Upload Qwen-Click-DiT model

.gitattributes

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3750/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2500/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
+}

checkpoint-2500/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 %}

checkpoint-2500/config.json

@@ -0,0 +1,145 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dit_dropout": 0.1,
+  "dit_hidden_size": 512,
+  "dit_num_heads": 8,
+  "dit_num_layers": 6,
+  "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_inference_steps": 16,
+  "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_VLForClickPrediction"
+    ],
+    "attention_dropout": 0.0,
+    "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": false,
+    "use_sliding_window": false,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "bfloat16",
+    "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
+}

checkpoint-2500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f248e8ca4585035260fbf35efa0c4f919cc28e6d464877210215fef8b0d0ac0
+size 4997750760

checkpoint-2500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15fc33caa076b7cb4405c9fb15fcf3d3c2d5271657bf3f2bef0cc020eb54d5eb
+size 2565696568

checkpoint-2500/model.safetensors.index.json

@@ -0,0 +1,926 @@
+{
+  "metadata": {
+    "total_parameters": 3781672450,
+    "total_size": 7563344904
+  },
+  "weight_map": {
+    "action_head.action_decoder.layer1.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer1.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.weight": "model-00002-of-00002.safetensors",
+    "action_head.beta_alpha": "model-00002-of-00002.safetensors",
+    "action_head.beta_beta": "model-00002-of-00002.safetensors",
+    "action_head.cond_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.cond_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_1.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_1.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_2.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_2.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
+    "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"
+  }
+}

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77369a34ea1386b7a5d92b8cb1c59df4f6667e0122b2cb2e70dbc55f6c2e898
+size 255114251

checkpoint-2500/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1888d05b90b224b4cdadda399519df0c98650b4504a7f4353bbbd651cbc307ea
+size 14645

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cf269ef8feb052c03e06ea39ca055395dd38abec696484d81b89ff96a63a2e
+size 1465

checkpoint-2500/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
+  }
+}

checkpoint-2500/tokenizer.json

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

checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2500/trainer_state.json

@@ -0,0 +1,1784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.964601769911505e-06,
+      "loss": 1.4112,
+      "step": 10
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 5.3125,
+      "learning_rate": 1.6814159292035402e-05,
+      "loss": 1.4365,
+      "step": 20
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 2.265625,
+      "learning_rate": 2.5663716814159294e-05,
+      "loss": 1.2118,
+      "step": 30
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 2.78125,
+      "learning_rate": 3.451327433628319e-05,
+      "loss": 1.1222,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.3362831858407084e-05,
+      "loss": 1.0566,
+      "step": 50
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.75,
+      "learning_rate": 5.221238938053098e-05,
+      "loss": 1.0392,
+      "step": 60
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 2.578125,
+      "learning_rate": 6.106194690265487e-05,
+      "loss": 1.1753,
+      "step": 70
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 1.421875,
+      "learning_rate": 6.991150442477876e-05,
+      "loss": 1.0422,
+      "step": 80
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 3.765625,
+      "learning_rate": 7.876106194690266e-05,
+      "loss": 1.026,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.609375,
+      "learning_rate": 8.761061946902655e-05,
+      "loss": 1.0633,
+      "step": 100
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 3.171875,
+      "learning_rate": 9.646017699115044e-05,
+      "loss": 1.1138,
+      "step": 110
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 3.609375,
+      "learning_rate": 9.999932848660433e-05,
+      "loss": 1.1079,
+      "step": 120
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.765625,
+      "learning_rate": 9.99952248589506e-05,
+      "loss": 1.0538,
+      "step": 130
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 3.5625,
+      "learning_rate": 9.998739097245067e-05,
+      "loss": 0.9637,
+      "step": 140
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.6875,
+      "learning_rate": 9.997582741160886e-05,
+      "loss": 0.8554,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 7.40625,
+      "learning_rate": 9.99605350392091e-05,
+      "loss": 0.6704,
+      "step": 160
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 7.03125,
+      "learning_rate": 9.994151499625049e-05,
+      "loss": 0.8075,
+      "step": 170
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.828125,
+      "learning_rate": 9.991876870186222e-05,
+      "loss": 0.7331,
+      "step": 180
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 3.890625,
+      "learning_rate": 9.98922978531977e-05,
+      "loss": 0.7264,
+      "step": 190
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.15625,
+      "learning_rate": 9.986210442530788e-05,
+      "loss": 0.5792,
+      "step": 200
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 5.53125,
+      "learning_rate": 9.982819067099396e-05,
+      "loss": 0.6228,
+      "step": 210
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 5.875,
+      "learning_rate": 9.979055912063925e-05,
+      "loss": 0.7417,
+      "step": 220
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 3.71875,
+      "learning_rate": 9.974921258202036e-05,
+      "loss": 0.472,
+      "step": 230
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 4.15625,
+      "learning_rate": 9.970415414009773e-05,
+      "loss": 0.6284,
+      "step": 240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.965538715678548e-05,
+      "loss": 0.5349,
+      "step": 250
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.960291527070051e-05,
+      "loss": 0.5165,
+      "step": 260
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 4.0625,
+      "learning_rate": 9.954674239689109e-05,
+      "loss": 0.5656,
+      "step": 270
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 3.875,
+      "learning_rate": 9.948687272654464e-05,
+      "loss": 0.6713,
+      "step": 280
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 5.375,
+      "learning_rate": 9.942331072667517e-05,
+      "loss": 0.4347,
+      "step": 290
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.875,
+      "learning_rate": 9.935606113978981e-05,
+      "loss": 0.4404,
+      "step": 300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 4.28125,
+      "learning_rate": 9.92851289835351e-05,
+      "loss": 0.4865,
+      "step": 310
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 6.46875,
+      "learning_rate": 9.921051955032253e-05,
+      "loss": 0.5393,
+      "step": 320
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 9.0625,
+      "learning_rate": 9.913223840693375e-05,
+      "loss": 0.5358,
+      "step": 330
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.905029139410508e-05,
+      "loss": 0.5756,
+      "step": 340
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 10.625,
+      "learning_rate": 9.896468462609186e-05,
+      "loss": 0.4554,
+      "step": 350
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 3.6875,
+      "learning_rate": 9.887542449021214e-05,
+      "loss": 0.3889,
+      "step": 360
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 6.25,
+      "learning_rate": 9.878251764637023e-05,
+      "loss": 0.4468,
+      "step": 370
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 5.5,
+      "learning_rate": 9.868597102655968e-05,
+      "loss": 0.4612,
+      "step": 380
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.858579183434605e-05,
+      "loss": 0.6069,
+      "step": 390
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.848198754432959e-05,
+      "loss": 0.4464,
+      "step": 400
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 5.125,
+      "learning_rate": 9.837456590158738e-05,
+      "loss": 0.5598,
+      "step": 410
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 3.671875,
+      "learning_rate": 9.826353492109555e-05,
+      "loss": 0.4534,
+      "step": 420
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 7.34375,
+      "learning_rate": 9.814890288713121e-05,
+      "loss": 0.5155,
+      "step": 430
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 6.875,
+      "learning_rate": 9.803067835265436e-05,
+      "loss": 0.484,
+      "step": 440
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.875,
+      "learning_rate": 9.790887013866973e-05,
+      "loss": 0.4077,
+      "step": 450
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.778348733356868e-05,
+      "loss": 0.3779,
+      "step": 460
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.765453929245096e-05,
+      "loss": 0.521,
+      "step": 470
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.752203563642688e-05,
+      "loss": 0.4114,
+      "step": 480
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 8.25,
+      "learning_rate": 9.73859862518993e-05,
+      "loss": 0.4361,
+      "step": 490
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 7.40625,
+      "learning_rate": 9.724640128982605e-05,
+      "loss": 0.518,
+      "step": 500
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 5.5625,
+      "learning_rate": 9.710329116496259e-05,
+      "loss": 0.4413,
+      "step": 510
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 5.46875,
+      "learning_rate": 9.695666655508483e-05,
+      "loss": 0.4276,
+      "step": 520
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 5.375,
+      "learning_rate": 9.680653840019259e-05,
+      "loss": 0.4476,
+      "step": 530
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 5.875,
+      "learning_rate": 9.665291790169311e-05,
+      "loss": 0.3562,
+      "step": 540
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.4375,
+      "learning_rate": 9.649581652156559e-05,
+      "loss": 0.4511,
+      "step": 550
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.633524598150568e-05,
+      "loss": 0.3985,
+      "step": 560
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 4.1875,
+      "learning_rate": 9.617121826205116e-05,
+      "loss": 0.5117,
+      "step": 570
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 5.5,
+      "learning_rate": 9.600374560168783e-05,
+      "loss": 0.4569,
+      "step": 580
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 4.5,
+      "learning_rate": 9.583284049593652e-05,
+      "loss": 0.449,
+      "step": 590
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.25,
+      "learning_rate": 9.56585156964207e-05,
+      "loss": 0.4769,
+      "step": 600
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 5.9375,
+      "learning_rate": 9.548078420991506e-05,
+      "loss": 0.5081,
+      "step": 610
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 7.4375,
+      "learning_rate": 9.529965929737506e-05,
+      "loss": 0.4803,
+      "step": 620
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.511515447294748e-05,
+      "loss": 0.5015,
+      "step": 630
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 6.71875,
+      "learning_rate": 9.49272835029621e-05,
+      "loss": 0.5174,
+      "step": 640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.875,
+      "learning_rate": 9.47360604049046e-05,
+      "loss": 0.4957,
+      "step": 650
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 4.71875,
+      "learning_rate": 9.454149944637064e-05,
+      "loss": 0.379,
+      "step": 660
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.434361514400132e-05,
+      "loss": 0.4857,
+      "step": 670
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 5.71875,
+      "learning_rate": 9.414242226240012e-05,
+      "loss": 0.4595,
+      "step": 680
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 6.8125,
+      "learning_rate": 9.393793581303116e-05,
+      "loss": 0.4157,
+      "step": 690
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.37301710530993e-05,
+      "loss": 0.4432,
+      "step": 700
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 6.75,
+      "learning_rate": 9.351914348441169e-05,
+      "loss": 0.4695,
+      "step": 710
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 2.890625,
+      "learning_rate": 9.330486885222114e-05,
+      "loss": 0.3493,
+      "step": 720
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 3.4375,
+      "learning_rate": 9.308736314405134e-05,
+      "loss": 0.4304,
+      "step": 730
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.286664258850402e-05,
+      "loss": 0.5057,
+      "step": 740
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.375,
+      "learning_rate": 9.264272365404805e-05,
+      "loss": 0.4159,
+      "step": 750
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.241562304779072e-05,
+      "loss": 0.3647,
+      "step": 760
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 10.3125,
+      "learning_rate": 9.21853577142312e-05,
+      "loss": 0.4851,
+      "step": 770
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.195194483399625e-05,
+      "loss": 0.5071,
+      "step": 780
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 4.34375,
+      "learning_rate": 9.17154018225583e-05,
+      "loss": 0.3939,
+      "step": 790
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.03125,
+      "learning_rate": 9.147574632893611e-05,
+      "loss": 0.3762,
+      "step": 800
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.12329962343779e-05,
+      "loss": 0.4427,
+      "step": 810
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 3.890625,
+      "learning_rate": 9.098716965102716e-05,
+      "loss": 0.357,
+      "step": 820
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 8.25,
+      "learning_rate": 9.073828492057133e-05,
+      "loss": 0.4071,
+      "step": 830
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 5.78125,
+      "learning_rate": 9.048636061287325e-05,
+      "loss": 0.4037,
+      "step": 840
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.84375,
+      "learning_rate": 9.023141552458559e-05,
+      "loss": 0.3884,
+      "step": 850
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 3.453125,
+      "learning_rate": 8.997346867774839e-05,
+      "loss": 0.3641,
+      "step": 860
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 7.875,
+      "learning_rate": 8.97125393183699e-05,
+      "loss": 0.5387,
+      "step": 870
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 4.6875,
+      "learning_rate": 8.94486469149904e-05,
+      "loss": 0.4085,
+      "step": 880
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 6.03125,
+      "learning_rate": 8.918181115722976e-05,
+      "loss": 0.4055,
+      "step": 890
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.375,
+      "learning_rate": 8.891205195431831e-05,
+      "loss": 0.42,
+      "step": 900
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 3.21875,
+      "learning_rate": 8.863938943361128e-05,
+      "loss": 0.3372,
+      "step": 910
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 3.65625,
+      "learning_rate": 8.836384393908721e-05,
+      "loss": 0.4544,
+      "step": 920
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 3.703125,
+      "learning_rate": 8.808543602982993e-05,
+      "loss": 0.4979,
+      "step": 930
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 2.90625,
+      "learning_rate": 8.780418647849458e-05,
+      "loss": 0.3366,
+      "step": 940
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.53125,
+      "learning_rate": 8.752011626975781e-05,
+      "loss": 0.3778,
+      "step": 950
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 3.4375,
+      "learning_rate": 8.723324659875201e-05,
+      "loss": 0.4498,
+      "step": 960
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 4.90625,
+      "learning_rate": 8.694359886948384e-05,
+      "loss": 0.4232,
+      "step": 970
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 4.15625,
+      "learning_rate": 8.665119469323737e-05,
+      "loss": 0.3602,
+      "step": 980
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 5.375,
+      "learning_rate": 8.635605588696148e-05,
+      "loss": 0.4095,
+      "step": 990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.5625,
+      "learning_rate": 8.605820447164206e-05,
+      "loss": 0.405,
+      "step": 1000
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 4.40625,
+      "learning_rate": 8.575766267065905e-05,
+      "loss": 0.3137,
+      "step": 1010
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 5.65625,
+      "learning_rate": 8.54544529081283e-05,
+      "loss": 0.3701,
+      "step": 1020
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 5.0,
+      "learning_rate": 8.514859780722833e-05,
+      "loss": 0.3759,
+      "step": 1030
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 4.9375,
+      "learning_rate": 8.484012018851246e-05,
+      "loss": 0.3032,
+      "step": 1040
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.375,
+      "learning_rate": 8.452904306820618e-05,
+      "loss": 0.4171,
+      "step": 1050
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 4.53125,
+      "learning_rate": 8.421538965648966e-05,
+      "loss": 0.374,
+      "step": 1060
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 4.3125,
+      "learning_rate": 8.389918335576623e-05,
+      "loss": 0.3358,
+      "step": 1070
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 4.21875,
+      "learning_rate": 8.358044775891605e-05,
+      "loss": 0.3586,
+      "step": 1080
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 4.15625,
+      "learning_rate": 8.325920664753595e-05,
+      "loss": 0.4036,
+      "step": 1090
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.625,
+      "learning_rate": 8.293548399016491e-05,
+      "loss": 0.3673,
+      "step": 1100
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 2.625,
+      "learning_rate": 8.260930394049583e-05,
+      "loss": 0.3388,
+      "step": 1110
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 4.78125,
+      "learning_rate": 8.228069083557328e-05,
+      "loss": 0.427,
+      "step": 1120
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 4.21875,
+      "learning_rate": 8.194966919397767e-05,
+      "loss": 0.3926,
+      "step": 1130
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 5.84375,
+      "learning_rate": 8.161626371399591e-05,
+      "loss": 0.3654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.71875,
+      "learning_rate": 8.128049927177854e-05,
+      "loss": 0.4047,
+      "step": 1150
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 5.0,
+      "learning_rate": 8.094240091948375e-05,
+      "loss": 0.4114,
+      "step": 1160
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 6.625,
+      "learning_rate": 8.06019938834081e-05,
+      "loss": 0.4485,
+      "step": 1170
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 4.4375,
+      "learning_rate": 8.025930356210439e-05,
+      "loss": 0.3833,
+      "step": 1180
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 3.171875,
+      "learning_rate": 7.991435552448657e-05,
+      "loss": 0.3742,
+      "step": 1190
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.65625,
+      "learning_rate": 7.956717550792199e-05,
+      "loss": 0.3284,
+      "step": 1200
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 4.4375,
+      "learning_rate": 7.921778941631113e-05,
+      "loss": 0.3862,
+      "step": 1210
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 8.9375,
+      "learning_rate": 7.886622331815477e-05,
+      "loss": 0.4144,
+      "step": 1220
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 3.875,
+      "learning_rate": 7.851250344460902e-05,
+      "loss": 0.3654,
+      "step": 1230
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 2.59375,
+      "learning_rate": 7.815665618752812e-05,
+      "loss": 0.3808,
+      "step": 1240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.0625,
+      "learning_rate": 7.77987080974953e-05,
+      "loss": 0.3482,
+      "step": 1250
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 3.28125,
+      "learning_rate": 7.743868588184176e-05,
+      "loss": 0.3312,
+      "step": 1260
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 4.375,
+      "learning_rate": 7.707661640265401e-05,
+      "loss": 0.37,
+      "step": 1270
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 4.40625,
+      "learning_rate": 7.67125266747696e-05,
+      "loss": 0.3253,
+      "step": 1280
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 4.0625,
+      "learning_rate": 7.634644386376149e-05,
+      "loss": 0.4361,
+      "step": 1290
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 3.953125,
+      "learning_rate": 7.597839528391114e-05,
+      "loss": 0.3981,
+      "step": 1300
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 7.6875,
+      "learning_rate": 7.560840839617056e-05,
+      "loss": 0.3634,
+      "step": 1310
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 4.03125,
+      "learning_rate": 7.523651080611341e-05,
+      "loss": 0.3653,
+      "step": 1320
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 3.09375,
+      "learning_rate": 7.48627302618752e-05,
+      "loss": 0.3433,
+      "step": 1330
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 4.21875,
+      "learning_rate": 7.448709465208299e-05,
+      "loss": 0.3587,
+      "step": 1340
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 5.375,
+      "learning_rate": 7.410963200377458e-05,
+      "loss": 0.346,
+      "step": 1350
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 4.0625,
+      "learning_rate": 7.373037048030731e-05,
+      "loss": 0.4562,
+      "step": 1360
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 3.75,
+      "learning_rate": 7.334933837925675e-05,
+      "loss": 0.4333,
+      "step": 1370
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 3.46875,
+      "learning_rate": 7.296656413030531e-05,
+      "loss": 0.306,
+      "step": 1380
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 5.25,
+      "learning_rate": 7.25820762931211e-05,
+      "loss": 0.4095,
+      "step": 1390
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.578125,
+      "learning_rate": 7.219590355522697e-05,
+      "loss": 0.369,
+      "step": 1400
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.180807472986009e-05,
+      "loss": 0.3763,
+      "step": 1410
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 5.25,
+      "learning_rate": 7.141861875382215e-05,
+      "loss": 0.4269,
+      "step": 1420
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 3.53125,
+      "learning_rate": 7.102756468532027e-05,
+      "loss": 0.4017,
+      "step": 1430
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 4.6875,
+      "learning_rate": 7.063494170179898e-05,
+      "loss": 0.3601,
+      "step": 1440
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.8125,
+      "learning_rate": 7.024077909776309e-05,
+      "loss": 0.3678,
+      "step": 1450
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 5.25,
+      "learning_rate": 6.984510628259212e-05,
+      "loss": 0.3732,
+      "step": 1460
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 2.140625,
+      "learning_rate": 6.94479527783459e-05,
+      "loss": 0.3332,
+      "step": 1470
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 4.5,
+      "learning_rate": 6.904934821756184e-05,
+      "loss": 0.3887,
+      "step": 1480
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 2.296875,
+      "learning_rate": 6.864932234104409e-05,
+      "loss": 0.3196,
+      "step": 1490
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.15625,
+      "learning_rate": 6.824790499564435e-05,
+      "loss": 0.3256,
+      "step": 1500
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 3.6875,
+      "learning_rate": 6.784512613203511e-05,
+      "loss": 0.3074,
+      "step": 1510
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 3.0,
+      "learning_rate": 6.744101580247481e-05,
+      "loss": 0.35,
+      "step": 1520
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 3.828125,
+      "learning_rate": 6.703560415856565e-05,
+      "loss": 0.3731,
+      "step": 1530
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 5.625,
+      "learning_rate": 6.662892144900388e-05,
+      "loss": 0.3769,
+      "step": 1540
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 8.1875,
+      "learning_rate": 6.62209980173229e-05,
+      "loss": 0.4385,
+      "step": 1550
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 5.9375,
+      "learning_rate": 6.581186429962922e-05,
+      "loss": 0.3563,
+      "step": 1560
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 3.53125,
+      "learning_rate": 6.54015508223316e-05,
+      "loss": 0.3225,
+      "step": 1570
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 4.125,
+      "learning_rate": 6.499008819986339e-05,
+      "loss": 0.3246,
+      "step": 1580
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 4.34375,
+      "learning_rate": 6.457750713239828e-05,
+      "loss": 0.304,
+      "step": 1590
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 4.75,
+      "learning_rate": 6.41638384035597e-05,
+      "loss": 0.383,
+      "step": 1600
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 4.46875,
+      "learning_rate": 6.374911287812406e-05,
+      "loss": 0.331,
+      "step": 1610
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 3.984375,
+      "learning_rate": 6.333336149971776e-05,
+      "loss": 0.3022,
+      "step": 1620
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 5.53125,
+      "learning_rate": 6.291661528850844e-05,
+      "loss": 0.3257,
+      "step": 1630
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.249890533889054e-05,
+      "loss": 0.3071,
+      "step": 1640
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 4.25,
+      "learning_rate": 6.208026281716521e-05,
+      "loss": 0.3833,
+      "step": 1650
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 3.109375,
+      "learning_rate": 6.166071895921496e-05,
+      "loss": 0.3378,
+      "step": 1660
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 3.5,
+      "learning_rate": 6.124030506817309e-05,
+      "loss": 0.31,
+      "step": 1670
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 2.65625,
+      "learning_rate": 6.0819052512088057e-05,
+      "loss": 0.3139,
+      "step": 1680
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 4.90625,
+      "learning_rate": 6.039699272158305e-05,
+      "loss": 0.4388,
+      "step": 1690
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 5.59375,
+      "learning_rate": 5.997415718751086e-05,
+      "loss": 0.3989,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 5.5,
+      "learning_rate": 5.955057745860435e-05,
+      "loss": 0.3977,
+      "step": 1710
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 6.25,
+      "learning_rate": 5.9126285139122406e-05,
+      "loss": 0.3527,
+      "step": 1720
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 3.28125,
+      "learning_rate": 5.8701311886491947e-05,
+      "loss": 0.4044,
+      "step": 1730
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 5.5625,
+      "learning_rate": 5.827568940894593e-05,
+      "loss": 0.374,
+      "step": 1740
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.625,
+      "learning_rate": 5.7849449463157435e-05,
+      "loss": 0.3479,
+      "step": 1750
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 4.84375,
+      "learning_rate": 5.742262385187028e-05,
+      "loss": 0.3666,
+      "step": 1760
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.699524442152613e-05,
+      "loss": 0.3707,
+      "step": 1770
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 4.4375,
+      "learning_rate": 5.656734305988839e-05,
+      "loss": 0.3847,
+      "step": 1780
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 3.96875,
+      "learning_rate": 5.613895169366292e-05,
+      "loss": 0.3515,
+      "step": 1790
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.734375,
+      "learning_rate": 5.571010228611597e-05,
+      "loss": 0.3763,
+      "step": 1800
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 5.71875,
+      "learning_rate": 5.528082683468934e-05,
+      "loss": 0.3548,
+      "step": 1810
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 5.03125,
+      "learning_rate": 5.485115736861288e-05,
+      "loss": 0.3903,
+      "step": 1820
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 4.375,
+      "learning_rate": 5.442112594651484e-05,
+      "loss": 0.257,
+      "step": 1830
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 5.46875,
+      "learning_rate": 5.399076465402979e-05,
+      "loss": 0.3424,
+      "step": 1840
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 3.40625,
+      "learning_rate": 5.356010560140475e-05,
+      "loss": 0.3317,
+      "step": 1850
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 5.0,
+      "learning_rate": 5.312918092110325e-05,
+      "loss": 0.2753,
+      "step": 1860
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 3.84375,
+      "learning_rate": 5.269802276540795e-05,
+      "loss": 0.3318,
+      "step": 1870
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 5.71875,
+      "learning_rate": 5.226666330402164e-05,
+      "loss": 0.3836,
+      "step": 1880
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 3.671875,
+      "learning_rate": 5.1835134721666956e-05,
+      "loss": 0.3498,
+      "step": 1890
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.90625,
+      "learning_rate": 5.1403469215685094e-05,
+      "loss": 0.4228,
+      "step": 1900
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 4.4375,
+      "learning_rate": 5.097169899363342e-05,
+      "loss": 0.3703,
+      "step": 1910
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 3.90625,
+      "learning_rate": 5.053985627088238e-05,
+      "loss": 0.3816,
+      "step": 1920
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 2.71875,
+      "learning_rate": 5.010797326821189e-05,
+      "loss": 0.3842,
+      "step": 1930
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 3.875,
+      "learning_rate": 4.9676082209407254e-05,
+      "loss": 0.3848,
+      "step": 1940
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 3.484375,
+      "learning_rate": 4.924421531885481e-05,
+      "loss": 0.3416,
+      "step": 1950
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.881240481913773e-05,
+      "loss": 0.3407,
+      "step": 1960
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.838068292863164e-05,
+      "loss": 0.3319,
+      "step": 1970
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 4.4375,
+      "learning_rate": 4.7949081859100896e-05,
+      "loss": 0.3979,
+      "step": 1980
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.7517633813295114e-05,
+      "loss": 0.4184,
+      "step": 1990
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.708637098254644e-05,
+      "loss": 0.3959,
+      "step": 2000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 4.8125,
+      "learning_rate": 4.6655325544367715e-05,
+      "loss": 0.313,
+      "step": 2010
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.6224529660051593e-05,
+      "loss": 0.3012,
+      "step": 2020
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.579401547227096e-05,
+      "loss": 0.2532,
+      "step": 2030
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 2.953125,
+      "learning_rate": 4.53638151026807e-05,
+      "loss": 0.2714,
+      "step": 2040
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.493396064952093e-05,
+      "loss": 0.3468,
+      "step": 2050
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 5.125,
+      "learning_rate": 4.450448418522221e-05,
+      "loss": 0.4547,
+      "step": 2060
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 3.5,
+      "learning_rate": 4.4075417754012475e-05,
+      "loss": 0.2839,
+      "step": 2070
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 5.84375,
+      "learning_rate": 4.364679336952609e-05,
+      "loss": 0.3426,
+      "step": 2080
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.321864301241535e-05,
+      "loss": 0.3325,
+      "step": 2090
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 4.46875,
+      "learning_rate": 4.279099862796427e-05,
+      "loss": 0.314,
+      "step": 2100
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 2.8125,
+      "learning_rate": 4.23638921237051e-05,
+      "loss": 0.4189,
+      "step": 2110
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 3.59375,
+      "learning_rate": 4.1937355367037516e-05,
+      "loss": 0.3436,
+      "step": 2120
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 6.21875,
+      "learning_rate": 4.151142018285112e-05,
+      "loss": 0.3681,
+      "step": 2130
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.1086118351150785e-05,
+      "loss": 0.3716,
+      "step": 2140
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.703125,
+      "learning_rate": 4.066148160468543e-05,
+      "loss": 0.2761,
+      "step": 2150
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 3.765625,
+      "learning_rate": 4.023754162658051e-05,
+      "loss": 0.2904,
+      "step": 2160
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.981433004797395e-05,
+      "loss": 0.3563,
+      "step": 2170
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 4.125,
+      "learning_rate": 3.939187844565616e-05,
+      "loss": 0.3248,
+      "step": 2180
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 5.71875,
+      "learning_rate": 3.897021833971386e-05,
+      "loss": 0.3246,
+      "step": 2190
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.21875,
+      "learning_rate": 3.8549381191178516e-05,
+      "loss": 0.4073,
+      "step": 2200
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.8129398399678814e-05,
+      "loss": 0.4147,
+      "step": 2210
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.771030130109785e-05,
+      "loss": 0.2378,
+      "step": 2220
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 3.65625,
+      "learning_rate": 3.729212116523518e-05,
+      "loss": 0.3305,
+      "step": 2230
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 3.09375,
+      "learning_rate": 3.6874889193473646e-05,
+      "loss": 0.3865,
+      "step": 2240
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.5,
+      "learning_rate": 3.64586365164514e-05,
+      "loss": 0.3443,
+      "step": 2250
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 2.71875,
+      "learning_rate": 3.604339419173912e-05,
+      "loss": 0.2762,
+      "step": 2260
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.5629193201522794e-05,
+      "loss": 0.3787,
+      "step": 2270
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.521606445029208e-05,
+      "loss": 0.4157,
+      "step": 2280
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.480403876253432e-05,
+      "loss": 0.3345,
+      "step": 2290
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 3.3125,
+      "learning_rate": 3.4393146880434845e-05,
+      "loss": 0.3111,
+      "step": 2300
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.398341946158311e-05,
+      "loss": 0.3763,
+      "step": 2310
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.357488707668529e-05,
+      "loss": 0.3246,
+      "step": 2320
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 4.65625,
+      "learning_rate": 3.316758020728327e-05,
+      "loss": 0.3852,
+      "step": 2330
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.276152924348046e-05,
+      "loss": 0.3295,
+      "step": 2340
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.2356764481674254e-05,
+      "loss": 0.3567,
+      "step": 2350
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 3.421875,
+      "learning_rate": 3.1953316122295554e-05,
+      "loss": 0.3091,
+      "step": 2360
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 3.265625,
+      "learning_rate": 3.1551214267555416e-05,
+      "loss": 0.3847,
+      "step": 2370
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 6.09375,
+      "learning_rate": 3.1150488919199124e-05,
+      "loss": 0.3958,
+      "step": 2380
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.075116997626764e-05,
+      "loss": 0.384,
+      "step": 2390
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.0353287232866736e-05,
+      "loss": 0.3349,
+      "step": 2400
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 4.375,
+      "learning_rate": 2.995687037594408e-05,
+      "loss": 0.3801,
+      "step": 2410
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.9561948983074174e-05,
+      "loss": 0.3281,
+      "step": 2420
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 6.8125,
+      "learning_rate": 2.916855252025149e-05,
+      "loss": 0.3549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 4.125,
+      "learning_rate": 2.877671033969193e-05,
+      "loss": 0.4092,
+      "step": 2440
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 4.21875,
+      "learning_rate": 2.8386451677642878e-05,
+      "loss": 0.3866,
+      "step": 2450
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 3.078125,
+      "learning_rate": 2.7997805652201714e-05,
+      "loss": 0.3484,
+      "step": 2460
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.7610801261143283e-05,
+      "loss": 0.3496,
+      "step": 2470
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 4.6875,
+      "learning_rate": 2.7225467379756314e-05,
+      "loss": 0.3691,
+      "step": 2480
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 5.5,
+      "learning_rate": 2.6841832758689002e-05,
+      "loss": 0.3698,
+      "step": 2490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.875,
+      "learning_rate": 2.645992602180377e-05,
+      "loss": 0.3577,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.257447323738318e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2d0a1d294de71591829114cab72751317ef618785189b344d35019839741e4
+size 6673

checkpoint-2500/video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

checkpoint-3750/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
+}

checkpoint-3750/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 %}

checkpoint-3750/config.json

@@ -0,0 +1,145 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dit_dropout": 0.1,
+  "dit_hidden_size": 512,
+  "dit_num_heads": 8,
+  "dit_num_layers": 6,
+  "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_inference_steps": 16,
+  "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_VLForClickPrediction"
+    ],
+    "attention_dropout": 0.0,
+    "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": false,
+    "use_sliding_window": false,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "bfloat16",
+    "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
+}

checkpoint-3750/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e89da2acef14776f3d1439e440e0990b929333dbb2f2bcf0fd93cda3cfcc45e
+size 4997750760

checkpoint-3750/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3fd91c1d4a2b2314af25a020df3ac318489902bb7c5f68d4436ca4b03dfcc5
+size 2565696568

checkpoint-3750/model.safetensors.index.json

@@ -0,0 +1,926 @@
+{
+  "metadata": {
+    "total_parameters": 3781672450,
+    "total_size": 7563344904
+  },
+  "weight_map": {
+    "action_head.action_decoder.layer1.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer1.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.weight": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.bias": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.weight": "model-00002-of-00002.safetensors",
+    "action_head.beta_alpha": "model-00002-of-00002.safetensors",
+    "action_head.beta_beta": "model-00002-of-00002.safetensors",
+    "action_head.cond_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.cond_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.0.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.1.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.2.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.3.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.4.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ada_ln.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ada_ln.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.cross_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.3.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff.3.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff_norm.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.blocks.5.ff_norm.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_1.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_1.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_2.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.proj_out_2.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.dit.timestep_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
+    "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"
+  }
+}

checkpoint-3750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bee161ab95c11f0f257ad333394d3e8cbe11552728b67e40b5d23b361ad7a5c
+size 255114251

checkpoint-3750/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-3750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c059f51a0dad2c5394f91567ea4c00d0a408851c7b5b03941a33003035308b
+size 14645

checkpoint-3750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c307672fcef00c92b93051d3cebdf6dd2a4706b3737aee9e6c7966b9c6d193cf
+size 1465

checkpoint-3750/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
+  }
+}

checkpoint-3750/tokenizer.json

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

checkpoint-3750/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-3750/trainer_state.json

@@ -0,0 +1,2659 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.964601769911505e-06,
+      "loss": 1.4112,
+      "step": 10
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 5.3125,
+      "learning_rate": 1.6814159292035402e-05,
+      "loss": 1.4365,
+      "step": 20
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 2.265625,
+      "learning_rate": 2.5663716814159294e-05,
+      "loss": 1.2118,
+      "step": 30
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 2.78125,
+      "learning_rate": 3.451327433628319e-05,
+      "loss": 1.1222,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.3362831858407084e-05,
+      "loss": 1.0566,
+      "step": 50
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.75,
+      "learning_rate": 5.221238938053098e-05,
+      "loss": 1.0392,
+      "step": 60
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 2.578125,
+      "learning_rate": 6.106194690265487e-05,
+      "loss": 1.1753,
+      "step": 70
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 1.421875,
+      "learning_rate": 6.991150442477876e-05,
+      "loss": 1.0422,
+      "step": 80
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 3.765625,
+      "learning_rate": 7.876106194690266e-05,
+      "loss": 1.026,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.609375,
+      "learning_rate": 8.761061946902655e-05,
+      "loss": 1.0633,
+      "step": 100
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 3.171875,
+      "learning_rate": 9.646017699115044e-05,
+      "loss": 1.1138,
+      "step": 110
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 3.609375,
+      "learning_rate": 9.999932848660433e-05,
+      "loss": 1.1079,
+      "step": 120
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.765625,
+      "learning_rate": 9.99952248589506e-05,
+      "loss": 1.0538,
+      "step": 130
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 3.5625,
+      "learning_rate": 9.998739097245067e-05,
+      "loss": 0.9637,
+      "step": 140
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.6875,
+      "learning_rate": 9.997582741160886e-05,
+      "loss": 0.8554,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 7.40625,
+      "learning_rate": 9.99605350392091e-05,
+      "loss": 0.6704,
+      "step": 160
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 7.03125,
+      "learning_rate": 9.994151499625049e-05,
+      "loss": 0.8075,
+      "step": 170
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.828125,
+      "learning_rate": 9.991876870186222e-05,
+      "loss": 0.7331,
+      "step": 180
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 3.890625,
+      "learning_rate": 9.98922978531977e-05,
+      "loss": 0.7264,
+      "step": 190
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.15625,
+      "learning_rate": 9.986210442530788e-05,
+      "loss": 0.5792,
+      "step": 200
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 5.53125,
+      "learning_rate": 9.982819067099396e-05,
+      "loss": 0.6228,
+      "step": 210
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 5.875,
+      "learning_rate": 9.979055912063925e-05,
+      "loss": 0.7417,
+      "step": 220
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 3.71875,
+      "learning_rate": 9.974921258202036e-05,
+      "loss": 0.472,
+      "step": 230
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 4.15625,
+      "learning_rate": 9.970415414009773e-05,
+      "loss": 0.6284,
+      "step": 240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.965538715678548e-05,
+      "loss": 0.5349,
+      "step": 250
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.960291527070051e-05,
+      "loss": 0.5165,
+      "step": 260
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 4.0625,
+      "learning_rate": 9.954674239689109e-05,
+      "loss": 0.5656,
+      "step": 270
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 3.875,
+      "learning_rate": 9.948687272654464e-05,
+      "loss": 0.6713,
+      "step": 280
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 5.375,
+      "learning_rate": 9.942331072667517e-05,
+      "loss": 0.4347,
+      "step": 290
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.875,
+      "learning_rate": 9.935606113978981e-05,
+      "loss": 0.4404,
+      "step": 300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 4.28125,
+      "learning_rate": 9.92851289835351e-05,
+      "loss": 0.4865,
+      "step": 310
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 6.46875,
+      "learning_rate": 9.921051955032253e-05,
+      "loss": 0.5393,
+      "step": 320
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 9.0625,
+      "learning_rate": 9.913223840693375e-05,
+      "loss": 0.5358,
+      "step": 330
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.905029139410508e-05,
+      "loss": 0.5756,
+      "step": 340
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 10.625,
+      "learning_rate": 9.896468462609186e-05,
+      "loss": 0.4554,
+      "step": 350
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 3.6875,
+      "learning_rate": 9.887542449021214e-05,
+      "loss": 0.3889,
+      "step": 360
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 6.25,
+      "learning_rate": 9.878251764637023e-05,
+      "loss": 0.4468,
+      "step": 370
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 5.5,
+      "learning_rate": 9.868597102655968e-05,
+      "loss": 0.4612,
+      "step": 380
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.858579183434605e-05,
+      "loss": 0.6069,
+      "step": 390
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.848198754432959e-05,
+      "loss": 0.4464,
+      "step": 400
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 5.125,
+      "learning_rate": 9.837456590158738e-05,
+      "loss": 0.5598,
+      "step": 410
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 3.671875,
+      "learning_rate": 9.826353492109555e-05,
+      "loss": 0.4534,
+      "step": 420
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 7.34375,
+      "learning_rate": 9.814890288713121e-05,
+      "loss": 0.5155,
+      "step": 430
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 6.875,
+      "learning_rate": 9.803067835265436e-05,
+      "loss": 0.484,
+      "step": 440
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.875,
+      "learning_rate": 9.790887013866973e-05,
+      "loss": 0.4077,
+      "step": 450
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.778348733356868e-05,
+      "loss": 0.3779,
+      "step": 460
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.765453929245096e-05,
+      "loss": 0.521,
+      "step": 470
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.752203563642688e-05,
+      "loss": 0.4114,
+      "step": 480
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 8.25,
+      "learning_rate": 9.73859862518993e-05,
+      "loss": 0.4361,
+      "step": 490
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 7.40625,
+      "learning_rate": 9.724640128982605e-05,
+      "loss": 0.518,
+      "step": 500
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 5.5625,
+      "learning_rate": 9.710329116496259e-05,
+      "loss": 0.4413,
+      "step": 510
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 5.46875,
+      "learning_rate": 9.695666655508483e-05,
+      "loss": 0.4276,
+      "step": 520
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 5.375,
+      "learning_rate": 9.680653840019259e-05,
+      "loss": 0.4476,
+      "step": 530
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 5.875,
+      "learning_rate": 9.665291790169311e-05,
+      "loss": 0.3562,
+      "step": 540
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.4375,
+      "learning_rate": 9.649581652156559e-05,
+      "loss": 0.4511,
+      "step": 550
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.633524598150568e-05,
+      "loss": 0.3985,
+      "step": 560
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 4.1875,
+      "learning_rate": 9.617121826205116e-05,
+      "loss": 0.5117,
+      "step": 570
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 5.5,
+      "learning_rate": 9.600374560168783e-05,
+      "loss": 0.4569,
+      "step": 580
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 4.5,
+      "learning_rate": 9.583284049593652e-05,
+      "loss": 0.449,
+      "step": 590
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.25,
+      "learning_rate": 9.56585156964207e-05,
+      "loss": 0.4769,
+      "step": 600
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 5.9375,
+      "learning_rate": 9.548078420991506e-05,
+      "loss": 0.5081,
+      "step": 610
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 7.4375,
+      "learning_rate": 9.529965929737506e-05,
+      "loss": 0.4803,
+      "step": 620
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.511515447294748e-05,
+      "loss": 0.5015,
+      "step": 630
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 6.71875,
+      "learning_rate": 9.49272835029621e-05,
+      "loss": 0.5174,
+      "step": 640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.875,
+      "learning_rate": 9.47360604049046e-05,
+      "loss": 0.4957,
+      "step": 650
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 4.71875,
+      "learning_rate": 9.454149944637064e-05,
+      "loss": 0.379,
+      "step": 660
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.434361514400132e-05,
+      "loss": 0.4857,
+      "step": 670
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 5.71875,
+      "learning_rate": 9.414242226240012e-05,
+      "loss": 0.4595,
+      "step": 680
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 6.8125,
+      "learning_rate": 9.393793581303116e-05,
+      "loss": 0.4157,
+      "step": 690
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.37301710530993e-05,
+      "loss": 0.4432,
+      "step": 700
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 6.75,
+      "learning_rate": 9.351914348441169e-05,
+      "loss": 0.4695,
+      "step": 710
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 2.890625,
+      "learning_rate": 9.330486885222114e-05,
+      "loss": 0.3493,
+      "step": 720
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 3.4375,
+      "learning_rate": 9.308736314405134e-05,
+      "loss": 0.4304,
+      "step": 730
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.286664258850402e-05,
+      "loss": 0.5057,
+      "step": 740
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.375,
+      "learning_rate": 9.264272365404805e-05,
+      "loss": 0.4159,
+      "step": 750
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.241562304779072e-05,
+      "loss": 0.3647,
+      "step": 760
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 10.3125,
+      "learning_rate": 9.21853577142312e-05,
+      "loss": 0.4851,
+      "step": 770
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.195194483399625e-05,
+      "loss": 0.5071,
+      "step": 780
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 4.34375,
+      "learning_rate": 9.17154018225583e-05,
+      "loss": 0.3939,
+      "step": 790
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.03125,
+      "learning_rate": 9.147574632893611e-05,
+      "loss": 0.3762,
+      "step": 800
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 3.1875,
+      "learning_rate": 9.12329962343779e-05,
+      "loss": 0.4427,
+      "step": 810
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 3.890625,
+      "learning_rate": 9.098716965102716e-05,
+      "loss": 0.357,
+      "step": 820
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 8.25,
+      "learning_rate": 9.073828492057133e-05,
+      "loss": 0.4071,
+      "step": 830
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 5.78125,
+      "learning_rate": 9.048636061287325e-05,
+      "loss": 0.4037,
+      "step": 840
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.84375,
+      "learning_rate": 9.023141552458559e-05,
+      "loss": 0.3884,
+      "step": 850
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 3.453125,
+      "learning_rate": 8.997346867774839e-05,
+      "loss": 0.3641,
+      "step": 860
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 7.875,
+      "learning_rate": 8.97125393183699e-05,
+      "loss": 0.5387,
+      "step": 870
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 4.6875,
+      "learning_rate": 8.94486469149904e-05,
+      "loss": 0.4085,
+      "step": 880
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 6.03125,
+      "learning_rate": 8.918181115722976e-05,
+      "loss": 0.4055,
+      "step": 890
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.375,
+      "learning_rate": 8.891205195431831e-05,
+      "loss": 0.42,
+      "step": 900
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 3.21875,
+      "learning_rate": 8.863938943361128e-05,
+      "loss": 0.3372,
+      "step": 910
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 3.65625,
+      "learning_rate": 8.836384393908721e-05,
+      "loss": 0.4544,
+      "step": 920
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 3.703125,
+      "learning_rate": 8.808543602982993e-05,
+      "loss": 0.4979,
+      "step": 930
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 2.90625,
+      "learning_rate": 8.780418647849458e-05,
+      "loss": 0.3366,
+      "step": 940
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.53125,
+      "learning_rate": 8.752011626975781e-05,
+      "loss": 0.3778,
+      "step": 950
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 3.4375,
+      "learning_rate": 8.723324659875201e-05,
+      "loss": 0.4498,
+      "step": 960
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 4.90625,
+      "learning_rate": 8.694359886948384e-05,
+      "loss": 0.4232,
+      "step": 970
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 4.15625,
+      "learning_rate": 8.665119469323737e-05,
+      "loss": 0.3602,
+      "step": 980
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 5.375,
+      "learning_rate": 8.635605588696148e-05,
+      "loss": 0.4095,
+      "step": 990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.5625,
+      "learning_rate": 8.605820447164206e-05,
+      "loss": 0.405,
+      "step": 1000
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 4.40625,
+      "learning_rate": 8.575766267065905e-05,
+      "loss": 0.3137,
+      "step": 1010
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 5.65625,
+      "learning_rate": 8.54544529081283e-05,
+      "loss": 0.3701,
+      "step": 1020
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 5.0,
+      "learning_rate": 8.514859780722833e-05,
+      "loss": 0.3759,
+      "step": 1030
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 4.9375,
+      "learning_rate": 8.484012018851246e-05,
+      "loss": 0.3032,
+      "step": 1040
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.375,
+      "learning_rate": 8.452904306820618e-05,
+      "loss": 0.4171,
+      "step": 1050
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 4.53125,
+      "learning_rate": 8.421538965648966e-05,
+      "loss": 0.374,
+      "step": 1060
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 4.3125,
+      "learning_rate": 8.389918335576623e-05,
+      "loss": 0.3358,
+      "step": 1070
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 4.21875,
+      "learning_rate": 8.358044775891605e-05,
+      "loss": 0.3586,
+      "step": 1080
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 4.15625,
+      "learning_rate": 8.325920664753595e-05,
+      "loss": 0.4036,
+      "step": 1090
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.625,
+      "learning_rate": 8.293548399016491e-05,
+      "loss": 0.3673,
+      "step": 1100
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 2.625,
+      "learning_rate": 8.260930394049583e-05,
+      "loss": 0.3388,
+      "step": 1110
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 4.78125,
+      "learning_rate": 8.228069083557328e-05,
+      "loss": 0.427,
+      "step": 1120
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 4.21875,
+      "learning_rate": 8.194966919397767e-05,
+      "loss": 0.3926,
+      "step": 1130
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 5.84375,
+      "learning_rate": 8.161626371399591e-05,
+      "loss": 0.3654,
+      "step": 1140
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.71875,
+      "learning_rate": 8.128049927177854e-05,
+      "loss": 0.4047,
+      "step": 1150
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 5.0,
+      "learning_rate": 8.094240091948375e-05,
+      "loss": 0.4114,
+      "step": 1160
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 6.625,
+      "learning_rate": 8.06019938834081e-05,
+      "loss": 0.4485,
+      "step": 1170
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 4.4375,
+      "learning_rate": 8.025930356210439e-05,
+      "loss": 0.3833,
+      "step": 1180
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 3.171875,
+      "learning_rate": 7.991435552448657e-05,
+      "loss": 0.3742,
+      "step": 1190
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.65625,
+      "learning_rate": 7.956717550792199e-05,
+      "loss": 0.3284,
+      "step": 1200
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 4.4375,
+      "learning_rate": 7.921778941631113e-05,
+      "loss": 0.3862,
+      "step": 1210
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 8.9375,
+      "learning_rate": 7.886622331815477e-05,
+      "loss": 0.4144,
+      "step": 1220
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 3.875,
+      "learning_rate": 7.851250344460902e-05,
+      "loss": 0.3654,
+      "step": 1230
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 2.59375,
+      "learning_rate": 7.815665618752812e-05,
+      "loss": 0.3808,
+      "step": 1240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.0625,
+      "learning_rate": 7.77987080974953e-05,
+      "loss": 0.3482,
+      "step": 1250
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 3.28125,
+      "learning_rate": 7.743868588184176e-05,
+      "loss": 0.3312,
+      "step": 1260
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 4.375,
+      "learning_rate": 7.707661640265401e-05,
+      "loss": 0.37,
+      "step": 1270
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 4.40625,
+      "learning_rate": 7.67125266747696e-05,
+      "loss": 0.3253,
+      "step": 1280
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 4.0625,
+      "learning_rate": 7.634644386376149e-05,
+      "loss": 0.4361,
+      "step": 1290
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 3.953125,
+      "learning_rate": 7.597839528391114e-05,
+      "loss": 0.3981,
+      "step": 1300
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 7.6875,
+      "learning_rate": 7.560840839617056e-05,
+      "loss": 0.3634,
+      "step": 1310
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 4.03125,
+      "learning_rate": 7.523651080611341e-05,
+      "loss": 0.3653,
+      "step": 1320
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 3.09375,
+      "learning_rate": 7.48627302618752e-05,
+      "loss": 0.3433,
+      "step": 1330
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 4.21875,
+      "learning_rate": 7.448709465208299e-05,
+      "loss": 0.3587,
+      "step": 1340
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 5.375,
+      "learning_rate": 7.410963200377458e-05,
+      "loss": 0.346,
+      "step": 1350
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 4.0625,
+      "learning_rate": 7.373037048030731e-05,
+      "loss": 0.4562,
+      "step": 1360
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 3.75,
+      "learning_rate": 7.334933837925675e-05,
+      "loss": 0.4333,
+      "step": 1370
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 3.46875,
+      "learning_rate": 7.296656413030531e-05,
+      "loss": 0.306,
+      "step": 1380
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 5.25,
+      "learning_rate": 7.25820762931211e-05,
+      "loss": 0.4095,
+      "step": 1390
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.578125,
+      "learning_rate": 7.219590355522697e-05,
+      "loss": 0.369,
+      "step": 1400
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.180807472986009e-05,
+      "loss": 0.3763,
+      "step": 1410
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 5.25,
+      "learning_rate": 7.141861875382215e-05,
+      "loss": 0.4269,
+      "step": 1420
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 3.53125,
+      "learning_rate": 7.102756468532027e-05,
+      "loss": 0.4017,
+      "step": 1430
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 4.6875,
+      "learning_rate": 7.063494170179898e-05,
+      "loss": 0.3601,
+      "step": 1440
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.8125,
+      "learning_rate": 7.024077909776309e-05,
+      "loss": 0.3678,
+      "step": 1450
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 5.25,
+      "learning_rate": 6.984510628259212e-05,
+      "loss": 0.3732,
+      "step": 1460
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 2.140625,
+      "learning_rate": 6.94479527783459e-05,
+      "loss": 0.3332,
+      "step": 1470
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 4.5,
+      "learning_rate": 6.904934821756184e-05,
+      "loss": 0.3887,
+      "step": 1480
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 2.296875,
+      "learning_rate": 6.864932234104409e-05,
+      "loss": 0.3196,
+      "step": 1490
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.15625,
+      "learning_rate": 6.824790499564435e-05,
+      "loss": 0.3256,
+      "step": 1500
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 3.6875,
+      "learning_rate": 6.784512613203511e-05,
+      "loss": 0.3074,
+      "step": 1510
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 3.0,
+      "learning_rate": 6.744101580247481e-05,
+      "loss": 0.35,
+      "step": 1520
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 3.828125,
+      "learning_rate": 6.703560415856565e-05,
+      "loss": 0.3731,
+      "step": 1530
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 5.625,
+      "learning_rate": 6.662892144900388e-05,
+      "loss": 0.3769,
+      "step": 1540
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 8.1875,
+      "learning_rate": 6.62209980173229e-05,
+      "loss": 0.4385,
+      "step": 1550
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 5.9375,
+      "learning_rate": 6.581186429962922e-05,
+      "loss": 0.3563,
+      "step": 1560
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 3.53125,
+      "learning_rate": 6.54015508223316e-05,
+      "loss": 0.3225,
+      "step": 1570
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 4.125,
+      "learning_rate": 6.499008819986339e-05,
+      "loss": 0.3246,
+      "step": 1580
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 4.34375,
+      "learning_rate": 6.457750713239828e-05,
+      "loss": 0.304,
+      "step": 1590
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 4.75,
+      "learning_rate": 6.41638384035597e-05,
+      "loss": 0.383,
+      "step": 1600
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 4.46875,
+      "learning_rate": 6.374911287812406e-05,
+      "loss": 0.331,
+      "step": 1610
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 3.984375,
+      "learning_rate": 6.333336149971776e-05,
+      "loss": 0.3022,
+      "step": 1620
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 5.53125,
+      "learning_rate": 6.291661528850844e-05,
+      "loss": 0.3257,
+      "step": 1630
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.249890533889054e-05,
+      "loss": 0.3071,
+      "step": 1640
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 4.25,
+      "learning_rate": 6.208026281716521e-05,
+      "loss": 0.3833,
+      "step": 1650
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 3.109375,
+      "learning_rate": 6.166071895921496e-05,
+      "loss": 0.3378,
+      "step": 1660
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 3.5,
+      "learning_rate": 6.124030506817309e-05,
+      "loss": 0.31,
+      "step": 1670
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 2.65625,
+      "learning_rate": 6.0819052512088057e-05,
+      "loss": 0.3139,
+      "step": 1680
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 4.90625,
+      "learning_rate": 6.039699272158305e-05,
+      "loss": 0.4388,
+      "step": 1690
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 5.59375,
+      "learning_rate": 5.997415718751086e-05,
+      "loss": 0.3989,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 5.5,
+      "learning_rate": 5.955057745860435e-05,
+      "loss": 0.3977,
+      "step": 1710
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 6.25,
+      "learning_rate": 5.9126285139122406e-05,
+      "loss": 0.3527,
+      "step": 1720
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 3.28125,
+      "learning_rate": 5.8701311886491947e-05,
+      "loss": 0.4044,
+      "step": 1730
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 5.5625,
+      "learning_rate": 5.827568940894593e-05,
+      "loss": 0.374,
+      "step": 1740
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.625,
+      "learning_rate": 5.7849449463157435e-05,
+      "loss": 0.3479,
+      "step": 1750
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 4.84375,
+      "learning_rate": 5.742262385187028e-05,
+      "loss": 0.3666,
+      "step": 1760
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.699524442152613e-05,
+      "loss": 0.3707,
+      "step": 1770
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 4.4375,
+      "learning_rate": 5.656734305988839e-05,
+      "loss": 0.3847,
+      "step": 1780
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 3.96875,
+      "learning_rate": 5.613895169366292e-05,
+      "loss": 0.3515,
+      "step": 1790
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.734375,
+      "learning_rate": 5.571010228611597e-05,
+      "loss": 0.3763,
+      "step": 1800
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 5.71875,
+      "learning_rate": 5.528082683468934e-05,
+      "loss": 0.3548,
+      "step": 1810
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 5.03125,
+      "learning_rate": 5.485115736861288e-05,
+      "loss": 0.3903,
+      "step": 1820
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 4.375,
+      "learning_rate": 5.442112594651484e-05,
+      "loss": 0.257,
+      "step": 1830
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 5.46875,
+      "learning_rate": 5.399076465402979e-05,
+      "loss": 0.3424,
+      "step": 1840
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 3.40625,
+      "learning_rate": 5.356010560140475e-05,
+      "loss": 0.3317,
+      "step": 1850
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 5.0,
+      "learning_rate": 5.312918092110325e-05,
+      "loss": 0.2753,
+      "step": 1860
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 3.84375,
+      "learning_rate": 5.269802276540795e-05,
+      "loss": 0.3318,
+      "step": 1870
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 5.71875,
+      "learning_rate": 5.226666330402164e-05,
+      "loss": 0.3836,
+      "step": 1880
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 3.671875,
+      "learning_rate": 5.1835134721666956e-05,
+      "loss": 0.3498,
+      "step": 1890
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.90625,
+      "learning_rate": 5.1403469215685094e-05,
+      "loss": 0.4228,
+      "step": 1900
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 4.4375,
+      "learning_rate": 5.097169899363342e-05,
+      "loss": 0.3703,
+      "step": 1910
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 3.90625,
+      "learning_rate": 5.053985627088238e-05,
+      "loss": 0.3816,
+      "step": 1920
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 2.71875,
+      "learning_rate": 5.010797326821189e-05,
+      "loss": 0.3842,
+      "step": 1930
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 3.875,
+      "learning_rate": 4.9676082209407254e-05,
+      "loss": 0.3848,
+      "step": 1940
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 3.484375,
+      "learning_rate": 4.924421531885481e-05,
+      "loss": 0.3416,
+      "step": 1950
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.881240481913773e-05,
+      "loss": 0.3407,
+      "step": 1960
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.838068292863164e-05,
+      "loss": 0.3319,
+      "step": 1970
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 4.4375,
+      "learning_rate": 4.7949081859100896e-05,
+      "loss": 0.3979,
+      "step": 1980
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.7517633813295114e-05,
+      "loss": 0.4184,
+      "step": 1990
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.708637098254644e-05,
+      "loss": 0.3959,
+      "step": 2000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 4.8125,
+      "learning_rate": 4.6655325544367715e-05,
+      "loss": 0.313,
+      "step": 2010
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.6224529660051593e-05,
+      "loss": 0.3012,
+      "step": 2020
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.579401547227096e-05,
+      "loss": 0.2532,
+      "step": 2030
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 2.953125,
+      "learning_rate": 4.53638151026807e-05,
+      "loss": 0.2714,
+      "step": 2040
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.493396064952093e-05,
+      "loss": 0.3468,
+      "step": 2050
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 5.125,
+      "learning_rate": 4.450448418522221e-05,
+      "loss": 0.4547,
+      "step": 2060
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 3.5,
+      "learning_rate": 4.4075417754012475e-05,
+      "loss": 0.2839,
+      "step": 2070
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 5.84375,
+      "learning_rate": 4.364679336952609e-05,
+      "loss": 0.3426,
+      "step": 2080
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.321864301241535e-05,
+      "loss": 0.3325,
+      "step": 2090
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 4.46875,
+      "learning_rate": 4.279099862796427e-05,
+      "loss": 0.314,
+      "step": 2100
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 2.8125,
+      "learning_rate": 4.23638921237051e-05,
+      "loss": 0.4189,
+      "step": 2110
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 3.59375,
+      "learning_rate": 4.1937355367037516e-05,
+      "loss": 0.3436,
+      "step": 2120
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 6.21875,
+      "learning_rate": 4.151142018285112e-05,
+      "loss": 0.3681,
+      "step": 2130
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.1086118351150785e-05,
+      "loss": 0.3716,
+      "step": 2140
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.703125,
+      "learning_rate": 4.066148160468543e-05,
+      "loss": 0.2761,
+      "step": 2150
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 3.765625,
+      "learning_rate": 4.023754162658051e-05,
+      "loss": 0.2904,
+      "step": 2160
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.981433004797395e-05,
+      "loss": 0.3563,
+      "step": 2170
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 4.125,
+      "learning_rate": 3.939187844565616e-05,
+      "loss": 0.3248,
+      "step": 2180
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 5.71875,
+      "learning_rate": 3.897021833971386e-05,
+      "loss": 0.3246,
+      "step": 2190
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.21875,
+      "learning_rate": 3.8549381191178516e-05,
+      "loss": 0.4073,
+      "step": 2200
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.8129398399678814e-05,
+      "loss": 0.4147,
+      "step": 2210
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.771030130109785e-05,
+      "loss": 0.2378,
+      "step": 2220
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 3.65625,
+      "learning_rate": 3.729212116523518e-05,
+      "loss": 0.3305,
+      "step": 2230
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 3.09375,
+      "learning_rate": 3.6874889193473646e-05,
+      "loss": 0.3865,
+      "step": 2240
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.5,
+      "learning_rate": 3.64586365164514e-05,
+      "loss": 0.3443,
+      "step": 2250
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 2.71875,
+      "learning_rate": 3.604339419173912e-05,
+      "loss": 0.2762,
+      "step": 2260
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.5629193201522794e-05,
+      "loss": 0.3787,
+      "step": 2270
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.521606445029208e-05,
+      "loss": 0.4157,
+      "step": 2280
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.480403876253432e-05,
+      "loss": 0.3345,
+      "step": 2290
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 3.3125,
+      "learning_rate": 3.4393146880434845e-05,
+      "loss": 0.3111,
+      "step": 2300
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.398341946158311e-05,
+      "loss": 0.3763,
+      "step": 2310
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.357488707668529e-05,
+      "loss": 0.3246,
+      "step": 2320
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 4.65625,
+      "learning_rate": 3.316758020728327e-05,
+      "loss": 0.3852,
+      "step": 2330
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.276152924348046e-05,
+      "loss": 0.3295,
+      "step": 2340
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.2356764481674254e-05,
+      "loss": 0.3567,
+      "step": 2350
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 3.421875,
+      "learning_rate": 3.1953316122295554e-05,
+      "loss": 0.3091,
+      "step": 2360
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 3.265625,
+      "learning_rate": 3.1551214267555416e-05,
+      "loss": 0.3847,
+      "step": 2370
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 6.09375,
+      "learning_rate": 3.1150488919199124e-05,
+      "loss": 0.3958,
+      "step": 2380
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.075116997626764e-05,
+      "loss": 0.384,
+      "step": 2390
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.0353287232866736e-05,
+      "loss": 0.3349,
+      "step": 2400
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 4.375,
+      "learning_rate": 2.995687037594408e-05,
+      "loss": 0.3801,
+      "step": 2410
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.9561948983074174e-05,
+      "loss": 0.3281,
+      "step": 2420
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 6.8125,
+      "learning_rate": 2.916855252025149e-05,
+      "loss": 0.3549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 4.125,
+      "learning_rate": 2.877671033969193e-05,
+      "loss": 0.4092,
+      "step": 2440
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 4.21875,
+      "learning_rate": 2.8386451677642878e-05,
+      "loss": 0.3866,
+      "step": 2450
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 3.078125,
+      "learning_rate": 2.7997805652201714e-05,
+      "loss": 0.3484,
+      "step": 2460
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.7610801261143283e-05,
+      "loss": 0.3496,
+      "step": 2470
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 4.6875,
+      "learning_rate": 2.7225467379756314e-05,
+      "loss": 0.3691,
+      "step": 2480
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 5.5,
+      "learning_rate": 2.6841832758689002e-05,
+      "loss": 0.3698,
+      "step": 2490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.875,
+      "learning_rate": 2.645992602180377e-05,
+      "loss": 0.3577,
+      "step": 2500
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 4.40625,
+      "learning_rate": 2.607977566404164e-05,
+      "loss": 0.2871,
+      "step": 2510
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 4.0625,
+      "learning_rate": 2.570141004929612e-05,
+      "loss": 0.3426,
+      "step": 2520
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 3.5,
+      "learning_rate": 2.5324857408296994e-05,
+      "loss": 0.2656,
+      "step": 2530
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 3.578125,
+      "learning_rate": 2.4950145836503836e-05,
+      "loss": 0.3473,
+      "step": 2540
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.953125,
+      "learning_rate": 2.4577303292009822e-05,
+      "loss": 0.3588,
+      "step": 2550
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 4.75,
+      "learning_rate": 2.4206357593455743e-05,
+      "loss": 0.3953,
+      "step": 2560
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 3.96875,
+      "learning_rate": 2.383733641795428e-05,
+      "loss": 0.3209,
+      "step": 2570
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 2.515625,
+      "learning_rate": 2.3470267299025068e-05,
+      "loss": 0.3299,
+      "step": 2580
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 3.375,
+      "learning_rate": 2.3105177624540252e-05,
+      "loss": 0.2311,
+      "step": 2590
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.46875,
+      "learning_rate": 2.274209463468117e-05,
+      "loss": 0.3035,
+      "step": 2600
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 2.578125,
+      "learning_rate": 2.2381045419905655e-05,
+      "loss": 0.3344,
+      "step": 2610
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 5.28125,
+      "learning_rate": 2.2022056918927037e-05,
+      "loss": 0.2794,
+      "step": 2620
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 5.25,
+      "learning_rate": 2.166515591670394e-05,
+      "loss": 0.3416,
+      "step": 2630
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 3.96875,
+      "learning_rate": 2.1310369042441985e-05,
+      "loss": 0.3152,
+      "step": 2640
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 3.203125,
+      "learning_rate": 2.0957722767606774e-05,
+      "loss": 0.3015,
+      "step": 2650
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 3.78125,
+      "learning_rate": 2.0607243403948863e-05,
+      "loss": 0.3843,
+      "step": 2660
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 6.34375,
+      "learning_rate": 2.0258957101540625e-05,
+      "loss": 0.3299,
+      "step": 2670
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.9912889846825038e-05,
+      "loss": 0.3636,
+      "step": 2680
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.956906746067683e-05,
+      "loss": 0.3596,
+      "step": 2690
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.922751559647591e-05,
+      "loss": 0.3796,
+      "step": 2700
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.888825973819336e-05,
+      "loss": 0.3175,
+      "step": 2710
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.8551325198489887e-05,
+      "loss": 0.2928,
+      "step": 2720
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.8216737116827378e-05,
+      "loss": 0.2791,
+      "step": 2730
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.7884520457592984e-05,
+      "loss": 0.3925,
+      "step": 2740
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.755470000823667e-05,
+      "loss": 0.2967,
+      "step": 2750
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.7227300377421574e-05,
+      "loss": 0.2475,
+      "step": 2760
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.6902345993188017e-05,
+      "loss": 0.34,
+      "step": 2770
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.6579861101130896e-05,
+      "loss": 0.3418,
+      "step": 2780
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 6.5,
+      "learning_rate": 1.6259869762590503e-05,
+      "loss": 0.4639,
+      "step": 2790
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 5.0625,
+      "learning_rate": 1.5942395852857466e-05,
+      "loss": 0.4252,
+      "step": 2800
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 4.71875,
+      "learning_rate": 1.5627463059391173e-05,
+      "loss": 0.3562,
+      "step": 2810
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 3.78125,
+      "learning_rate": 1.531509488005257e-05,
+      "loss": 0.2792,
+      "step": 2820
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 5.25,
+      "learning_rate": 1.5005314621350709e-05,
+      "loss": 0.2659,
+      "step": 2830
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.4698145396704044e-05,
+      "loss": 0.2647,
+      "step": 2840
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 5.3125,
+      "learning_rate": 1.4393610124715696e-05,
+      "loss": 0.2826,
+      "step": 2850
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.4091731527463526e-05,
+      "loss": 0.2643,
+      "step": 2860
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 5.75,
+      "learning_rate": 1.3792532128804803e-05,
+      "loss": 0.3758,
+      "step": 2870
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 6.25,
+      "learning_rate": 1.3496034252695599e-05,
+      "loss": 0.3,
+      "step": 2880
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.3202260021525158e-05,
+      "loss": 0.3376,
+      "step": 2890
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 4.90625,
+      "learning_rate": 1.2911231354465303e-05,
+      "loss": 0.3686,
+      "step": 2900
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 3.859375,
+      "learning_rate": 1.262296996583504e-05,
+      "loss": 0.3372,
+      "step": 2910
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 3.421875,
+      "learning_rate": 1.2337497363480317e-05,
+      "loss": 0.3071,
+      "step": 2920
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 4.15625,
+      "learning_rate": 1.2054834847169316e-05,
+      "loss": 0.3724,
+      "step": 2930
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 4.21875,
+      "learning_rate": 1.1775003507003236e-05,
+      "loss": 0.2919,
+      "step": 2940
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.1498024221842735e-05,
+      "loss": 0.2496,
+      "step": 2950
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 5.28125,
+      "learning_rate": 1.1223917657750033e-05,
+      "loss": 0.265,
+      "step": 2960
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.095270426644705e-05,
+      "loss": 0.3083,
+      "step": 2970
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 4.25,
+      "learning_rate": 1.0684404283789385e-05,
+      "loss": 0.3392,
+      "step": 2980
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.0419037728256564e-05,
+      "loss": 0.3743,
+      "step": 2990
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 4.5625,
+      "learning_rate": 1.015662439945832e-05,
+      "loss": 0.3846,
+      "step": 3000
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 4.28125,
+      "learning_rate": 9.89718387665734e-06,
+      "loss": 0.2818,
+      "step": 3010
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 4.1875,
+      "learning_rate": 9.640735517308435e-06,
+      "loss": 0.3442,
+      "step": 3020
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.387298455614191e-06,
+      "loss": 0.2982,
+      "step": 3030
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 7.5,
+      "learning_rate": 9.136891601097347e-06,
+      "loss": 0.3924,
+      "step": 3040
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 3.15625,
+      "learning_rate": 8.889533637189895e-06,
+      "loss": 0.2838,
+      "step": 3050
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 6.125,
+      "learning_rate": 8.645243019839112e-06,
+      "loss": 0.3035,
+      "step": 3060
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 3.609375,
+      "learning_rate": 8.404037976130458e-06,
+      "loss": 0.3713,
+      "step": 3070
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 4.84375,
+      "learning_rate": 8.16593650292764e-06,
+      "loss": 0.3242,
+      "step": 3080
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 3.21875,
+      "learning_rate": 7.930956365529818e-06,
+      "loss": 0.3214,
+      "step": 3090
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.953125,
+      "learning_rate": 7.699115096346139e-06,
+      "loss": 0.3072,
+      "step": 3100
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 4.5,
+      "learning_rate": 7.4704299935875185e-06,
+      "loss": 0.2528,
+      "step": 3110
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 4.28125,
+      "learning_rate": 7.244918119976035e-06,
+      "loss": 0.3366,
+      "step": 3120
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 5.53125,
+      "learning_rate": 7.022596301471868e-06,
+      "loss": 0.3603,
+      "step": 3130
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 4.28125,
+      "learning_rate": 6.803481126017808e-06,
+      "loss": 0.2996,
+      "step": 3140
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.90625,
+      "learning_rate": 6.587588942301626e-06,
+      "loss": 0.3519,
+      "step": 3150
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 5.3125,
+      "learning_rate": 6.374935858536257e-06,
+      "loss": 0.2668,
+      "step": 3160
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 5.25,
+      "learning_rate": 6.165537741257971e-06,
+      "loss": 0.3093,
+      "step": 3170
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 5.0,
+      "learning_rate": 5.959410214142419e-06,
+      "loss": 0.3223,
+      "step": 3180
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 5.15625,
+      "learning_rate": 5.756568656839056e-06,
+      "loss": 0.4137,
+      "step": 3190
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.78125,
+      "learning_rate": 5.557028203823522e-06,
+      "loss": 0.3785,
+      "step": 3200
+    },
+    {
+      "epoch": 2.568,
+      "grad_norm": 3.59375,
+      "learning_rate": 5.360803743268494e-06,
+      "loss": 0.3343,
+      "step": 3210
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 4.96875,
+      "learning_rate": 5.167909915932801e-06,
+      "loss": 0.3217,
+      "step": 3220
+    },
+    {
+      "epoch": 2.584,
+      "grad_norm": 3.6875,
+      "learning_rate": 4.9783611140690415e-06,
+      "loss": 0.3157,
+      "step": 3230
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 3.84375,
+      "learning_rate": 4.7921714803498165e-06,
+      "loss": 0.2983,
+      "step": 3240
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 5.3125,
+      "learning_rate": 4.609354906812374e-06,
+      "loss": 0.3362,
+      "step": 3250
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 3.953125,
+      "learning_rate": 4.429925033822252e-06,
+      "loss": 0.3844,
+      "step": 3260
+    },
+    {
+      "epoch": 2.616,
+      "grad_norm": 4.28125,
+      "learning_rate": 4.253895249055412e-06,
+      "loss": 0.2974,
+      "step": 3270
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.0812786864994566e-06,
+      "loss": 0.3442,
+      "step": 3280
+    },
+    {
+      "epoch": 2.632,
+      "grad_norm": 3.171875,
+      "learning_rate": 3.912088225473537e-06,
+      "loss": 0.3572,
+      "step": 3290
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.7463364896675735e-06,
+      "loss": 0.3092,
+      "step": 3300
+    },
+    {
+      "epoch": 2.648,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.584035846200201e-06,
+      "loss": 0.3093,
+      "step": 3310
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 3.8125,
+      "learning_rate": 3.425198404696178e-06,
+      "loss": 0.3035,
+      "step": 3320
+    },
+    {
+      "epoch": 2.664,
+      "grad_norm": 4.90625,
+      "learning_rate": 3.2698360163827325e-06,
+      "loss": 0.3166,
+      "step": 3330
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.1179602732053947e-06,
+      "loss": 0.2739,
+      "step": 3340
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 6.4375,
+      "learning_rate": 2.969582506963098e-06,
+      "loss": 0.3551,
+      "step": 3350
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 4.625,
+      "learning_rate": 2.824713788462602e-06,
+      "loss": 0.3293,
+      "step": 3360
+    },
+    {
+      "epoch": 2.6959999999999997,
+      "grad_norm": 3.71875,
+      "learning_rate": 2.6833649266925943e-06,
+      "loss": 0.3278,
+      "step": 3370
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 3.984375,
+      "learning_rate": 2.5455464680171126e-06,
+      "loss": 0.2763,
+      "step": 3380
+    },
+    {
+      "epoch": 2.7119999999999997,
+      "grad_norm": 6.125,
+      "learning_rate": 2.411268695388719e-06,
+      "loss": 0.3378,
+      "step": 3390
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.28054162758119e-06,
+      "loss": 0.2644,
+      "step": 3400
+    },
+    {
+      "epoch": 2.7279999999999998,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.1533750184420832e-06,
+      "loss": 0.3154,
+      "step": 3410
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 5.28125,
+      "learning_rate": 2.0297783561649244e-06,
+      "loss": 0.2217,
+      "step": 3420
+    },
+    {
+      "epoch": 2.7439999999999998,
+      "grad_norm": 5.59375,
+      "learning_rate": 1.9097608625812726e-06,
+      "loss": 0.3446,
+      "step": 3430
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 5.25,
+      "learning_rate": 1.7933314924726886e-06,
+      "loss": 0.387,
+      "step": 3440
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.6804989329025521e-06,
+      "loss": 0.3531,
+      "step": 3450
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 5.9375,
+      "learning_rate": 1.5712716025679587e-06,
+      "loss": 0.2906,
+      "step": 3460
+    },
+    {
+      "epoch": 2.776,
+      "grad_norm": 5.28125,
+      "learning_rate": 1.4656576511715204e-06,
+      "loss": 0.2759,
+      "step": 3470
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.3636649588133432e-06,
+      "loss": 0.3646,
+      "step": 3480
+    },
+    {
+      "epoch": 2.792,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.265301135403052e-06,
+      "loss": 0.3467,
+      "step": 3490
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.1705735200920053e-06,
+      "loss": 0.2817,
+      "step": 3500
+    },
+    {
+      "epoch": 2.808,
+      "grad_norm": 5.4375,
+      "learning_rate": 1.0794891807256956e-06,
+      "loss": 0.3304,
+      "step": 3510
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 3.53125,
+      "learning_rate": 9.920549133164314e-07,
+      "loss": 0.3544,
+      "step": 3520
+    },
+    {
+      "epoch": 2.824,
+      "grad_norm": 6.21875,
+      "learning_rate": 9.08277241536215e-07,
+      "loss": 0.3082,
+      "step": 3530
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 3.984375,
+      "learning_rate": 8.281624162300494e-07,
+      "loss": 0.2201,
+      "step": 3540
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.9375,
+      "learning_rate": 7.517164149495326e-07,
+      "loss": 0.2885,
+      "step": 3550
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 5.625,
+      "learning_rate": 6.789449415068316e-07,
+      "loss": 0.2716,
+      "step": 3560
+    },
+    {
+      "epoch": 2.856,
+      "grad_norm": 5.46875,
+      "learning_rate": 6.098534255491561e-07,
+      "loss": 0.2723,
+      "step": 3570
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 2.765625,
+      "learning_rate": 5.44447022153588e-07,
+      "loss": 0.3245,
+      "step": 3580
+    },
+    {
+      "epoch": 2.872,
+      "grad_norm": 5.34375,
+      "learning_rate": 4.827306114425056e-07,
+      "loss": 0.2905,
+      "step": 3590
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.59375,
+      "learning_rate": 4.2470879821941423e-07,
+      "loss": 0.3986,
+      "step": 3600
+    },
+    {
+      "epoch": 2.888,
+      "grad_norm": 3.203125,
+      "learning_rate": 3.703859116254038e-07,
+      "loss": 0.3328,
+      "step": 3610
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 5.875,
+      "learning_rate": 3.197660048161133e-07,
+      "loss": 0.2893,
+      "step": 3620
+    },
+    {
+      "epoch": 2.904,
+      "grad_norm": 4.875,
+      "learning_rate": 2.728528546593667e-07,
+      "loss": 0.3573,
+      "step": 3630
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 3.921875,
+      "learning_rate": 2.2964996145330986e-07,
+      "loss": 0.2721,
+      "step": 3640
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.9016054866528576e-07,
+      "loss": 0.2943,
+      "step": 3650
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.5438756269130495e-07,
+      "loss": 0.3179,
+      "step": 3660
+    },
+    {
+      "epoch": 2.936,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.223336726362323e-07,
+      "loss": 0.3203,
+      "step": 3670
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 3.34375,
+      "learning_rate": 9.400127011461312e-08,
+      "loss": 0.3184,
+      "step": 3680
+    },
+    {
+      "epoch": 2.952,
+      "grad_norm": 4.625,
+      "learning_rate": 6.939246907222696e-08,
+      "loss": 0.3581,
+      "step": 3690
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 4.5,
+      "learning_rate": 4.850910562839151e-08,
+      "loss": 0.3222,
+      "step": 3700
+    },
+    {
+      "epoch": 2.968,
+      "grad_norm": 6.59375,
+      "learning_rate": 3.135273793893889e-08,
+      "loss": 0.2907,
+      "step": 3710
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 3.5625,
+      "learning_rate": 1.7924646079964248e-08,
+      "loss": 0.3589,
+      "step": 3720
+    },
+    {
+      "epoch": 2.984,
+      "grad_norm": 4.625,
+      "learning_rate": 8.225831952324292e-09,
+      "loss": 0.3172,
+      "step": 3730
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 5.75,
+      "learning_rate": 2.257019206874933e-09,
+      "loss": 0.29,
+      "step": 3740
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.109375,
+      "learning_rate": 1.8653190470008242e-11,
+      "loss": 0.2897,
+      "step": 3750
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.386198055566157e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2d0a1d294de71591829114cab72751317ef618785189b344d35019839741e4
+size 6673

checkpoint-3750/video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

config.json

@@ -104,7 +104,7 @@
     "rope_theta": 1000000.0,
     "sliding_window": null,
     "tie_word_embeddings": true,
-    "use_cache": false,
+    "use_cache": true,
     "use_sliding_window": false,
     "vision_token_id": 151654,
     "vocab_size": 151936

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcfdd62df5095d237461f590de81a8e1db5171b6575021ae7e053ea537f4b1df
+oid sha256:0e89da2acef14776f3d1439e440e0990b929333dbb2f2bcf0fd93cda3cfcc45e
 size 4997750760

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d048bfb99d9a98d5a052e1fa57b71ce44908f4c682f97b52b029bf4ae7bf39
+oid sha256:dc3fd91c1d4a2b2314af25a020df3ac318489902bb7c5f68d4436ca4b03dfcc5
 size 2565696568

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1250,
+  "global_step": 3750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -883,6 +883,1765 @@
       "learning_rate": 7.77987080974953e-05,
       "loss": 0.3482,
       "step": 1250
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 3.28125,
+      "learning_rate": 7.743868588184176e-05,
+      "loss": 0.3312,
+      "step": 1260
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 4.375,
+      "learning_rate": 7.707661640265401e-05,
+      "loss": 0.37,
+      "step": 1270
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 4.40625,
+      "learning_rate": 7.67125266747696e-05,
+      "loss": 0.3253,
+      "step": 1280
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 4.0625,
+      "learning_rate": 7.634644386376149e-05,
+      "loss": 0.4361,
+      "step": 1290
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 3.953125,
+      "learning_rate": 7.597839528391114e-05,
+      "loss": 0.3981,
+      "step": 1300
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 7.6875,
+      "learning_rate": 7.560840839617056e-05,
+      "loss": 0.3634,
+      "step": 1310
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 4.03125,
+      "learning_rate": 7.523651080611341e-05,
+      "loss": 0.3653,
+      "step": 1320
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 3.09375,
+      "learning_rate": 7.48627302618752e-05,
+      "loss": 0.3433,
+      "step": 1330
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 4.21875,
+      "learning_rate": 7.448709465208299e-05,
+      "loss": 0.3587,
+      "step": 1340
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 5.375,
+      "learning_rate": 7.410963200377458e-05,
+      "loss": 0.346,
+      "step": 1350
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 4.0625,
+      "learning_rate": 7.373037048030731e-05,
+      "loss": 0.4562,
+      "step": 1360
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 3.75,
+      "learning_rate": 7.334933837925675e-05,
+      "loss": 0.4333,
+      "step": 1370
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 3.46875,
+      "learning_rate": 7.296656413030531e-05,
+      "loss": 0.306,
+      "step": 1380
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 5.25,
+      "learning_rate": 7.25820762931211e-05,
+      "loss": 0.4095,
+      "step": 1390
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.578125,
+      "learning_rate": 7.219590355522697e-05,
+      "loss": 0.369,
+      "step": 1400
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.180807472986009e-05,
+      "loss": 0.3763,
+      "step": 1410
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 5.25,
+      "learning_rate": 7.141861875382215e-05,
+      "loss": 0.4269,
+      "step": 1420
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 3.53125,
+      "learning_rate": 7.102756468532027e-05,
+      "loss": 0.4017,
+      "step": 1430
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 4.6875,
+      "learning_rate": 7.063494170179898e-05,
+      "loss": 0.3601,
+      "step": 1440
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.8125,
+      "learning_rate": 7.024077909776309e-05,
+      "loss": 0.3678,
+      "step": 1450
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 5.25,
+      "learning_rate": 6.984510628259212e-05,
+      "loss": 0.3732,
+      "step": 1460
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 2.140625,
+      "learning_rate": 6.94479527783459e-05,
+      "loss": 0.3332,
+      "step": 1470
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 4.5,
+      "learning_rate": 6.904934821756184e-05,
+      "loss": 0.3887,
+      "step": 1480
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 2.296875,
+      "learning_rate": 6.864932234104409e-05,
+      "loss": 0.3196,
+      "step": 1490
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.15625,
+      "learning_rate": 6.824790499564435e-05,
+      "loss": 0.3256,
+      "step": 1500
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 3.6875,
+      "learning_rate": 6.784512613203511e-05,
+      "loss": 0.3074,
+      "step": 1510
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 3.0,
+      "learning_rate": 6.744101580247481e-05,
+      "loss": 0.35,
+      "step": 1520
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 3.828125,
+      "learning_rate": 6.703560415856565e-05,
+      "loss": 0.3731,
+      "step": 1530
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 5.625,
+      "learning_rate": 6.662892144900388e-05,
+      "loss": 0.3769,
+      "step": 1540
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 8.1875,
+      "learning_rate": 6.62209980173229e-05,
+      "loss": 0.4385,
+      "step": 1550
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 5.9375,
+      "learning_rate": 6.581186429962922e-05,
+      "loss": 0.3563,
+      "step": 1560
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 3.53125,
+      "learning_rate": 6.54015508223316e-05,
+      "loss": 0.3225,
+      "step": 1570
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 4.125,
+      "learning_rate": 6.499008819986339e-05,
+      "loss": 0.3246,
+      "step": 1580
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 4.34375,
+      "learning_rate": 6.457750713239828e-05,
+      "loss": 0.304,
+      "step": 1590
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 4.75,
+      "learning_rate": 6.41638384035597e-05,
+      "loss": 0.383,
+      "step": 1600
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 4.46875,
+      "learning_rate": 6.374911287812406e-05,
+      "loss": 0.331,
+      "step": 1610
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 3.984375,
+      "learning_rate": 6.333336149971776e-05,
+      "loss": 0.3022,
+      "step": 1620
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 5.53125,
+      "learning_rate": 6.291661528850844e-05,
+      "loss": 0.3257,
+      "step": 1630
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.249890533889054e-05,
+      "loss": 0.3071,
+      "step": 1640
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 4.25,
+      "learning_rate": 6.208026281716521e-05,
+      "loss": 0.3833,
+      "step": 1650
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 3.109375,
+      "learning_rate": 6.166071895921496e-05,
+      "loss": 0.3378,
+      "step": 1660
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 3.5,
+      "learning_rate": 6.124030506817309e-05,
+      "loss": 0.31,
+      "step": 1670
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 2.65625,
+      "learning_rate": 6.0819052512088057e-05,
+      "loss": 0.3139,
+      "step": 1680
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 4.90625,
+      "learning_rate": 6.039699272158305e-05,
+      "loss": 0.4388,
+      "step": 1690
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 5.59375,
+      "learning_rate": 5.997415718751086e-05,
+      "loss": 0.3989,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 5.5,
+      "learning_rate": 5.955057745860435e-05,
+      "loss": 0.3977,
+      "step": 1710
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 6.25,
+      "learning_rate": 5.9126285139122406e-05,
+      "loss": 0.3527,
+      "step": 1720
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 3.28125,
+      "learning_rate": 5.8701311886491947e-05,
+      "loss": 0.4044,
+      "step": 1730
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 5.5625,
+      "learning_rate": 5.827568940894593e-05,
+      "loss": 0.374,
+      "step": 1740
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.625,
+      "learning_rate": 5.7849449463157435e-05,
+      "loss": 0.3479,
+      "step": 1750
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 4.84375,
+      "learning_rate": 5.742262385187028e-05,
+      "loss": 0.3666,
+      "step": 1760
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.699524442152613e-05,
+      "loss": 0.3707,
+      "step": 1770
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 4.4375,
+      "learning_rate": 5.656734305988839e-05,
+      "loss": 0.3847,
+      "step": 1780
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 3.96875,
+      "learning_rate": 5.613895169366292e-05,
+      "loss": 0.3515,
+      "step": 1790
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.734375,
+      "learning_rate": 5.571010228611597e-05,
+      "loss": 0.3763,
+      "step": 1800
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 5.71875,
+      "learning_rate": 5.528082683468934e-05,
+      "loss": 0.3548,
+      "step": 1810
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 5.03125,
+      "learning_rate": 5.485115736861288e-05,
+      "loss": 0.3903,
+      "step": 1820
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 4.375,
+      "learning_rate": 5.442112594651484e-05,
+      "loss": 0.257,
+      "step": 1830
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 5.46875,
+      "learning_rate": 5.399076465402979e-05,
+      "loss": 0.3424,
+      "step": 1840
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 3.40625,
+      "learning_rate": 5.356010560140475e-05,
+      "loss": 0.3317,
+      "step": 1850
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 5.0,
+      "learning_rate": 5.312918092110325e-05,
+      "loss": 0.2753,
+      "step": 1860
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 3.84375,
+      "learning_rate": 5.269802276540795e-05,
+      "loss": 0.3318,
+      "step": 1870
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 5.71875,
+      "learning_rate": 5.226666330402164e-05,
+      "loss": 0.3836,
+      "step": 1880
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 3.671875,
+      "learning_rate": 5.1835134721666956e-05,
+      "loss": 0.3498,
+      "step": 1890
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.90625,
+      "learning_rate": 5.1403469215685094e-05,
+      "loss": 0.4228,
+      "step": 1900
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 4.4375,
+      "learning_rate": 5.097169899363342e-05,
+      "loss": 0.3703,
+      "step": 1910
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 3.90625,
+      "learning_rate": 5.053985627088238e-05,
+      "loss": 0.3816,
+      "step": 1920
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 2.71875,
+      "learning_rate": 5.010797326821189e-05,
+      "loss": 0.3842,
+      "step": 1930
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 3.875,
+      "learning_rate": 4.9676082209407254e-05,
+      "loss": 0.3848,
+      "step": 1940
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 3.484375,
+      "learning_rate": 4.924421531885481e-05,
+      "loss": 0.3416,
+      "step": 1950
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.881240481913773e-05,
+      "loss": 0.3407,
+      "step": 1960
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.838068292863164e-05,
+      "loss": 0.3319,
+      "step": 1970
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 4.4375,
+      "learning_rate": 4.7949081859100896e-05,
+      "loss": 0.3979,
+      "step": 1980
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.7517633813295114e-05,
+      "loss": 0.4184,
+      "step": 1990
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.708637098254644e-05,
+      "loss": 0.3959,
+      "step": 2000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 4.8125,
+      "learning_rate": 4.6655325544367715e-05,
+      "loss": 0.313,
+      "step": 2010
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.6224529660051593e-05,
+      "loss": 0.3012,
+      "step": 2020
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.579401547227096e-05,
+      "loss": 0.2532,
+      "step": 2030
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 2.953125,
+      "learning_rate": 4.53638151026807e-05,
+      "loss": 0.2714,
+      "step": 2040
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.493396064952093e-05,
+      "loss": 0.3468,
+      "step": 2050
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 5.125,
+      "learning_rate": 4.450448418522221e-05,
+      "loss": 0.4547,
+      "step": 2060
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 3.5,
+      "learning_rate": 4.4075417754012475e-05,
+      "loss": 0.2839,
+      "step": 2070
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 5.84375,
+      "learning_rate": 4.364679336952609e-05,
+      "loss": 0.3426,
+      "step": 2080
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.321864301241535e-05,
+      "loss": 0.3325,
+      "step": 2090
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 4.46875,
+      "learning_rate": 4.279099862796427e-05,
+      "loss": 0.314,
+      "step": 2100
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 2.8125,
+      "learning_rate": 4.23638921237051e-05,
+      "loss": 0.4189,
+      "step": 2110
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 3.59375,
+      "learning_rate": 4.1937355367037516e-05,
+      "loss": 0.3436,
+      "step": 2120
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 6.21875,
+      "learning_rate": 4.151142018285112e-05,
+      "loss": 0.3681,
+      "step": 2130
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.1086118351150785e-05,
+      "loss": 0.3716,
+      "step": 2140
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.703125,
+      "learning_rate": 4.066148160468543e-05,
+      "loss": 0.2761,
+      "step": 2150
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 3.765625,
+      "learning_rate": 4.023754162658051e-05,
+      "loss": 0.2904,
+      "step": 2160
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.981433004797395e-05,
+      "loss": 0.3563,
+      "step": 2170
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 4.125,
+      "learning_rate": 3.939187844565616e-05,
+      "loss": 0.3248,
+      "step": 2180
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 5.71875,
+      "learning_rate": 3.897021833971386e-05,
+      "loss": 0.3246,
+      "step": 2190
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 4.21875,
+      "learning_rate": 3.8549381191178516e-05,
+      "loss": 0.4073,
+      "step": 2200
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.8129398399678814e-05,
+      "loss": 0.4147,
+      "step": 2210
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.771030130109785e-05,
+      "loss": 0.2378,
+      "step": 2220
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 3.65625,
+      "learning_rate": 3.729212116523518e-05,
+      "loss": 0.3305,
+      "step": 2230
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 3.09375,
+      "learning_rate": 3.6874889193473646e-05,
+      "loss": 0.3865,
+      "step": 2240
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.5,
+      "learning_rate": 3.64586365164514e-05,
+      "loss": 0.3443,
+      "step": 2250
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 2.71875,
+      "learning_rate": 3.604339419173912e-05,
+      "loss": 0.2762,
+      "step": 2260
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.5629193201522794e-05,
+      "loss": 0.3787,
+      "step": 2270
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.521606445029208e-05,
+      "loss": 0.4157,
+      "step": 2280
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.480403876253432e-05,
+      "loss": 0.3345,
+      "step": 2290
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 3.3125,
+      "learning_rate": 3.4393146880434845e-05,
+      "loss": 0.3111,
+      "step": 2300
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.398341946158311e-05,
+      "loss": 0.3763,
+      "step": 2310
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.357488707668529e-05,
+      "loss": 0.3246,
+      "step": 2320
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 4.65625,
+      "learning_rate": 3.316758020728327e-05,
+      "loss": 0.3852,
+      "step": 2330
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.276152924348046e-05,
+      "loss": 0.3295,
+      "step": 2340
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.2356764481674254e-05,
+      "loss": 0.3567,
+      "step": 2350
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 3.421875,
+      "learning_rate": 3.1953316122295554e-05,
+      "loss": 0.3091,
+      "step": 2360
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 3.265625,
+      "learning_rate": 3.1551214267555416e-05,
+      "loss": 0.3847,
+      "step": 2370
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 6.09375,
+      "learning_rate": 3.1150488919199124e-05,
+      "loss": 0.3958,
+      "step": 2380
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.075116997626764e-05,
+      "loss": 0.384,
+      "step": 2390
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.0353287232866736e-05,
+      "loss": 0.3349,
+      "step": 2400
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 4.375,
+      "learning_rate": 2.995687037594408e-05,
+      "loss": 0.3801,
+      "step": 2410
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.9561948983074174e-05,
+      "loss": 0.3281,
+      "step": 2420
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 6.8125,
+      "learning_rate": 2.916855252025149e-05,
+      "loss": 0.3549,
+      "step": 2430
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 4.125,
+      "learning_rate": 2.877671033969193e-05,
+      "loss": 0.4092,
+      "step": 2440
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 4.21875,
+      "learning_rate": 2.8386451677642878e-05,
+      "loss": 0.3866,
+      "step": 2450
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 3.078125,
+      "learning_rate": 2.7997805652201714e-05,
+      "loss": 0.3484,
+      "step": 2460
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.7610801261143283e-05,
+      "loss": 0.3496,
+      "step": 2470
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 4.6875,
+      "learning_rate": 2.7225467379756314e-05,
+      "loss": 0.3691,
+      "step": 2480
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 5.5,
+      "learning_rate": 2.6841832758689002e-05,
+      "loss": 0.3698,
+      "step": 2490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.875,
+      "learning_rate": 2.645992602180377e-05,
+      "loss": 0.3577,
+      "step": 2500
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 4.40625,
+      "learning_rate": 2.607977566404164e-05,
+      "loss": 0.2871,
+      "step": 2510
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 4.0625,
+      "learning_rate": 2.570141004929612e-05,
+      "loss": 0.3426,
+      "step": 2520
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 3.5,
+      "learning_rate": 2.5324857408296994e-05,
+      "loss": 0.2656,
+      "step": 2530
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 3.578125,
+      "learning_rate": 2.4950145836503836e-05,
+      "loss": 0.3473,
+      "step": 2540
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.953125,
+      "learning_rate": 2.4577303292009822e-05,
+      "loss": 0.3588,
+      "step": 2550
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 4.75,
+      "learning_rate": 2.4206357593455743e-05,
+      "loss": 0.3953,
+      "step": 2560
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 3.96875,
+      "learning_rate": 2.383733641795428e-05,
+      "loss": 0.3209,
+      "step": 2570
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 2.515625,
+      "learning_rate": 2.3470267299025068e-05,
+      "loss": 0.3299,
+      "step": 2580
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 3.375,
+      "learning_rate": 2.3105177624540252e-05,
+      "loss": 0.2311,
+      "step": 2590
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 4.46875,
+      "learning_rate": 2.274209463468117e-05,
+      "loss": 0.3035,
+      "step": 2600
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 2.578125,
+      "learning_rate": 2.2381045419905655e-05,
+      "loss": 0.3344,
+      "step": 2610
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 5.28125,
+      "learning_rate": 2.2022056918927037e-05,
+      "loss": 0.2794,
+      "step": 2620
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 5.25,
+      "learning_rate": 2.166515591670394e-05,
+      "loss": 0.3416,
+      "step": 2630
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 3.96875,
+      "learning_rate": 2.1310369042441985e-05,
+      "loss": 0.3152,
+      "step": 2640
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 3.203125,
+      "learning_rate": 2.0957722767606774e-05,
+      "loss": 0.3015,
+      "step": 2650
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 3.78125,
+      "learning_rate": 2.0607243403948863e-05,
+      "loss": 0.3843,
+      "step": 2660
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 6.34375,
+      "learning_rate": 2.0258957101540625e-05,
+      "loss": 0.3299,
+      "step": 2670
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.9912889846825038e-05,
+      "loss": 0.3636,
+      "step": 2680
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.956906746067683e-05,
+      "loss": 0.3596,
+      "step": 2690
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.922751559647591e-05,
+      "loss": 0.3796,
+      "step": 2700
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.888825973819336e-05,
+      "loss": 0.3175,
+      "step": 2710
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.8551325198489887e-05,
+      "loss": 0.2928,
+      "step": 2720
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.8216737116827378e-05,
+      "loss": 0.2791,
+      "step": 2730
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.7884520457592984e-05,
+      "loss": 0.3925,
+      "step": 2740
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.755470000823667e-05,
+      "loss": 0.2967,
+      "step": 2750
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.7227300377421574e-05,
+      "loss": 0.2475,
+      "step": 2760
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.6902345993188017e-05,
+      "loss": 0.34,
+      "step": 2770
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.6579861101130896e-05,
+      "loss": 0.3418,
+      "step": 2780
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 6.5,
+      "learning_rate": 1.6259869762590503e-05,
+      "loss": 0.4639,
+      "step": 2790
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 5.0625,
+      "learning_rate": 1.5942395852857466e-05,
+      "loss": 0.4252,
+      "step": 2800
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 4.71875,
+      "learning_rate": 1.5627463059391173e-05,
+      "loss": 0.3562,
+      "step": 2810
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 3.78125,
+      "learning_rate": 1.531509488005257e-05,
+      "loss": 0.2792,
+      "step": 2820
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 5.25,
+      "learning_rate": 1.5005314621350709e-05,
+      "loss": 0.2659,
+      "step": 2830
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.4698145396704044e-05,
+      "loss": 0.2647,
+      "step": 2840
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 5.3125,
+      "learning_rate": 1.4393610124715696e-05,
+      "loss": 0.2826,
+      "step": 2850
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.4091731527463526e-05,
+      "loss": 0.2643,
+      "step": 2860
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 5.75,
+      "learning_rate": 1.3792532128804803e-05,
+      "loss": 0.3758,
+      "step": 2870
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 6.25,
+      "learning_rate": 1.3496034252695599e-05,
+      "loss": 0.3,
+      "step": 2880
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.3202260021525158e-05,
+      "loss": 0.3376,
+      "step": 2890
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 4.90625,
+      "learning_rate": 1.2911231354465303e-05,
+      "loss": 0.3686,
+      "step": 2900
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 3.859375,
+      "learning_rate": 1.262296996583504e-05,
+      "loss": 0.3372,
+      "step": 2910
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 3.421875,
+      "learning_rate": 1.2337497363480317e-05,
+      "loss": 0.3071,
+      "step": 2920
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 4.15625,
+      "learning_rate": 1.2054834847169316e-05,
+      "loss": 0.3724,
+      "step": 2930
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 4.21875,
+      "learning_rate": 1.1775003507003236e-05,
+      "loss": 0.2919,
+      "step": 2940
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.1498024221842735e-05,
+      "loss": 0.2496,
+      "step": 2950
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 5.28125,
+      "learning_rate": 1.1223917657750033e-05,
+      "loss": 0.265,
+      "step": 2960
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.095270426644705e-05,
+      "loss": 0.3083,
+      "step": 2970
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 4.25,
+      "learning_rate": 1.0684404283789385e-05,
+      "loss": 0.3392,
+      "step": 2980
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.0419037728256564e-05,
+      "loss": 0.3743,
+      "step": 2990
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 4.5625,
+      "learning_rate": 1.015662439945832e-05,
+      "loss": 0.3846,
+      "step": 3000
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 4.28125,
+      "learning_rate": 9.89718387665734e-06,
+      "loss": 0.2818,
+      "step": 3010
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 4.1875,
+      "learning_rate": 9.640735517308435e-06,
+      "loss": 0.3442,
+      "step": 3020
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.387298455614191e-06,
+      "loss": 0.2982,
+      "step": 3030
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 7.5,
+      "learning_rate": 9.136891601097347e-06,
+      "loss": 0.3924,
+      "step": 3040
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 3.15625,
+      "learning_rate": 8.889533637189895e-06,
+      "loss": 0.2838,
+      "step": 3050
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 6.125,
+      "learning_rate": 8.645243019839112e-06,
+      "loss": 0.3035,
+      "step": 3060
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 3.609375,
+      "learning_rate": 8.404037976130458e-06,
+      "loss": 0.3713,
+      "step": 3070
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 4.84375,
+      "learning_rate": 8.16593650292764e-06,
+      "loss": 0.3242,
+      "step": 3080
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 3.21875,
+      "learning_rate": 7.930956365529818e-06,
+      "loss": 0.3214,
+      "step": 3090
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.953125,
+      "learning_rate": 7.699115096346139e-06,
+      "loss": 0.3072,
+      "step": 3100
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 4.5,
+      "learning_rate": 7.4704299935875185e-06,
+      "loss": 0.2528,
+      "step": 3110
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 4.28125,
+      "learning_rate": 7.244918119976035e-06,
+      "loss": 0.3366,
+      "step": 3120
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 5.53125,
+      "learning_rate": 7.022596301471868e-06,
+      "loss": 0.3603,
+      "step": 3130
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 4.28125,
+      "learning_rate": 6.803481126017808e-06,
+      "loss": 0.2996,
+      "step": 3140
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.90625,
+      "learning_rate": 6.587588942301626e-06,
+      "loss": 0.3519,
+      "step": 3150
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 5.3125,
+      "learning_rate": 6.374935858536257e-06,
+      "loss": 0.2668,
+      "step": 3160
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 5.25,
+      "learning_rate": 6.165537741257971e-06,
+      "loss": 0.3093,
+      "step": 3170
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 5.0,
+      "learning_rate": 5.959410214142419e-06,
+      "loss": 0.3223,
+      "step": 3180
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 5.15625,
+      "learning_rate": 5.756568656839056e-06,
+      "loss": 0.4137,
+      "step": 3190
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 5.78125,
+      "learning_rate": 5.557028203823522e-06,
+      "loss": 0.3785,
+      "step": 3200
+    },
+    {
+      "epoch": 2.568,
+      "grad_norm": 3.59375,
+      "learning_rate": 5.360803743268494e-06,
+      "loss": 0.3343,
+      "step": 3210
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 4.96875,
+      "learning_rate": 5.167909915932801e-06,
+      "loss": 0.3217,
+      "step": 3220
+    },
+    {
+      "epoch": 2.584,
+      "grad_norm": 3.6875,
+      "learning_rate": 4.9783611140690415e-06,
+      "loss": 0.3157,
+      "step": 3230
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 3.84375,
+      "learning_rate": 4.7921714803498165e-06,
+      "loss": 0.2983,
+      "step": 3240
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 5.3125,
+      "learning_rate": 4.609354906812374e-06,
+      "loss": 0.3362,
+      "step": 3250
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 3.953125,
+      "learning_rate": 4.429925033822252e-06,
+      "loss": 0.3844,
+      "step": 3260
+    },
+    {
+      "epoch": 2.616,
+      "grad_norm": 4.28125,
+      "learning_rate": 4.253895249055412e-06,
+      "loss": 0.2974,
+      "step": 3270
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.0812786864994566e-06,
+      "loss": 0.3442,
+      "step": 3280
+    },
+    {
+      "epoch": 2.632,
+      "grad_norm": 3.171875,
+      "learning_rate": 3.912088225473537e-06,
+      "loss": 0.3572,
+      "step": 3290
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.7463364896675735e-06,
+      "loss": 0.3092,
+      "step": 3300
+    },
+    {
+      "epoch": 2.648,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.584035846200201e-06,
+      "loss": 0.3093,
+      "step": 3310
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 3.8125,
+      "learning_rate": 3.425198404696178e-06,
+      "loss": 0.3035,
+      "step": 3320
+    },
+    {
+      "epoch": 2.664,
+      "grad_norm": 4.90625,
+      "learning_rate": 3.2698360163827325e-06,
+      "loss": 0.3166,
+      "step": 3330
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.1179602732053947e-06,
+      "loss": 0.2739,
+      "step": 3340
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 6.4375,
+      "learning_rate": 2.969582506963098e-06,
+      "loss": 0.3551,
+      "step": 3350
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 4.625,
+      "learning_rate": 2.824713788462602e-06,
+      "loss": 0.3293,
+      "step": 3360
+    },
+    {
+      "epoch": 2.6959999999999997,
+      "grad_norm": 3.71875,
+      "learning_rate": 2.6833649266925943e-06,
+      "loss": 0.3278,
+      "step": 3370
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 3.984375,
+      "learning_rate": 2.5455464680171126e-06,
+      "loss": 0.2763,
+      "step": 3380
+    },
+    {
+      "epoch": 2.7119999999999997,
+      "grad_norm": 6.125,
+      "learning_rate": 2.411268695388719e-06,
+      "loss": 0.3378,
+      "step": 3390
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.28054162758119e-06,
+      "loss": 0.2644,
+      "step": 3400
+    },
+    {
+      "epoch": 2.7279999999999998,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.1533750184420832e-06,
+      "loss": 0.3154,
+      "step": 3410
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 5.28125,
+      "learning_rate": 2.0297783561649244e-06,
+      "loss": 0.2217,
+      "step": 3420
+    },
+    {
+      "epoch": 2.7439999999999998,
+      "grad_norm": 5.59375,
+      "learning_rate": 1.9097608625812726e-06,
+      "loss": 0.3446,
+      "step": 3430
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 5.25,
+      "learning_rate": 1.7933314924726886e-06,
+      "loss": 0.387,
+      "step": 3440
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.6804989329025521e-06,
+      "loss": 0.3531,
+      "step": 3450
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 5.9375,
+      "learning_rate": 1.5712716025679587e-06,
+      "loss": 0.2906,
+      "step": 3460
+    },
+    {
+      "epoch": 2.776,
+      "grad_norm": 5.28125,
+      "learning_rate": 1.4656576511715204e-06,
+      "loss": 0.2759,
+      "step": 3470
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.3636649588133432e-06,
+      "loss": 0.3646,
+      "step": 3480
+    },
+    {
+      "epoch": 2.792,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.265301135403052e-06,
+      "loss": 0.3467,
+      "step": 3490
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.1705735200920053e-06,
+      "loss": 0.2817,
+      "step": 3500
+    },
+    {
+      "epoch": 2.808,
+      "grad_norm": 5.4375,
+      "learning_rate": 1.0794891807256956e-06,
+      "loss": 0.3304,
+      "step": 3510
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 3.53125,
+      "learning_rate": 9.920549133164314e-07,
+      "loss": 0.3544,
+      "step": 3520
+    },
+    {
+      "epoch": 2.824,
+      "grad_norm": 6.21875,
+      "learning_rate": 9.08277241536215e-07,
+      "loss": 0.3082,
+      "step": 3530
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 3.984375,
+      "learning_rate": 8.281624162300494e-07,
+      "loss": 0.2201,
+      "step": 3540
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 6.9375,
+      "learning_rate": 7.517164149495326e-07,
+      "loss": 0.2885,
+      "step": 3550
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 5.625,
+      "learning_rate": 6.789449415068316e-07,
+      "loss": 0.2716,
+      "step": 3560
+    },
+    {
+      "epoch": 2.856,
+      "grad_norm": 5.46875,
+      "learning_rate": 6.098534255491561e-07,
+      "loss": 0.2723,
+      "step": 3570
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 2.765625,
+      "learning_rate": 5.44447022153588e-07,
+      "loss": 0.3245,
+      "step": 3580
+    },
+    {
+      "epoch": 2.872,
+      "grad_norm": 5.34375,
+      "learning_rate": 4.827306114425056e-07,
+      "loss": 0.2905,
+      "step": 3590
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.59375,
+      "learning_rate": 4.2470879821941423e-07,
+      "loss": 0.3986,
+      "step": 3600
+    },
+    {
+      "epoch": 2.888,
+      "grad_norm": 3.203125,
+      "learning_rate": 3.703859116254038e-07,
+      "loss": 0.3328,
+      "step": 3610
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 5.875,
+      "learning_rate": 3.197660048161133e-07,
+      "loss": 0.2893,
+      "step": 3620
+    },
+    {
+      "epoch": 2.904,
+      "grad_norm": 4.875,
+      "learning_rate": 2.728528546593667e-07,
+      "loss": 0.3573,
+      "step": 3630
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 3.921875,
+      "learning_rate": 2.2964996145330986e-07,
+      "loss": 0.2721,
+      "step": 3640
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.9016054866528576e-07,
+      "loss": 0.2943,
+      "step": 3650
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.5438756269130495e-07,
+      "loss": 0.3179,
+      "step": 3660
+    },
+    {
+      "epoch": 2.936,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.223336726362323e-07,
+      "loss": 0.3203,
+      "step": 3670
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 3.34375,
+      "learning_rate": 9.400127011461312e-08,
+      "loss": 0.3184,
+      "step": 3680
+    },
+    {
+      "epoch": 2.952,
+      "grad_norm": 4.625,
+      "learning_rate": 6.939246907222696e-08,
+      "loss": 0.3581,
+      "step": 3690
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 4.5,
+      "learning_rate": 4.850910562839151e-08,
+      "loss": 0.3222,
+      "step": 3700
+    },
+    {
+      "epoch": 2.968,
+      "grad_norm": 6.59375,
+      "learning_rate": 3.135273793893889e-08,
+      "loss": 0.2907,
+      "step": 3710
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 3.5625,
+      "learning_rate": 1.7924646079964248e-08,
+      "loss": 0.3589,
+      "step": 3720
+    },
+    {
+      "epoch": 2.984,
+      "grad_norm": 4.625,
+      "learning_rate": 8.225831952324292e-09,
+      "loss": 0.3172,
+      "step": 3730
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 5.75,
+      "learning_rate": 2.257019206874933e-09,
+      "loss": 0.29,
+      "step": 3740
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.109375,
+      "learning_rate": 1.8653190470008242e-11,
+      "loss": 0.2897,
+      "step": 3750
+    },
+    {
+      "epoch": 3.0,
+      "step": 3750,
+      "total_flos": 6.386198055566157e+17,
+      "train_loss": 0.40305233942667645,
+      "train_runtime": 8900.4049,
+      "train_samples_per_second": 6.741,
+      "train_steps_per_second": 0.421
     }
   ],
   "logging_steps": 10,
@@ -897,12 +2656,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.1287107515811744e+17,
+  "total_flos": 6.386198055566157e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null