate": 1.951414107980036e-05,
+      "loss": 0.2915,
+      "step": 36
+    },
+    {
+      "epoch": 0.13214285714285715,
+      "grad_norm": 1.7710183716574244,
+      "learning_rate": 1.9477807345199717e-05,
+      "loss": 0.2988,
+      "step": 37
+    },
+    {
+      "epoch": 0.1357142857142857,
+      "grad_norm": 1.5435872694843102,
+      "learning_rate": 1.9440199919316125e-05,
+      "loss": 0.3193,
+      "step": 38
+    },
+    {
+      "epoch": 0.1392857142857143,
+      "grad_norm": 1.4974545128185939,
+      "learning_rate": 1.9401323856087573e-05,
+      "loss": 0.2942,
+      "step": 39
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.979554894627583,
+      "learning_rate": 1.936118437994003e-05,
+      "loss": 0.3484,
+      "step": 40
+    },
+    {
+      "epoch": 0.14642857142857144,
+      "grad_norm": 1.8516404419926875,
+      "learning_rate": 1.9319786885085366e-05,
+      "loss": 0.2917,
+      "step": 41
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.611856432512013,
+      "learning_rate": 1.927713693479643e-05,
+      "loss": 0.2778,
+      "step": 42
+    },
+    {
+      "epoch": 0.15357142857142858,
+      "grad_norm": 1.6388606321400045,
+      "learning_rate": 1.923324026065944e-05,
+      "loss": 0.3183,
+      "step": 43
+    },
+    {
+      "epoch": 0.15714285714285714,
+      "grad_norm": 1.4127369301924584,
+      "learning_rate": 1.918810276180372e-05,
+      "loss": 0.2338,
+      "step": 44
+    },
+    {
+      "epoch": 0.16071428571428573,
+      "grad_norm": 1.6679263766835408,
+      "learning_rate": 1.9141730504108923e-05,
+      "loss": 0.2994,
+      "step": 45
+    },
+    {
+      "epoch": 0.16428571428571428,
+      "grad_norm": 1.5488370761368482,
+      "learning_rate": 1.9094129719389886e-05,
+      "loss": 0.2491,
+      "step": 46
+    },
+    {
+      "epoch": 0.16785714285714284,
+      "grad_norm": 1.7141365258968089,
+      "learning_rate": 1.904530680455914e-05,
+      "loss": 0.3044,
+      "step": 47
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 1.866364886426368,
+      "learning_rate": 1.8995268320767254e-05,
+      "loss": 0.2883,
+      "step": 48
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 1.7088119845888674,
+      "learning_rate": 1.894402099252109e-05,
+      "loss": 0.299,
+      "step": 49
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 1.751808369129802,
+      "learning_rate": 1.889157170678015e-05,
+      "loss": 0.31,
+      "step": 50
+    },
+    {
+      "epoch": 0.18214285714285713,
+      "grad_norm": 1.556582715455483,
+      "learning_rate": 1.8837927512031022e-05,
+      "loss": 0.3129,
+      "step": 51
+    },
+    {
+      "epoch": 0.18571428571428572,
+      "grad_norm": 1.3347082087439248,
+      "learning_rate": 1.8783095617340193e-05,
+      "loss": 0.2271,
+      "step": 52
+    },
+    {
+      "epoch": 0.18928571428571428,
+      "grad_norm": 1.3905516221818923,
+      "learning_rate": 1.872708339138522e-05,
+      "loss": 0.2191,
+      "step": 53
+    },
+    {
+      "epoch": 0.19285714285714287,
+      "grad_norm": 1.1222097376850546,
+      "learning_rate": 1.866989836146449e-05,
+      "loss": 0.2382,
+      "step": 54
+    },
+    {
+      "epoch": 0.19642857142857142,
+      "grad_norm": 1.4002181147554662,
+      "learning_rate": 1.861154821248565e-05,
+      "loss": 0.2613,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.641076339997439,
+      "learning_rate": 1.8552040785932846e-05,
+      "loss": 0.2825,
+      "step": 56
+    },
+    {
+      "epoch": 0.20357142857142857,
+      "grad_norm": 1.6474552553110247,
+      "learning_rate": 1.849138407881296e-05,
+      "loss": 0.2417,
+      "step": 57
+    },
+    {
+      "epoch": 0.20714285714285716,
+      "grad_norm": 1.4534260440271216,
+      "learning_rate": 1.8429586242580884e-05,
+      "loss": 0.3019,
+      "step": 58
+    },
+    {
+      "epoch": 0.21071428571428572,
+      "grad_norm": 1.3597727058809432,
+      "learning_rate": 1.8366655582044096e-05,
+      "loss": 0.2565,
+      "step": 59
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 1.870334097716497,
+      "learning_rate": 1.83026005542466e-05,
+      "loss": 0.3622,
+      "step": 60
+    },
+    {
+      "epoch": 0.21785714285714286,
+      "grad_norm": 1.5861555594774857,
+      "learning_rate": 1.8237429767332407e-05,
+      "loss": 0.3039,
+      "step": 61
+    },
+    {
+      "epoch": 0.22142857142857142,
+      "grad_norm": 1.1611735523531768,
+      "learning_rate": 1.8171151979388715e-05,
+      "loss": 0.2296,
+      "step": 62
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 1.597258165214944,
+      "learning_rate": 1.8103776097268942e-05,
+      "loss": 0.2858,
+      "step": 63
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 1.267156194367651,
+      "learning_rate": 1.803531117539577e-05,
+      "loss": 0.2515,
+      "step": 64
+    },
+    {
+      "epoch": 0.23214285714285715,
+      "grad_norm": 1.2209418650880846,
+      "learning_rate": 1.7965766414544328e-05,
+      "loss": 0.2029,
+      "step": 65
+    },
+    {
+      "epoch": 0.2357142857142857,
+      "grad_norm": 1.5784545253398363,
+      "learning_rate": 1.7895151160605758e-05,
+      "loss": 0.2815,
+      "step": 66
+    },
+    {
+      "epoch": 0.2392857142857143,
+      "grad_norm": 1.3166831042898355,
+      "learning_rate": 1.782347490333123e-05,
+      "loss": 0.2757,
+      "step": 67
+    },
+    {
+      "epoch": 0.24285714285714285,
+      "grad_norm": 1.3394874541825403,
+      "learning_rate": 1.775074727505667e-05,
+      "loss": 0.2854,
+      "step": 68
+    },
+    {
+      "epoch": 0.24642857142857144,
+      "grad_norm": 1.3349412708678627,
+      "learning_rate": 1.7676978049408262e-05,
+      "loss": 0.2652,
+      "step": 69
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3491578911743884,
+      "learning_rate": 1.7602177139989046e-05,
+      "loss": 0.2657,
+      "step": 70
+    },
+    {
+      "epoch": 0.25357142857142856,
+      "grad_norm": 1.58498207546815,
+      "learning_rate": 1.7526354599046637e-05,
+      "loss": 0.2862,
+      "step": 71
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 1.171893508877287,
+      "learning_rate": 1.7449520616122344e-05,
+      "loss": 0.219,
+      "step": 72
+    },
+    {
+      "epoch": 0.26071428571428573,
+      "grad_norm": 1.226272384543111,
+      "learning_rate": 1.7371685516681825e-05,
+      "loss": 0.2251,
+      "step": 73
+    },
+    {
+      "epoch": 0.2642857142857143,
+      "grad_norm": 1.0306760814770153,
+      "learning_rate": 1.7292859760727493e-05,
+      "loss": 0.2258,
+      "step": 74
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 1.0229977640356496,
+      "learning_rate": 1.721305394139282e-05,
+      "loss": 0.1638,
+      "step": 75
+    },
+    {
+      "epoch": 0.2714285714285714,
+      "grad_norm": 1.2145240100493355,
+      "learning_rate": 1.7132278783518756e-05,
+      "loss": 0.2185,
+      "step": 76
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 1.3356962026479282,
+      "learning_rate": 1.7050545142212483e-05,
+      "loss": 0.2806,
+      "step": 77
+    },
+    {
+      "epoch": 0.2785714285714286,
+      "grad_norm": 1.0977667442323567,
+      "learning_rate": 1.696786400138859e-05,
+      "loss": 0.2154,
+      "step": 78
+    },
+    {
+      "epoch": 0.28214285714285714,
+      "grad_norm": 1.309488643176942,
+      "learning_rate": 1.6884246472293018e-05,
+      "loss": 0.2568,
+      "step": 79
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.3416013142436383,
+      "learning_rate": 1.679970379200983e-05,
+      "loss": 0.2184,
+      "step": 80
+    },
+    {
+      "epoch": 0.2892857142857143,
+      "grad_norm": 1.2963383953013474,
+      "learning_rate": 1.6714247321951106e-05,
+      "loss": 0.2425,
+      "step": 81
+    },
+    {
+      "epoch": 0.29285714285714287,
+      "grad_norm": 1.4861227357647886,
+      "learning_rate": 1.6627888546330136e-05,
+      "loss": 0.2744,
+      "step": 82
+    },
+    {
+      "epoch": 0.29642857142857143,
+      "grad_norm": 1.353214497406482,
+      "learning_rate": 1.654063907061807e-05,
+      "loss": 0.2804,
+      "step": 83
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3163290550130933,
+      "learning_rate": 1.64525106199843e-05,
+      "loss": 0.2431,
+      "step": 84
+    },
+    {
+      "epoch": 0.30357142857142855,
+      "grad_norm": 1.555156616987962,
+      "learning_rate": 1.6363515037720774e-05,
+      "loss": 0.2329,
+      "step": 85
+    },
+    {
+      "epoch": 0.30714285714285716,
+      "grad_norm": 1.4311224448239375,
+      "learning_rate": 1.6273664283650393e-05,
+      "loss": 0.2693,
+      "step": 86
+    },
+    {
+      "epoch": 0.3107142857142857,
+      "grad_norm": 1.1858774044469511,
+      "learning_rate": 1.6182970432519772e-05,
+      "loss": 0.1841,
+      "step": 87
+    },
+    {
+      "epoch": 0.3142857142857143,
+      "grad_norm": 1.6644796988372217,
+      "learning_rate": 1.609144567237658e-05,
+      "loss": 0.2719,
+      "step": 88
+    },
+    {
+      "epoch": 0.31785714285714284,
+      "grad_norm": 1.3696683048573934,
+      "learning_rate": 1.5999102302931585e-05,
+      "loss": 0.2616,
+      "step": 89
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 1.5107400214466982,
+      "learning_rate": 1.5905952733905777e-05,
+      "loss": 0.2545,
+      "step": 90
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 1.285707466960112,
+      "learning_rate": 1.5812009483362643e-05,
+      "loss": 0.2895,
+      "step": 91
+    },
+    {
+      "epoch": 0.32857142857142857,
+      "grad_norm": 1.56616098695484,
+      "learning_rate": 1.5717285176025913e-05,
+      "loss": 0.2476,
+      "step": 92
+    },
+    {
+      "epoch": 0.33214285714285713,
+      "grad_norm": 1.7743804634348541,
+      "learning_rate": 1.5621792541582968e-05,
+      "loss": 0.2673,
+      "step": 93
+    },
+    {
+      "epoch": 0.3357142857142857,
+      "grad_norm": 1.089841818003734,
+      "learning_rate": 1.552554441297413e-05,
+      "loss": 0.2599,
+      "step": 94
+    },
+    {
+      "epoch": 0.3392857142857143,
+      "grad_norm": 1.2680035769347011,
+      "learning_rate": 1.5428553724668103e-05,
+      "loss": 0.2668,
+      "step": 95
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 1.0865522840256474,
+      "learning_rate": 1.533083351092372e-05,
+      "loss": 0.2005,
+      "step": 96
+    },
+    {
+      "epoch": 0.3464285714285714,
+      "grad_norm": 1.0123098394706083,
+      "learning_rate": 1.5232396904038352e-05,
+      "loss": 0.1887,
+      "step": 97
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.8113315743427978,
+      "learning_rate": 1.5133257132583074e-05,
+      "loss": 0.287,
+      "step": 98
+    },
+    {
+      "epoch": 0.3535714285714286,
+      "grad_norm": 1.3172656748850875,
+      "learning_rate": 1.503342751962493e-05,
+      "loss": 0.2783,
+      "step": 99
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 1.179896450443836,
+      "learning_rate": 1.4932921480936491e-05,
+      "loss": 0.2414,
+      "step": 100
+    },
+    {
+      "epoch": 0.3607142857142857,
+      "grad_norm": 1.1648309148794773,
+      "learning_rate": 1.4831752523192949e-05,
+      "loss": 0.269,
+      "step": 101
+    },
+    {
+      "epoch": 0.36428571428571427,
+      "grad_norm": 1.8191572830668183,
+      "learning_rate": 1.4729934242157005e-05,
+      "loss": 0.3319,
+      "step": 102
+    },
+    {
+      "epoch": 0.3678571428571429,
+      "grad_norm": 1.4582365911234842,
+      "learning_rate": 1.4627480320851775e-05,
+      "loss": 0.3024,
+      "step": 103
+    },
+    {
+      "epoch": 0.37142857142857144,
+      "grad_norm": 1.619730041700966,
+      "learning_rate": 1.4524404527721977e-05,
+      "loss": 0.2573,
+      "step": 104
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 1.4428222360092964,
+      "learning_rate": 1.4420720714783635e-05,
+      "loss": 0.2122,
+      "step": 105
+    },
+    {
+      "epoch": 0.37857142857142856,
+      "grad_norm": 1.496668621981025,
+      "learning_rate": 1.4316442815762543e-05,
+      "loss": 0.2826,
+      "step": 106
+    },
+    {
+      "epoch": 0.3821428571428571,
+      "grad_norm": 1.3757794288437821,
+      "learning_rate": 1.4211584844221771e-05,
+      "loss": 0.2326,
+      "step": 107
+    },
+    {
+      "epoch": 0.38571428571428573,
+      "grad_norm": 0.9453032979935134,
+      "learning_rate": 1.4106160891678422e-05,
+      "loss": 0.1757,
+      "step": 108
+    },
+    {
+      "epoch": 0.3892857142857143,
+      "grad_norm": 1.106077532109773,
+      "learning_rate": 1.4000185125709919e-05,
+      "loss": 0.2055,
+      "step": 109
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 1.8473368430201997,
+      "learning_rate": 1.3893671788050073e-05,
+      "loss": 0.2294,
+      "step": 110
+    },
+    {
+      "epoch": 0.3964285714285714,
+      "grad_norm": 1.12407301069148,
+      "learning_rate": 1.3786635192675184e-05,
+      "loss": 0.2267,
+      "step": 111
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3142341007569383,
+      "learning_rate": 1.3679089723880427e-05,
+      "loss": 0.2907,
+      "step": 112
+    },
+    {
+      "epoch": 0.4035714285714286,
+      "grad_norm": 0.9831815070654757,
+      "learning_rate": 1.35710498343468e-05,
+      "loss": 0.213,
+      "step": 113
+    },
+    {
+      "epoch": 0.40714285714285714,
+      "grad_norm": 1.2924545103679281,
+      "learning_rate": 1.3462530043198874e-05,
+      "loss": 0.2369,
+      "step": 114
+    },
+    {
+      "epoch": 0.4107142857142857,
+      "grad_norm": 1.143093640110013,
+      "learning_rate": 1.3353544934053618e-05,
+      "loss": 0.1952,
+      "step": 115
+    },
+    {
+      "epoch": 0.4142857142857143,
+      "grad_norm": 1.449490820405882,
+      "learning_rate": 1.324410915306055e-05,
+      "loss": 0.2469,
+      "step": 116
+    },
+    {
+      "epoch": 0.41785714285714287,
+      "grad_norm": 1.0509308801147463,
+      "learning_rate": 1.3134237406933493e-05,
+      "loss": 0.2159,
+      "step": 117
+    },
+    {
+      "epoch": 0.42142857142857143,
+      "grad_norm": 1.0387634034119408,
+      "learning_rate": 1.3023944460974183e-05,
+      "loss": 0.1873,
+      "step": 118
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 1.1390999952556673,
+      "learning_rate": 1.2913245137088024e-05,
+      "loss": 0.2268,
+      "step": 119
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 1.191930121217241,
+      "learning_rate": 1.2802154311792196e-05,
+      "loss": 0.1802,
+      "step": 120
+    },
+    {
+      "epoch": 0.43214285714285716,
+      "grad_norm": 2.1479677833767346,
+      "learning_rate": 1.2690686914216475e-05,
+      "loss": 0.2443,
+      "step": 121
+    },
+    {
+      "epoch": 0.4357142857142857,
+      "grad_norm": 1.1279379735659398,
+      "learning_rate": 1.2578857924096935e-05,
+      "loss": 0.2343,
+      "step": 122
+    },
+    {
+      "epoch": 0.4392857142857143,
+      "grad_norm": 1.1052324092758952,
+      "learning_rate": 1.2466682369762883e-05,
+      "loss": 0.2046,
+      "step": 123
+    },
+    {
+      "epoch": 0.44285714285714284,
+      "grad_norm": 1.472504881720173,
+      "learning_rate": 1.2354175326117252e-05,
+      "loss": 0.2898,
+      "step": 124
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": 1.1018034210975085,
+      "learning_rate": 1.2241351912610726e-05,
+      "loss": 0.2396,
+      "step": 125
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1277919338070725,
+      "learning_rate": 1.212822729120989e-05,
+      "loss": 0.2119,
+      "step": 126
+    },
+    {
+      "epoch": 0.45357142857142857,
+      "grad_norm": 1.0251894751196213,
+      "learning_rate": 1.2014816664359671e-05,
+      "loss": 0.2217,
+      "step": 127
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 1.2653248942443196,
+      "learning_rate": 1.190113527294032e-05,
+      "loss": 0.2495,
+      "step": 128
+    },
+    {
+      "epoch": 0.4607142857142857,
+      "grad_norm": 1.0802469483987345,
+      "learning_rate": 1.178719839421925e-05,
+      "loss": 0.2147,
+      "step": 129
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 1.1686985534056804,
+      "learning_rate": 1.1673021339797967e-05,
+      "loss": 0.2277,
+      "step": 130
+    },
+    {
+      "epoch": 0.46785714285714286,
+      "grad_norm": 1.3088805640776975,
+      "learning_rate": 1.15586194535544e-05,
+      "loss": 0.264,
+      "step": 131
+    },
+    {
+      "epoch": 0.4714285714285714,
+      "grad_norm": 1.1351073631702513,
+      "learning_rate": 1.1444008109580884e-05,
+      "loss": 0.21,
+      "step": 132
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 1.2883146419720632,
+      "learning_rate": 1.1329202710118088e-05,
+      "loss": 0.2685,
+      "step": 133
+    },
+    {
+      "epoch": 0.4785714285714286,
+      "grad_norm": 1.4725292137870305,
+      "learning_rate": 1.1214218683485159e-05,
+      "loss": 0.1975,
+      "step": 134
+    },
+    {
+      "epoch": 0.48214285714285715,
+      "grad_norm": 1.2751267943442854,
+      "learning_rate": 1.1099071482006361e-05,
+      "loss": 0.2573,
+      "step": 135
+    },
+    {
+      "epoch": 0.4857142857142857,
+      "grad_norm": 1.7023636548064425,
+      "learning_rate": 1.0983776579934483e-05,
+      "loss": 0.2112,
+      "step": 136
+    },
+    {
+      "epoch": 0.48928571428571427,
+      "grad_norm": 1.5402177588840071,
+      "learning_rate": 1.0868349471371316e-05,
+      "loss": 0.303,
+      "step": 137
+    },
+    {
+      "epoch": 0.4928571428571429,
+      "grad_norm": 1.2648554791558448,
+      "learning_rate": 1.0752805668185442e-05,
+      "loss": 0.1758,
+      "step": 138
+    },
+    {
+      "epoch": 0.49642857142857144,
+      "grad_norm": 1.3839965770435088,
+      "learning_rate": 1.0637160697927651e-05,
+      "loss": 0.2718,
+      "step": 139
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.2722688069957164,
+      "learning_rate": 1.0521430101744238e-05,
+      "loss": 0.2357,
+      "step": 140
+    },
+    {
+      "epoch": 0.5035714285714286,
+      "grad_norm": 1.1504746047285683,
+      "learning_rate": 1.040562943228849e-05,
+      "loss": 0.2579,
+      "step": 141
+    },
+    {
+      "epoch": 0.5071428571428571,
+      "grad_norm": 1.7864043948989798,
+      "learning_rate": 1.0289774251630602e-05,
+      "loss": 0.1912,
+      "step": 142
+    },
+    {
+      "epoch": 0.5107142857142857,
+      "grad_norm": 1.1380881548027113,
+      "learning_rate": 1.0173880129166358e-05,
+      "loss": 0.2269,
+      "step": 143
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.8840201662637246,
+      "learning_rate": 1.0057962639524799e-05,
+      "loss": 0.1516,
+      "step": 144
+    },
+    {
+      "epoch": 0.5178571428571429,
+      "grad_norm": 1.6657099708925043,
+      "learning_rate": 9.942037360475205e-06,
+      "loss": 0.2565,
+      "step": 145
+    },
+    {
+      "epoch": 0.5214285714285715,
+      "grad_norm": 1.4468502527223739,
+      "learning_rate": 9.826119870833644e-06,
+      "loss": 0.3103,
+      "step": 146
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 1.2621846286615812,
+      "learning_rate": 9.710225748369402e-06,
+      "loss": 0.2456,
+      "step": 147
+    },
+    {
+      "epoch": 0.5285714285714286,
+      "grad_norm": 0.9166676754843754,
+      "learning_rate": 9.594370567711512e-06,
+      "loss": 0.2032,
+      "step": 148
+    },
+    {
+      "epoch": 0.5321428571428571,
+      "grad_norm": 1.225342226989512,
+      "learning_rate": 9.478569898255765e-06,
+      "loss": 0.3012,
+      "step": 149
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.9511767036487417,
+      "learning_rate": 9.362839302072354e-06,
+      "loss": 0.1791,
+      "step": 150
+    },
+    {
+      "epoch": 0.5392857142857143,
+      "grad_norm": 1.577891316555798,
+      "learning_rate": 9.247194331814561e-06,
+      "loss": 0.2744,
+      "step": 151
+    },
+    {
+      "epoch": 0.5428571428571428,
+      "grad_norm": 1.3480886982794977,
+      "learning_rate": 9.131650528628688e-06,
+      "loss": 0.2063,
+      "step": 152
+    },
+    {
+      "epoch": 0.5464285714285714,
+      "grad_norm": 1.0465704327176806,
+      "learning_rate": 9.016223420065519e-06,
+      "loss": 0.2196,
+      "step": 153
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.3978895811247751,
+      "learning_rate": 8.900928517993644e-06,
+      "loss": 0.2883,
+      "step": 154
+    },
+    {
+      "epoch": 0.5535714285714286,
+      "grad_norm": 1.5565905344815472,
+      "learning_rate": 8.785781316514841e-06,
+      "loss": 0.2373,
+      "step": 155
+    },
+    {
+      "epoch": 0.5571428571428572,
+      "grad_norm": 1.1802769847438437,
+      "learning_rate": 8.670797289881915e-06,
+      "loss": 0.2144,
+      "step": 156
+    },
+    {
+      "epoch": 0.5607142857142857,
+      "grad_norm": 1.5333745920655681,
+      "learning_rate": 8.555991890419116e-06,
+      "loss": 0.2494,
+      "step": 157
+    },
+    {
+      "epoch": 0.5642857142857143,
+      "grad_norm": 1.0689996187105173,
+      "learning_rate": 8.441380546445603e-06,
+      "loss": 0.1507,
+      "step": 158
+    },
+    {
+      "epoch": 0.5678571428571428,
+      "grad_norm": 1.176757884404756,
+      "learning_rate": 8.326978660202034e-06,
+      "loss": 0.2364,
+      "step": 159
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.4621461054180933,
+      "learning_rate": 8.212801605780754e-06,
+      "loss": 0.2253,
+      "step": 160
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 1.141490471223301,
+      "learning_rate": 8.098864727059685e-06,
+      "loss": 0.1769,
+      "step": 161
+    },
+    {
+      "epoch": 0.5785714285714286,
+      "grad_norm": 1.3901439045604576,
+      "learning_rate": 7.985183335640332e-06,
+      "loss": 0.2968,
+      "step": 162
+    },
+    {
+      "epoch": 0.5821428571428572,
+      "grad_norm": 0.7912708015331797,
+      "learning_rate": 7.871772708790114e-06,
+      "loss": 0.1466,
+      "step": 163
+    },
+    {
+      "epoch": 0.5857142857142857,
+      "grad_norm": 1.4667684919380188,
+      "learning_rate": 7.758648087389277e-06,
+      "loss": 0.2535,
+      "step": 164
+    },
+    {
+      "epoch": 0.5892857142857143,
+      "grad_norm": 1.4042772064201299,
+      "learning_rate": 7.64582467388275e-06,
+      "loss": 0.29,
+      "step": 165
+    },
+    {
+      "epoch": 0.5928571428571429,
+      "grad_norm": 1.0410163107697814,
+      "learning_rate": 7.533317630237117e-06,
+      "loss": 0.1942,
+      "step": 166
+    },
+    {
+      "epoch": 0.5964285714285714,
+      "grad_norm": 1.1834862825759473,
+      "learning_rate": 7.421142075903067e-06,
+      "loss": 0.2608,
+      "step": 167
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2461737709298746,
+      "learning_rate": 7.3093130857835245e-06,
+      "loss": 0.2681,
+      "step": 168
+    },
+    {
+      "epoch": 0.6035714285714285,
+      "grad_norm": 1.2115559292341946,
+      "learning_rate": 7.197845688207805e-06,
+      "loss": 0.2352,
+      "step": 169
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 1.0701575902544511,
+      "learning_rate": 7.086754862911982e-06,
+      "loss": 0.2076,
+      "step": 170
+    },
+    {
+      "epoch": 0.6107142857142858,
+      "grad_norm": 1.2618870831545073,
+      "learning_rate": 6.976055539025819e-06,
+      "loss": 0.2606,
+      "step": 171
+    },
+    {
+      "epoch": 0.6142857142857143,
+      "grad_norm": 1.0888180029112944,
+      "learning_rate": 6.865762593066514e-06,
+      "loss": 0.209,
+      "step": 172
+    },
+    {
+      "epoch": 0.6178571428571429,
+      "grad_norm": 0.9637644783258941,
+      "learning_rate": 6.755890846939454e-06,
+      "loss": 0.1868,
+      "step": 173
+    },
+    {
+      "epoch": 0.6214285714285714,
+      "grad_norm": 1.1752207319969545,
+      "learning_rate": 6.646455065946386e-06,
+      "loss": 0.2386,
+      "step": 174
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.531148390345953,
+      "learning_rate": 6.537469956801128e-06,
+      "loss": 0.2812,
+      "step": 175
+    },
+    {
+      "epoch": 0.6285714285714286,
+      "grad_norm": 1.050739342183355,
+      "learning_rate": 6.428950165653204e-06,
+      "loss": 0.1571,
+      "step": 176
+    },
+    {
+      "epoch": 0.6321428571428571,
+      "grad_norm": 1.3025828316437698,
+      "learning_rate": 6.320910276119576e-06,
+      "loss": 0.3264,
+      "step": 177
+    },
+    {
+      "epoch": 0.6357142857142857,
+      "grad_norm": 1.1230296801704063,
+      "learning_rate": 6.213364807324817e-06,
+      "loss": 0.2526,
+      "step": 178
+    },
+    {
+      "epoch": 0.6392857142857142,
+      "grad_norm": 1.2236699933441972,
+      "learning_rate": 6.106328211949928e-06,
+      "loss": 0.2438,
+      "step": 179
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 1.2849500197810382,
+      "learning_rate": 5.999814874290084e-06,
+      "loss": 0.2766,
+      "step": 180
+    },
+    {
+      "epoch": 0.6464285714285715,
+      "grad_norm": 1.4068460865502705,
+      "learning_rate": 5.893839108321584e-06,
+      "loss": 0.2487,
+      "step": 181
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.1234261454392709,
+      "learning_rate": 5.7884151557782305e-06,
+      "loss": 0.2068,
+      "step": 182
+    },
+    {
+      "epoch": 0.6535714285714286,
+      "grad_norm": 1.2039141602608157,
+      "learning_rate": 5.68355718423746e-06,
+      "loss": 0.241,
+      "step": 183
+    },
+    {
+      "epoch": 0.6571428571428571,
+      "grad_norm": 1.3354328705229657,
+      "learning_rate": 5.579279285216369e-06,
+      "loss": 0.2511,
+      "step": 184
+    },
+    {
+      "epoch": 0.6607142857142857,
+      "grad_norm": 1.1773442465336659,
+      "learning_rate": 5.4755954722780236e-06,
+      "loss": 0.214,
+      "step": 185
+    },
+    {
+      "epoch": 0.6642857142857143,
+      "grad_norm": 1.3214351825616737,
+      "learning_rate": 5.372519679148227e-06,
+      "loss": 0.2574,
+      "step": 186
+    },
+    {
+      "epoch": 0.6678571428571428,
+      "grad_norm": 1.28890435626217,
+      "learning_rate": 5.270065757843e-06,
+      "loss": 0.2602,
+      "step": 187
+    },
+    {
+      "epoch": 0.6714285714285714,
+      "grad_norm": 1.6842217065033716,
+      "learning_rate": 5.168247476807054e-06,
+      "loss": 0.3211,
+      "step": 188
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 1.1068969575276253,
+      "learning_rate": 5.067078519063514e-06,
+      "loss": 0.2504,
+      "step": 189
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 1.2277392727513172,
+      "learning_rate": 4.966572480375076e-06,
+      "loss": 0.262,
+      "step": 190
+    },
+    {
+      "epoch": 0.6821428571428572,
+      "grad_norm": 1.377027535299938,
+      "learning_rate": 4.86674286741693e-06,
+      "loss": 0.2522,
+      "step": 191
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 1.4334001855394087,
+      "learning_rate": 4.767603095961652e-06,
+      "loss": 0.3384,
+      "step": 192
+    },
+    {
+      "epoch": 0.6892857142857143,
+      "grad_norm": 1.5791708581175883,
+      "learning_rate": 4.669166489076283e-06,
+      "loss": 0.2997,
+      "step": 193
+    },
+    {
+      "epoch": 0.6928571428571428,
+      "grad_norm": 1.1161675043079184,
+      "learning_rate": 4.571446275331903e-06,
+      "loss": 0.2313,
+      "step": 194
+    },
+    {
+      "epoch": 0.6964285714285714,
+      "grad_norm": 1.3277561027589218,
+      "learning_rate": 4.47445558702587e-06,
+      "loss": 0.2781,
+      "step": 195
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.397733081014858,
+      "learning_rate": 4.378207458417035e-06,
+      "loss": 0.2251,
+      "step": 196
+    },
+    {
+      "epoch": 0.7035714285714286,
+      "grad_norm": 1.388095136090467,
+      "learning_rate": 4.282714823974088e-06,
+      "loss": 0.2325,
+      "step": 197
+    },
+    {
+      "epoch": 0.7071428571428572,
+      "grad_norm": 1.2996099360813929,
+      "learning_rate": 4.187990516637361e-06,
+      "loss": 0.2275,
+      "step": 198
+    },
+    {
+      "epoch": 0.7107142857142857,
+      "grad_norm": 1.0179815368690175,
+      "learning_rate": 4.094047266094225e-06,
+      "loss": 0.2071,
+      "step": 199
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.9626077999899579,
+      "learning_rate": 4.000897697068418e-06,
+      "loss": 0.1527,
+      "step": 200
+    },
+    {
+      "epoch": 0.7178571428571429,
+      "grad_norm": 1.6709210188049672,
+      "learning_rate": 3.908554327623425e-06,
+      "loss": 0.248,
+      "step": 201
+    },
+    {
+      "epoch": 0.7214285714285714,
+      "grad_norm": 1.051314061168948,
+      "learning_rate": 3.817029567480228e-06,
+      "loss": 0.2226,
+      "step": 202
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 1.1570066153879779,
+      "learning_rate": 3.7263357163496118e-06,
+      "loss": 0.2513,
+      "step": 203
+    },
+    {
+      "epoch": 0.7285714285714285,
+      "grad_norm": 1.3529998234784348,
+      "learning_rate": 3.6364849622792262e-06,
+      "loss": 0.2708,
+      "step": 204
+    },
+    {
+      "epoch": 0.7321428571428571,
+      "grad_norm": 1.0344848554055432,
+      "learning_rate": 3.5474893800157005e-06,
+      "loss": 0.22,
+      "step": 205
+    },
+    {
+      "epoch": 0.7357142857142858,
+      "grad_norm": 1.0551120664321756,
+      "learning_rate": 3.459360929381931e-06,
+      "loss": 0.1951,
+      "step": 206
+    },
+    {
+      "epoch": 0.7392857142857143,
+      "grad_norm": 1.7154681645984657,
+      "learning_rate": 3.372111453669864e-06,
+      "loss": 0.2517,
+      "step": 207
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 1.1803702945936567,
+      "learning_rate": 3.2857526780488925e-06,
+      "loss": 0.262,
+      "step": 208
+    },
+    {
+      "epoch": 0.7464285714285714,
+      "grad_norm": 1.2630814905706433,
+      "learning_rate": 3.2002962079901743e-06,
+      "loss": 0.2033,
+      "step": 209
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.2721013537455719,
+      "learning_rate": 3.115753527706986e-06,
+      "loss": 0.2518,
+      "step": 210
+    },
+    {
+      "epoch": 0.7535714285714286,
+      "grad_norm": 1.1124710395238153,
+      "learning_rate": 3.0321359986114096e-06,
+      "loss": 0.2167,
+      "step": 211
+    },
+    {
+      "epoch": 0.7571428571428571,
+      "grad_norm": 1.2457716210186396,
+      "learning_rate": 2.9494548577875195e-06,
+      "loss": 0.2503,
+      "step": 212
+    },
+    {
+      "epoch": 0.7607142857142857,
+      "grad_norm": 1.065915466497783,
+      "learning_rate": 2.8677212164812464e-06,
+      "loss": 0.2231,
+      "step": 213
+    },
+    {
+      "epoch": 0.7642857142857142,
+      "grad_norm": 1.393741901609287,
+      "learning_rate": 2.786946058607187e-06,
+      "loss": 0.2805,
+      "step": 214
+    },
+    {
+      "epoch": 0.7678571428571429,
+      "grad_norm": 1.470041450071081,
+      "learning_rate": 2.70714023927251e-06,
+      "loss": 0.2825,
+      "step": 215
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 1.584342453794814,
+      "learning_rate": 2.628314483318178e-06,
+      "loss": 0.2371,
+      "step": 216
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 1.2693297007059587,
+      "learning_rate": 2.5504793838776585e-06,
+      "loss": 0.1873,
+      "step": 217
+    },
+    {
+      "epoch": 0.7785714285714286,
+      "grad_norm": 1.245289271957977,
+      "learning_rate": 2.473645400953366e-06,
+      "loss": 0.2927,
+      "step": 218
+    },
+    {
+      "epoch": 0.7821428571428571,
+      "grad_norm": 1.2607863831123327,
+      "learning_rate": 2.3978228600109564e-06,
+      "loss": 0.2481,
+      "step": 219
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 1.220441989484938,
+      "learning_rate": 2.323021950591743e-06,
+      "loss": 0.2467,
+      "step": 220
+    },
+    {
+      "epoch": 0.7892857142857143,
+      "grad_norm": 1.2281982746356181,
+      "learning_rate": 2.249252724943336e-06,
+      "loss": 0.2803,
+      "step": 221
+    },
+    {
+      "epoch": 0.7928571428571428,
+      "grad_norm": 1.1044689521328117,
+      "learning_rate": 2.176525096668769e-06,
+      "loss": 0.2193,
+      "step": 222
+    },
+    {
+      "epoch": 0.7964285714285714,
+      "grad_norm": 1.2170961838678331,
+      "learning_rate": 2.1048488393942455e-06,
+      "loss": 0.2375,
+      "step": 223
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.4573446345071543,
+      "learning_rate": 2.0342335854556738e-06,
+      "loss": 0.173,
+      "step": 224
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 1.3111764579287404,
+      "learning_rate": 1.964688824604234e-06,
+      "loss": 0.2661,
+      "step": 225
+    },
+    {
+      "epoch": 0.8071428571428572,
+      "grad_norm": 1.2417003827196513,
+      "learning_rate": 1.896223902731058e-06,
+      "loss": 0.171,
+      "step": 226
+    },
+    {
+      "epoch": 0.8107142857142857,
+      "grad_norm": 1.2141425887816526,
+      "learning_rate": 1.8288480206112879e-06,
+      "loss": 0.1738,
+      "step": 227
+    },
+    {
+      "epoch": 0.8142857142857143,
+      "grad_norm": 1.022425021077555,
+      "learning_rate": 1.7625702326675952e-06,
+      "loss": 0.2134,
+      "step": 228
+    },
+    {
+      "epoch": 0.8178571428571428,
+      "grad_norm": 1.173032374888002,
+      "learning_rate": 1.6973994457534026e-06,
+      "loss": 0.1938,
+      "step": 229
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 1.2420049692742343,
+      "learning_rate": 1.6333444179559078e-06,
+      "loss": 0.242,
+      "step": 230
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 1.3513993245030391,
+      "learning_rate": 1.5704137574191202e-06,
+      "loss": 0.2845,
+      "step": 231
+    },
+    {
+      "epoch": 0.8285714285714286,
+      "grad_norm": 1.420715401993255,
+      "learning_rate": 1.5086159211870445e-06,
+      "loss": 0.2712,
+      "step": 232
+    },
+    {
+      "epoch": 0.8321428571428572,
+      "grad_norm": 1.3005819770422833,
+      "learning_rate": 1.447959214067155e-06,
+      "loss": 0.2802,
+      "step": 233
+    },
+    {
+      "epoch": 0.8357142857142857,
+      "grad_norm": 1.24571536421542,
+      "learning_rate": 1.3884517875143544e-06,
+      "loss": 0.2453,
+      "step": 234
+    },
+    {
+      "epoch": 0.8392857142857143,
+      "grad_norm": 1.2919819879535368,
+      "learning_rate": 1.3301016385355093e-06,
+      "loss": 0.2508,
+      "step": 235
+    },
+    {
+      "epoch": 0.8428571428571429,
+      "grad_norm": 0.9961699450434693,
+      "learning_rate": 1.2729166086147803e-06,
+      "loss": 0.1887,
+      "step": 236
+    },
+    {
+      "epoch": 0.8464285714285714,
+      "grad_norm": 1.5467428872844788,
+      "learning_rate": 1.216904382659806e-06,
+      "loss": 0.2464,
+      "step": 237
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.2271290810407274,
+      "learning_rate": 1.1620724879689793e-06,
+      "loss": 0.2713,
+      "step": 238
+    },
+    {
+      "epoch": 0.8535714285714285,
+      "grad_norm": 1.2286226770029365,
+      "learning_rate": 1.1084282932198543e-06,
+      "loss": 0.2567,
+      "step": 239
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.4011585388122023,
+      "learning_rate": 1.0559790074789134e-06,
+      "loss": 0.2516,
+      "step": 240
+    },
+    {
+      "epoch": 0.8607142857142858,
+      "grad_norm": 1.0840441689282334,
+      "learning_rate": 1.00473167923275e-06,
+      "loss": 0.2096,
+      "step": 241
+    },
+    {
+      "epoch": 0.8642857142857143,
+      "grad_norm": 1.0119652758464874,
+      "learning_rate": 9.546931954408622e-07,
+      "loss": 0.231,
+      "step": 242
+    },
+    {
+      "epoch": 0.8678571428571429,
+      "grad_norm": 1.1616671662945137,
+      "learning_rate": 9.058702806101172e-07,
+      "loss": 0.2804,
+      "step": 243
+    },
+    {
+      "epoch": 0.8714285714285714,
+      "grad_norm": 1.1036882519778652,
+      "learning_rate": 8.582694958910809e-07,
+      "loss": 0.1926,
+      "step": 244
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.7805078175984956,
+      "learning_rate": 8.118972381962853e-07,
+      "loss": 0.3517,
+      "step": 245
+    },
+    {
+      "epoch": 0.8785714285714286,
+      "grad_norm": 1.2419453931218212,
+      "learning_rate": 7.667597393405602e-07,
+      "loss": 0.2201,
+      "step": 246
+    },
+    {
+      "epoch": 0.8821428571428571,
+      "grad_norm": 0.8945656937138003,
+      "learning_rate": 7.228630652035717e-07,
+      "loss": 0.1451,
+      "step": 247
+    },
+    {
+      "epoch": 0.8857142857142857,
+      "grad_norm": 1.2252025609614527,
+      "learning_rate": 6.802131149146374e-07,
+      "loss": 0.3105,
+      "step": 248
+    },
+    {
+      "epoch": 0.8892857142857142,
+      "grad_norm": 1.1094193856675925,
+      "learning_rate": 6.388156200599726e-07,
+      "loss": 0.225,
+      "step": 249
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 1.0631388104002977,
+      "learning_rate": 5.986761439124289e-07,
+      "loss": 0.2284,
+      "step": 250
+    },
+    {
+      "epoch": 0.8964285714285715,
+      "grad_norm": 1.5617314258638755,
+      "learning_rate": 5.598000806838766e-07,
+      "loss": 0.3088,
+      "step": 251
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8332568522068625,
+      "learning_rate": 5.221926548002876e-07,
+      "loss": 0.191,
+      "step": 252
+    },
+    {
+      "epoch": 0.9035714285714286,
+      "grad_norm": 1.1719547220888427,
+      "learning_rate": 4.858589201996433e-07,
+      "loss": 0.2583,
+      "step": 253
+    },
+    {
+      "epoch": 0.9071428571428571,
+      "grad_norm": 1.133908730656366,
+      "learning_rate": 4.5080375965275256e-07,
+      "loss": 0.2348,
+      "step": 254
+    },
+    {
+      "epoch": 0.9107142857142857,
+      "grad_norm": 1.2831543354154942,
+      "learning_rate": 4.1703188410707087e-07,
+      "loss": 0.2904,
+      "step": 255
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 1.213206651154921,
+      "learning_rate": 3.845478320536178e-07,
+      "loss": 0.2238,
+      "step": 256
+    },
+    {
+      "epoch": 0.9178571428571428,
+      "grad_norm": 1.3840560824968653,
+      "learning_rate": 3.5335596891705406e-07,
+      "loss": 0.2866,
+      "step": 257
+    },
+    {
+      "epoch": 0.9214285714285714,
+      "grad_norm": 1.3419476428558208,
+      "learning_rate": 3.2346048646903494e-07,
+      "loss": 0.2296,
+      "step": 258
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 1.4783515097524067,
+      "learning_rate": 2.9486540226488556e-07,
+      "loss": 0.2632,
+      "step": 259
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 1.3082741743155946,
+      "learning_rate": 2.6757455910370486e-07,
+      "loss": 0.2832,
+      "step": 260
+    },
+    {
+      "epoch": 0.9321428571428572,
+      "grad_norm": 0.924363054834178,
+      "learning_rate": 2.41591624511931e-07,
+      "loss": 0.1768,
+      "step": 261
+    },
+    {
+      "epoch": 0.9357142857142857,
+      "grad_norm": 1.372435978704722,
+      "learning_rate": 2.169200902504842e-07,
+      "loss": 0.2593,
+      "step": 262
+    },
+    {
+      "epoch": 0.9392857142857143,
+      "grad_norm": 1.269349570999231,
+      "learning_rate": 1.9356327184551716e-07,
+      "loss": 0.2495,
+      "step": 263
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 1.6570864541919217,
+      "learning_rate": 1.7152430814285303e-07,
+      "loss": 0.2717,
+      "step": 264
+    },
+    {
+      "epoch": 0.9464285714285714,
+      "grad_norm": 1.5325685430573508,
+      "learning_rate": 1.5080616088616884e-07,
+      "loss": 0.2778,
+      "step": 265
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.713144760919195,
+      "learning_rate": 1.3141161431896809e-07,
+      "loss": 0.2987,
+      "step": 266
+    },
+    {
+      "epoch": 0.9535714285714286,
+      "grad_norm": 1.0634955690701426,
+      "learning_rate": 1.1334327481042573e-07,
+      "loss": 0.2011,
+      "step": 267
+    },
+    {
+      "epoch": 0.9571428571428572,
+      "grad_norm": 1.1332677973711514,
+      "learning_rate": 9.660357050512158e-08,
+      "loss": 0.2668,
+      "step": 268
+    },
+    {
+      "epoch": 0.9607142857142857,
+      "grad_norm": 1.4787789883914229,
+      "learning_rate": 8.119475099673035e-08,
+      "loss": 0.2699,
+      "step": 269
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 1.209673848563743,
+      "learning_rate": 6.711888702570556e-08,
+      "loss": 0.2596,
+      "step": 270
+    },
+    {
+      "epoch": 0.9678571428571429,
+      "grad_norm": 1.0972839709989628,
+      "learning_rate": 5.437787020100116e-08,
+      "loss": 0.2103,
+      "step": 271
+    },
+    {
+      "epoch": 0.9714285714285714,
+      "grad_norm": 1.1231193864258897,
+      "learning_rate": 4.297341274586475e-08,
+      "loss": 0.268,
+      "step": 272
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 1.1956915997206494,
+      "learning_rate": 3.290704726773619e-08,
+      "loss": 0.2847,
+      "step": 273
+    },
+    {
+      "epoch": 0.9785714285714285,
+      "grad_norm": 1.2913125354215045,
+      "learning_rate": 2.4180126552284523e-08,
+      "loss": 0.1953,
+      "step": 274
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "grad_norm": 1.6578431833331362,
+      "learning_rate": 1.6793823381614506e-08,
+      "loss": 0.2722,
+      "step": 275
+    },
+    {
+      "epoch": 0.9857142857142858,
+      "grad_norm": 1.3559712443207177,
+      "learning_rate": 1.0749130376659366e-08,
+      "loss": 0.2642,
+      "step": 276
+    },
+    {
+      "epoch": 0.9892857142857143,
+      "grad_norm": 1.685274029995845,
+      "learning_rate": 6.046859863781951e-09,
+      "loss": 0.3095,
+      "step": 277
+    },
+    {
+      "epoch": 0.9928571428571429,
+      "grad_norm": 1.2538217785970582,
+      "learning_rate": 2.6876437656153663e-09,
+      "loss": 0.2671,
+      "step": 278
+    },
+    {
+      "epoch": 0.9964285714285714,
+      "grad_norm": 1.1032012427011666,
+      "learning_rate": 6.719335161364804e-10,
+      "loss": 0.1944,
+      "step": 279
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1581903539113911,
+      "learning_rate": 0.0,
+      "loss": 0.2819,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "step": 280,
+      "total_flos": 237319253655552.0,
+      "train_loss": 0.29905301529381956,
+      "train_runtime": 2053.3952,
+      "train_samples_per_second": 17.448,
+      "train_steps_per_second": 0.136
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 237319253655552.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554e83488156a1eb60de0329b2fcc4131bfa518655b10de77f66f786ddaf499e
+size 7288