Upload folder using huggingface_hub

.gitattributes

@@ -3,3 +3,4 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,140 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 70,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  },
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.57.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65331b7be744ab5287590b2a47d7d7b96cef1e46a9d88e6dfb10efb12bd0591e
+size 4997750760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a57379a0d519c9a23c851f5576ec6f550a67f382e4d4ce93334124c47f6558
+size 2511587184

model.safetensors.index.json

@@ -0,0 +1,832 @@
+{
+  "metadata": {
+    "total_parameters": 3754622976,
+    "total_size": 7509245952
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-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.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.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.bias": "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.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-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.bias": "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.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98fd06bf3422a6f6b61d55832fd7d895265e546dd958c103c13f08b499239ce
+size 15019212310

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03266608a06085d480d9fedb463e4a8c3a283d5bdc2ea2ec07dc9c024070185
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1609 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4895729890764646,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006620324395895399,
+      "grad_norm": 31.25,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 1.6298,
+      "step": 20
+    },
+    {
+      "epoch": 0.013240648791790799,
+      "grad_norm": 17.125,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 1.1324,
+      "step": 40
+    },
+    {
+      "epoch": 0.019860973187686197,
+      "grad_norm": 24.0,
+      "learning_rate": 9.984979973297732e-06,
+      "loss": 0.782,
+      "step": 60
+    },
+    {
+      "epoch": 0.026481297583581597,
+      "grad_norm": 14.875,
+      "learning_rate": 9.951602136181577e-06,
+      "loss": 0.732,
+      "step": 80
+    },
+    {
+      "epoch": 0.033101621979477,
+      "grad_norm": 12.375,
+      "learning_rate": 9.918224299065421e-06,
+      "loss": 0.7183,
+      "step": 100
+    },
+    {
+      "epoch": 0.039721946375372394,
+      "grad_norm": 17.625,
+      "learning_rate": 9.884846461949267e-06,
+      "loss": 0.6998,
+      "step": 120
+    },
+    {
+      "epoch": 0.04634227077126779,
+      "grad_norm": 17.25,
+      "learning_rate": 9.851468624833111e-06,
+      "loss": 0.6805,
+      "step": 140
+    },
+    {
+      "epoch": 0.052962595167163194,
+      "grad_norm": 22.125,
+      "learning_rate": 9.818090787716956e-06,
+      "loss": 0.6887,
+      "step": 160
+    },
+    {
+      "epoch": 0.05958291956305859,
+      "grad_norm": 13.3125,
+      "learning_rate": 9.784712950600802e-06,
+      "loss": 0.6688,
+      "step": 180
+    },
+    {
+      "epoch": 0.066203243958954,
+      "grad_norm": 14.1875,
+      "learning_rate": 9.751335113484648e-06,
+      "loss": 0.6448,
+      "step": 200
+    },
+    {
+      "epoch": 0.07282356835484939,
+      "grad_norm": 53.0,
+      "learning_rate": 9.717957276368492e-06,
+      "loss": 0.6303,
+      "step": 220
+    },
+    {
+      "epoch": 0.07944389275074479,
+      "grad_norm": 21.375,
+      "learning_rate": 9.684579439252338e-06,
+      "loss": 0.6824,
+      "step": 240
+    },
+    {
+      "epoch": 0.08606421714664018,
+      "grad_norm": 35.0,
+      "learning_rate": 9.651201602136182e-06,
+      "loss": 0.6308,
+      "step": 260
+    },
+    {
+      "epoch": 0.09268454154253558,
+      "grad_norm": 38.5,
+      "learning_rate": 9.617823765020028e-06,
+      "loss": 0.6079,
+      "step": 280
+    },
+    {
+      "epoch": 0.09930486593843098,
+      "grad_norm": 10.875,
+      "learning_rate": 9.584445927903873e-06,
+      "loss": 0.6296,
+      "step": 300
+    },
+    {
+      "epoch": 0.10592519033432639,
+      "grad_norm": 15.6875,
+      "learning_rate": 9.551068090787717e-06,
+      "loss": 0.6119,
+      "step": 320
+    },
+    {
+      "epoch": 0.11254551473022179,
+      "grad_norm": 33.75,
+      "learning_rate": 9.517690253671563e-06,
+      "loss": 0.6681,
+      "step": 340
+    },
+    {
+      "epoch": 0.11916583912611718,
+      "grad_norm": 17.25,
+      "learning_rate": 9.484312416555407e-06,
+      "loss": 0.6765,
+      "step": 360
+    },
+    {
+      "epoch": 0.12578616352201258,
+      "grad_norm": 17.625,
+      "learning_rate": 9.450934579439253e-06,
+      "loss": 0.611,
+      "step": 380
+    },
+    {
+      "epoch": 0.132406487917908,
+      "grad_norm": 15.75,
+      "learning_rate": 9.4175567423231e-06,
+      "loss": 0.623,
+      "step": 400
+    },
+    {
+      "epoch": 0.13902681231380337,
+      "grad_norm": 24.5,
+      "learning_rate": 9.384178905206944e-06,
+      "loss": 0.6483,
+      "step": 420
+    },
+    {
+      "epoch": 0.14564713670969878,
+      "grad_norm": 19.5,
+      "learning_rate": 9.35080106809079e-06,
+      "loss": 0.5895,
+      "step": 440
+    },
+    {
+      "epoch": 0.15226746110559417,
+      "grad_norm": 20.5,
+      "learning_rate": 9.317423230974634e-06,
+      "loss": 0.6381,
+      "step": 460
+    },
+    {
+      "epoch": 0.15888778550148958,
+      "grad_norm": 21.875,
+      "learning_rate": 9.284045393858478e-06,
+      "loss": 0.6208,
+      "step": 480
+    },
+    {
+      "epoch": 0.16550810989738496,
+      "grad_norm": 16.0,
+      "learning_rate": 9.250667556742324e-06,
+      "loss": 0.5864,
+      "step": 500
+    },
+    {
+      "epoch": 0.17212843429328037,
+      "grad_norm": 15.375,
+      "learning_rate": 9.217289719626169e-06,
+      "loss": 0.6343,
+      "step": 520
+    },
+    {
+      "epoch": 0.17874875868917578,
+      "grad_norm": 18.75,
+      "learning_rate": 9.183911882510013e-06,
+      "loss": 0.6316,
+      "step": 540
+    },
+    {
+      "epoch": 0.18536908308507116,
+      "grad_norm": 12.0625,
+      "learning_rate": 9.150534045393859e-06,
+      "loss": 0.6067,
+      "step": 560
+    },
+    {
+      "epoch": 0.19198940748096657,
+      "grad_norm": 19.375,
+      "learning_rate": 9.117156208277705e-06,
+      "loss": 0.6179,
+      "step": 580
+    },
+    {
+      "epoch": 0.19860973187686196,
+      "grad_norm": 22.0,
+      "learning_rate": 9.08377837116155e-06,
+      "loss": 0.6558,
+      "step": 600
+    },
+    {
+      "epoch": 0.20523005627275737,
+      "grad_norm": 16.75,
+      "learning_rate": 9.050400534045395e-06,
+      "loss": 0.6367,
+      "step": 620
+    },
+    {
+      "epoch": 0.21185038066865278,
+      "grad_norm": 19.75,
+      "learning_rate": 9.01702269692924e-06,
+      "loss": 0.6075,
+      "step": 640
+    },
+    {
+      "epoch": 0.21847070506454816,
+      "grad_norm": 19.875,
+      "learning_rate": 8.983644859813084e-06,
+      "loss": 0.6385,
+      "step": 660
+    },
+    {
+      "epoch": 0.22509102946044357,
+      "grad_norm": 31.375,
+      "learning_rate": 8.95026702269693e-06,
+      "loss": 0.6369,
+      "step": 680
+    },
+    {
+      "epoch": 0.23171135385633895,
+      "grad_norm": 10.9375,
+      "learning_rate": 8.916889185580774e-06,
+      "loss": 0.6156,
+      "step": 700
+    },
+    {
+      "epoch": 0.23833167825223436,
+      "grad_norm": 30.125,
+      "learning_rate": 8.88351134846462e-06,
+      "loss": 0.6265,
+      "step": 720
+    },
+    {
+      "epoch": 0.24495200264812975,
+      "grad_norm": 462.0,
+      "learning_rate": 8.850133511348466e-06,
+      "loss": 0.5881,
+      "step": 740
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "grad_norm": 15.1875,
+      "learning_rate": 8.81675567423231e-06,
+      "loss": 0.5912,
+      "step": 760
+    },
+    {
+      "epoch": 0.25819265143992054,
+      "grad_norm": 25.25,
+      "learning_rate": 8.783377837116157e-06,
+      "loss": 0.6167,
+      "step": 780
+    },
+    {
+      "epoch": 0.264812975835816,
+      "grad_norm": 15.75,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.6106,
+      "step": 800
+    },
+    {
+      "epoch": 0.27143330023171136,
+      "grad_norm": 22.5,
+      "learning_rate": 8.716622162883845e-06,
+      "loss": 0.6762,
+      "step": 820
+    },
+    {
+      "epoch": 0.27805362462760674,
+      "grad_norm": 25.375,
+      "learning_rate": 8.683244325767691e-06,
+      "loss": 0.5455,
+      "step": 840
+    },
+    {
+      "epoch": 0.2846739490235021,
+      "grad_norm": 18.5,
+      "learning_rate": 8.649866488651536e-06,
+      "loss": 0.6118,
+      "step": 860
+    },
+    {
+      "epoch": 0.29129427341939756,
+      "grad_norm": 26.5,
+      "learning_rate": 8.61648865153538e-06,
+      "loss": 0.6339,
+      "step": 880
+    },
+    {
+      "epoch": 0.29791459781529295,
+      "grad_norm": 8.8125,
+      "learning_rate": 8.583110814419226e-06,
+      "loss": 0.5795,
+      "step": 900
+    },
+    {
+      "epoch": 0.30453492221118833,
+      "grad_norm": 13.75,
+      "learning_rate": 8.549732977303072e-06,
+      "loss": 0.5702,
+      "step": 920
+    },
+    {
+      "epoch": 0.31115524660708377,
+      "grad_norm": 13.8125,
+      "learning_rate": 8.516355140186918e-06,
+      "loss": 0.5617,
+      "step": 940
+    },
+    {
+      "epoch": 0.31777557100297915,
+      "grad_norm": 14.25,
+      "learning_rate": 8.482977303070762e-06,
+      "loss": 0.6257,
+      "step": 960
+    },
+    {
+      "epoch": 0.32439589539887453,
+      "grad_norm": 15.5,
+      "learning_rate": 8.449599465954607e-06,
+      "loss": 0.6205,
+      "step": 980
+    },
+    {
+      "epoch": 0.3310162197947699,
+      "grad_norm": 19.375,
+      "learning_rate": 8.416221628838453e-06,
+      "loss": 0.5731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.33763654419066536,
+      "grad_norm": 46.0,
+      "learning_rate": 8.382843791722297e-06,
+      "loss": 0.6116,
+      "step": 1020
+    },
+    {
+      "epoch": 0.34425686858656074,
+      "grad_norm": 15.5,
+      "learning_rate": 8.349465954606141e-06,
+      "loss": 0.612,
+      "step": 1040
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 36.0,
+      "learning_rate": 8.316088117489987e-06,
+      "loss": 0.5932,
+      "step": 1060
+    },
+    {
+      "epoch": 0.35749751737835156,
+      "grad_norm": 16.875,
+      "learning_rate": 8.282710280373832e-06,
+      "loss": 0.5667,
+      "step": 1080
+    },
+    {
+      "epoch": 0.36411784177424694,
+      "grad_norm": 19.25,
+      "learning_rate": 8.249332443257678e-06,
+      "loss": 0.5846,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3707381661701423,
+      "grad_norm": 26.875,
+      "learning_rate": 8.215954606141524e-06,
+      "loss": 0.6549,
+      "step": 1120
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 15.0625,
+      "learning_rate": 8.182576769025368e-06,
+      "loss": 0.6129,
+      "step": 1140
+    },
+    {
+      "epoch": 0.38397881496193315,
+      "grad_norm": 11.4375,
+      "learning_rate": 8.149198931909212e-06,
+      "loss": 0.5143,
+      "step": 1160
+    },
+    {
+      "epoch": 0.39059913935782853,
+      "grad_norm": 9.3125,
+      "learning_rate": 8.115821094793058e-06,
+      "loss": 0.5842,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3972194637537239,
+      "grad_norm": 20.0,
+      "learning_rate": 8.082443257676903e-06,
+      "loss": 0.5485,
+      "step": 1200
+    },
+    {
+      "epoch": 0.40383978814961935,
+      "grad_norm": 29.625,
+      "learning_rate": 8.049065420560749e-06,
+      "loss": 0.5844,
+      "step": 1220
+    },
+    {
+      "epoch": 0.41046011254551473,
+      "grad_norm": 16.0,
+      "learning_rate": 8.015687583444593e-06,
+      "loss": 0.5959,
+      "step": 1240
+    },
+    {
+      "epoch": 0.4170804369414101,
+      "grad_norm": 42.25,
+      "learning_rate": 7.982309746328439e-06,
+      "loss": 0.5758,
+      "step": 1260
+    },
+    {
+      "epoch": 0.42370076133730555,
+      "grad_norm": 18.25,
+      "learning_rate": 7.948931909212283e-06,
+      "loss": 0.5289,
+      "step": 1280
+    },
+    {
+      "epoch": 0.43032108573320094,
+      "grad_norm": 26.75,
+      "learning_rate": 7.91555407209613e-06,
+      "loss": 0.6503,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4369414101290963,
+      "grad_norm": 26.75,
+      "learning_rate": 7.882176234979974e-06,
+      "loss": 0.6088,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4435617345249917,
+      "grad_norm": 11.4375,
+      "learning_rate": 7.84879839786382e-06,
+      "loss": 0.58,
+      "step": 1340
+    },
+    {
+      "epoch": 0.45018205892088714,
+      "grad_norm": 14.5625,
+      "learning_rate": 7.815420560747664e-06,
+      "loss": 0.6087,
+      "step": 1360
+    },
+    {
+      "epoch": 0.4568023833167825,
+      "grad_norm": 21.375,
+      "learning_rate": 7.782042723631508e-06,
+      "loss": 0.531,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4634227077126779,
+      "grad_norm": 20.5,
+      "learning_rate": 7.748664886515354e-06,
+      "loss": 0.57,
+      "step": 1400
+    },
+    {
+      "epoch": 0.47004303210857334,
+      "grad_norm": 22.375,
+      "learning_rate": 7.715287049399199e-06,
+      "loss": 0.57,
+      "step": 1420
+    },
+    {
+      "epoch": 0.4766633565044687,
+      "grad_norm": 24.75,
+      "learning_rate": 7.681909212283045e-06,
+      "loss": 0.5944,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4832836809003641,
+      "grad_norm": 14.6875,
+      "learning_rate": 7.64853137516689e-06,
+      "loss": 0.6433,
+      "step": 1460
+    },
+    {
+      "epoch": 0.4899040052962595,
+      "grad_norm": 11.1875,
+      "learning_rate": 7.615153538050735e-06,
+      "loss": 0.5787,
+      "step": 1480
+    },
+    {
+      "epoch": 0.49652432969215493,
+      "grad_norm": 13.5,
+      "learning_rate": 7.58177570093458e-06,
+      "loss": 0.5239,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 26.875,
+      "learning_rate": 7.548397863818425e-06,
+      "loss": 0.5663,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5097649784839458,
+      "grad_norm": 11.0625,
+      "learning_rate": 7.5150200267022696e-06,
+      "loss": 0.5335,
+      "step": 1540
+    },
+    {
+      "epoch": 0.5163853028798411,
+      "grad_norm": 13.6875,
+      "learning_rate": 7.481642189586116e-06,
+      "loss": 0.5628,
+      "step": 1560
+    },
+    {
+      "epoch": 0.5230056272757365,
+      "grad_norm": 27.625,
+      "learning_rate": 7.448264352469961e-06,
+      "loss": 0.6499,
+      "step": 1580
+    },
+    {
+      "epoch": 0.529625951671632,
+      "grad_norm": 57.25,
+      "learning_rate": 7.414886515353805e-06,
+      "loss": 0.578,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5362462760675273,
+      "grad_norm": 13.8125,
+      "learning_rate": 7.381508678237651e-06,
+      "loss": 0.5788,
+      "step": 1620
+    },
+    {
+      "epoch": 0.5428666004634227,
+      "grad_norm": 10.6875,
+      "learning_rate": 7.348130841121495e-06,
+      "loss": 0.541,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5494869248593182,
+      "grad_norm": 14.375,
+      "learning_rate": 7.314753004005341e-06,
+      "loss": 0.5834,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5561072492552135,
+      "grad_norm": 10.8125,
+      "learning_rate": 7.281375166889187e-06,
+      "loss": 0.5852,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5627275736511089,
+      "grad_norm": 61.0,
+      "learning_rate": 7.247997329773031e-06,
+      "loss": 0.6254,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5693478980470043,
+      "grad_norm": 14.9375,
+      "learning_rate": 7.214619492656877e-06,
+      "loss": 0.5635,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5759682224428997,
+      "grad_norm": 14.0,
+      "learning_rate": 7.181241655540721e-06,
+      "loss": 0.543,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5825885468387951,
+      "grad_norm": 16.0,
+      "learning_rate": 7.147863818424566e-06,
+      "loss": 0.6006,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5892088712346905,
+      "grad_norm": 26.875,
+      "learning_rate": 7.114485981308412e-06,
+      "loss": 0.5916,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5958291956305859,
+      "grad_norm": 36.75,
+      "learning_rate": 7.081108144192257e-06,
+      "loss": 0.5724,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6024495200264813,
+      "grad_norm": 14.6875,
+      "learning_rate": 7.047730307076102e-06,
+      "loss": 0.562,
+      "step": 1820
+    },
+    {
+      "epoch": 0.6090698444223767,
+      "grad_norm": 15.25,
+      "learning_rate": 7.014352469959947e-06,
+      "loss": 0.5978,
+      "step": 1840
+    },
+    {
+      "epoch": 0.6156901688182721,
+      "grad_norm": 12.0625,
+      "learning_rate": 6.980974632843792e-06,
+      "loss": 0.5607,
+      "step": 1860
+    },
+    {
+      "epoch": 0.6223104932141675,
+      "grad_norm": 8.8125,
+      "learning_rate": 6.9475967957276366e-06,
+      "loss": 0.5186,
+      "step": 1880
+    },
+    {
+      "epoch": 0.6289308176100629,
+      "grad_norm": 23.25,
+      "learning_rate": 6.9142189586114826e-06,
+      "loss": 0.5954,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6355511420059583,
+      "grad_norm": 24.75,
+      "learning_rate": 6.880841121495328e-06,
+      "loss": 0.5794,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6421714664018537,
+      "grad_norm": 15.0,
+      "learning_rate": 6.847463284379173e-06,
+      "loss": 0.5931,
+      "step": 1940
+    },
+    {
+      "epoch": 0.6487917907977491,
+      "grad_norm": 13.875,
+      "learning_rate": 6.814085447263018e-06,
+      "loss": 0.6028,
+      "step": 1960
+    },
+    {
+      "epoch": 0.6554121151936445,
+      "grad_norm": 23.125,
+      "learning_rate": 6.780707610146862e-06,
+      "loss": 0.6216,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6620324395895398,
+      "grad_norm": 14.9375,
+      "learning_rate": 6.747329773030708e-06,
+      "loss": 0.6056,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6686527639854353,
+      "grad_norm": 17.25,
+      "learning_rate": 6.713951935914554e-06,
+      "loss": 0.5911,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6752730883813307,
+      "grad_norm": 18.0,
+      "learning_rate": 6.680574098798398e-06,
+      "loss": 0.5472,
+      "step": 2040
+    },
+    {
+      "epoch": 0.681893412777226,
+      "grad_norm": 8.5,
+      "learning_rate": 6.647196261682244e-06,
+      "loss": 0.5363,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6885137371731215,
+      "grad_norm": 13.5,
+      "learning_rate": 6.613818424566088e-06,
+      "loss": 0.5892,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6951340615690169,
+      "grad_norm": 140.0,
+      "learning_rate": 6.580440587449933e-06,
+      "loss": 0.5527,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 10.375,
+      "learning_rate": 6.547062750333779e-06,
+      "loss": 0.5269,
+      "step": 2120
+    },
+    {
+      "epoch": 0.7083747103608077,
+      "grad_norm": 18.375,
+      "learning_rate": 6.513684913217624e-06,
+      "loss": 0.5787,
+      "step": 2140
+    },
+    {
+      "epoch": 0.7149950347567031,
+      "grad_norm": 91.0,
+      "learning_rate": 6.48030707610147e-06,
+      "loss": 0.5397,
+      "step": 2160
+    },
+    {
+      "epoch": 0.7216153591525984,
+      "grad_norm": 46.25,
+      "learning_rate": 6.446929238985314e-06,
+      "loss": 0.5864,
+      "step": 2180
+    },
+    {
+      "epoch": 0.7282356835484939,
+      "grad_norm": 19.0,
+      "learning_rate": 6.413551401869159e-06,
+      "loss": 0.6393,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7348560079443893,
+      "grad_norm": 16.125,
+      "learning_rate": 6.380173564753005e-06,
+      "loss": 0.5432,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7414763323402846,
+      "grad_norm": 13.8125,
+      "learning_rate": 6.3467957276368496e-06,
+      "loss": 0.5974,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7480966567361801,
+      "grad_norm": 18.0,
+      "learning_rate": 6.313417890520695e-06,
+      "loss": 0.5572,
+      "step": 2260
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 28.0,
+      "learning_rate": 6.28004005340454e-06,
+      "loss": 0.5552,
+      "step": 2280
+    },
+    {
+      "epoch": 0.7613373055279709,
+      "grad_norm": 19.0,
+      "learning_rate": 6.246662216288385e-06,
+      "loss": 0.5658,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7679576299238663,
+      "grad_norm": 13.375,
+      "learning_rate": 6.213284379172229e-06,
+      "loss": 0.62,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7745779543197616,
+      "grad_norm": 12.0,
+      "learning_rate": 6.179906542056075e-06,
+      "loss": 0.5836,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7811982787156571,
+      "grad_norm": 15.3125,
+      "learning_rate": 6.1465287049399206e-06,
+      "loss": 0.5605,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7878186031115525,
+      "grad_norm": 9.125,
+      "learning_rate": 6.113150867823765e-06,
+      "loss": 0.5827,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7944389275074478,
+      "grad_norm": 16.875,
+      "learning_rate": 6.079773030707611e-06,
+      "loss": 0.5932,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8010592519033433,
+      "grad_norm": 15.3125,
+      "learning_rate": 6.046395193591455e-06,
+      "loss": 0.5565,
+      "step": 2420
+    },
+    {
+      "epoch": 0.8076795762992387,
+      "grad_norm": 15.6875,
+      "learning_rate": 6.013017356475301e-06,
+      "loss": 0.5594,
+      "step": 2440
+    },
+    {
+      "epoch": 0.814299900695134,
+      "grad_norm": 28.75,
+      "learning_rate": 5.979639519359146e-06,
+      "loss": 0.5853,
+      "step": 2460
+    },
+    {
+      "epoch": 0.8209202250910295,
+      "grad_norm": 28.0,
+      "learning_rate": 5.946261682242991e-06,
+      "loss": 0.5193,
+      "step": 2480
+    },
+    {
+      "epoch": 0.8275405494869249,
+      "grad_norm": 9.875,
+      "learning_rate": 5.912883845126837e-06,
+      "loss": 0.5588,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8341608738828202,
+      "grad_norm": 13.25,
+      "learning_rate": 5.879506008010681e-06,
+      "loss": 0.5621,
+      "step": 2520
+    },
+    {
+      "epoch": 0.8407811982787157,
+      "grad_norm": 48.5,
+      "learning_rate": 5.846128170894526e-06,
+      "loss": 0.5788,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8474015226746111,
+      "grad_norm": 20.375,
+      "learning_rate": 5.812750333778372e-06,
+      "loss": 0.6038,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8540218470705064,
+      "grad_norm": 10.0,
+      "learning_rate": 5.7793724966622166e-06,
+      "loss": 0.516,
+      "step": 2580
+    },
+    {
+      "epoch": 0.8606421714664019,
+      "grad_norm": 15.0625,
+      "learning_rate": 5.745994659546062e-06,
+      "loss": 0.5329,
+      "step": 2600
+    },
+    {
+      "epoch": 0.8672624958622972,
+      "grad_norm": 33.0,
+      "learning_rate": 5.712616822429907e-06,
+      "loss": 0.5484,
+      "step": 2620
+    },
+    {
+      "epoch": 0.8738828202581926,
+      "grad_norm": 11.125,
+      "learning_rate": 5.679238985313752e-06,
+      "loss": 0.53,
+      "step": 2640
+    },
+    {
+      "epoch": 0.8805031446540881,
+      "grad_norm": 11.5625,
+      "learning_rate": 5.645861148197598e-06,
+      "loss": 0.6449,
+      "step": 2660
+    },
+    {
+      "epoch": 0.8871234690499834,
+      "grad_norm": 17.75,
+      "learning_rate": 5.612483311081442e-06,
+      "loss": 0.6072,
+      "step": 2680
+    },
+    {
+      "epoch": 0.8937437934458788,
+      "grad_norm": 15.8125,
+      "learning_rate": 5.5791054739652876e-06,
+      "loss": 0.5155,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9003641178417743,
+      "grad_norm": 13.1875,
+      "learning_rate": 5.545727636849133e-06,
+      "loss": 0.5687,
+      "step": 2720
+    },
+    {
+      "epoch": 0.9069844422376696,
+      "grad_norm": 14.4375,
+      "learning_rate": 5.512349799732978e-06,
+      "loss": 0.5353,
+      "step": 2740
+    },
+    {
+      "epoch": 0.913604766633565,
+      "grad_norm": 17.75,
+      "learning_rate": 5.478971962616822e-06,
+      "loss": 0.5925,
+      "step": 2760
+    },
+    {
+      "epoch": 0.9202250910294605,
+      "grad_norm": 29.125,
+      "learning_rate": 5.445594125500668e-06,
+      "loss": 0.5391,
+      "step": 2780
+    },
+    {
+      "epoch": 0.9268454154253558,
+      "grad_norm": 48.5,
+      "learning_rate": 5.412216288384513e-06,
+      "loss": 0.6109,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9334657398212513,
+      "grad_norm": 22.375,
+      "learning_rate": 5.378838451268358e-06,
+      "loss": 0.5756,
+      "step": 2820
+    },
+    {
+      "epoch": 0.9400860642171467,
+      "grad_norm": 23.375,
+      "learning_rate": 5.345460614152204e-06,
+      "loss": 0.6174,
+      "step": 2840
+    },
+    {
+      "epoch": 0.946706388613042,
+      "grad_norm": 31.125,
+      "learning_rate": 5.312082777036048e-06,
+      "loss": 0.5758,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9533267130089375,
+      "grad_norm": 25.125,
+      "learning_rate": 5.278704939919893e-06,
+      "loss": 0.5311,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9599470374048328,
+      "grad_norm": 14.375,
+      "learning_rate": 5.245327102803739e-06,
+      "loss": 0.5638,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9665673618007282,
+      "grad_norm": 12.5,
+      "learning_rate": 5.2119492656875836e-06,
+      "loss": 0.5714,
+      "step": 2920
+    },
+    {
+      "epoch": 0.9731876861966237,
+      "grad_norm": 23.375,
+      "learning_rate": 5.1785714285714296e-06,
+      "loss": 0.5827,
+      "step": 2940
+    },
+    {
+      "epoch": 0.979808010592519,
+      "grad_norm": 13.4375,
+      "learning_rate": 5.145193591455274e-06,
+      "loss": 0.5574,
+      "step": 2960
+    },
+    {
+      "epoch": 0.9864283349884144,
+      "grad_norm": 13.25,
+      "learning_rate": 5.111815754339119e-06,
+      "loss": 0.5829,
+      "step": 2980
+    },
+    {
+      "epoch": 0.9930486593843099,
+      "grad_norm": 18.125,
+      "learning_rate": 5.078437917222965e-06,
+      "loss": 0.5748,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9996689837802052,
+      "grad_norm": 24.875,
+      "learning_rate": 5.045060080106809e-06,
+      "loss": 0.5445,
+      "step": 3020
+    },
+    {
+      "epoch": 1.0062893081761006,
+      "grad_norm": 15.75,
+      "learning_rate": 5.0116822429906546e-06,
+      "loss": 0.5045,
+      "step": 3040
+    },
+    {
+      "epoch": 1.012909632571996,
+      "grad_norm": 30.75,
+      "learning_rate": 4.9783044058745e-06,
+      "loss": 0.5523,
+      "step": 3060
+    },
+    {
+      "epoch": 1.0195299569678915,
+      "grad_norm": 15.0,
+      "learning_rate": 4.944926568758345e-06,
+      "loss": 0.5192,
+      "step": 3080
+    },
+    {
+      "epoch": 1.0261502813637868,
+      "grad_norm": 9.625,
+      "learning_rate": 4.91154873164219e-06,
+      "loss": 0.6295,
+      "step": 3100
+    },
+    {
+      "epoch": 1.0327706057596822,
+      "grad_norm": 15.6875,
+      "learning_rate": 4.878170894526035e-06,
+      "loss": 0.5496,
+      "step": 3120
+    },
+    {
+      "epoch": 1.0393909301555777,
+      "grad_norm": 10.9375,
+      "learning_rate": 4.84479305740988e-06,
+      "loss": 0.4973,
+      "step": 3140
+    },
+    {
+      "epoch": 1.046011254551473,
+      "grad_norm": 49.75,
+      "learning_rate": 4.8114152202937256e-06,
+      "loss": 0.5615,
+      "step": 3160
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 25.75,
+      "learning_rate": 4.778037383177571e-06,
+      "loss": 0.4783,
+      "step": 3180
+    },
+    {
+      "epoch": 1.059251903343264,
+      "grad_norm": 13.8125,
+      "learning_rate": 4.744659546061416e-06,
+      "loss": 0.5049,
+      "step": 3200
+    },
+    {
+      "epoch": 1.0658722277391592,
+      "grad_norm": 15.625,
+      "learning_rate": 4.71128170894526e-06,
+      "loss": 0.5896,
+      "step": 3220
+    },
+    {
+      "epoch": 1.0724925521350546,
+      "grad_norm": 19.375,
+      "learning_rate": 4.677903871829106e-06,
+      "loss": 0.5383,
+      "step": 3240
+    },
+    {
+      "epoch": 1.0791128765309501,
+      "grad_norm": 15.0625,
+      "learning_rate": 4.644526034712951e-06,
+      "loss": 0.4912,
+      "step": 3260
+    },
+    {
+      "epoch": 1.0857332009268454,
+      "grad_norm": 10.875,
+      "learning_rate": 4.611148197596796e-06,
+      "loss": 0.4702,
+      "step": 3280
+    },
+    {
+      "epoch": 1.0923535253227408,
+      "grad_norm": 51.0,
+      "learning_rate": 4.577770360480641e-06,
+      "loss": 0.4749,
+      "step": 3300
+    },
+    {
+      "epoch": 1.0989738497186363,
+      "grad_norm": 9.125,
+      "learning_rate": 4.544392523364486e-06,
+      "loss": 0.5195,
+      "step": 3320
+    },
+    {
+      "epoch": 1.1055941741145316,
+      "grad_norm": 15.875,
+      "learning_rate": 4.511014686248332e-06,
+      "loss": 0.5295,
+      "step": 3340
+    },
+    {
+      "epoch": 1.112214498510427,
+      "grad_norm": 18.375,
+      "learning_rate": 4.477636849132176e-06,
+      "loss": 0.5202,
+      "step": 3360
+    },
+    {
+      "epoch": 1.1188348229063223,
+      "grad_norm": 18.75,
+      "learning_rate": 4.4442590120160216e-06,
+      "loss": 0.5237,
+      "step": 3380
+    },
+    {
+      "epoch": 1.1254551473022179,
+      "grad_norm": 19.625,
+      "learning_rate": 4.410881174899867e-06,
+      "loss": 0.475,
+      "step": 3400
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 21.0,
+      "learning_rate": 4.377503337783712e-06,
+      "loss": 0.4982,
+      "step": 3420
+    },
+    {
+      "epoch": 1.1386957960940087,
+      "grad_norm": 19.75,
+      "learning_rate": 4.344125500667557e-06,
+      "loss": 0.5446,
+      "step": 3440
+    },
+    {
+      "epoch": 1.145316120489904,
+      "grad_norm": 18.0,
+      "learning_rate": 4.310747663551402e-06,
+      "loss": 0.5471,
+      "step": 3460
+    },
+    {
+      "epoch": 1.1519364448857994,
+      "grad_norm": 13.375,
+      "learning_rate": 4.277369826435247e-06,
+      "loss": 0.4676,
+      "step": 3480
+    },
+    {
+      "epoch": 1.1585567692816947,
+      "grad_norm": 17.25,
+      "learning_rate": 4.2439919893190926e-06,
+      "loss": 0.5296,
+      "step": 3500
+    },
+    {
+      "epoch": 1.1651770936775903,
+      "grad_norm": 19.125,
+      "learning_rate": 4.210614152202938e-06,
+      "loss": 0.5449,
+      "step": 3520
+    },
+    {
+      "epoch": 1.1717974180734856,
+      "grad_norm": 13.625,
+      "learning_rate": 4.177236315086783e-06,
+      "loss": 0.517,
+      "step": 3540
+    },
+    {
+      "epoch": 1.178417742469381,
+      "grad_norm": 11.3125,
+      "learning_rate": 4.143858477970627e-06,
+      "loss": 0.562,
+      "step": 3560
+    },
+    {
+      "epoch": 1.1850380668652765,
+      "grad_norm": 12.8125,
+      "learning_rate": 4.110480640854473e-06,
+      "loss": 0.5341,
+      "step": 3580
+    },
+    {
+      "epoch": 1.1916583912611718,
+      "grad_norm": 13.9375,
+      "learning_rate": 4.077102803738318e-06,
+      "loss": 0.5291,
+      "step": 3600
+    },
+    {
+      "epoch": 1.1982787156570671,
+      "grad_norm": 15.6875,
+      "learning_rate": 4.0437249666221636e-06,
+      "loss": 0.4853,
+      "step": 3620
+    },
+    {
+      "epoch": 1.2048990400529627,
+      "grad_norm": 7.40625,
+      "learning_rate": 4.010347129506008e-06,
+      "loss": 0.49,
+      "step": 3640
+    },
+    {
+      "epoch": 1.211519364448858,
+      "grad_norm": 17.625,
+      "learning_rate": 3.976969292389853e-06,
+      "loss": 0.5523,
+      "step": 3660
+    },
+    {
+      "epoch": 1.2181396888447533,
+      "grad_norm": 13.4375,
+      "learning_rate": 3.943591455273699e-06,
+      "loss": 0.5599,
+      "step": 3680
+    },
+    {
+      "epoch": 1.2247600132406489,
+      "grad_norm": 35.5,
+      "learning_rate": 3.910213618157544e-06,
+      "loss": 0.5391,
+      "step": 3700
+    },
+    {
+      "epoch": 1.2313803376365442,
+      "grad_norm": 26.75,
+      "learning_rate": 3.8768357810413885e-06,
+      "loss": 0.4959,
+      "step": 3720
+    },
+    {
+      "epoch": 1.2380006620324395,
+      "grad_norm": 11.375,
+      "learning_rate": 3.843457943925234e-06,
+      "loss": 0.5286,
+      "step": 3740
+    },
+    {
+      "epoch": 1.244620986428335,
+      "grad_norm": 11.375,
+      "learning_rate": 3.8100801068090793e-06,
+      "loss": 0.4926,
+      "step": 3760
+    },
+    {
+      "epoch": 1.2512413108242304,
+      "grad_norm": 12.0,
+      "learning_rate": 3.776702269692924e-06,
+      "loss": 0.4793,
+      "step": 3780
+    },
+    {
+      "epoch": 1.2578616352201257,
+      "grad_norm": 13.125,
+      "learning_rate": 3.7433244325767692e-06,
+      "loss": 0.5229,
+      "step": 3800
+    },
+    {
+      "epoch": 1.2644819596160213,
+      "grad_norm": 18.25,
+      "learning_rate": 3.7099465954606144e-06,
+      "loss": 0.4884,
+      "step": 3820
+    },
+    {
+      "epoch": 1.2711022840119166,
+      "grad_norm": 18.75,
+      "learning_rate": 3.67656875834446e-06,
+      "loss": 0.4978,
+      "step": 3840
+    },
+    {
+      "epoch": 1.277722608407812,
+      "grad_norm": 11.8125,
+      "learning_rate": 3.6431909212283047e-06,
+      "loss": 0.5222,
+      "step": 3860
+    },
+    {
+      "epoch": 1.2843429328037073,
+      "grad_norm": 11.8125,
+      "learning_rate": 3.60981308411215e-06,
+      "loss": 0.4939,
+      "step": 3880
+    },
+    {
+      "epoch": 1.2909632571996028,
+      "grad_norm": 13.9375,
+      "learning_rate": 3.576435246995995e-06,
+      "loss": 0.5503,
+      "step": 3900
+    },
+    {
+      "epoch": 1.2975835815954981,
+      "grad_norm": 18.0,
+      "learning_rate": 3.54305740987984e-06,
+      "loss": 0.4838,
+      "step": 3920
+    },
+    {
+      "epoch": 1.3042039059913937,
+      "grad_norm": 10.25,
+      "learning_rate": 3.509679572763685e-06,
+      "loss": 0.5089,
+      "step": 3940
+    },
+    {
+      "epoch": 1.310824230387289,
+      "grad_norm": 10.625,
+      "learning_rate": 3.4763017356475305e-06,
+      "loss": 0.5303,
+      "step": 3960
+    },
+    {
+      "epoch": 1.3174445547831843,
+      "grad_norm": 26.625,
+      "learning_rate": 3.4429238985313757e-06,
+      "loss": 0.5523,
+      "step": 3980
+    },
+    {
+      "epoch": 1.3240648791790797,
+      "grad_norm": 15.125,
+      "learning_rate": 3.4095460614152205e-06,
+      "loss": 0.4822,
+      "step": 4000
+    },
+    {
+      "epoch": 1.3306852035749752,
+      "grad_norm": 15.8125,
+      "learning_rate": 3.3761682242990656e-06,
+      "loss": 0.5181,
+      "step": 4020
+    },
+    {
+      "epoch": 1.3373055279708705,
+      "grad_norm": 16.125,
+      "learning_rate": 3.342790387182911e-06,
+      "loss": 0.4931,
+      "step": 4040
+    },
+    {
+      "epoch": 1.343925852366766,
+      "grad_norm": 19.875,
+      "learning_rate": 3.3094125500667564e-06,
+      "loss": 0.5432,
+      "step": 4060
+    },
+    {
+      "epoch": 1.3505461767626614,
+      "grad_norm": 15.6875,
+      "learning_rate": 3.276034712950601e-06,
+      "loss": 0.5477,
+      "step": 4080
+    },
+    {
+      "epoch": 1.3571665011585567,
+      "grad_norm": 24.625,
+      "learning_rate": 3.2426568758344463e-06,
+      "loss": 0.543,
+      "step": 4100
+    },
+    {
+      "epoch": 1.363786825554452,
+      "grad_norm": 15.0625,
+      "learning_rate": 3.2092790387182915e-06,
+      "loss": 0.4995,
+      "step": 4120
+    },
+    {
+      "epoch": 1.3704071499503476,
+      "grad_norm": 16.875,
+      "learning_rate": 3.175901201602136e-06,
+      "loss": 0.5271,
+      "step": 4140
+    },
+    {
+      "epoch": 1.377027474346243,
+      "grad_norm": 18.125,
+      "learning_rate": 3.1425233644859814e-06,
+      "loss": 0.5472,
+      "step": 4160
+    },
+    {
+      "epoch": 1.3836477987421385,
+      "grad_norm": 16.25,
+      "learning_rate": 3.109145527369827e-06,
+      "loss": 0.5145,
+      "step": 4180
+    },
+    {
+      "epoch": 1.3902681231380338,
+      "grad_norm": 16.625,
+      "learning_rate": 3.075767690253672e-06,
+      "loss": 0.5653,
+      "step": 4200
+    },
+    {
+      "epoch": 1.3968884475339292,
+      "grad_norm": 33.0,
+      "learning_rate": 3.042389853137517e-06,
+      "loss": 0.5437,
+      "step": 4220
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 40.75,
+      "learning_rate": 3.009012016021362e-06,
+      "loss": 0.4881,
+      "step": 4240
+    },
+    {
+      "epoch": 1.41012909632572,
+      "grad_norm": 15.625,
+      "learning_rate": 2.975634178905207e-06,
+      "loss": 0.5415,
+      "step": 4260
+    },
+    {
+      "epoch": 1.4167494207216154,
+      "grad_norm": 29.625,
+      "learning_rate": 2.942256341789052e-06,
+      "loss": 0.475,
+      "step": 4280
+    },
+    {
+      "epoch": 1.4233697451175107,
+      "grad_norm": 9.4375,
+      "learning_rate": 2.9088785046728975e-06,
+      "loss": 0.5296,
+      "step": 4300
+    },
+    {
+      "epoch": 1.4299900695134062,
+      "grad_norm": 24.5,
+      "learning_rate": 2.8755006675567427e-06,
+      "loss": 0.5698,
+      "step": 4320
+    },
+    {
+      "epoch": 1.4366103939093016,
+      "grad_norm": 16.5,
+      "learning_rate": 2.842122830440588e-06,
+      "loss": 0.4731,
+      "step": 4340
+    },
+    {
+      "epoch": 1.443230718305197,
+      "grad_norm": 17.125,
+      "learning_rate": 2.8087449933244326e-06,
+      "loss": 0.5652,
+      "step": 4360
+    },
+    {
+      "epoch": 1.4498510427010922,
+      "grad_norm": 16.5,
+      "learning_rate": 2.7753671562082778e-06,
+      "loss": 0.5158,
+      "step": 4380
+    },
+    {
+      "epoch": 1.4564713670969878,
+      "grad_norm": 27.25,
+      "learning_rate": 2.7419893190921234e-06,
+      "loss": 0.5035,
+      "step": 4400
+    },
+    {
+      "epoch": 1.463091691492883,
+      "grad_norm": 12.25,
+      "learning_rate": 2.7086114819759677e-06,
+      "loss": 0.4578,
+      "step": 4420
+    },
+    {
+      "epoch": 1.4697120158887786,
+      "grad_norm": 14.6875,
+      "learning_rate": 2.6752336448598133e-06,
+      "loss": 0.4649,
+      "step": 4440
+    },
+    {
+      "epoch": 1.476332340284674,
+      "grad_norm": 32.5,
+      "learning_rate": 2.6418558077436585e-06,
+      "loss": 0.5685,
+      "step": 4460
+    },
+    {
+      "epoch": 1.4829526646805693,
+      "grad_norm": 15.25,
+      "learning_rate": 2.6084779706275036e-06,
+      "loss": 0.5348,
+      "step": 4480
+    },
+    {
+      "epoch": 1.4895729890764646,
+      "grad_norm": 26.75,
+      "learning_rate": 2.5751001335113484e-06,
+      "loss": 0.4996,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 6042,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.12103856601301e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ea2753dff854e8e09118fad2b94d07fdd5bbc2d934713839734238a958f055
+size 5432