Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|action_end|>": 151669,
+  "<|action_start|>": 151668,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|diff_marker|>": 151665,
+  "<|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,
+  "<|think_end|>": 151667,
+  "<|think_start|>": 151666,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151665
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "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,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151670
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151665
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.50.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1020957d35c82d98453b9be44ed164821d9969811aa977fbce9072577fac2aca
+size 4996661224

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3f142a82745e96af1fdd8bd735ddc1c6c065312ba6866aa4eca90cd51fc66a
+size 2511587184

model.safetensors.index.json

@@ -0,0 +1,831 @@
+{
+  "metadata": {
+    "total_size": 7508156416
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 250000,
+  "merge_size": 2,
+  "min_pixels": 250000,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 250000,
+    "shortest_edge": 250000
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,138 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|diff_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|think_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|think_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|action_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|action_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": "<|diff_marker|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dfa8f847d7f89db1955e36c2faaf9a35cdd9c4a63e9a103f153d8c1dbd972ea
+size 11422854

tokenizer_config.json

@@ -0,0 +1,255 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|diff_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|think_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|think_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|action_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|action_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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|>",
+    "<|diff_marker|>",
+    "<|think_start|>",
+    "<|think_end|>",
+    "<|action_start|>",
+    "<|action_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|diff_marker|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3571 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 504,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003968253968253968,
+      "grad_norm": 480.6939697265625,
+      "learning_rate": 3.846153846153847e-07,
+      "loss": 1.9332,
+      "step": 1
+    },
+    {
+      "epoch": 0.007936507936507936,
+      "grad_norm": 485.58526611328125,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.9959,
+      "step": 2
+    },
+    {
+      "epoch": 0.011904761904761904,
+      "grad_norm": 502.3266296386719,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 2.0371,
+      "step": 3
+    },
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 626.9771118164062,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 2.1148,
+      "step": 4
+    },
+    {
+      "epoch": 0.01984126984126984,
+      "grad_norm": 491.1722412109375,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 2.186,
+      "step": 5
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 363.6409606933594,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.9466,
+      "step": 6
+    },
+    {
+      "epoch": 0.027777777777777776,
+      "grad_norm": 224.33517456054688,
+      "learning_rate": 2.6923076923076923e-06,
+      "loss": 1.8087,
+      "step": 7
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 65.55188751220703,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.6339,
+      "step": 8
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 107.53528594970703,
+      "learning_rate": 3.4615384615384617e-06,
+      "loss": 1.5849,
+      "step": 9
+    },
+    {
+      "epoch": 0.03968253968253968,
+      "grad_norm": 93.20413208007812,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 1.5984,
+      "step": 10
+    },
+    {
+      "epoch": 0.04365079365079365,
+      "grad_norm": 25.42405891418457,
+      "learning_rate": 4.230769230769231e-06,
+      "loss": 1.4529,
+      "step": 11
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 99.05838775634766,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 1.3944,
+      "step": 12
+    },
+    {
+      "epoch": 0.051587301587301584,
+      "grad_norm": 16.312206268310547,
+      "learning_rate": 5e-06,
+      "loss": 1.3128,
+      "step": 13
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 14.814692497253418,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 1.3119,
+      "step": 14
+    },
+    {
+      "epoch": 0.05952380952380952,
+      "grad_norm": 20.357574462890625,
+      "learning_rate": 5.769230769230769e-06,
+      "loss": 1.1976,
+      "step": 15
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 15.262699127197266,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 1.1386,
+      "step": 16
+    },
+    {
+      "epoch": 0.06746031746031746,
+      "grad_norm": 14.989243507385254,
+      "learning_rate": 6.538461538461539e-06,
+      "loss": 1.0688,
+      "step": 17
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 9.59119701385498,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.0538,
+      "step": 18
+    },
+    {
+      "epoch": 0.07539682539682539,
+      "grad_norm": 8.450692176818848,
+      "learning_rate": 7.307692307692308e-06,
+      "loss": 0.9889,
+      "step": 19
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "grad_norm": 9.870237350463867,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.9955,
+      "step": 20
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 5.6950788497924805,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 0.9486,
+      "step": 21
+    },
+    {
+      "epoch": 0.0873015873015873,
+      "grad_norm": 7.79123067855835,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 1.0479,
+      "step": 22
+    },
+    {
+      "epoch": 0.09126984126984126,
+      "grad_norm": 4.994154453277588,
+      "learning_rate": 8.846153846153847e-06,
+      "loss": 1.1122,
+      "step": 23
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 4.5346879959106445,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 1.0289,
+      "step": 24
+    },
+    {
+      "epoch": 0.0992063492063492,
+      "grad_norm": 4.251474380493164,
+      "learning_rate": 9.615384615384616e-06,
+      "loss": 0.9206,
+      "step": 25
+    },
+    {
+      "epoch": 0.10317460317460317,
+      "grad_norm": 2.8367598056793213,
+      "learning_rate": 1e-05,
+      "loss": 0.6243,
+      "step": 26
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 2.6357839107513428,
+      "learning_rate": 9.999892010284378e-06,
+      "loss": 0.6254,
+      "step": 27
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 2.7344064712524414,
+      "learning_rate": 9.999568045802216e-06,
+      "loss": 0.6485,
+      "step": 28
+    },
+    {
+      "epoch": 0.11507936507936507,
+      "grad_norm": 2.1355581283569336,
+      "learning_rate": 9.999028120547456e-06,
+      "loss": 0.5566,
+      "step": 29
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 2.1411855220794678,
+      "learning_rate": 9.99827225784264e-06,
+      "loss": 0.6042,
+      "step": 30
+    },
+    {
+      "epoch": 0.12301587301587301,
+      "grad_norm": 2.0088932514190674,
+      "learning_rate": 9.99730049033793e-06,
+      "loss": 0.5592,
+      "step": 31
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 2.1030216217041016,
+      "learning_rate": 9.996112860009689e-06,
+      "loss": 0.5772,
+      "step": 32
+    },
+    {
+      "epoch": 0.13095238095238096,
+      "grad_norm": 2.0733652114868164,
+      "learning_rate": 9.994709418158652e-06,
+      "loss": 0.5338,
+      "step": 33
+    },
+    {
+      "epoch": 0.1349206349206349,
+      "grad_norm": 2.132509469985962,
+      "learning_rate": 9.993090225407743e-06,
+      "loss": 0.6218,
+      "step": 34
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.952929139137268,
+      "learning_rate": 9.991255351699422e-06,
+      "loss": 0.5433,
+      "step": 35
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 2.200437307357788,
+      "learning_rate": 9.98920487629269e-06,
+      "loss": 0.6256,
+      "step": 36
+    },
+    {
+      "epoch": 0.14682539682539683,
+      "grad_norm": 2.1493747234344482,
+      "learning_rate": 9.986938887759643e-06,
+      "loss": 0.6211,
+      "step": 37
+    },
+    {
+      "epoch": 0.15079365079365079,
+      "grad_norm": 2.1535778045654297,
+      "learning_rate": 9.98445748398167e-06,
+      "loss": 0.6083,
+      "step": 38
+    },
+    {
+      "epoch": 0.15476190476190477,
+      "grad_norm": 2.30021071434021,
+      "learning_rate": 9.981760772145201e-06,
+      "loss": 0.6339,
+      "step": 39
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 2.382420301437378,
+      "learning_rate": 9.978848868737099e-06,
+      "loss": 0.6369,
+      "step": 40
+    },
+    {
+      "epoch": 0.1626984126984127,
+      "grad_norm": 2.483940362930298,
+      "learning_rate": 9.975721899539607e-06,
+      "loss": 0.6274,
+      "step": 41
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 2.7135977745056152,
+      "learning_rate": 9.972379999624935e-06,
+      "loss": 0.6848,
+      "step": 42
+    },
+    {
+      "epoch": 0.17063492063492064,
+      "grad_norm": 2.600355625152588,
+      "learning_rate": 9.968823313349412e-06,
+      "loss": 0.5952,
+      "step": 43
+    },
+    {
+      "epoch": 0.1746031746031746,
+      "grad_norm": 2.6748218536376953,
+      "learning_rate": 9.96505199434725e-06,
+      "loss": 0.6108,
+      "step": 44
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 2.8031914234161377,
+      "learning_rate": 9.961066205523917e-06,
+      "loss": 0.6465,
+      "step": 45
+    },
+    {
+      "epoch": 0.18253968253968253,
+      "grad_norm": 2.8012661933898926,
+      "learning_rate": 9.956866119049095e-06,
+      "loss": 0.6535,
+      "step": 46
+    },
+    {
+      "epoch": 0.1865079365079365,
+      "grad_norm": 2.715590715408325,
+      "learning_rate": 9.952451916349242e-06,
+      "loss": 0.5868,
+      "step": 47
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 2.4733760356903076,
+      "learning_rate": 9.947823788099754e-06,
+      "loss": 0.5289,
+      "step": 48
+    },
+    {
+      "epoch": 0.19444444444444445,
+      "grad_norm": 2.615929126739502,
+      "learning_rate": 9.942981934216731e-06,
+      "loss": 0.5471,
+      "step": 49
+    },
+    {
+      "epoch": 0.1984126984126984,
+      "grad_norm": 3.093095302581787,
+      "learning_rate": 9.937926563848345e-06,
+      "loss": 0.5972,
+      "step": 50
+    },
+    {
+      "epoch": 0.20238095238095238,
+      "grad_norm": 2.6352145671844482,
+      "learning_rate": 9.9326578953658e-06,
+      "loss": 0.4981,
+      "step": 51
+    },
+    {
+      "epoch": 0.20634920634920634,
+      "grad_norm": 2.5553276538848877,
+      "learning_rate": 9.9271761563539e-06,
+      "loss": 0.4797,
+      "step": 52
+    },
+    {
+      "epoch": 0.21031746031746032,
+      "grad_norm": 2.4648044109344482,
+      "learning_rate": 9.921481583601218e-06,
+      "loss": 0.5402,
+      "step": 53
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 2.549119472503662,
+      "learning_rate": 9.915574423089872e-06,
+      "loss": 0.4704,
+      "step": 54
+    },
+    {
+      "epoch": 0.21825396825396826,
+      "grad_norm": 2.5682594776153564,
+      "learning_rate": 9.909454929984894e-06,
+      "loss": 0.4773,
+      "step": 55
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 2.702852487564087,
+      "learning_rate": 9.903123368623216e-06,
+      "loss": 0.457,
+      "step": 56
+    },
+    {
+      "epoch": 0.2261904761904762,
+      "grad_norm": 2.838491916656494,
+      "learning_rate": 9.896580012502238e-06,
+      "loss": 0.5493,
+      "step": 57
+    },
+    {
+      "epoch": 0.23015873015873015,
+      "grad_norm": 2.9078750610351562,
+      "learning_rate": 9.889825144268029e-06,
+      "loss": 0.4775,
+      "step": 58
+    },
+    {
+      "epoch": 0.23412698412698413,
+      "grad_norm": 2.8761308193206787,
+      "learning_rate": 9.882859055703109e-06,
+      "loss": 0.457,
+      "step": 59
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 2.8357808589935303,
+      "learning_rate": 9.875682047713847e-06,
+      "loss": 0.4793,
+      "step": 60
+    },
+    {
+      "epoch": 0.24206349206349206,
+      "grad_norm": 3.1367876529693604,
+      "learning_rate": 9.868294430317464e-06,
+      "loss": 0.5198,
+      "step": 61
+    },
+    {
+      "epoch": 0.24603174603174602,
+      "grad_norm": 3.1271591186523438,
+      "learning_rate": 9.860696522628638e-06,
+      "loss": 0.5188,
+      "step": 62
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.2067031860351562,
+      "learning_rate": 9.852888652845729e-06,
+      "loss": 0.5269,
+      "step": 63
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 3.4634389877319336,
+      "learning_rate": 9.84487115823659e-06,
+      "loss": 0.5052,
+      "step": 64
+    },
+    {
+      "epoch": 0.25793650793650796,
+      "grad_norm": 3.568326711654663,
+      "learning_rate": 9.836644385124006e-06,
+      "loss": 0.4946,
+      "step": 65
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 3.6015052795410156,
+      "learning_rate": 9.828208688870736e-06,
+      "loss": 0.5278,
+      "step": 66
+    },
+    {
+      "epoch": 0.26587301587301587,
+      "grad_norm": 3.848020553588867,
+      "learning_rate": 9.81956443386415e-06,
+      "loss": 0.5644,
+      "step": 67
+    },
+    {
+      "epoch": 0.2698412698412698,
+      "grad_norm": 3.9349775314331055,
+      "learning_rate": 9.810711993500506e-06,
+      "loss": 0.4741,
+      "step": 68
+    },
+    {
+      "epoch": 0.27380952380952384,
+      "grad_norm": 4.226278305053711,
+      "learning_rate": 9.801651750168815e-06,
+      "loss": 0.4848,
+      "step": 69
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 4.300480365753174,
+      "learning_rate": 9.792384095234312e-06,
+      "loss": 0.4714,
+      "step": 70
+    },
+    {
+      "epoch": 0.28174603174603174,
+      "grad_norm": 4.545813083648682,
+      "learning_rate": 9.782909429021568e-06,
+      "loss": 0.4671,
+      "step": 71
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 3.9301016330718994,
+      "learning_rate": 9.773228160797187e-06,
+      "loss": 0.4722,
+      "step": 72
+    },
+    {
+      "epoch": 0.2896825396825397,
+      "grad_norm": 3.616159439086914,
+      "learning_rate": 9.76334070875213e-06,
+      "loss": 0.4701,
+      "step": 73
+    },
+    {
+      "epoch": 0.29365079365079366,
+      "grad_norm": 3.7994768619537354,
+      "learning_rate": 9.753247499983649e-06,
+      "loss": 0.4218,
+      "step": 74
+    },
+    {
+      "epoch": 0.2976190476190476,
+      "grad_norm": 4.179572105407715,
+      "learning_rate": 9.742948970476845e-06,
+      "loss": 0.4193,
+      "step": 75
+    },
+    {
+      "epoch": 0.30158730158730157,
+      "grad_norm": 3.17275071144104,
+      "learning_rate": 9.732445565085823e-06,
+      "loss": 0.3507,
+      "step": 76
+    },
+    {
+      "epoch": 0.3055555555555556,
+      "grad_norm": 3.49688720703125,
+      "learning_rate": 9.721737737514492e-06,
+      "loss": 0.3275,
+      "step": 77
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 3.5590732097625732,
+      "learning_rate": 9.71082595029695e-06,
+      "loss": 0.3758,
+      "step": 78
+    },
+    {
+      "epoch": 0.3134920634920635,
+      "grad_norm": 3.6648528575897217,
+      "learning_rate": 9.699710674777519e-06,
+      "loss": 0.3371,
+      "step": 79
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 3.7211573123931885,
+      "learning_rate": 9.688392391090374e-06,
+      "loss": 0.3903,
+      "step": 80
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 3.65028715133667,
+      "learning_rate": 9.676871588138812e-06,
+      "loss": 0.3434,
+      "step": 81
+    },
+    {
+      "epoch": 0.3253968253968254,
+      "grad_norm": 3.7291440963745117,
+      "learning_rate": 9.665148763574123e-06,
+      "loss": 0.3484,
+      "step": 82
+    },
+    {
+      "epoch": 0.32936507936507936,
+      "grad_norm": 3.76412296295166,
+      "learning_rate": 9.653224423774107e-06,
+      "loss": 0.3287,
+      "step": 83
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.787276029586792,
+      "learning_rate": 9.64109908382119e-06,
+      "loss": 0.3141,
+      "step": 84
+    },
+    {
+      "epoch": 0.3373015873015873,
+      "grad_norm": 3.8091228008270264,
+      "learning_rate": 9.628773267480177e-06,
+      "loss": 0.3818,
+      "step": 85
+    },
+    {
+      "epoch": 0.3412698412698413,
+      "grad_norm": 3.8210535049438477,
+      "learning_rate": 9.616247507175624e-06,
+      "loss": 0.3543,
+      "step": 86
+    },
+    {
+      "epoch": 0.34523809523809523,
+      "grad_norm": 3.869622230529785,
+      "learning_rate": 9.603522343968852e-06,
+      "loss": 0.3727,
+      "step": 87
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 3.8349802494049072,
+      "learning_rate": 9.590598327534563e-06,
+      "loss": 0.3453,
+      "step": 88
+    },
+    {
+      "epoch": 0.3531746031746032,
+      "grad_norm": 3.91221022605896,
+      "learning_rate": 9.577476016137105e-06,
+      "loss": 0.3196,
+      "step": 89
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 3.895413398742676,
+      "learning_rate": 9.56415597660634e-06,
+      "loss": 0.3514,
+      "step": 90
+    },
+    {
+      "epoch": 0.3611111111111111,
+      "grad_norm": 4.032989501953125,
+      "learning_rate": 9.550638784313187e-06,
+      "loss": 0.3396,
+      "step": 91
+    },
+    {
+      "epoch": 0.36507936507936506,
+      "grad_norm": 4.055191516876221,
+      "learning_rate": 9.536925023144742e-06,
+      "loss": 0.3044,
+      "step": 92
+    },
+    {
+      "epoch": 0.36904761904761907,
+      "grad_norm": 4.113070487976074,
+      "learning_rate": 9.523015285479076e-06,
+      "loss": 0.3536,
+      "step": 93
+    },
+    {
+      "epoch": 0.373015873015873,
+      "grad_norm": 4.107305526733398,
+      "learning_rate": 9.508910172159635e-06,
+      "loss": 0.3166,
+      "step": 94
+    },
+    {
+      "epoch": 0.376984126984127,
+      "grad_norm": 3.969236135482788,
+      "learning_rate": 9.494610292469287e-06,
+      "loss": 0.3001,
+      "step": 95
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 4.075791358947754,
+      "learning_rate": 9.48011626410401e-06,
+      "loss": 0.3347,
+      "step": 96
+    },
+    {
+      "epoch": 0.38492063492063494,
+      "grad_norm": 3.4200732707977295,
+      "learning_rate": 9.465428713146206e-06,
+      "loss": 0.3097,
+      "step": 97
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 3.148775339126587,
+      "learning_rate": 9.450548274037652e-06,
+      "loss": 0.3032,
+      "step": 98
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 3.1194303035736084,
+      "learning_rate": 9.435475589552107e-06,
+      "loss": 0.2867,
+      "step": 99
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 3.5353922843933105,
+      "learning_rate": 9.420211310767534e-06,
+      "loss": 0.3074,
+      "step": 100
+    },
+    {
+      "epoch": 0.4007936507936508,
+      "grad_norm": 2.467332363128662,
+      "learning_rate": 9.40475609703798e-06,
+      "loss": 0.2468,
+      "step": 101
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 2.804072141647339,
+      "learning_rate": 9.389110615965102e-06,
+      "loss": 0.2623,
+      "step": 102
+    },
+    {
+      "epoch": 0.4087301587301587,
+      "grad_norm": 2.6840615272521973,
+      "learning_rate": 9.37327554336932e-06,
+      "loss": 0.1996,
+      "step": 103
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 2.739384412765503,
+      "learning_rate": 9.35725156326063e-06,
+      "loss": 0.2387,
+      "step": 104
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 2.587768316268921,
+      "learning_rate": 9.341039367809056e-06,
+      "loss": 0.2555,
+      "step": 105
+    },
+    {
+      "epoch": 0.42063492063492064,
+      "grad_norm": 2.5864408016204834,
+      "learning_rate": 9.324639657314742e-06,
+      "loss": 0.2634,
+      "step": 106
+    },
+    {
+      "epoch": 0.4246031746031746,
+      "grad_norm": 2.4532299041748047,
+      "learning_rate": 9.308053140177722e-06,
+      "loss": 0.2237,
+      "step": 107
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 2.4923110008239746,
+      "learning_rate": 9.291280532867301e-06,
+      "loss": 0.2183,
+      "step": 108
+    },
+    {
+      "epoch": 0.43253968253968256,
+      "grad_norm": 2.3666458129882812,
+      "learning_rate": 9.27432255989112e-06,
+      "loss": 0.2509,
+      "step": 109
+    },
+    {
+      "epoch": 0.4365079365079365,
+      "grad_norm": 2.2944254875183105,
+      "learning_rate": 9.257179953763846e-06,
+      "loss": 0.2376,
+      "step": 110
+    },
+    {
+      "epoch": 0.44047619047619047,
+      "grad_norm": 2.174125909805298,
+      "learning_rate": 9.239853454975548e-06,
+      "loss": 0.2304,
+      "step": 111
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.0383496284484863,
+      "learning_rate": 9.222343811959694e-06,
+      "loss": 0.2482,
+      "step": 112
+    },
+    {
+      "epoch": 0.44841269841269843,
+      "grad_norm": 2.0460424423217773,
+      "learning_rate": 9.204651781060832e-06,
+      "loss": 0.1998,
+      "step": 113
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 1.945266842842102,
+      "learning_rate": 9.186778126501916e-06,
+      "loss": 0.2179,
+      "step": 114
+    },
+    {
+      "epoch": 0.45634920634920634,
+      "grad_norm": 1.8012604713439941,
+      "learning_rate": 9.168723620351298e-06,
+      "loss": 0.2255,
+      "step": 115
+    },
+    {
+      "epoch": 0.4603174603174603,
+      "grad_norm": 1.6935973167419434,
+      "learning_rate": 9.150489042489368e-06,
+      "loss": 0.1993,
+      "step": 116
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 1.698236346244812,
+      "learning_rate": 9.13207518057488e-06,
+      "loss": 0.229,
+      "step": 117
+    },
+    {
+      "epoch": 0.46825396825396826,
+      "grad_norm": 1.4979168176651,
+      "learning_rate": 9.113482830010918e-06,
+      "loss": 0.1925,
+      "step": 118
+    },
+    {
+      "epoch": 0.4722222222222222,
+      "grad_norm": 1.5552384853363037,
+      "learning_rate": 9.094712793910541e-06,
+      "loss": 0.2142,
+      "step": 119
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.4717791080474854,
+      "learning_rate": 9.075765883062093e-06,
+      "loss": 0.2088,
+      "step": 120
+    },
+    {
+      "epoch": 0.4801587301587302,
+      "grad_norm": 1.4267648458480835,
+      "learning_rate": 9.056642915894182e-06,
+      "loss": 0.207,
+      "step": 121
+    },
+    {
+      "epoch": 0.48412698412698413,
+      "grad_norm": 1.3177474737167358,
+      "learning_rate": 9.037344718440321e-06,
+      "loss": 0.2254,
+      "step": 122
+    },
+    {
+      "epoch": 0.4880952380952381,
+      "grad_norm": 1.243403673171997,
+      "learning_rate": 9.017872124303255e-06,
+      "loss": 0.2271,
+      "step": 123
+    },
+    {
+      "epoch": 0.49206349206349204,
+      "grad_norm": 1.3508583307266235,
+      "learning_rate": 8.99822597461894e-06,
+      "loss": 0.183,
+      "step": 124
+    },
+    {
+      "epoch": 0.49603174603174605,
+      "grad_norm": 1.3412503004074097,
+      "learning_rate": 8.978407118020226e-06,
+      "loss": 0.1905,
+      "step": 125
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.2498844861984253,
+      "learning_rate": 8.958416410600188e-06,
+      "loss": 0.2132,
+      "step": 126
+    },
+    {
+      "epoch": 0.503968253968254,
+      "grad_norm": 1.0604239702224731,
+      "learning_rate": 8.938254715875152e-06,
+      "loss": 0.1791,
+      "step": 127
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.0373965501785278,
+      "learning_rate": 8.917922904747385e-06,
+      "loss": 0.1659,
+      "step": 128
+    },
+    {
+      "epoch": 0.5119047619047619,
+      "grad_norm": 1.2815697193145752,
+      "learning_rate": 8.897421855467491e-06,
+      "loss": 0.2173,
+      "step": 129
+    },
+    {
+      "epoch": 0.5158730158730159,
+      "grad_norm": 1.3789927959442139,
+      "learning_rate": 8.876752453596462e-06,
+      "loss": 0.2577,
+      "step": 130
+    },
+    {
+      "epoch": 0.5198412698412699,
+      "grad_norm": 1.2774096727371216,
+      "learning_rate": 8.85591559196743e-06,
+      "loss": 0.2371,
+      "step": 131
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 1.1230323314666748,
+      "learning_rate": 8.834912170647102e-06,
+      "loss": 0.2083,
+      "step": 132
+    },
+    {
+      "epoch": 0.5277777777777778,
+      "grad_norm": 1.0352874994277954,
+      "learning_rate": 8.813743096896872e-06,
+      "loss": 0.1897,
+      "step": 133
+    },
+    {
+      "epoch": 0.5317460317460317,
+      "grad_norm": 1.0328984260559082,
+      "learning_rate": 8.792409285133644e-06,
+      "loss": 0.1948,
+      "step": 134
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 1.0041017532348633,
+      "learning_rate": 8.770911656890325e-06,
+      "loss": 0.2194,
+      "step": 135
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.1615849733352661,
+      "learning_rate": 8.749251140776016e-06,
+      "loss": 0.2055,
+      "step": 136
+    },
+    {
+      "epoch": 0.5436507936507936,
+      "grad_norm": 1.0535426139831543,
+      "learning_rate": 8.727428672435911e-06,
+      "loss": 0.2035,
+      "step": 137
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 1.1168123483657837,
+      "learning_rate": 8.705445194510868e-06,
+      "loss": 0.1957,
+      "step": 138
+    },
+    {
+      "epoch": 0.5515873015873016,
+      "grad_norm": 1.1942194700241089,
+      "learning_rate": 8.6833016565967e-06,
+      "loss": 0.2302,
+      "step": 139
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.1593937873840332,
+      "learning_rate": 8.660999015203152e-06,
+      "loss": 0.1917,
+      "step": 140
+    },
+    {
+      "epoch": 0.5595238095238095,
+      "grad_norm": 1.19351065158844,
+      "learning_rate": 8.638538233712581e-06,
+      "loss": 0.2032,
+      "step": 141
+    },
+    {
+      "epoch": 0.5634920634920635,
+      "grad_norm": 1.2246677875518799,
+      "learning_rate": 8.615920282338355e-06,
+      "loss": 0.2091,
+      "step": 142
+    },
+    {
+      "epoch": 0.5674603174603174,
+      "grad_norm": 1.3597017526626587,
+      "learning_rate": 8.593146138082925e-06,
+      "loss": 0.2555,
+      "step": 143
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.2056429386138916,
+      "learning_rate": 8.570216784695637e-06,
+      "loss": 0.1968,
+      "step": 144
+    },
+    {
+      "epoch": 0.5753968253968254,
+      "grad_norm": 1.2337775230407715,
+      "learning_rate": 8.54713321263023e-06,
+      "loss": 0.1903,
+      "step": 145
+    },
+    {
+      "epoch": 0.5793650793650794,
+      "grad_norm": 1.2018787860870361,
+      "learning_rate": 8.52389641900206e-06,
+      "loss": 0.1913,
+      "step": 146
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 1.3740088939666748,
+      "learning_rate": 8.50050740754502e-06,
+      "loss": 0.2399,
+      "step": 147
+    },
+    {
+      "epoch": 0.5873015873015873,
+      "grad_norm": 1.295432209968567,
+      "learning_rate": 8.476967188568187e-06,
+      "loss": 0.1896,
+      "step": 148
+    },
+    {
+      "epoch": 0.5912698412698413,
+      "grad_norm": 1.19464910030365,
+      "learning_rate": 8.453276778912186e-06,
+      "loss": 0.2082,
+      "step": 149
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 1.139990210533142,
+      "learning_rate": 8.429437201905254e-06,
+      "loss": 0.1717,
+      "step": 150
+    },
+    {
+      "epoch": 0.5992063492063492,
+      "grad_norm": 1.0607414245605469,
+      "learning_rate": 8.405449487319049e-06,
+      "loss": 0.1722,
+      "step": 151
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.1491377353668213,
+      "learning_rate": 8.38131467132416e-06,
+      "loss": 0.1612,
+      "step": 152
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 1.1927894353866577,
+      "learning_rate": 8.357033796445356e-06,
+      "loss": 0.1813,
+      "step": 153
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 1.134826421737671,
+      "learning_rate": 8.332607911516545e-06,
+      "loss": 0.1515,
+      "step": 154
+    },
+    {
+      "epoch": 0.6150793650793651,
+      "grad_norm": 1.366958737373352,
+      "learning_rate": 8.308038071635475e-06,
+      "loss": 0.2749,
+      "step": 155
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 1.1841325759887695,
+      "learning_rate": 8.283325338118154e-06,
+      "loss": 0.1741,
+      "step": 156
+    },
+    {
+      "epoch": 0.623015873015873,
+      "grad_norm": 1.2794548273086548,
+      "learning_rate": 8.258470778453005e-06,
+      "loss": 0.2085,
+      "step": 157
+    },
+    {
+      "epoch": 0.626984126984127,
+      "grad_norm": 1.3475635051727295,
+      "learning_rate": 8.233475466254766e-06,
+      "loss": 0.1747,
+      "step": 158
+    },
+    {
+      "epoch": 0.6309523809523809,
+      "grad_norm": 1.4117634296417236,
+      "learning_rate": 8.208340481218094e-06,
+      "loss": 0.1848,
+      "step": 159
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 1.281284213066101,
+      "learning_rate": 8.183066909070946e-06,
+      "loss": 0.1632,
+      "step": 160
+    },
+    {
+      "epoch": 0.6388888888888888,
+      "grad_norm": 1.350193977355957,
+      "learning_rate": 8.15765584152767e-06,
+      "loss": 0.1752,
+      "step": 161
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 1.2969999313354492,
+      "learning_rate": 8.132108376241849e-06,
+      "loss": 0.1508,
+      "step": 162
+    },
+    {
+      "epoch": 0.6468253968253969,
+      "grad_norm": 1.3409817218780518,
+      "learning_rate": 8.106425616758886e-06,
+      "loss": 0.2002,
+      "step": 163
+    },
+    {
+      "epoch": 0.6507936507936508,
+      "grad_norm": 1.4258953332901,
+      "learning_rate": 8.08060867246834e-06,
+      "loss": 0.2164,
+      "step": 164
+    },
+    {
+      "epoch": 0.6547619047619048,
+      "grad_norm": 1.4764114618301392,
+      "learning_rate": 8.054658658555998e-06,
+      "loss": 0.2046,
+      "step": 165
+    },
+    {
+      "epoch": 0.6587301587301587,
+      "grad_norm": 1.3869717121124268,
+      "learning_rate": 8.028576695955711e-06,
+      "loss": 0.2042,
+      "step": 166
+    },
+    {
+      "epoch": 0.6626984126984127,
+      "grad_norm": 1.4131327867507935,
+      "learning_rate": 8.002363911300966e-06,
+      "loss": 0.1778,
+      "step": 167
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.467511534690857,
+      "learning_rate": 7.976021436876232e-06,
+      "loss": 0.1637,
+      "step": 168
+    },
+    {
+      "epoch": 0.6706349206349206,
+      "grad_norm": 1.5328935384750366,
+      "learning_rate": 7.949550410568033e-06,
+      "loss": 0.1737,
+      "step": 169
+    },
+    {
+      "epoch": 0.6746031746031746,
+      "grad_norm": 1.4699673652648926,
+      "learning_rate": 7.92295197581581e-06,
+      "loss": 0.1521,
+      "step": 170
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 1.5993800163269043,
+      "learning_rate": 7.89622728156253e-06,
+      "loss": 0.1663,
+      "step": 171
+    },
+    {
+      "epoch": 0.6825396825396826,
+      "grad_norm": 1.4890751838684082,
+      "learning_rate": 7.869377482205042e-06,
+      "loss": 0.2153,
+      "step": 172
+    },
+    {
+      "epoch": 0.6865079365079365,
+      "grad_norm": 1.1941518783569336,
+      "learning_rate": 7.842403737544226e-06,
+      "loss": 0.1638,
+      "step": 173
+    },
+    {
+      "epoch": 0.6904761904761905,
+      "grad_norm": 1.2471840381622314,
+      "learning_rate": 7.815307212734888e-06,
+      "loss": 0.1356,
+      "step": 174
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 1.277548909187317,
+      "learning_rate": 7.788089078235432e-06,
+      "loss": 0.1715,
+      "step": 175
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.2489705085754395,
+      "learning_rate": 7.7607505097573e-06,
+      "loss": 0.1787,
+      "step": 176
+    },
+    {
+      "epoch": 0.7023809523809523,
+      "grad_norm": 1.1460860967636108,
+      "learning_rate": 7.733292688214182e-06,
+      "loss": 0.1403,
+      "step": 177
+    },
+    {
+      "epoch": 0.7063492063492064,
+      "grad_norm": 1.1960135698318481,
+      "learning_rate": 7.705716799671019e-06,
+      "loss": 0.1723,
+      "step": 178
+    },
+    {
+      "epoch": 0.7103174603174603,
+      "grad_norm": 1.2745386362075806,
+      "learning_rate": 7.678024035292757e-06,
+      "loss": 0.1464,
+      "step": 179
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.1538077592849731,
+      "learning_rate": 7.650215591292888e-06,
+      "loss": 0.1363,
+      "step": 180
+    },
+    {
+      "epoch": 0.7182539682539683,
+      "grad_norm": 1.1868458986282349,
+      "learning_rate": 7.622292668881805e-06,
+      "loss": 0.1686,
+      "step": 181
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 1.137481451034546,
+      "learning_rate": 7.594256474214883e-06,
+      "loss": 0.1437,
+      "step": 182
+    },
+    {
+      "epoch": 0.7261904761904762,
+      "grad_norm": 1.206611156463623,
+      "learning_rate": 7.566108218340399e-06,
+      "loss": 0.1287,
+      "step": 183
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.2275463342666626,
+      "learning_rate": 7.537849117147212e-06,
+      "loss": 0.1682,
+      "step": 184
+    },
+    {
+      "epoch": 0.7341269841269841,
+      "grad_norm": 1.156783103942871,
+      "learning_rate": 7.509480391312243e-06,
+      "loss": 0.114,
+      "step": 185
+    },
+    {
+      "epoch": 0.7380952380952381,
+      "grad_norm": 1.312717318534851,
+      "learning_rate": 7.481003266247745e-06,
+      "loss": 0.1836,
+      "step": 186
+    },
+    {
+      "epoch": 0.7420634920634921,
+      "grad_norm": 1.3326442241668701,
+      "learning_rate": 7.452418972048372e-06,
+      "loss": 0.1698,
+      "step": 187
+    },
+    {
+      "epoch": 0.746031746031746,
+      "grad_norm": 1.1632299423217773,
+      "learning_rate": 7.4237287434380485e-06,
+      "loss": 0.1727,
+      "step": 188
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.304856777191162,
+      "learning_rate": 7.394933819716625e-06,
+      "loss": 0.1814,
+      "step": 189
+    },
+    {
+      "epoch": 0.753968253968254,
+      "grad_norm": 1.054636001586914,
+      "learning_rate": 7.366035444706346e-06,
+      "loss": 0.1315,
+      "step": 190
+    },
+    {
+      "epoch": 0.7579365079365079,
+      "grad_norm": 1.4124561548233032,
+      "learning_rate": 7.337034866698138e-06,
+      "loss": 0.1527,
+      "step": 191
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.2737467288970947,
+      "learning_rate": 7.307933338397667e-06,
+      "loss": 0.2051,
+      "step": 192
+    },
+    {
+      "epoch": 0.7658730158730159,
+      "grad_norm": 1.2019504308700562,
+      "learning_rate": 7.278732116871239e-06,
+      "loss": 0.1599,
+      "step": 193
+    },
+    {
+      "epoch": 0.7698412698412699,
+      "grad_norm": 1.1740680932998657,
+      "learning_rate": 7.249432463491498e-06,
+      "loss": 0.1309,
+      "step": 194
+    },
+    {
+      "epoch": 0.7738095238095238,
+      "grad_norm": 1.3344628810882568,
+      "learning_rate": 7.220035643882938e-06,
+      "loss": 0.1452,
+      "step": 195
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 1.1748477220535278,
+      "learning_rate": 7.190542927867234e-06,
+      "loss": 0.1264,
+      "step": 196
+    },
+    {
+      "epoch": 0.7817460317460317,
+      "grad_norm": 1.344280481338501,
+      "learning_rate": 7.160955589408395e-06,
+      "loss": 0.2139,
+      "step": 197
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 1.1319468021392822,
+      "learning_rate": 7.131274906557725e-06,
+      "loss": 0.1705,
+      "step": 198
+    },
+    {
+      "epoch": 0.7896825396825397,
+      "grad_norm": 1.0703827142715454,
+      "learning_rate": 7.101502161398626e-06,
+      "loss": 0.139,
+      "step": 199
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.0375055074691772,
+      "learning_rate": 7.0716386399912075e-06,
+      "loss": 0.1329,
+      "step": 200
+    },
+    {
+      "epoch": 0.7976190476190477,
+      "grad_norm": 1.0811136960983276,
+      "learning_rate": 7.041685632316748e-06,
+      "loss": 0.1423,
+      "step": 201
+    },
+    {
+      "epoch": 0.8015873015873016,
+      "grad_norm": 0.9610537886619568,
+      "learning_rate": 7.0116444322219575e-06,
+      "loss": 0.1137,
+      "step": 202
+    },
+    {
+      "epoch": 0.8055555555555556,
+      "grad_norm": 1.199352741241455,
+      "learning_rate": 6.981516337363099e-06,
+      "loss": 0.1073,
+      "step": 203
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.952040433883667,
+      "learning_rate": 6.95130264914993e-06,
+      "loss": 0.123,
+      "step": 204
+    },
+    {
+      "epoch": 0.8134920634920635,
+      "grad_norm": 0.9396257400512695,
+      "learning_rate": 6.9210046726894885e-06,
+      "loss": 0.1092,
+      "step": 205
+    },
+    {
+      "epoch": 0.8174603174603174,
+      "grad_norm": 1.0251622200012207,
+      "learning_rate": 6.890623716729724e-06,
+      "loss": 0.1484,
+      "step": 206
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 1.2053864002227783,
+      "learning_rate": 6.860161093602949e-06,
+      "loss": 0.1455,
+      "step": 207
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 0.9859071373939514,
+      "learning_rate": 6.829618119169169e-06,
+      "loss": 0.1455,
+      "step": 208
+    },
+    {
+      "epoch": 0.8293650793650794,
+      "grad_norm": 1.0955175161361694,
+      "learning_rate": 6.798996112759233e-06,
+      "loss": 0.1515,
+      "step": 209
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.956035315990448,
+      "learning_rate": 6.768296397117848e-06,
+      "loss": 0.1657,
+      "step": 210
+    },
+    {
+      "epoch": 0.8373015873015873,
+      "grad_norm": 1.0417743921279907,
+      "learning_rate": 6.737520298346438e-06,
+      "loss": 0.1245,
+      "step": 211
+    },
+    {
+      "epoch": 0.8412698412698413,
+      "grad_norm": 0.9253073930740356,
+      "learning_rate": 6.706669145845863e-06,
+      "loss": 0.1117,
+      "step": 212
+    },
+    {
+      "epoch": 0.8452380952380952,
+      "grad_norm": 1.183728814125061,
+      "learning_rate": 6.6757442722590015e-06,
+      "loss": 0.1802,
+      "step": 213
+    },
+    {
+      "epoch": 0.8492063492063492,
+      "grad_norm": 1.0416171550750732,
+      "learning_rate": 6.6447470134131685e-06,
+      "loss": 0.1274,
+      "step": 214
+    },
+    {
+      "epoch": 0.8531746031746031,
+      "grad_norm": 0.9164001941680908,
+      "learning_rate": 6.613678708262439e-06,
+      "loss": 0.1032,
+      "step": 215
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.1456245183944702,
+      "learning_rate": 6.5825406988297815e-06,
+      "loss": 0.1471,
+      "step": 216
+    },
+    {
+      "epoch": 0.8611111111111112,
+      "grad_norm": 1.0662381649017334,
+      "learning_rate": 6.551334330149114e-06,
+      "loss": 0.1478,
+      "step": 217
+    },
+    {
+      "epoch": 0.8650793650793651,
+      "grad_norm": 0.9697524905204773,
+      "learning_rate": 6.520060950207186e-06,
+      "loss": 0.1473,
+      "step": 218
+    },
+    {
+      "epoch": 0.8690476190476191,
+      "grad_norm": 1.0304609537124634,
+      "learning_rate": 6.488721909885359e-06,
+      "loss": 0.1768,
+      "step": 219
+    },
+    {
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.8136041164398193,
+      "learning_rate": 6.457318562901257e-06,
+      "loss": 0.097,
+      "step": 220
+    },
+    {
+      "epoch": 0.876984126984127,
+      "grad_norm": 1.09493088722229,
+      "learning_rate": 6.425852265750282e-06,
+      "loss": 0.1575,
+      "step": 221
+    },
+    {
+      "epoch": 0.8809523809523809,
+      "grad_norm": 1.1294385194778442,
+      "learning_rate": 6.394324377647028e-06,
+      "loss": 0.161,
+      "step": 222
+    },
+    {
+      "epoch": 0.8849206349206349,
+      "grad_norm": 1.1903278827667236,
+      "learning_rate": 6.362736260466561e-06,
+      "loss": 0.1358,
+      "step": 223
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.0960198640823364,
+      "learning_rate": 6.331089278685599e-06,
+      "loss": 0.1835,
+      "step": 224
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 1.0908770561218262,
+      "learning_rate": 6.299384799323568e-06,
+      "loss": 0.1171,
+      "step": 225
+    },
+    {
+      "epoch": 0.8968253968253969,
+      "grad_norm": 0.971628725528717,
+      "learning_rate": 6.267624191883551e-06,
+      "loss": 0.1335,
+      "step": 226
+    },
+    {
+      "epoch": 0.9007936507936508,
+      "grad_norm": 0.8757287263870239,
+      "learning_rate": 6.235808828293135e-06,
+      "loss": 0.1229,
+      "step": 227
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.989013135433197,
+      "learning_rate": 6.203940082845144e-06,
+      "loss": 0.1633,
+      "step": 228
+    },
+    {
+      "epoch": 0.9087301587301587,
+      "grad_norm": 0.7591527104377747,
+      "learning_rate": 6.172019332138285e-06,
+      "loss": 0.1041,
+      "step": 229
+    },
+    {
+      "epoch": 0.9126984126984127,
+      "grad_norm": 0.8997424244880676,
+      "learning_rate": 6.140047955017672e-06,
+      "loss": 0.1541,
+      "step": 230
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.7937338352203369,
+      "learning_rate": 6.108027332515276e-06,
+      "loss": 0.0954,
+      "step": 231
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 0.9379100203514099,
+      "learning_rate": 6.075958847790262e-06,
+      "loss": 0.1284,
+      "step": 232
+    },
+    {
+      "epoch": 0.9246031746031746,
+      "grad_norm": 0.8153742551803589,
+      "learning_rate": 6.043843886069251e-06,
+      "loss": 0.119,
+      "step": 233
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.9349873661994934,
+      "learning_rate": 6.011683834586474e-06,
+      "loss": 0.1286,
+      "step": 234
+    },
+    {
+      "epoch": 0.9325396825396826,
+      "grad_norm": 0.9875138998031616,
+      "learning_rate": 5.979480082523858e-06,
+      "loss": 0.1601,
+      "step": 235
+    },
+    {
+      "epoch": 0.9365079365079365,
+      "grad_norm": 0.9074680209159851,
+      "learning_rate": 5.947234020951015e-06,
+      "loss": 0.133,
+      "step": 236
+    },
+    {
+      "epoch": 0.9404761904761905,
+      "grad_norm": 0.9646974802017212,
+      "learning_rate": 5.914947042765149e-06,
+      "loss": 0.1515,
+      "step": 237
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 0.9159960746765137,
+      "learning_rate": 5.882620542630901e-06,
+      "loss": 0.1399,
+      "step": 238
+    },
+    {
+      "epoch": 0.9484126984126984,
+      "grad_norm": 0.9413661956787109,
+      "learning_rate": 5.850255916920093e-06,
+      "loss": 0.1329,
+      "step": 239
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.8890795707702637,
+      "learning_rate": 5.817854563651415e-06,
+      "loss": 0.1414,
+      "step": 240
+    },
+    {
+      "epoch": 0.9563492063492064,
+      "grad_norm": 0.9007329940795898,
+      "learning_rate": 5.785417882430035e-06,
+      "loss": 0.1165,
+      "step": 241
+    },
+    {
+      "epoch": 0.9603174603174603,
+      "grad_norm": 1.0007832050323486,
+      "learning_rate": 5.752947274387147e-06,
+      "loss": 0.131,
+      "step": 242
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.8886591196060181,
+      "learning_rate": 5.720444142119445e-06,
+      "loss": 0.1492,
+      "step": 243
+    },
+    {
+      "epoch": 0.9682539682539683,
+      "grad_norm": 0.8927666544914246,
+      "learning_rate": 5.687909889628529e-06,
+      "loss": 0.1153,
+      "step": 244
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.9265084862709045,
+      "learning_rate": 5.6553459222602714e-06,
+      "loss": 0.1504,
+      "step": 245
+    },
+    {
+      "epoch": 0.9761904761904762,
+      "grad_norm": 0.8157972693443298,
+      "learning_rate": 5.622753646644102e-06,
+      "loss": 0.0995,
+      "step": 246
+    },
+    {
+      "epoch": 0.9801587301587301,
+      "grad_norm": 0.9079906344413757,
+      "learning_rate": 5.59013447063225e-06,
+      "loss": 0.1582,
+      "step": 247
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 0.9579424858093262,
+      "learning_rate": 5.557489803238934e-06,
+      "loss": 0.1196,
+      "step": 248
+    },
+    {
+      "epoch": 0.9880952380952381,
+      "grad_norm": 0.8123847842216492,
+      "learning_rate": 5.524821054579491e-06,
+      "loss": 0.1295,
+      "step": 249
+    },
+    {
+      "epoch": 0.9920634920634921,
+      "grad_norm": 0.8786181807518005,
+      "learning_rate": 5.492129635809473e-06,
+      "loss": 0.1142,
+      "step": 250
+    },
+    {
+      "epoch": 0.996031746031746,
+      "grad_norm": 0.9151430130004883,
+      "learning_rate": 5.459416959063688e-06,
+      "loss": 0.1337,
+      "step": 251
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9185081720352173,
+      "learning_rate": 5.426684437395196e-06,
+      "loss": 0.171,
+      "step": 252
+    },
+    {
+      "epoch": 1.003968253968254,
+      "grad_norm": 0.8412165641784668,
+      "learning_rate": 5.393933484714284e-06,
+      "loss": 0.1082,
+      "step": 253
+    },
+    {
+      "epoch": 1.007936507936508,
+      "grad_norm": 0.8413107991218567,
+      "learning_rate": 5.361165515727374e-06,
+      "loss": 0.1153,
+      "step": 254
+    },
+    {
+      "epoch": 1.0119047619047619,
+      "grad_norm": 0.8458530902862549,
+      "learning_rate": 5.328381945875933e-06,
+      "loss": 0.123,
+      "step": 255
+    },
+    {
+      "epoch": 1.0158730158730158,
+      "grad_norm": 0.9277226328849792,
+      "learning_rate": 5.295584191275308e-06,
+      "loss": 0.121,
+      "step": 256
+    },
+    {
+      "epoch": 1.0198412698412698,
+      "grad_norm": 0.9794259667396545,
+      "learning_rate": 5.26277366865358e-06,
+      "loss": 0.1504,
+      "step": 257
+    },
+    {
+      "epoch": 1.0238095238095237,
+      "grad_norm": 0.8696649670600891,
+      "learning_rate": 5.229951795290353e-06,
+      "loss": 0.1193,
+      "step": 258
+    },
+    {
+      "epoch": 1.0277777777777777,
+      "grad_norm": 0.7507579326629639,
+      "learning_rate": 5.197119988955534e-06,
+      "loss": 0.08,
+      "step": 259
+    },
+    {
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.74959397315979,
+      "learning_rate": 5.164279667848094e-06,
+      "loss": 0.0953,
+      "step": 260
+    },
+    {
+      "epoch": 1.0357142857142858,
+      "grad_norm": 0.7617223262786865,
+      "learning_rate": 5.131432250534809e-06,
+      "loss": 0.0734,
+      "step": 261
+    },
+    {
+      "epoch": 1.0396825396825398,
+      "grad_norm": 0.9482263922691345,
+      "learning_rate": 5.0985791558889785e-06,
+      "loss": 0.1184,
+      "step": 262
+    },
+    {
+      "epoch": 1.0436507936507937,
+      "grad_norm": 0.9822360277175903,
+      "learning_rate": 5.065721803029146e-06,
+      "loss": 0.1303,
+      "step": 263
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.8670525550842285,
+      "learning_rate": 5.032861611257783e-06,
+      "loss": 0.0961,
+      "step": 264
+    },
+    {
+      "epoch": 1.0515873015873016,
+      "grad_norm": 0.9051881432533264,
+      "learning_rate": 5e-06,
+      "loss": 0.1017,
+      "step": 265
+    },
+    {
+      "epoch": 1.0555555555555556,
+      "grad_norm": 0.9463195204734802,
+      "learning_rate": 4.967138388742218e-06,
+      "loss": 0.1128,
+      "step": 266
+    },
+    {
+      "epoch": 1.0595238095238095,
+      "grad_norm": 0.837642252445221,
+      "learning_rate": 4.934278196970857e-06,
+      "loss": 0.1014,
+      "step": 267
+    },
+    {
+      "epoch": 1.0634920634920635,
+      "grad_norm": 0.9752260446548462,
+      "learning_rate": 4.9014208441110215e-06,
+      "loss": 0.132,
+      "step": 268
+    },
+    {
+      "epoch": 1.0674603174603174,
+      "grad_norm": 0.7861972451210022,
+      "learning_rate": 4.868567749465192e-06,
+      "loss": 0.0865,
+      "step": 269
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.7748413681983948,
+      "learning_rate": 4.835720332151907e-06,
+      "loss": 0.0887,
+      "step": 270
+    },
+    {
+      "epoch": 1.0753968253968254,
+      "grad_norm": 0.769105076789856,
+      "learning_rate": 4.802880011044467e-06,
+      "loss": 0.0913,
+      "step": 271
+    },
+    {
+      "epoch": 1.0793650793650793,
+      "grad_norm": 0.801043689250946,
+      "learning_rate": 4.770048204709648e-06,
+      "loss": 0.0862,
+      "step": 272
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.8220937252044678,
+      "learning_rate": 4.73722633134642e-06,
+      "loss": 0.0845,
+      "step": 273
+    },
+    {
+      "epoch": 1.0873015873015872,
+      "grad_norm": 0.8764519095420837,
+      "learning_rate": 4.7044158087246926e-06,
+      "loss": 0.1076,
+      "step": 274
+    },
+    {
+      "epoch": 1.0912698412698412,
+      "grad_norm": 0.8750497102737427,
+      "learning_rate": 4.67161805412407e-06,
+      "loss": 0.1001,
+      "step": 275
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 0.8208699226379395,
+      "learning_rate": 4.6388344842726266e-06,
+      "loss": 0.0887,
+      "step": 276
+    },
+    {
+      "epoch": 1.0992063492063493,
+      "grad_norm": 0.7672670483589172,
+      "learning_rate": 4.606066515285719e-06,
+      "loss": 0.1031,
+      "step": 277
+    },
+    {
+      "epoch": 1.1031746031746033,
+      "grad_norm": 0.7054154872894287,
+      "learning_rate": 4.573315562604804e-06,
+      "loss": 0.0852,
+      "step": 278
+    },
+    {
+      "epoch": 1.1071428571428572,
+      "grad_norm": 0.8251184821128845,
+      "learning_rate": 4.540583040936313e-06,
+      "loss": 0.0944,
+      "step": 279
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.7829627990722656,
+      "learning_rate": 4.5078703641905275e-06,
+      "loss": 0.0807,
+      "step": 280
+    },
+    {
+      "epoch": 1.1150793650793651,
+      "grad_norm": 0.7606924772262573,
+      "learning_rate": 4.4751789454205105e-06,
+      "loss": 0.0866,
+      "step": 281
+    },
+    {
+      "epoch": 1.119047619047619,
+      "grad_norm": 0.8723813891410828,
+      "learning_rate": 4.442510196761068e-06,
+      "loss": 0.0936,
+      "step": 282
+    },
+    {
+      "epoch": 1.123015873015873,
+      "grad_norm": 0.7986534833908081,
+      "learning_rate": 4.409865529367751e-06,
+      "loss": 0.0856,
+      "step": 283
+    },
+    {
+      "epoch": 1.126984126984127,
+      "grad_norm": 0.78840571641922,
+      "learning_rate": 4.377246353355899e-06,
+      "loss": 0.0824,
+      "step": 284
+    },
+    {
+      "epoch": 1.130952380952381,
+      "grad_norm": 0.8160957098007202,
+      "learning_rate": 4.34465407773973e-06,
+      "loss": 0.0844,
+      "step": 285
+    },
+    {
+      "epoch": 1.1349206349206349,
+      "grad_norm": 0.8608824014663696,
+      "learning_rate": 4.312090110371473e-06,
+      "loss": 0.1139,
+      "step": 286
+    },
+    {
+      "epoch": 1.1388888888888888,
+      "grad_norm": 0.8378157019615173,
+      "learning_rate": 4.279555857880558e-06,
+      "loss": 0.0813,
+      "step": 287
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.8858137130737305,
+      "learning_rate": 4.247052725612853e-06,
+      "loss": 0.0903,
+      "step": 288
+    },
+    {
+      "epoch": 1.1468253968253967,
+      "grad_norm": 0.8838244676589966,
+      "learning_rate": 4.214582117569966e-06,
+      "loss": 0.1004,
+      "step": 289
+    },
+    {
+      "epoch": 1.1507936507936507,
+      "grad_norm": 0.888434648513794,
+      "learning_rate": 4.182145436348587e-06,
+      "loss": 0.1037,
+      "step": 290
+    },
+    {
+      "epoch": 1.1547619047619047,
+      "grad_norm": 0.8349224328994751,
+      "learning_rate": 4.1497440830799084e-06,
+      "loss": 0.0849,
+      "step": 291
+    },
+    {
+      "epoch": 1.1587301587301586,
+      "grad_norm": 0.8272682428359985,
+      "learning_rate": 4.1173794573691e-06,
+      "loss": 0.1053,
+      "step": 292
+    },
+    {
+      "epoch": 1.1626984126984128,
+      "grad_norm": 0.8138509392738342,
+      "learning_rate": 4.0850529572348505e-06,
+      "loss": 0.0857,
+      "step": 293
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.8172481060028076,
+      "learning_rate": 4.052765979048986e-06,
+      "loss": 0.0908,
+      "step": 294
+    },
+    {
+      "epoch": 1.1706349206349207,
+      "grad_norm": 0.8132976293563843,
+      "learning_rate": 4.0205199174761435e-06,
+      "loss": 0.0848,
+      "step": 295
+    },
+    {
+      "epoch": 1.1746031746031746,
+      "grad_norm": 0.8448895215988159,
+      "learning_rate": 3.988316165413528e-06,
+      "loss": 0.0854,
+      "step": 296
+    },
+    {
+      "epoch": 1.1785714285714286,
+      "grad_norm": 0.8900222182273865,
+      "learning_rate": 3.956156113930752e-06,
+      "loss": 0.0841,
+      "step": 297
+    },
+    {
+      "epoch": 1.1825396825396826,
+      "grad_norm": 0.7989954352378845,
+      "learning_rate": 3.924041152209739e-06,
+      "loss": 0.0984,
+      "step": 298
+    },
+    {
+      "epoch": 1.1865079365079365,
+      "grad_norm": 0.894929826259613,
+      "learning_rate": 3.891972667484726e-06,
+      "loss": 0.0983,
+      "step": 299
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.8010528087615967,
+      "learning_rate": 3.859952044982329e-06,
+      "loss": 0.1,
+      "step": 300
+    },
+    {
+      "epoch": 1.1944444444444444,
+      "grad_norm": 0.7610393762588501,
+      "learning_rate": 3.827980667861716e-06,
+      "loss": 0.0982,
+      "step": 301
+    },
+    {
+      "epoch": 1.1984126984126984,
+      "grad_norm": 0.7270869612693787,
+      "learning_rate": 3.7960599171548572e-06,
+      "loss": 0.0808,
+      "step": 302
+    },
+    {
+      "epoch": 1.2023809523809523,
+      "grad_norm": 0.8192585110664368,
+      "learning_rate": 3.764191171706867e-06,
+      "loss": 0.0991,
+      "step": 303
+    },
+    {
+      "epoch": 1.2063492063492063,
+      "grad_norm": 0.7628523707389832,
+      "learning_rate": 3.732375808116451e-06,
+      "loss": 0.0795,
+      "step": 304
+    },
+    {
+      "epoch": 1.2103174603174602,
+      "grad_norm": 0.8737412095069885,
+      "learning_rate": 3.7006152006764336e-06,
+      "loss": 0.1045,
+      "step": 305
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.8825508952140808,
+      "learning_rate": 3.6689107213144025e-06,
+      "loss": 0.0845,
+      "step": 306
+    },
+    {
+      "epoch": 1.2182539682539684,
+      "grad_norm": 0.8843568563461304,
+      "learning_rate": 3.6372637395334416e-06,
+      "loss": 0.1215,
+      "step": 307
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.8430192470550537,
+      "learning_rate": 3.6056756223529734e-06,
+      "loss": 0.09,
+      "step": 308
+    },
+    {
+      "epoch": 1.2261904761904763,
+      "grad_norm": 0.678902804851532,
+      "learning_rate": 3.574147734249719e-06,
+      "loss": 0.0749,
+      "step": 309
+    },
+    {
+      "epoch": 1.2301587301587302,
+      "grad_norm": 0.8882924318313599,
+      "learning_rate": 3.542681437098745e-06,
+      "loss": 0.1003,
+      "step": 310
+    },
+    {
+      "epoch": 1.2341269841269842,
+      "grad_norm": 0.9567738771438599,
+      "learning_rate": 3.5112780901146426e-06,
+      "loss": 0.1038,
+      "step": 311
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.8461977243423462,
+      "learning_rate": 3.479939049792817e-06,
+      "loss": 0.0962,
+      "step": 312
+    },
+    {
+      "epoch": 1.242063492063492,
+      "grad_norm": 0.8283154368400574,
+      "learning_rate": 3.448665669850888e-06,
+      "loss": 0.0889,
+      "step": 313
+    },
+    {
+      "epoch": 1.246031746031746,
+      "grad_norm": 0.9821956753730774,
+      "learning_rate": 3.4174593011702197e-06,
+      "loss": 0.1202,
+      "step": 314
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.7908430695533752,
+      "learning_rate": 3.386321291737563e-06,
+      "loss": 0.0789,
+      "step": 315
+    },
+    {
+      "epoch": 1.253968253968254,
+      "grad_norm": 0.9723663330078125,
+      "learning_rate": 3.3552529865868323e-06,
+      "loss": 0.1009,
+      "step": 316
+    },
+    {
+      "epoch": 1.257936507936508,
+      "grad_norm": 0.7394662499427795,
+      "learning_rate": 3.3242557277410015e-06,
+      "loss": 0.0743,
+      "step": 317
+    },
+    {
+      "epoch": 1.2619047619047619,
+      "grad_norm": 0.8046512603759766,
+      "learning_rate": 3.2933308541541365e-06,
+      "loss": 0.0986,
+      "step": 318
+    },
+    {
+      "epoch": 1.2658730158730158,
+      "grad_norm": 0.7483407855033875,
+      "learning_rate": 3.2624797016535626e-06,
+      "loss": 0.0798,
+      "step": 319
+    },
+    {
+      "epoch": 1.2698412698412698,
+      "grad_norm": 1.0179373025894165,
+      "learning_rate": 3.2317036028821523e-06,
+      "loss": 0.1198,
+      "step": 320
+    },
+    {
+      "epoch": 1.2738095238095237,
+      "grad_norm": 0.794193685054779,
+      "learning_rate": 3.201003887240768e-06,
+      "loss": 0.0876,
+      "step": 321
+    },
+    {
+      "epoch": 1.2777777777777777,
+      "grad_norm": 0.8476602435112,
+      "learning_rate": 3.1703818808308327e-06,
+      "loss": 0.0746,
+      "step": 322
+    },
+    {
+      "epoch": 1.2817460317460316,
+      "grad_norm": 0.9657560586929321,
+      "learning_rate": 3.1398389063970512e-06,
+      "loss": 0.0952,
+      "step": 323
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.8030561208724976,
+      "learning_rate": 3.1093762832702775e-06,
+      "loss": 0.1035,
+      "step": 324
+    },
+    {
+      "epoch": 1.2896825396825398,
+      "grad_norm": 0.8488226532936096,
+      "learning_rate": 3.0789953273105123e-06,
+      "loss": 0.0968,
+      "step": 325
+    },
+    {
+      "epoch": 1.2936507936507937,
+      "grad_norm": 0.9824974536895752,
+      "learning_rate": 3.048697350850073e-06,
+      "loss": 0.1233,
+      "step": 326
+    },
+    {
+      "epoch": 1.2976190476190477,
+      "grad_norm": 0.8766565918922424,
+      "learning_rate": 3.0184836626369034e-06,
+      "loss": 0.1042,
+      "step": 327
+    },
+    {
+      "epoch": 1.3015873015873016,
+      "grad_norm": 0.7361365556716919,
+      "learning_rate": 2.988355567778043e-06,
+      "loss": 0.0844,
+      "step": 328
+    },
+    {
+      "epoch": 1.3055555555555556,
+      "grad_norm": 0.7968645691871643,
+      "learning_rate": 2.9583143676832526e-06,
+      "loss": 0.096,
+      "step": 329
+    },
+    {
+      "epoch": 1.3095238095238095,
+      "grad_norm": 0.7606014609336853,
+      "learning_rate": 2.9283613600087933e-06,
+      "loss": 0.0665,
+      "step": 330
+    },
+    {
+      "epoch": 1.3134920634920635,
+      "grad_norm": 0.7167039513587952,
+      "learning_rate": 2.8984978386013767e-06,
+      "loss": 0.0875,
+      "step": 331
+    },
+    {
+      "epoch": 1.3174603174603174,
+      "grad_norm": 0.7731678485870361,
+      "learning_rate": 2.8687250934422774e-06,
+      "loss": 0.0818,
+      "step": 332
+    },
+    {
+      "epoch": 1.3214285714285714,
+      "grad_norm": 0.9659709930419922,
+      "learning_rate": 2.839044410591606e-06,
+      "loss": 0.1325,
+      "step": 333
+    },
+    {
+      "epoch": 1.3253968253968254,
+      "grad_norm": 0.8399143815040588,
+      "learning_rate": 2.809457072132766e-06,
+      "loss": 0.103,
+      "step": 334
+    },
+    {
+      "epoch": 1.3293650793650793,
+      "grad_norm": 0.7453393936157227,
+      "learning_rate": 2.779964356117063e-06,
+      "loss": 0.0803,
+      "step": 335
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.8334883451461792,
+      "learning_rate": 2.750567536508504e-06,
+      "loss": 0.0927,
+      "step": 336
+    },
+    {
+      "epoch": 1.3373015873015874,
+      "grad_norm": 0.8300994038581848,
+      "learning_rate": 2.7212678831287627e-06,
+      "loss": 0.0941,
+      "step": 337
+    },
+    {
+      "epoch": 1.3412698412698414,
+      "grad_norm": 0.8167857527732849,
+      "learning_rate": 2.692066661602333e-06,
+      "loss": 0.0859,
+      "step": 338
+    },
+    {
+      "epoch": 1.3452380952380953,
+      "grad_norm": 0.8473389744758606,
+      "learning_rate": 2.662965133301862e-06,
+      "loss": 0.0951,
+      "step": 339
+    },
+    {
+      "epoch": 1.3492063492063493,
+      "grad_norm": 0.8304094076156616,
+      "learning_rate": 2.633964555293654e-06,
+      "loss": 0.091,
+      "step": 340
+    },
+    {
+      "epoch": 1.3531746031746033,
+      "grad_norm": 0.7690606713294983,
+      "learning_rate": 2.605066180283378e-06,
+      "loss": 0.0758,
+      "step": 341
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.8668590784072876,
+      "learning_rate": 2.576271256561953e-06,
+      "loss": 0.0879,
+      "step": 342
+    },
+    {
+      "epoch": 1.3611111111111112,
+      "grad_norm": 0.8535332083702087,
+      "learning_rate": 2.5475810279516287e-06,
+      "loss": 0.0975,
+      "step": 343
+    },
+    {
+      "epoch": 1.3650793650793651,
+      "grad_norm": 0.828132688999176,
+      "learning_rate": 2.5189967337522574e-06,
+      "loss": 0.0844,
+      "step": 344
+    },
+    {
+      "epoch": 1.369047619047619,
+      "grad_norm": 0.9968429207801819,
+      "learning_rate": 2.49051960868776e-06,
+      "loss": 0.1099,
+      "step": 345
+    },
+    {
+      "epoch": 1.373015873015873,
+      "grad_norm": 0.7960136532783508,
+      "learning_rate": 2.46215088285279e-06,
+      "loss": 0.0855,
+      "step": 346
+    },
+    {
+      "epoch": 1.376984126984127,
+      "grad_norm": 0.7763605713844299,
+      "learning_rate": 2.433891781659603e-06,
+      "loss": 0.0733,
+      "step": 347
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.8548492789268494,
+      "learning_rate": 2.4057435257851173e-06,
+      "loss": 0.1079,
+      "step": 348
+    },
+    {
+      "epoch": 1.3849206349206349,
+      "grad_norm": 0.7584509253501892,
+      "learning_rate": 2.377707331118196e-06,
+      "loss": 0.0945,
+      "step": 349
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.6710481643676758,
+      "learning_rate": 2.349784408707112e-06,
+      "loss": 0.0846,
+      "step": 350
+    },
+    {
+      "epoch": 1.3928571428571428,
+      "grad_norm": 0.7176137566566467,
+      "learning_rate": 2.3219759647072467e-06,
+      "loss": 0.076,
+      "step": 351
+    },
+    {
+      "epoch": 1.3968253968253967,
+      "grad_norm": 0.8469821810722351,
+      "learning_rate": 2.2942832003289823e-06,
+      "loss": 0.0865,
+      "step": 352
+    },
+    {
+      "epoch": 1.4007936507936507,
+      "grad_norm": 0.8207787275314331,
+      "learning_rate": 2.2667073117858185e-06,
+      "loss": 0.1097,
+      "step": 353
+    },
+    {
+      "epoch": 1.4047619047619047,
+      "grad_norm": 0.6846061944961548,
+      "learning_rate": 2.2392494902427027e-06,
+      "loss": 0.0741,
+      "step": 354
+    },
+    {
+      "epoch": 1.4087301587301586,
+      "grad_norm": 0.7113244533538818,
+      "learning_rate": 2.2119109217645697e-06,
+      "loss": 0.0873,
+      "step": 355
+    },
+    {
+      "epoch": 1.4126984126984126,
+      "grad_norm": 0.7556560039520264,
+      "learning_rate": 2.1846927872651135e-06,
+      "loss": 0.0819,
+      "step": 356
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 1.043052315711975,
+      "learning_rate": 2.1575962624557754e-06,
+      "loss": 0.0958,
+      "step": 357
+    },
+    {
+      "epoch": 1.4206349206349207,
+      "grad_norm": 0.8609367609024048,
+      "learning_rate": 2.1306225177949584e-06,
+      "loss": 0.1056,
+      "step": 358
+    },
+    {
+      "epoch": 1.4246031746031746,
+      "grad_norm": 0.7151347994804382,
+      "learning_rate": 2.1037727184374705e-06,
+      "loss": 0.0737,
+      "step": 359
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.8181217312812805,
+      "learning_rate": 2.07704802418419e-06,
+      "loss": 0.0946,
+      "step": 360
+    },
+    {
+      "epoch": 1.4325396825396826,
+      "grad_norm": 0.9127845764160156,
+      "learning_rate": 2.050449589431969e-06,
+      "loss": 0.1061,
+      "step": 361
+    },
+    {
+      "epoch": 1.4365079365079365,
+      "grad_norm": 0.782051146030426,
+      "learning_rate": 2.023978563123771e-06,
+      "loss": 0.0819,
+      "step": 362
+    },
+    {
+      "epoch": 1.4404761904761905,
+      "grad_norm": 0.8060847520828247,
+      "learning_rate": 1.997636088699035e-06,
+      "loss": 0.09,
+      "step": 363
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.8724985122680664,
+      "learning_rate": 1.9714233040442915e-06,
+      "loss": 0.0938,
+      "step": 364
+    },
+    {
+      "epoch": 1.4484126984126984,
+      "grad_norm": 0.7807143330574036,
+      "learning_rate": 1.9453413414440043e-06,
+      "loss": 0.091,
+      "step": 365
+    },
+    {
+      "epoch": 1.4523809523809523,
+      "grad_norm": 0.9308791160583496,
+      "learning_rate": 1.919391327531663e-06,
+      "loss": 0.1177,
+      "step": 366
+    },
+    {
+      "epoch": 1.4563492063492063,
+      "grad_norm": 0.7229511141777039,
+      "learning_rate": 1.8935743832411163e-06,
+      "loss": 0.075,
+      "step": 367
+    },
+    {
+      "epoch": 1.4603174603174602,
+      "grad_norm": 0.9192443490028381,
+      "learning_rate": 1.8678916237581524e-06,
+      "loss": 0.0981,
+      "step": 368
+    },
+    {
+      "epoch": 1.4642857142857144,
+      "grad_norm": 0.9448950886726379,
+      "learning_rate": 1.8423441584723312e-06,
+      "loss": 0.0965,
+      "step": 369
+    },
+    {
+      "epoch": 1.4682539682539684,
+      "grad_norm": 0.9117385149002075,
+      "learning_rate": 1.816933090929055e-06,
+      "loss": 0.0952,
+      "step": 370
+    },
+    {
+      "epoch": 1.4722222222222223,
+      "grad_norm": 0.8257307410240173,
+      "learning_rate": 1.791659518781908e-06,
+      "loss": 0.0794,
+      "step": 371
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.9818858504295349,
+      "learning_rate": 1.7665245337452368e-06,
+      "loss": 0.1018,
+      "step": 372
+    },
+    {
+      "epoch": 1.4801587301587302,
+      "grad_norm": 0.8639586567878723,
+      "learning_rate": 1.7415292215469948e-06,
+      "loss": 0.0831,
+      "step": 373
+    },
+    {
+      "epoch": 1.4841269841269842,
+      "grad_norm": 0.7928310036659241,
+      "learning_rate": 1.716674661881848e-06,
+      "loss": 0.0954,
+      "step": 374
+    },
+    {
+      "epoch": 1.4880952380952381,
+      "grad_norm": 0.972807765007019,
+      "learning_rate": 1.6919619283645262e-06,
+      "loss": 0.1005,
+      "step": 375
+    },
+    {
+      "epoch": 1.492063492063492,
+      "grad_norm": 0.7709330320358276,
+      "learning_rate": 1.667392088483456e-06,
+      "loss": 0.0866,
+      "step": 376
+    },
+    {
+      "epoch": 1.496031746031746,
+      "grad_norm": 0.8894091248512268,
+      "learning_rate": 1.6429662035546451e-06,
+      "loss": 0.0831,
+      "step": 377
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.6335495114326477,
+      "learning_rate": 1.6186853286758397e-06,
+      "loss": 0.0706,
+      "step": 378
+    },
+    {
+      "epoch": 1.503968253968254,
+      "grad_norm": 0.6157211065292358,
+      "learning_rate": 1.5945505126809524e-06,
+      "loss": 0.0578,
+      "step": 379
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.6663343906402588,
+      "learning_rate": 1.570562798094747e-06,
+      "loss": 0.0643,
+      "step": 380
+    },
+    {
+      "epoch": 1.5119047619047619,
+      "grad_norm": 0.817520022392273,
+      "learning_rate": 1.5467232210878153e-06,
+      "loss": 0.1108,
+      "step": 381
+    },
+    {
+      "epoch": 1.5158730158730158,
+      "grad_norm": 0.856833279132843,
+      "learning_rate": 1.5230328114318127e-06,
+      "loss": 0.0938,
+      "step": 382
+    },
+    {
+      "epoch": 1.5198412698412698,
+      "grad_norm": 0.6747552156448364,
+      "learning_rate": 1.4994925924549797e-06,
+      "loss": 0.0691,
+      "step": 383
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.7864953875541687,
+      "learning_rate": 1.4761035809979395e-06,
+      "loss": 0.0689,
+      "step": 384
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.7300853729248047,
+      "learning_rate": 1.452866787369771e-06,
+      "loss": 0.0903,
+      "step": 385
+    },
+    {
+      "epoch": 1.5317460317460316,
+      "grad_norm": 0.7783157825469971,
+      "learning_rate": 1.4297832153043657e-06,
+      "loss": 0.0843,
+      "step": 386
+    },
+    {
+      "epoch": 1.5357142857142856,
+      "grad_norm": 0.7717552185058594,
+      "learning_rate": 1.4068538619170763e-06,
+      "loss": 0.0732,
+      "step": 387
+    },
+    {
+      "epoch": 1.5396825396825395,
+      "grad_norm": 0.7834195494651794,
+      "learning_rate": 1.3840797176616467e-06,
+      "loss": 0.0751,
+      "step": 388
+    },
+    {
+      "epoch": 1.5436507936507935,
+      "grad_norm": 0.8702894449234009,
+      "learning_rate": 1.3614617662874197e-06,
+      "loss": 0.1005,
+      "step": 389
+    },
+    {
+      "epoch": 1.5476190476190477,
+      "grad_norm": 0.8433047533035278,
+      "learning_rate": 1.3390009847968505e-06,
+      "loss": 0.0861,
+      "step": 390
+    },
+    {
+      "epoch": 1.5515873015873016,
+      "grad_norm": 0.8168141841888428,
+      "learning_rate": 1.316698343403302e-06,
+      "loss": 0.1047,
+      "step": 391
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.9714818596839905,
+      "learning_rate": 1.2945548054891322e-06,
+      "loss": 0.1194,
+      "step": 392
+    },
+    {
+      "epoch": 1.5595238095238095,
+      "grad_norm": 0.8196632266044617,
+      "learning_rate": 1.27257132756409e-06,
+      "loss": 0.0811,
+      "step": 393
+    },
+    {
+      "epoch": 1.5634920634920635,
+      "grad_norm": 0.8637920022010803,
+      "learning_rate": 1.2507488592239848e-06,
+      "loss": 0.0912,
+      "step": 394
+    },
+    {
+      "epoch": 1.5674603174603174,
+      "grad_norm": 0.9072219133377075,
+      "learning_rate": 1.2290883431096778e-06,
+      "loss": 0.0846,
+      "step": 395
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.8047322630882263,
+      "learning_rate": 1.2075907148663579e-06,
+      "loss": 0.0799,
+      "step": 396
+    },
+    {
+      "epoch": 1.5753968253968254,
+      "grad_norm": 0.7913994193077087,
+      "learning_rate": 1.186256903103129e-06,
+      "loss": 0.073,
+      "step": 397
+    },
+    {
+      "epoch": 1.5793650793650795,
+      "grad_norm": 0.9412828087806702,
+      "learning_rate": 1.1650878293528994e-06,
+      "loss": 0.1013,
+      "step": 398
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.8140155673027039,
+      "learning_rate": 1.1440844080325703e-06,
+      "loss": 0.0901,
+      "step": 399
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.7938934564590454,
+      "learning_rate": 1.1232475464035386e-06,
+      "loss": 0.0883,
+      "step": 400
+    },
+    {
+      "epoch": 1.5912698412698414,
+      "grad_norm": 0.6305232048034668,
+      "learning_rate": 1.10257814453251e-06,
+      "loss": 0.0605,
+      "step": 401
+    },
+    {
+      "epoch": 1.5952380952380953,
+      "grad_norm": 0.8313385248184204,
+      "learning_rate": 1.0820770952526155e-06,
+      "loss": 0.0903,
+      "step": 402
+    },
+    {
+      "epoch": 1.5992063492063493,
+      "grad_norm": 0.6266860365867615,
+      "learning_rate": 1.0617452841248494e-06,
+      "loss": 0.0847,
+      "step": 403
+    },
+    {
+      "epoch": 1.6031746031746033,
+      "grad_norm": 0.769794225692749,
+      "learning_rate": 1.0415835893998116e-06,
+      "loss": 0.0916,
+      "step": 404
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 0.8159760236740112,
+      "learning_rate": 1.0215928819797744e-06,
+      "loss": 0.0984,
+      "step": 405
+    },
+    {
+      "epoch": 1.6111111111111112,
+      "grad_norm": 0.6972020268440247,
+      "learning_rate": 1.0017740253810608e-06,
+      "loss": 0.0589,
+      "step": 406
+    },
+    {
+      "epoch": 1.6150793650793651,
+      "grad_norm": 0.7206509709358215,
+      "learning_rate": 9.821278756967467e-07,
+      "loss": 0.0778,
+      "step": 407
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.9815142750740051,
+      "learning_rate": 9.62655281559679e-07,
+      "loss": 0.1159,
+      "step": 408
+    },
+    {
+      "epoch": 1.623015873015873,
+      "grad_norm": 0.7741109728813171,
+      "learning_rate": 9.433570841058187e-07,
+      "loss": 0.0804,
+      "step": 409
+    },
+    {
+      "epoch": 1.626984126984127,
+      "grad_norm": 0.8201466202735901,
+      "learning_rate": 9.242341169379077e-07,
+      "loss": 0.0907,
+      "step": 410
+    },
+    {
+      "epoch": 1.630952380952381,
+      "grad_norm": 0.7901651263237,
+      "learning_rate": 9.052872060894613e-07,
+      "loss": 0.0854,
+      "step": 411
+    },
+    {
+      "epoch": 1.6349206349206349,
+      "grad_norm": 0.828625500202179,
+      "learning_rate": 8.865171699890835e-07,
+      "loss": 0.0786,
+      "step": 412
+    },
+    {
+      "epoch": 1.6388888888888888,
+      "grad_norm": 0.854513943195343,
+      "learning_rate": 8.679248194251211e-07,
+      "loss": 0.099,
+      "step": 413
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.7350807189941406,
+      "learning_rate": 8.495109575106331e-07,
+      "loss": 0.0804,
+      "step": 414
+    },
+    {
+      "epoch": 1.6468253968253967,
+      "grad_norm": 0.742985725402832,
+      "learning_rate": 8.312763796487038e-07,
+      "loss": 0.0731,
+      "step": 415
+    },
+    {
+      "epoch": 1.6507936507936507,
+      "grad_norm": 0.7394562363624573,
+      "learning_rate": 8.132218734980852e-07,
+      "loss": 0.0811,
+      "step": 416
+    },
+    {
+      "epoch": 1.6547619047619047,
+      "grad_norm": 0.8178054094314575,
+      "learning_rate": 7.953482189391687e-07,
+      "loss": 0.089,
+      "step": 417
+    },
+    {
+      "epoch": 1.6587301587301586,
+      "grad_norm": 0.863472044467926,
+      "learning_rate": 7.776561880403072e-07,
+      "loss": 0.0876,
+      "step": 418
+    },
+    {
+      "epoch": 1.6626984126984126,
+      "grad_norm": 1.0591928958892822,
+      "learning_rate": 7.601465450244528e-07,
+      "loss": 0.1542,
+      "step": 419
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.8059977293014526,
+      "learning_rate": 7.42820046236154e-07,
+      "loss": 0.0785,
+      "step": 420
+    },
+    {
+      "epoch": 1.6706349206349205,
+      "grad_norm": 0.9021475315093994,
+      "learning_rate": 7.256774401088817e-07,
+      "loss": 0.0971,
+      "step": 421
+    },
+    {
+      "epoch": 1.6746031746031746,
+      "grad_norm": 0.8722649216651917,
+      "learning_rate": 7.087194671326986e-07,
+      "loss": 0.0797,
+      "step": 422
+    },
+    {
+      "epoch": 1.6785714285714286,
+      "grad_norm": 0.9459144473075867,
+      "learning_rate": 6.91946859822279e-07,
+      "loss": 0.1087,
+      "step": 423
+    },
+    {
+      "epoch": 1.6825396825396826,
+      "grad_norm": 0.8489049077033997,
+      "learning_rate": 6.753603426852589e-07,
+      "loss": 0.1114,
+      "step": 424
+    },
+    {
+      "epoch": 1.6865079365079365,
+      "grad_norm": 0.6769583225250244,
+      "learning_rate": 6.589606321909464e-07,
+      "loss": 0.0799,
+      "step": 425
+    },
+    {
+      "epoch": 1.6904761904761905,
+      "grad_norm": 0.806599497795105,
+      "learning_rate": 6.427484367393699e-07,
+      "loss": 0.1004,
+      "step": 426
+    },
+    {
+      "epoch": 1.6944444444444444,
+      "grad_norm": 0.7337989807128906,
+      "learning_rate": 6.267244566306801e-07,
+      "loss": 0.0786,
+      "step": 427
+    },
+    {
+      "epoch": 1.6984126984126984,
+      "grad_norm": 0.7469695806503296,
+      "learning_rate": 6.108893840348995e-07,
+      "loss": 0.1028,
+      "step": 428
+    },
+    {
+      "epoch": 1.7023809523809523,
+      "grad_norm": 0.7320832014083862,
+      "learning_rate": 5.952439029620222e-07,
+      "loss": 0.075,
+      "step": 429
+    },
+    {
+      "epoch": 1.7063492063492065,
+      "grad_norm": 0.6765589118003845,
+      "learning_rate": 5.797886892324695e-07,
+      "loss": 0.0674,
+      "step": 430
+    },
+    {
+      "epoch": 1.7103174603174605,
+      "grad_norm": 0.6787246465682983,
+      "learning_rate": 5.645244104478947e-07,
+      "loss": 0.0773,
+      "step": 431
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.8502627611160278,
+      "learning_rate": 5.494517259623478e-07,
+      "loss": 0.1127,
+      "step": 432
+    },
+    {
+      "epoch": 1.7182539682539684,
+      "grad_norm": 0.793020486831665,
+      "learning_rate": 5.34571286853795e-07,
+      "loss": 0.1059,
+      "step": 433
+    },
+    {
+      "epoch": 1.7222222222222223,
+      "grad_norm": 0.8450143933296204,
+      "learning_rate": 5.198837358959901e-07,
+      "loss": 0.1051,
+      "step": 434
+    },
+    {
+      "epoch": 1.7261904761904763,
+      "grad_norm": 0.6854594945907593,
+      "learning_rate": 5.05389707530714e-07,
+      "loss": 0.0646,
+      "step": 435
+    },
+    {
+      "epoch": 1.7301587301587302,
+      "grad_norm": 0.6840714812278748,
+      "learning_rate": 4.91089827840367e-07,
+      "loss": 0.0778,
+      "step": 436
+    },
+    {
+      "epoch": 1.7341269841269842,
+      "grad_norm": 0.8606773018836975,
+      "learning_rate": 4.769847145209244e-07,
+      "loss": 0.1084,
+      "step": 437
+    },
+    {
+      "epoch": 1.7380952380952381,
+      "grad_norm": 0.7901908159255981,
+      "learning_rate": 4.6307497685525894e-07,
+      "loss": 0.0863,
+      "step": 438
+    },
+    {
+      "epoch": 1.742063492063492,
+      "grad_norm": 0.7910974025726318,
+      "learning_rate": 4.4936121568681546e-07,
+      "loss": 0.0849,
+      "step": 439
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.7289157509803772,
+      "learning_rate": 4.3584402339366174e-07,
+      "loss": 0.0724,
+      "step": 440
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.7375960350036621,
+      "learning_rate": 4.225239838628981e-07,
+      "loss": 0.0737,
+      "step": 441
+    },
+    {
+      "epoch": 1.753968253968254,
+      "grad_norm": 0.8164241909980774,
+      "learning_rate": 4.0940167246543595e-07,
+      "loss": 0.086,
+      "step": 442
+    },
+    {
+      "epoch": 1.757936507936508,
+      "grad_norm": 0.8139920234680176,
+      "learning_rate": 3.964776560311484e-07,
+      "loss": 0.0933,
+      "step": 443
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.7812939286231995,
+      "learning_rate": 3.8375249282437743e-07,
+      "loss": 0.0882,
+      "step": 444
+    },
+    {
+      "epoch": 1.7658730158730158,
+      "grad_norm": 0.8722679615020752,
+      "learning_rate": 3.71226732519826e-07,
+      "loss": 0.0974,
+      "step": 445
+    },
+    {
+      "epoch": 1.7698412698412698,
+      "grad_norm": 0.8438254594802856,
+      "learning_rate": 3.589009161788104e-07,
+      "loss": 0.0828,
+      "step": 446
+    },
+    {
+      "epoch": 1.7738095238095237,
+      "grad_norm": 0.7687845826148987,
+      "learning_rate": 3.4677557622589175e-07,
+      "loss": 0.0774,
+      "step": 447
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.8137856125831604,
+      "learning_rate": 3.3485123642587657e-07,
+      "loss": 0.0812,
+      "step": 448
+    },
+    {
+      "epoch": 1.7817460317460316,
+      "grad_norm": 0.7595266699790955,
+      "learning_rate": 3.2312841186118937e-07,
+      "loss": 0.079,
+      "step": 449
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.8352352380752563,
+      "learning_rate": 3.116076089096265e-07,
+      "loss": 0.085,
+      "step": 450
+    },
+    {
+      "epoch": 1.7896825396825395,
+      "grad_norm": 0.7053031325340271,
+      "learning_rate": 3.0028932522248256e-07,
+      "loss": 0.0771,
+      "step": 451
+    },
+    {
+      "epoch": 1.7936507936507935,
+      "grad_norm": 0.6933891177177429,
+      "learning_rate": 2.8917404970305096e-07,
+      "loss": 0.0718,
+      "step": 452
+    },
+    {
+      "epoch": 1.7976190476190477,
+      "grad_norm": 0.7048924565315247,
+      "learning_rate": 2.782622624855097e-07,
+      "loss": 0.0847,
+      "step": 453
+    },
+    {
+      "epoch": 1.8015873015873016,
+      "grad_norm": 0.6969692707061768,
+      "learning_rate": 2.6755443491417786e-07,
+      "loss": 0.0814,
+      "step": 454
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.6592867374420166,
+      "learning_rate": 2.570510295231571e-07,
+      "loss": 0.0642,
+      "step": 455
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.7861699461936951,
+      "learning_rate": 2.467525000163523e-07,
+      "loss": 0.085,
+      "step": 456
+    },
+    {
+      "epoch": 1.8134920634920635,
+      "grad_norm": 0.8022602200508118,
+      "learning_rate": 2.36659291247871e-07,
+      "loss": 0.0945,
+      "step": 457
+    },
+    {
+      "epoch": 1.8174603174603174,
+      "grad_norm": 0.6735831499099731,
+      "learning_rate": 2.2677183920281342e-07,
+      "loss": 0.0562,
+      "step": 458
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 0.7735519409179688,
+      "learning_rate": 2.1709057097843266e-07,
+      "loss": 0.0736,
+      "step": 459
+    },
+    {
+      "epoch": 1.8253968253968254,
+      "grad_norm": 0.7292094826698303,
+      "learning_rate": 2.0761590476568893e-07,
+      "loss": 0.0664,
+      "step": 460
+    },
+    {
+      "epoch": 1.8293650793650795,
+      "grad_norm": 0.887444794178009,
+      "learning_rate": 1.9834824983118673e-07,
+      "loss": 0.1091,
+      "step": 461
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.6806834936141968,
+      "learning_rate": 1.892880064994934e-07,
+      "loss": 0.0634,
+      "step": 462
+    },
+    {
+      "epoch": 1.8373015873015874,
+      "grad_norm": 0.8866720199584961,
+      "learning_rate": 1.8043556613585143e-07,
+      "loss": 0.0999,
+      "step": 463
+    },
+    {
+      "epoch": 1.8412698412698414,
+      "grad_norm": 0.9056561589241028,
+      "learning_rate": 1.7179131112926628e-07,
+      "loss": 0.0974,
+      "step": 464
+    },
+    {
+      "epoch": 1.8452380952380953,
+      "grad_norm": 0.7735084891319275,
+      "learning_rate": 1.6335561487599406e-07,
+      "loss": 0.0776,
+      "step": 465
+    },
+    {
+      "epoch": 1.8492063492063493,
+      "grad_norm": 1.7332282066345215,
+      "learning_rate": 1.551288417634106e-07,
+      "loss": 0.1426,
+      "step": 466
+    },
+    {
+      "epoch": 1.8531746031746033,
+      "grad_norm": 0.8308102488517761,
+      "learning_rate": 1.471113471542712e-07,
+      "loss": 0.0869,
+      "step": 467
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.8413865566253662,
+      "learning_rate": 1.3930347737136195e-07,
+      "loss": 0.099,
+      "step": 468
+    },
+    {
+      "epoch": 1.8611111111111112,
+      "grad_norm": 1.0041447877883911,
+      "learning_rate": 1.3170556968253756e-07,
+      "loss": 0.1191,
+      "step": 469
+    },
+    {
+      "epoch": 1.8650793650793651,
+      "grad_norm": 0.8478453159332275,
+      "learning_rate": 1.2431795228615372e-07,
+      "loss": 0.0849,
+      "step": 470
+    },
+    {
+      "epoch": 1.869047619047619,
+      "grad_norm": 0.8766846656799316,
+      "learning_rate": 1.1714094429689127e-07,
+      "loss": 0.0827,
+      "step": 471
+    },
+    {
+      "epoch": 1.873015873015873,
+      "grad_norm": 0.8661823272705078,
+      "learning_rate": 1.1017485573197151e-07,
+      "loss": 0.093,
+      "step": 472
+    },
+    {
+      "epoch": 1.876984126984127,
+      "grad_norm": 0.7078859210014343,
+      "learning_rate": 1.0341998749776316e-07,
+      "loss": 0.0646,
+      "step": 473
+    },
+    {
+      "epoch": 1.880952380952381,
+      "grad_norm": 0.8136516809463501,
+      "learning_rate": 9.687663137678605e-08,
+      "loss": 0.095,
+      "step": 474
+    },
+    {
+      "epoch": 1.8849206349206349,
+      "grad_norm": 0.9041445851325989,
+      "learning_rate": 9.054507001510727e-08,
+      "loss": 0.1038,
+      "step": 475
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.694397509098053,
+      "learning_rate": 8.442557691013042e-08,
+      "loss": 0.0794,
+      "step": 476
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 0.8240735530853271,
+      "learning_rate": 7.851841639878399e-08,
+      "loss": 0.0805,
+      "step": 477
+    },
+    {
+      "epoch": 1.8968253968253967,
+      "grad_norm": 0.7979876399040222,
+      "learning_rate": 7.282384364610207e-08,
+      "loss": 0.1017,
+      "step": 478
+    },
+    {
+      "epoch": 1.9007936507936507,
+      "grad_norm": 0.6360365152359009,
+      "learning_rate": 6.734210463420099e-08,
+      "loss": 0.0615,
+      "step": 479
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.6626116633415222,
+      "learning_rate": 6.207343615165562e-08,
+      "loss": 0.0671,
+      "step": 480
+    },
+    {
+      "epoch": 1.9087301587301586,
+      "grad_norm": 0.7120184302330017,
+      "learning_rate": 5.701806578327029e-08,
+      "loss": 0.0673,
+      "step": 481
+    },
+    {
+      "epoch": 1.9126984126984126,
+      "grad_norm": 0.7189626097679138,
+      "learning_rate": 5.21762119002478e-08,
+      "loss": 0.0731,
+      "step": 482
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.6905253529548645,
+      "learning_rate": 4.7548083650759134e-08,
+      "loss": 0.0666,
+      "step": 483
+    },
+    {
+      "epoch": 1.9206349206349205,
+      "grad_norm": 0.6117310523986816,
+      "learning_rate": 4.31338809509052e-08,
+      "loss": 0.0551,
+      "step": 484
+    },
+    {
+      "epoch": 1.9246031746031746,
+      "grad_norm": 0.7856166362762451,
+      "learning_rate": 3.8933794476083143e-08,
+      "loss": 0.073,
+      "step": 485
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.7610016465187073,
+      "learning_rate": 3.494800565275125e-08,
+      "loss": 0.0715,
+      "step": 486
+    },
+    {
+      "epoch": 1.9325396825396826,
+      "grad_norm": 0.7038713097572327,
+      "learning_rate": 3.1176686650589147e-08,
+      "loss": 0.0746,
+      "step": 487
+    },
+    {
+      "epoch": 1.9365079365079365,
+      "grad_norm": 0.8484662771224976,
+      "learning_rate": 2.7620000375064848e-08,
+      "loss": 0.0991,
+      "step": 488
+    },
+    {
+      "epoch": 1.9404761904761905,
+      "grad_norm": 0.8162146210670471,
+      "learning_rate": 2.4278100460393138e-08,
+      "loss": 0.0709,
+      "step": 489
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.8962053060531616,
+      "learning_rate": 2.115113126290258e-08,
+      "loss": 0.102,
+      "step": 490
+    },
+    {
+      "epoch": 1.9484126984126984,
+      "grad_norm": 0.8036097884178162,
+      "learning_rate": 1.8239227854799368e-08,
+      "loss": 0.0728,
+      "step": 491
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 0.8631817698478699,
+      "learning_rate": 1.554251601833201e-08,
+      "loss": 0.0912,
+      "step": 492
+    },
+    {
+      "epoch": 1.9563492063492065,
+      "grad_norm": 0.8002811074256897,
+      "learning_rate": 1.3061112240357887e-08,
+      "loss": 0.0706,
+      "step": 493
+    },
+    {
+      "epoch": 1.9603174603174605,
+      "grad_norm": 0.7505822777748108,
+      "learning_rate": 1.0795123707312283e-08,
+      "loss": 0.0708,
+      "step": 494
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 0.8649543523788452,
+      "learning_rate": 8.744648300578196e-09,
+      "loss": 0.0926,
+      "step": 495
+    },
+    {
+      "epoch": 1.9682539682539684,
+      "grad_norm": 0.8728803992271423,
+      "learning_rate": 6.9097745922580564e-09,
+      "loss": 0.081,
+      "step": 496
+    },
+    {
+      "epoch": 1.9722222222222223,
+      "grad_norm": 0.7853608727455139,
+      "learning_rate": 5.2905818413478975e-09,
+      "loss": 0.0676,
+      "step": 497
+    },
+    {
+      "epoch": 1.9761904761904763,
+      "grad_norm": 0.8135411143302917,
+      "learning_rate": 3.887139990313427e-09,
+      "loss": 0.0859,
+      "step": 498
+    },
+    {
+      "epoch": 1.9801587301587302,
+      "grad_norm": 0.8057032823562622,
+      "learning_rate": 2.699509662069666e-09,
+      "loss": 0.0985,
+      "step": 499
+    },
+    {
+      "epoch": 1.9841269841269842,
+      "grad_norm": 0.6384691596031189,
+      "learning_rate": 1.7277421573608234e-09,
+      "loss": 0.0708,
+      "step": 500
+    },
+    {
+      "epoch": 1.9880952380952381,
+      "grad_norm": 0.6963675618171692,
+      "learning_rate": 9.71879452545399e-10,
+      "loss": 0.0785,
+      "step": 501
+    },
+    {
+      "epoch": 1.992063492063492,
+      "grad_norm": 0.9572624564170837,
+      "learning_rate": 4.3195419778319095e-10,
+      "loss": 0.1097,
+      "step": 502
+    },
+    {
+      "epoch": 1.996031746031746,
+      "grad_norm": 0.8002074360847473,
+      "learning_rate": 1.0798971562364647e-10,
+      "loss": 0.0811,
+      "step": 503
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6123743653297424,
+      "learning_rate": 0.0,
+      "loss": 0.0529,
+      "step": 504
+    },
+    {
+      "epoch": 2.0,
+      "step": 504,
+      "total_flos": 54880760659968.0,
+      "train_loss": 0.23895617312796058,
+      "train_runtime": 2813.5476,
+      "train_samples_per_second": 2.86,
+      "train_steps_per_second": 0.179
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 504,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 54880760659968.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d97084abc08c02981d9517a1de40ccd24c6fce9e5886f416743def96680e74
+size 8056