Upload model and track tokenizer.json with LFS

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

chat_template.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 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": false,
+  "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": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.0",
+  "use_cache": false
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc30cafe075491ca073c36cfddae587d233c6cda9df2498ab95c8bafe36da9b
+size 4997750760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695c490d29358f748ef6a250a33f6580c6346921a3892c1f351739b95b8d4dbe
+size 2511587184

model.safetensors.index.json

@@ -0,0 +1,831 @@
+{
+  "metadata": {
+    "total_size": 7509245952
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

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": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001,
+      "grad_norm": 8.88845157623291,
+      "learning_rate": 9.989999999999999e-07,
+      "loss": -0.0038,
+      "step": 1
+    },
+    {
+      "epoch": 0.002,
+      "grad_norm": 4.226269245147705,
+      "learning_rate": 9.98e-07,
+      "loss": -0.0048,
+      "step": 2
+    },
+    {
+      "epoch": 0.003,
+      "grad_norm": 4.763400077819824,
+      "learning_rate": 9.97e-07,
+      "loss": -0.0032,
+      "step": 3
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 6.258369445800781,
+      "learning_rate": 9.959999999999999e-07,
+      "loss": -0.0042,
+      "step": 4
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 6.801921844482422,
+      "learning_rate": 9.95e-07,
+      "loss": -0.0037,
+      "step": 5
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 2.404029130935669,
+      "learning_rate": 9.94e-07,
+      "loss": -0.0043,
+      "step": 6
+    },
+    {
+      "epoch": 0.007,
+      "grad_norm": 4.656682014465332,
+      "learning_rate": 9.929999999999999e-07,
+      "loss": -0.0034,
+      "step": 7
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 5.627880096435547,
+      "learning_rate": 9.92e-07,
+      "loss": -0.0031,
+      "step": 8
+    },
+    {
+      "epoch": 0.009,
+      "grad_norm": 4.78317403793335,
+      "learning_rate": 9.91e-07,
+      "loss": -0.004,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.175312519073486,
+      "learning_rate": 9.9e-07,
+      "loss": -0.0032,
+      "step": 10
+    },
+    {
+      "epoch": 0.011,
+      "grad_norm": 7.6933183670043945,
+      "learning_rate": 9.89e-07,
+      "loss": -0.005,
+      "step": 11
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 8.22114372253418,
+      "learning_rate": 9.88e-07,
+      "loss": -0.006,
+      "step": 12
+    },
+    {
+      "epoch": 0.013,
+      "grad_norm": 4.249200820922852,
+      "learning_rate": 9.87e-07,
+      "loss": -0.0025,
+      "step": 13
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 6.855690002441406,
+      "learning_rate": 9.86e-07,
+      "loss": -0.0037,
+      "step": 14
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 4.649789333343506,
+      "learning_rate": 9.849999999999999e-07,
+      "loss": -0.0037,
+      "step": 15
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 4.5621018409729,
+      "learning_rate": 9.84e-07,
+      "loss": -0.0049,
+      "step": 16
+    },
+    {
+      "epoch": 0.017,
+      "grad_norm": 6.4000067710876465,
+      "learning_rate": 9.83e-07,
+      "loss": -0.0036,
+      "step": 17
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 6.537838935852051,
+      "learning_rate": 9.819999999999999e-07,
+      "loss": -0.0035,
+      "step": 18
+    },
+    {
+      "epoch": 0.019,
+      "grad_norm": 2.909165859222412,
+      "learning_rate": 9.81e-07,
+      "loss": -0.0034,
+      "step": 19
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 38.25032043457031,
+      "learning_rate": 9.8e-07,
+      "loss": -0.0043,
+      "step": 20
+    },
+    {
+      "epoch": 0.021,
+      "grad_norm": 11.987759590148926,
+      "learning_rate": 9.789999999999999e-07,
+      "loss": -0.0047,
+      "step": 21
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 4.854317665100098,
+      "learning_rate": 9.78e-07,
+      "loss": -0.0033,
+      "step": 22
+    },
+    {
+      "epoch": 0.023,
+      "grad_norm": 10.64887523651123,
+      "learning_rate": 9.77e-07,
+      "loss": -0.0032,
+      "step": 23
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 4.268849849700928,
+      "learning_rate": 9.759999999999998e-07,
+      "loss": -0.0032,
+      "step": 24
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 5.237280368804932,
+      "learning_rate": 9.75e-07,
+      "loss": -0.0037,
+      "step": 25
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 5.276170253753662,
+      "learning_rate": 9.74e-07,
+      "loss": -0.0042,
+      "step": 26
+    },
+    {
+      "epoch": 0.027,
+      "grad_norm": 4.593943119049072,
+      "learning_rate": 9.729999999999998e-07,
+      "loss": -0.0036,
+      "step": 27
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 5.9058756828308105,
+      "learning_rate": 9.72e-07,
+      "loss": -0.0045,
+      "step": 28
+    },
+    {
+      "epoch": 0.029,
+      "grad_norm": 5.2677459716796875,
+      "learning_rate": 9.709999999999999e-07,
+      "loss": -0.004,
+      "step": 29
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.962713241577148,
+      "learning_rate": 9.7e-07,
+      "loss": -0.0035,
+      "step": 30
+    },
+    {
+      "epoch": 0.031,
+      "grad_norm": 6.9328742027282715,
+      "learning_rate": 9.69e-07,
+      "loss": -0.0039,
+      "step": 31
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 5.0893073081970215,
+      "learning_rate": 9.679999999999999e-07,
+      "loss": -0.0033,
+      "step": 32
+    },
+    {
+      "epoch": 0.033,
+      "grad_norm": 4.18739652633667,
+      "learning_rate": 9.67e-07,
+      "loss": -0.0034,
+      "step": 33
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 5.842318058013916,
+      "learning_rate": 9.66e-07,
+      "loss": -0.0042,
+      "step": 34
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 4.309342384338379,
+      "learning_rate": 9.649999999999999e-07,
+      "loss": -0.0037,
+      "step": 35
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 4.397903919219971,
+      "learning_rate": 9.64e-07,
+      "loss": -0.0035,
+      "step": 36
+    },
+    {
+      "epoch": 0.037,
+      "grad_norm": 5.345351696014404,
+      "learning_rate": 9.63e-07,
+      "loss": -0.0046,
+      "step": 37
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 6.413722515106201,
+      "learning_rate": 9.619999999999999e-07,
+      "loss": -0.0042,
+      "step": 38
+    },
+    {
+      "epoch": 0.039,
+      "grad_norm": 4.583013534545898,
+      "learning_rate": 9.61e-07,
+      "loss": -0.0039,
+      "step": 39
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.375754356384277,
+      "learning_rate": 9.6e-07,
+      "loss": -0.0046,
+      "step": 40
+    },
+    {
+      "epoch": 0.041,
+      "grad_norm": 6.022228240966797,
+      "learning_rate": 9.589999999999998e-07,
+      "loss": -0.0046,
+      "step": 41
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 7.181720733642578,
+      "learning_rate": 9.58e-07,
+      "loss": -0.0037,
+      "step": 42
+    },
+    {
+      "epoch": 0.043,
+      "grad_norm": 5.231449604034424,
+      "learning_rate": 9.57e-07,
+      "loss": -0.0037,
+      "step": 43
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 21.17510986328125,
+      "learning_rate": 9.559999999999998e-07,
+      "loss": -0.0049,
+      "step": 44
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 5.925566673278809,
+      "learning_rate": 9.55e-07,
+      "loss": -0.0049,
+      "step": 45
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 5.829775333404541,
+      "learning_rate": 9.539999999999999e-07,
+      "loss": -0.0045,
+      "step": 46
+    },
+    {
+      "epoch": 0.047,
+      "grad_norm": 6.279599666595459,
+      "learning_rate": 9.529999999999999e-07,
+      "loss": -0.0047,
+      "step": 47
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 5.868813514709473,
+      "learning_rate": 9.52e-07,
+      "loss": -0.0045,
+      "step": 48
+    },
+    {
+      "epoch": 0.049,
+      "grad_norm": 5.49916410446167,
+      "learning_rate": 9.509999999999999e-07,
+      "loss": -0.0041,
+      "step": 49
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.019808292388916,
+      "learning_rate": 9.499999999999999e-07,
+      "loss": -0.0045,
+      "step": 50
+    },
+    {
+      "epoch": 0.051,
+      "grad_norm": 0.24749566614627838,
+      "learning_rate": 9.489999999999999e-07,
+      "loss": -0.0046,
+      "step": 51
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 7.1395134925842285,
+      "learning_rate": 9.479999999999999e-07,
+      "loss": -0.0051,
+      "step": 52
+    },
+    {
+      "epoch": 0.053,
+      "grad_norm": 5.279783248901367,
+      "learning_rate": 9.469999999999999e-07,
+      "loss": -0.0045,
+      "step": 53
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 6.15852689743042,
+      "learning_rate": 9.459999999999999e-07,
+      "loss": -0.0056,
+      "step": 54
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 6.622757911682129,
+      "learning_rate": 9.45e-07,
+      "loss": -0.0125,
+      "step": 55
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 6.376431941986084,
+      "learning_rate": 9.439999999999999e-07,
+      "loss": -0.0052,
+      "step": 56
+    },
+    {
+      "epoch": 0.057,
+      "grad_norm": 7.688092231750488,
+      "learning_rate": 9.429999999999999e-07,
+      "loss": -0.0044,
+      "step": 57
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 5.144252777099609,
+      "learning_rate": 9.419999999999999e-07,
+      "loss": -0.0049,
+      "step": 58
+    },
+    {
+      "epoch": 0.059,
+      "grad_norm": 4.68715238571167,
+      "learning_rate": 9.409999999999999e-07,
+      "loss": -0.0044,
+      "step": 59
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 7.266247749328613,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": -0.0043,
+      "step": 60
+    },
+    {
+      "epoch": 0.061,
+      "grad_norm": 4.757603168487549,
+      "learning_rate": 9.389999999999999e-07,
+      "loss": -0.0049,
+      "step": 61
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 6.192087173461914,
+      "learning_rate": 9.379999999999998e-07,
+      "loss": -0.0038,
+      "step": 62
+    },
+    {
+      "epoch": 0.063,
+      "grad_norm": 3.5498993396759033,
+      "learning_rate": 9.37e-07,
+      "loss": -0.005,
+      "step": 63
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 5.5830278396606445,
+      "learning_rate": 9.36e-07,
+      "loss": -0.005,
+      "step": 64
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 5.5790276527404785,
+      "learning_rate": 9.35e-07,
+      "loss": -0.0042,
+      "step": 65
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 5.512165546417236,
+      "learning_rate": 9.34e-07,
+      "loss": -0.0046,
+      "step": 66
+    },
+    {
+      "epoch": 0.067,
+      "grad_norm": 4.104743480682373,
+      "learning_rate": 9.33e-07,
+      "loss": -0.0041,
+      "step": 67
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 6.665727615356445,
+      "learning_rate": 9.32e-07,
+      "loss": -0.0041,
+      "step": 68
+    },
+    {
+      "epoch": 0.069,
+      "grad_norm": 5.697459697723389,
+      "learning_rate": 9.31e-07,
+      "loss": -0.0059,
+      "step": 69
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.385350704193115,
+      "learning_rate": 9.3e-07,
+      "loss": -0.0054,
+      "step": 70
+    },
+    {
+      "epoch": 0.071,
+      "grad_norm": 3.9981255531311035,
+      "learning_rate": 9.29e-07,
+      "loss": -0.0047,
+      "step": 71
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 5.102632522583008,
+      "learning_rate": 9.28e-07,
+      "loss": -0.0041,
+      "step": 72
+    },
+    {
+      "epoch": 0.073,
+      "grad_norm": 3.6675994396209717,
+      "learning_rate": 9.27e-07,
+      "loss": -0.0046,
+      "step": 73
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 4.534061431884766,
+      "learning_rate": 9.26e-07,
+      "loss": -0.0046,
+      "step": 74
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 4.834553241729736,
+      "learning_rate": 9.25e-07,
+      "loss": -0.0043,
+      "step": 75
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 3.6336984634399414,
+      "learning_rate": 9.24e-07,
+      "loss": -0.0041,
+      "step": 76
+    },
+    {
+      "epoch": 0.077,
+      "grad_norm": 5.711594104766846,
+      "learning_rate": 9.23e-07,
+      "loss": -0.0041,
+      "step": 77
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 5.523354530334473,
+      "learning_rate": 9.22e-07,
+      "loss": -0.0043,
+      "step": 78
+    },
+    {
+      "epoch": 0.079,
+      "grad_norm": 0.10461787134408951,
+      "learning_rate": 9.21e-07,
+      "loss": -0.005,
+      "step": 79
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.470160007476807,
+      "learning_rate": 9.2e-07,
+      "loss": -0.0045,
+      "step": 80
+    },
+    {
+      "epoch": 0.081,
+      "grad_norm": 10.518538475036621,
+      "learning_rate": 9.19e-07,
+      "loss": -0.0137,
+      "step": 81
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 4.025298595428467,
+      "learning_rate": 9.18e-07,
+      "loss": -0.0043,
+      "step": 82
+    },
+    {
+      "epoch": 0.083,
+      "grad_norm": 5.518987655639648,
+      "learning_rate": 9.17e-07,
+      "loss": -0.0053,
+      "step": 83
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 3.3966658115386963,
+      "learning_rate": 9.16e-07,
+      "loss": -0.0043,
+      "step": 84
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 2.668159246444702,
+      "learning_rate": 9.15e-07,
+      "loss": -0.0038,
+      "step": 85
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 3.9800076484680176,
+      "learning_rate": 9.14e-07,
+      "loss": -0.0045,
+      "step": 86
+    },
+    {
+      "epoch": 0.087,
+      "grad_norm": 3.5814120769500732,
+      "learning_rate": 9.13e-07,
+      "loss": -0.005,
+      "step": 87
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 5.294524669647217,
+      "learning_rate": 9.12e-07,
+      "loss": -0.0048,
+      "step": 88
+    },
+    {
+      "epoch": 0.089,
+      "grad_norm": 2.9765090942382812,
+      "learning_rate": 9.109999999999999e-07,
+      "loss": -0.0041,
+      "step": 89
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5.190207004547119,
+      "learning_rate": 9.1e-07,
+      "loss": -0.0042,
+      "step": 90
+    },
+    {
+      "epoch": 0.091,
+      "grad_norm": 4.291192531585693,
+      "learning_rate": 9.09e-07,
+      "loss": -0.0046,
+      "step": 91
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 5.092918395996094,
+      "learning_rate": 9.08e-07,
+      "loss": -0.0054,
+      "step": 92
+    },
+    {
+      "epoch": 0.093,
+      "grad_norm": 4.564518928527832,
+      "learning_rate": 9.07e-07,
+      "loss": -0.0045,
+      "step": 93
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 5.203583240509033,
+      "learning_rate": 9.06e-07,
+      "loss": -0.0046,
+      "step": 94
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 15.981708526611328,
+      "learning_rate": 9.05e-07,
+      "loss": -0.005,
+      "step": 95
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 10.375612258911133,
+      "learning_rate": 9.039999999999999e-07,
+      "loss": -0.0045,
+      "step": 96
+    },
+    {
+      "epoch": 0.097,
+      "grad_norm": 4.14613676071167,
+      "learning_rate": 9.03e-07,
+      "loss": -0.0044,
+      "step": 97
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 6.144663333892822,
+      "learning_rate": 9.02e-07,
+      "loss": -0.0042,
+      "step": 98
+    },
+    {
+      "epoch": 0.099,
+      "grad_norm": 15.81885814666748,
+      "learning_rate": 9.01e-07,
+      "loss": -0.0041,
+      "step": 99
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.0946502685546875,
+      "learning_rate": 9e-07,
+      "loss": -0.005,
+      "step": 100
+    },
+    {
+      "epoch": 0.101,
+      "grad_norm": 5.329338550567627,
+      "learning_rate": 8.99e-07,
+      "loss": -0.0047,
+      "step": 101
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 3.0686638355255127,
+      "learning_rate": 8.98e-07,
+      "loss": -0.0036,
+      "step": 102
+    },
+    {
+      "epoch": 0.103,
+      "grad_norm": 6.707710266113281,
+      "learning_rate": 8.969999999999999e-07,
+      "loss": -0.0042,
+      "step": 103
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 5.295083999633789,
+      "learning_rate": 8.96e-07,
+      "loss": -0.0043,
+      "step": 104
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 6.824080467224121,
+      "learning_rate": 8.95e-07,
+      "loss": -0.0044,
+      "step": 105
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 5.95166015625,
+      "learning_rate": 8.939999999999999e-07,
+      "loss": -0.0042,
+      "step": 106
+    },
+    {
+      "epoch": 0.107,
+      "grad_norm": 5.822356224060059,
+      "learning_rate": 8.93e-07,
+      "loss": -0.0045,
+      "step": 107
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 3.8665878772735596,
+      "learning_rate": 8.92e-07,
+      "loss": -0.0048,
+      "step": 108
+    },
+    {
+      "epoch": 0.109,
+      "grad_norm": 7.900908470153809,
+      "learning_rate": 8.91e-07,
+      "loss": -0.0043,
+      "step": 109
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 6.5509114265441895,
+      "learning_rate": 8.9e-07,
+      "loss": -0.0049,
+      "step": 110
+    },
+    {
+      "epoch": 0.111,
+      "grad_norm": 5.75206995010376,
+      "learning_rate": 8.89e-07,
+      "loss": -0.0052,
+      "step": 111
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 4.980931282043457,
+      "learning_rate": 8.88e-07,
+      "loss": -0.0058,
+      "step": 112
+    },
+    {
+      "epoch": 0.113,
+      "grad_norm": 4.1734161376953125,
+      "learning_rate": 8.869999999999999e-07,
+      "loss": -0.0052,
+      "step": 113
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 19.266067504882812,
+      "learning_rate": 8.86e-07,
+      "loss": -0.0051,
+      "step": 114
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 4.487819194793701,
+      "learning_rate": 8.85e-07,
+      "loss": -0.0056,
+      "step": 115
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 6.28100061416626,
+      "learning_rate": 8.839999999999999e-07,
+      "loss": -0.0064,
+      "step": 116
+    },
+    {
+      "epoch": 0.117,
+      "grad_norm": 0.12271853536367416,
+      "learning_rate": 8.83e-07,
+      "loss": -0.006,
+      "step": 117
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 7.75722599029541,
+      "learning_rate": 8.82e-07,
+      "loss": -0.0057,
+      "step": 118
+    },
+    {
+      "epoch": 0.119,
+      "grad_norm": 5.561598300933838,
+      "learning_rate": 8.81e-07,
+      "loss": -0.0051,
+      "step": 119
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.516164779663086,
+      "learning_rate": 8.799999999999999e-07,
+      "loss": -0.0051,
+      "step": 120
+    },
+    {
+      "epoch": 0.121,
+      "grad_norm": 5.307635307312012,
+      "learning_rate": 8.79e-07,
+      "loss": -0.0052,
+      "step": 121
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 5.7740325927734375,
+      "learning_rate": 8.78e-07,
+      "loss": -0.0052,
+      "step": 122
+    },
+    {
+      "epoch": 0.123,
+      "grad_norm": 6.159525394439697,
+      "learning_rate": 8.769999999999999e-07,
+      "loss": -0.0055,
+      "step": 123
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 7.216506004333496,
+      "learning_rate": 8.76e-07,
+      "loss": -0.0103,
+      "step": 124
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 10.550005912780762,
+      "learning_rate": 8.75e-07,
+      "loss": -0.0048,
+      "step": 125
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 4.7772040367126465,
+      "learning_rate": 8.739999999999999e-07,
+      "loss": -0.0055,
+      "step": 126
+    },
+    {
+      "epoch": 0.127,
+      "grad_norm": 3.7170627117156982,
+      "learning_rate": 8.729999999999999e-07,
+      "loss": -0.0057,
+      "step": 127
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.522591590881348,
+      "learning_rate": 8.72e-07,
+      "loss": -0.0058,
+      "step": 128
+    },
+    {
+      "epoch": 0.129,
+      "grad_norm": 3.3577287197113037,
+      "learning_rate": 8.71e-07,
+      "loss": -0.0054,
+      "step": 129
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.20465120673179626,
+      "learning_rate": 8.699999999999999e-07,
+      "loss": -0.0058,
+      "step": 130
+    },
+    {
+      "epoch": 0.131,
+      "grad_norm": 6.8187665939331055,
+      "learning_rate": 8.69e-07,
+      "loss": -0.0072,
+      "step": 131
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 6.491813659667969,
+      "learning_rate": 8.68e-07,
+      "loss": -0.006,
+      "step": 132
+    },
+    {
+      "epoch": 0.133,
+      "grad_norm": 0.29179584980010986,
+      "learning_rate": 8.669999999999999e-07,
+      "loss": -0.0059,
+      "step": 133
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 5.8086838722229,
+      "learning_rate": 8.659999999999999e-07,
+      "loss": -0.0053,
+      "step": 134
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 0.1163095086812973,
+      "learning_rate": 8.65e-07,
+      "loss": -0.0057,
+      "step": 135
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 7.259735107421875,
+      "learning_rate": 8.639999999999999e-07,
+      "loss": -0.0058,
+      "step": 136
+    },
+    {
+      "epoch": 0.137,
+      "grad_norm": 4.0380473136901855,
+      "learning_rate": 8.629999999999999e-07,
+      "loss": -0.0063,
+      "step": 137
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 20.123931884765625,
+      "learning_rate": 8.62e-07,
+      "loss": -0.0052,
+      "step": 138
+    },
+    {
+      "epoch": 0.139,
+      "grad_norm": 10.119573593139648,
+      "learning_rate": 8.61e-07,
+      "loss": -0.007,
+      "step": 139
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 7.746423721313477,
+      "learning_rate": 8.599999999999999e-07,
+      "loss": -0.0058,
+      "step": 140
+    },
+    {
+      "epoch": 0.141,
+      "grad_norm": 6.323609352111816,
+      "learning_rate": 8.59e-07,
+      "loss": -0.0063,
+      "step": 141
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 8.147316932678223,
+      "learning_rate": 8.58e-07,
+      "loss": -0.0056,
+      "step": 142
+    },
+    {
+      "epoch": 0.143,
+      "grad_norm": 4.23258113861084,
+      "learning_rate": 8.569999999999999e-07,
+      "loss": -0.0065,
+      "step": 143
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 4.788832664489746,
+      "learning_rate": 8.559999999999999e-07,
+      "loss": -0.0053,
+      "step": 144
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 7.580941200256348,
+      "learning_rate": 8.55e-07,
+      "loss": -0.0062,
+      "step": 145
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 6.641035556793213,
+      "learning_rate": 8.539999999999999e-07,
+      "loss": -0.0061,
+      "step": 146
+    },
+    {
+      "epoch": 0.147,
+      "grad_norm": 7.254807949066162,
+      "learning_rate": 8.529999999999999e-07,
+      "loss": -0.0065,
+      "step": 147
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 8.243073463439941,
+      "learning_rate": 8.52e-07,
+      "loss": -0.0076,
+      "step": 148
+    },
+    {
+      "epoch": 0.149,
+      "grad_norm": 4.1485915184021,
+      "learning_rate": 8.51e-07,
+      "loss": -0.0058,
+      "step": 149
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.882201671600342,
+      "learning_rate": 8.499999999999999e-07,
+      "loss": -0.0077,
+      "step": 150
+    },
+    {
+      "epoch": 0.151,
+      "grad_norm": 6.606505870819092,
+      "learning_rate": 8.489999999999999e-07,
+      "loss": -0.0071,
+      "step": 151
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 6.566438674926758,
+      "learning_rate": 8.48e-07,
+      "loss": -0.0067,
+      "step": 152
+    },
+    {
+      "epoch": 0.153,
+      "grad_norm": 0.13758021593093872,
+      "learning_rate": 8.469999999999999e-07,
+      "loss": -0.006,
+      "step": 153
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 7.9011077880859375,
+      "learning_rate": 8.459999999999999e-07,
+      "loss": -0.007,
+      "step": 154
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 8.586587905883789,
+      "learning_rate": 8.45e-07,
+      "loss": -0.0065,
+      "step": 155
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 5.8413896560668945,
+      "learning_rate": 8.439999999999999e-07,
+      "loss": -0.0071,
+      "step": 156
+    },
+    {
+      "epoch": 0.157,
+      "grad_norm": 6.199925422668457,
+      "learning_rate": 8.429999999999999e-07,
+      "loss": -0.0057,
+      "step": 157
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 5.795785903930664,
+      "learning_rate": 8.419999999999999e-07,
+      "loss": -0.0062,
+      "step": 158
+    },
+    {
+      "epoch": 0.159,
+      "grad_norm": 6.807403564453125,
+      "learning_rate": 8.41e-07,
+      "loss": -0.0065,
+      "step": 159
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 7.480658531188965,
+      "learning_rate": 8.399999999999999e-07,
+      "loss": -0.0074,
+      "step": 160
+    },
+    {
+      "epoch": 0.161,
+      "grad_norm": 4.410843372344971,
+      "learning_rate": 8.389999999999999e-07,
+      "loss": -0.0068,
+      "step": 161
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 9.499409675598145,
+      "learning_rate": 8.38e-07,
+      "loss": -0.0103,
+      "step": 162
+    },
+    {
+      "epoch": 0.163,
+      "grad_norm": 5.689218997955322,
+      "learning_rate": 8.369999999999999e-07,
+      "loss": -0.0071,
+      "step": 163
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 7.260366916656494,
+      "learning_rate": 8.359999999999999e-07,
+      "loss": -0.006,
+      "step": 164
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 6.015467166900635,
+      "learning_rate": 8.349999999999999e-07,
+      "loss": -0.0074,
+      "step": 165
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 7.42357063293457,
+      "learning_rate": 8.34e-07,
+      "loss": -0.0073,
+      "step": 166
+    },
+    {
+      "epoch": 0.167,
+      "grad_norm": 9.56913948059082,
+      "learning_rate": 8.329999999999999e-07,
+      "loss": -0.0075,
+      "step": 167
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 6.862265110015869,
+      "learning_rate": 8.319999999999999e-07,
+      "loss": -0.0073,
+      "step": 168
+    },
+    {
+      "epoch": 0.169,
+      "grad_norm": 6.646910190582275,
+      "learning_rate": 8.31e-07,
+      "loss": -0.0076,
+      "step": 169
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 8.10696792602539,
+      "learning_rate": 8.299999999999999e-07,
+      "loss": -0.0081,
+      "step": 170
+    },
+    {
+      "epoch": 0.171,
+      "grad_norm": 12.921547889709473,
+      "learning_rate": 8.289999999999999e-07,
+      "loss": -0.0075,
+      "step": 171
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.3926668167114258,
+      "learning_rate": 8.28e-07,
+      "loss": -0.0082,
+      "step": 172
+    },
+    {
+      "epoch": 0.173,
+      "grad_norm": 7.2022786140441895,
+      "learning_rate": 8.269999999999999e-07,
+      "loss": -0.0084,
+      "step": 173
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 7.691386699676514,
+      "learning_rate": 8.259999999999999e-07,
+      "loss": -0.0076,
+      "step": 174
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 6.765666484832764,
+      "learning_rate": 8.249999999999999e-07,
+      "loss": -0.0076,
+      "step": 175
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 7.500133991241455,
+      "learning_rate": 8.24e-07,
+      "loss": -0.0077,
+      "step": 176
+    },
+    {
+      "epoch": 0.177,
+      "grad_norm": 6.143344879150391,
+      "learning_rate": 8.229999999999999e-07,
+      "loss": -0.0097,
+      "step": 177
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 5.279773712158203,
+      "learning_rate": 8.219999999999999e-07,
+      "loss": -0.0078,
+      "step": 178
+    },
+    {
+      "epoch": 0.179,
+      "grad_norm": 5.759856224060059,
+      "learning_rate": 8.21e-07,
+      "loss": -0.0075,
+      "step": 179
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 12.567288398742676,
+      "learning_rate": 8.199999999999999e-07,
+      "loss": -0.0104,
+      "step": 180
+    },
+    {
+      "epoch": 0.181,
+      "grad_norm": 7.646395683288574,
+      "learning_rate": 8.189999999999999e-07,
+      "loss": -0.0075,
+      "step": 181
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 7.993496417999268,
+      "learning_rate": 8.179999999999999e-07,
+      "loss": -0.0072,
+      "step": 182
+    },
+    {
+      "epoch": 0.183,
+      "grad_norm": 5.071593761444092,
+      "learning_rate": 8.169999999999999e-07,
+      "loss": -0.01,
+      "step": 183
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 6.940348148345947,
+      "learning_rate": 8.159999999999999e-07,
+      "loss": -0.0078,
+      "step": 184
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 10.190718650817871,
+      "learning_rate": 8.149999999999999e-07,
+      "loss": -0.0079,
+      "step": 185
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 6.952041149139404,
+      "learning_rate": 8.14e-07,
+      "loss": -0.0084,
+      "step": 186
+    },
+    {
+      "epoch": 0.187,
+      "grad_norm": 5.970053672790527,
+      "learning_rate": 8.129999999999999e-07,
+      "loss": -0.0083,
+      "step": 187
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.5876850485801697,
+      "learning_rate": 8.12e-07,
+      "loss": -0.0083,
+      "step": 188
+    },
+    {
+      "epoch": 0.189,
+      "grad_norm": 5.610873222351074,
+      "learning_rate": 8.11e-07,
+      "loss": -0.0087,
+      "step": 189
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 12.19083309173584,
+      "learning_rate": 8.1e-07,
+      "loss": -0.0096,
+      "step": 190
+    },
+    {
+      "epoch": 0.191,
+      "grad_norm": 5.680775165557861,
+      "learning_rate": 8.09e-07,
+      "loss": -0.0096,
+      "step": 191
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.2923887372016907,
+      "learning_rate": 8.08e-07,
+      "loss": -0.0093,
+      "step": 192
+    },
+    {
+      "epoch": 0.193,
+      "grad_norm": 5.202503681182861,
+      "learning_rate": 8.070000000000001e-07,
+      "loss": -0.0096,
+      "step": 193
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 5.700753688812256,
+      "learning_rate": 8.06e-07,
+      "loss": -0.0088,
+      "step": 194
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 0.17094002664089203,
+      "learning_rate": 8.05e-07,
+      "loss": -0.0082,
+      "step": 195
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 9.3015718460083,
+      "learning_rate": 8.04e-07,
+      "loss": -0.0094,
+      "step": 196
+    },
+    {
+      "epoch": 0.197,
+      "grad_norm": 5.283720970153809,
+      "learning_rate": 8.03e-07,
+      "loss": -0.009,
+      "step": 197
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 5.173987865447998,
+      "learning_rate": 8.02e-07,
+      "loss": -0.009,
+      "step": 198
+    },
+    {
+      "epoch": 0.199,
+      "grad_norm": 16.79398536682129,
+      "learning_rate": 8.01e-07,
+      "loss": -0.0096,
+      "step": 199
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.4461230933666229,
+      "learning_rate": 8e-07,
+      "loss": -0.0094,
+      "step": 200
+    },
+    {
+      "epoch": 0.201,
+      "grad_norm": 0.8155984878540039,
+      "learning_rate": 7.99e-07,
+      "loss": -0.0096,
+      "step": 201
+    },
+    {
+      "epoch": 0.202,
+      "grad_norm": 12.974409103393555,
+      "learning_rate": 7.98e-07,
+      "loss": -0.0092,
+      "step": 202
+    },
+    {
+      "epoch": 0.203,
+      "grad_norm": 5.8596038818359375,
+      "learning_rate": 7.970000000000001e-07,
+      "loss": -0.0103,
+      "step": 203
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 7.759433746337891,
+      "learning_rate": 7.96e-07,
+      "loss": -0.0098,
+      "step": 204
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 9.778124809265137,
+      "learning_rate": 7.95e-07,
+      "loss": -0.0085,
+      "step": 205
+    },
+    {
+      "epoch": 0.206,
+      "grad_norm": 5.659801006317139,
+      "learning_rate": 7.94e-07,
+      "loss": -0.009,
+      "step": 206
+    },
+    {
+      "epoch": 0.207,
+      "grad_norm": 0.17820116877555847,
+      "learning_rate": 7.93e-07,
+      "loss": -0.0088,
+      "step": 207
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 15.44992446899414,
+      "learning_rate": 7.92e-07,
+      "loss": -0.0095,
+      "step": 208
+    },
+    {
+      "epoch": 0.209,
+      "grad_norm": 6.655909061431885,
+      "learning_rate": 7.91e-07,
+      "loss": -0.0086,
+      "step": 209
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.978959321975708,
+      "learning_rate": 7.9e-07,
+      "loss": -0.01,
+      "step": 210
+    },
+    {
+      "epoch": 0.211,
+      "grad_norm": 5.2686567306518555,
+      "learning_rate": 7.89e-07,
+      "loss": -0.0095,
+      "step": 211
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 11.930782318115234,
+      "learning_rate": 7.88e-07,
+      "loss": -0.0095,
+      "step": 212
+    },
+    {
+      "epoch": 0.213,
+      "grad_norm": 4.796861171722412,
+      "learning_rate": 7.87e-07,
+      "loss": -0.0089,
+      "step": 213
+    },
+    {
+      "epoch": 0.214,
+      "grad_norm": 0.333877295255661,
+      "learning_rate": 7.86e-07,
+      "loss": -0.0096,
+      "step": 214
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 10.779296875,
+      "learning_rate": 7.85e-07,
+      "loss": -0.0105,
+      "step": 215
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.226885125041008,
+      "learning_rate": 7.84e-07,
+      "loss": -0.0087,
+      "step": 216
+    },
+    {
+      "epoch": 0.217,
+      "grad_norm": 5.52307653427124,
+      "learning_rate": 7.83e-07,
+      "loss": -0.0107,
+      "step": 217
+    },
+    {
+      "epoch": 0.218,
+      "grad_norm": 6.058752059936523,
+      "learning_rate": 7.82e-07,
+      "loss": -0.0098,
+      "step": 218
+    },
+    {
+      "epoch": 0.219,
+      "grad_norm": 4.812845706939697,
+      "learning_rate": 7.81e-07,
+      "loss": -0.0098,
+      "step": 219
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 8.045927047729492,
+      "learning_rate": 7.799999999999999e-07,
+      "loss": -0.0101,
+      "step": 220
+    },
+    {
+      "epoch": 0.221,
+      "grad_norm": 7.95838737487793,
+      "learning_rate": 7.79e-07,
+      "loss": -0.0086,
+      "step": 221
+    },
+    {
+      "epoch": 0.222,
+      "grad_norm": 0.36911702156066895,
+      "learning_rate": 7.78e-07,
+      "loss": -0.0087,
+      "step": 222
+    },
+    {
+      "epoch": 0.223,
+      "grad_norm": 0.3545754551887512,
+      "learning_rate": 7.77e-07,
+      "loss": -0.0098,
+      "step": 223
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.45118218660354614,
+      "learning_rate": 7.76e-07,
+      "loss": -0.0098,
+      "step": 224
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.2402823120355606,
+      "learning_rate": 7.75e-07,
+      "loss": -0.0098,
+      "step": 225
+    },
+    {
+      "epoch": 0.226,
+      "grad_norm": 6.395725250244141,
+      "learning_rate": 7.74e-07,
+      "loss": -0.0117,
+      "step": 226
+    },
+    {
+      "epoch": 0.227,
+      "grad_norm": 0.5056664347648621,
+      "learning_rate": 7.729999999999999e-07,
+      "loss": -0.0107,
+      "step": 227
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 7.519665718078613,
+      "learning_rate": 7.72e-07,
+      "loss": -0.0118,
+      "step": 228
+    },
+    {
+      "epoch": 0.229,
+      "grad_norm": 8.760887145996094,
+      "learning_rate": 7.71e-07,
+      "loss": -0.0092,
+      "step": 229
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.34272778034210205,
+      "learning_rate": 7.699999999999999e-07,
+      "loss": -0.0101,
+      "step": 230
+    },
+    {
+      "epoch": 0.231,
+      "grad_norm": 0.4276975095272064,
+      "learning_rate": 7.69e-07,
+      "loss": -0.0108,
+      "step": 231
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.22476638853549957,
+      "learning_rate": 7.68e-07,
+      "loss": -0.0109,
+      "step": 232
+    },
+    {
+      "epoch": 0.233,
+      "grad_norm": 9.426416397094727,
+      "learning_rate": 7.67e-07,
+      "loss": -0.0102,
+      "step": 233
+    },
+    {
+      "epoch": 0.234,
+      "grad_norm": 4.873260021209717,
+      "learning_rate": 7.66e-07,
+      "loss": -0.0118,
+      "step": 234
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 9.18245792388916,
+      "learning_rate": 7.65e-07,
+      "loss": -0.0138,
+      "step": 235
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 4.169106960296631,
+      "learning_rate": 7.64e-07,
+      "loss": -0.0122,
+      "step": 236
+    },
+    {
+      "epoch": 0.237,
+      "grad_norm": 13.195479393005371,
+      "learning_rate": 7.629999999999999e-07,
+      "loss": -0.0105,
+      "step": 237
+    },
+    {
+      "epoch": 0.238,
+      "grad_norm": 6.7612223625183105,
+      "learning_rate": 7.62e-07,
+      "loss": -0.0119,
+      "step": 238
+    },
+    {
+      "epoch": 0.239,
+      "grad_norm": 5.503846645355225,
+      "learning_rate": 7.61e-07,
+      "loss": -0.0114,
+      "step": 239
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 9.158905029296875,
+      "learning_rate": 7.599999999999999e-07,
+      "loss": -0.0134,
+      "step": 240
+    },
+    {
+      "epoch": 0.241,
+      "grad_norm": 8.985334396362305,
+      "learning_rate": 7.59e-07,
+      "loss": -0.0103,
+      "step": 241
+    },
+    {
+      "epoch": 0.242,
+      "grad_norm": 1.2102431058883667,
+      "learning_rate": 7.58e-07,
+      "loss": -0.0136,
+      "step": 242
+    },
+    {
+      "epoch": 0.243,
+      "grad_norm": 16.022090911865234,
+      "learning_rate": 7.57e-07,
+      "loss": -0.0111,
+      "step": 243
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 0.31077077984809875,
+      "learning_rate": 7.559999999999999e-07,
+      "loss": -0.0123,
+      "step": 244
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 6.734167575836182,
+      "learning_rate": 7.55e-07,
+      "loss": -0.0119,
+      "step": 245
+    },
+    {
+      "epoch": 0.246,
+      "grad_norm": 11.6829833984375,
+      "learning_rate": 7.54e-07,
+      "loss": -0.0129,
+      "step": 246
+    },
+    {
+      "epoch": 0.247,
+      "grad_norm": 12.950207710266113,
+      "learning_rate": 7.529999999999999e-07,
+      "loss": -0.0114,
+      "step": 247
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 1.4825127124786377,
+      "learning_rate": 7.52e-07,
+      "loss": -0.0114,
+      "step": 248
+    },
+    {
+      "epoch": 0.249,
+      "grad_norm": 19.799175262451172,
+      "learning_rate": 7.51e-07,
+      "loss": -0.0101,
+      "step": 249
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 8.865711212158203,
+      "learning_rate": 7.5e-07,
+      "loss": -0.0117,
+      "step": 250
+    },
+    {
+      "epoch": 0.251,
+      "grad_norm": 1.6455284357070923,
+      "learning_rate": 7.489999999999999e-07,
+      "loss": -0.0122,
+      "step": 251
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 0.25489675998687744,
+      "learning_rate": 7.48e-07,
+      "loss": -0.0105,
+      "step": 252
+    },
+    {
+      "epoch": 0.253,
+      "grad_norm": 11.264545440673828,
+      "learning_rate": 7.47e-07,
+      "loss": -0.0119,
+      "step": 253
+    },
+    {
+      "epoch": 0.254,
+      "grad_norm": 7.560001850128174,
+      "learning_rate": 7.459999999999999e-07,
+      "loss": -0.01,
+      "step": 254
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 0.5006900429725647,
+      "learning_rate": 7.45e-07,
+      "loss": -0.0116,
+      "step": 255
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.3368641436100006,
+      "learning_rate": 7.44e-07,
+      "loss": -0.0106,
+      "step": 256
+    },
+    {
+      "epoch": 0.257,
+      "grad_norm": 7.034303188323975,
+      "learning_rate": 7.429999999999999e-07,
+      "loss": -0.0108,
+      "step": 257
+    },
+    {
+      "epoch": 0.258,
+      "grad_norm": 11.665346145629883,
+      "learning_rate": 7.42e-07,
+      "loss": -0.0106,
+      "step": 258
+    },
+    {
+      "epoch": 0.259,
+      "grad_norm": 10.706096649169922,
+      "learning_rate": 7.41e-07,
+      "loss": -0.0102,
+      "step": 259
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 9.140202522277832,
+      "learning_rate": 7.4e-07,
+      "loss": -0.0109,
+      "step": 260
+    },
+    {
+      "epoch": 0.261,
+      "grad_norm": 5.4821929931640625,
+      "learning_rate": 7.389999999999999e-07,
+      "loss": -0.0103,
+      "step": 261
+    },
+    {
+      "epoch": 0.262,
+      "grad_norm": 10.502763748168945,
+      "learning_rate": 7.38e-07,
+      "loss": -0.0122,
+      "step": 262
+    },
+    {
+      "epoch": 0.263,
+      "grad_norm": 18.659250259399414,
+      "learning_rate": 7.37e-07,
+      "loss": -0.0129,
+      "step": 263
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.3509368896484375,
+      "learning_rate": 7.359999999999999e-07,
+      "loss": -0.0117,
+      "step": 264
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 11.362595558166504,
+      "learning_rate": 7.35e-07,
+      "loss": -0.0133,
+      "step": 265
+    },
+    {
+      "epoch": 0.266,
+      "grad_norm": 0.7363149523735046,
+      "learning_rate": 7.34e-07,
+      "loss": -0.0105,
+      "step": 266
+    },
+    {
+      "epoch": 0.267,
+      "grad_norm": 0.3848000466823578,
+      "learning_rate": 7.329999999999999e-07,
+      "loss": -0.0123,
+      "step": 267
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 0.30259615182876587,
+      "learning_rate": 7.319999999999999e-07,
+      "loss": -0.0127,
+      "step": 268
+    },
+    {
+      "epoch": 0.269,
+      "grad_norm": 0.5537352561950684,
+      "learning_rate": 7.31e-07,
+      "loss": -0.0139,
+      "step": 269
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.46785038709640503,
+      "learning_rate": 7.3e-07,
+      "loss": -0.0121,
+      "step": 270
+    },
+    {
+      "epoch": 0.271,
+      "grad_norm": 14.374626159667969,
+      "learning_rate": 7.289999999999999e-07,
+      "loss": -0.0134,
+      "step": 271
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.5538061857223511,
+      "learning_rate": 7.28e-07,
+      "loss": -0.0132,
+      "step": 272
+    },
+    {
+      "epoch": 0.273,
+      "grad_norm": 0.08790513873100281,
+      "learning_rate": 7.27e-07,
+      "loss": -0.0132,
+      "step": 273
+    },
+    {
+      "epoch": 0.274,
+      "grad_norm": 1.596326231956482,
+      "learning_rate": 7.259999999999999e-07,
+      "loss": -0.0154,
+      "step": 274
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 243.41571044921875,
+      "learning_rate": 7.249999999999999e-07,
+      "loss": -0.0146,
+      "step": 275
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 6.1953511238098145,
+      "learning_rate": 7.24e-07,
+      "loss": -0.0135,
+      "step": 276
+    },
+    {
+      "epoch": 0.277,
+      "grad_norm": 0.3177115023136139,
+      "learning_rate": 7.229999999999999e-07,
+      "loss": -0.0122,
+      "step": 277
+    },
+    {
+      "epoch": 0.278,
+      "grad_norm": 15.484610557556152,
+      "learning_rate": 7.219999999999999e-07,
+      "loss": -0.0139,
+      "step": 278
+    },
+    {
+      "epoch": 0.279,
+      "grad_norm": 0.20269319415092468,
+      "learning_rate": 7.21e-07,
+      "loss": -0.012,
+      "step": 279
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 11.770788192749023,
+      "learning_rate": 7.2e-07,
+      "loss": -0.0157,
+      "step": 280
+    },
+    {
+      "epoch": 0.281,
+      "grad_norm": 19.656126022338867,
+      "learning_rate": 7.189999999999999e-07,
+      "loss": -0.013,
+      "step": 281
+    },
+    {
+      "epoch": 0.282,
+      "grad_norm": 0.18115279078483582,
+      "learning_rate": 7.179999999999999e-07,
+      "loss": -0.0129,
+      "step": 282
+    },
+    {
+      "epoch": 0.283,
+      "grad_norm": 0.13747023046016693,
+      "learning_rate": 7.17e-07,
+      "loss": -0.0128,
+      "step": 283
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 3.1769118309020996,
+      "learning_rate": 7.159999999999999e-07,
+      "loss": -0.0156,
+      "step": 284
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 6.999953746795654,
+      "learning_rate": 7.149999999999999e-07,
+      "loss": -0.0237,
+      "step": 285
+    },
+    {
+      "epoch": 0.286,
+      "grad_norm": 4.049704074859619,
+      "learning_rate": 7.14e-07,
+      "loss": -0.0169,
+      "step": 286
+    },
+    {
+      "epoch": 0.287,
+      "grad_norm": 10.37075138092041,
+      "learning_rate": 7.129999999999999e-07,
+      "loss": -0.0169,
+      "step": 287
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 10.678406715393066,
+      "learning_rate": 7.119999999999999e-07,
+      "loss": -0.0148,
+      "step": 288
+    },
+    {
+      "epoch": 0.289,
+      "grad_norm": 24.931751251220703,
+      "learning_rate": 7.11e-07,
+      "loss": -0.0321,
+      "step": 289
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 7.926824569702148,
+      "learning_rate": 7.1e-07,
+      "loss": -0.014,
+      "step": 290
+    },
+    {
+      "epoch": 0.291,
+      "grad_norm": 11.509428024291992,
+      "learning_rate": 7.089999999999999e-07,
+      "loss": -0.0175,
+      "step": 291
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 581.7306518554688,
+      "learning_rate": 7.079999999999999e-07,
+      "loss": -16.2215,
+      "step": 292
+    },
+    {
+      "epoch": 0.293,
+      "grad_norm": 79.94517517089844,
+      "learning_rate": 7.07e-07,
+      "loss": -5.9011,
+      "step": 293
+    },
+    {
+      "epoch": 0.294,
+      "grad_norm": 7.418095588684082,
+      "learning_rate": 7.059999999999999e-07,
+      "loss": -0.0161,
+      "step": 294
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 19.29140853881836,
+      "learning_rate": 7.049999999999999e-07,
+      "loss": -9.5908,
+      "step": 295
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 11.766737937927246,
+      "learning_rate": 7.04e-07,
+      "loss": -0.0144,
+      "step": 296
+    },
+    {
+      "epoch": 0.297,
+      "grad_norm": 0.4649788439273834,
+      "learning_rate": 7.029999999999999e-07,
+      "loss": -0.016,
+      "step": 297
+    },
+    {
+      "epoch": 0.298,
+      "grad_norm": 17.348590850830078,
+      "learning_rate": 7.019999999999999e-07,
+      "loss": -0.0152,
+      "step": 298
+    },
+    {
+      "epoch": 0.299,
+      "grad_norm": 0.5954681634902954,
+      "learning_rate": 7.009999999999999e-07,
+      "loss": -0.0162,
+      "step": 299
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2508128583431244,
+      "learning_rate": 7e-07,
+      "loss": -0.0154,
+      "step": 300
+    },
+    {
+      "epoch": 0.301,
+      "grad_norm": 0.3036130964756012,
+      "learning_rate": 6.989999999999999e-07,
+      "loss": -2.9757,
+      "step": 301
+    },
+    {
+      "epoch": 0.302,
+      "grad_norm": 7.507372856140137,
+      "learning_rate": 6.979999999999999e-07,
+      "loss": -11.9835,
+      "step": 302
+    },
+    {
+      "epoch": 0.303,
+      "grad_norm": 0.2679802477359772,
+      "learning_rate": 6.97e-07,
+      "loss": -0.0161,
+      "step": 303
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 11.13752269744873,
+      "learning_rate": 6.959999999999999e-07,
+      "loss": -0.0171,
+      "step": 304
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 22.38118553161621,
+      "learning_rate": 6.949999999999999e-07,
+      "loss": -0.0163,
+      "step": 305
+    },
+    {
+      "epoch": 0.306,
+      "grad_norm": 19.349185943603516,
+      "learning_rate": 6.939999999999999e-07,
+      "loss": -0.0176,
+      "step": 306
+    },
+    {
+      "epoch": 0.307,
+      "grad_norm": 17.963581085205078,
+      "learning_rate": 6.929999999999999e-07,
+      "loss": -0.0165,
+      "step": 307
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.32542455196380615,
+      "learning_rate": 6.919999999999999e-07,
+      "loss": -0.0155,
+      "step": 308
+    },
+    {
+      "epoch": 0.309,
+      "grad_norm": 9.864352226257324,
+      "learning_rate": 6.909999999999999e-07,
+      "loss": -0.0168,
+      "step": 309
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 8.623437881469727,
+      "learning_rate": 6.9e-07,
+      "loss": -0.0201,
+      "step": 310
+    },
+    {
+      "epoch": 0.311,
+      "grad_norm": 0.3907215893268585,
+      "learning_rate": 6.889999999999999e-07,
+      "loss": -0.0178,
+      "step": 311
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 11.305391311645508,
+      "learning_rate": 6.879999999999999e-07,
+      "loss": -0.0171,
+      "step": 312
+    },
+    {
+      "epoch": 0.313,
+      "grad_norm": 15.94853687286377,
+      "learning_rate": 6.87e-07,
+      "loss": -0.0184,
+      "step": 313
+    },
+    {
+      "epoch": 0.314,
+      "grad_norm": 0.17825861275196075,
+      "learning_rate": 6.86e-07,
+      "loss": -0.019,
+      "step": 314
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 0.17389419674873352,
+      "learning_rate": 6.85e-07,
+      "loss": -0.0167,
+      "step": 315
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 20.032785415649414,
+      "learning_rate": 6.84e-07,
+      "loss": -0.0208,
+      "step": 316
+    },
+    {
+      "epoch": 0.317,
+      "grad_norm": 0.182404562830925,
+      "learning_rate": 6.830000000000001e-07,
+      "loss": -0.0177,
+      "step": 317
+    },
+    {
+      "epoch": 0.318,
+      "grad_norm": 14.42383861541748,
+      "learning_rate": 6.82e-07,
+      "loss": -0.0187,
+      "step": 318
+    },
+    {
+      "epoch": 0.319,
+      "grad_norm": 1.0760735273361206,
+      "learning_rate": 6.81e-07,
+      "loss": -0.0216,
+      "step": 319
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 17.380788803100586,
+      "learning_rate": 6.800000000000001e-07,
+      "loss": -0.0195,
+      "step": 320
+    },
+    {
+      "epoch": 0.321,
+      "grad_norm": 11.483375549316406,
+      "learning_rate": 6.79e-07,
+      "loss": -0.0207,
+      "step": 321
+    },
+    {
+      "epoch": 0.322,
+      "grad_norm": 0.6222103238105774,
+      "learning_rate": 6.78e-07,
+      "loss": -0.0181,
+      "step": 322
+    },
+    {
+      "epoch": 0.323,
+      "grad_norm": 38.73816680908203,
+      "learning_rate": 6.77e-07,
+      "loss": -0.0194,
+      "step": 323
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 0.16626837849617004,
+      "learning_rate": 6.76e-07,
+      "loss": -0.0196,
+      "step": 324
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.35895398259162903,
+      "learning_rate": 6.75e-07,
+      "loss": -0.0191,
+      "step": 325
+    },
+    {
+      "epoch": 0.326,
+      "grad_norm": 18.686931610107422,
+      "learning_rate": 6.74e-07,
+      "loss": -0.0194,
+      "step": 326
+    },
+    {
+      "epoch": 0.327,
+      "grad_norm": 14.747398376464844,
+      "learning_rate": 6.730000000000001e-07,
+      "loss": -0.0212,
+      "step": 327
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.8805068731307983,
+      "learning_rate": 6.72e-07,
+      "loss": -0.0203,
+      "step": 328
+    },
+    {
+      "epoch": 0.329,
+      "grad_norm": 10.390252113342285,
+      "learning_rate": 6.71e-07,
+      "loss": -0.0185,
+      "step": 329
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.11015713959932327,
+      "learning_rate": 6.7e-07,
+      "loss": -0.0179,
+      "step": 330
+    },
+    {
+      "epoch": 0.331,
+      "grad_norm": 22.30323028564453,
+      "learning_rate": 6.69e-07,
+      "loss": -0.02,
+      "step": 331
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 0.5948154926300049,
+      "learning_rate": 6.68e-07,
+      "loss": -0.0191,
+      "step": 332
+    },
+    {
+      "epoch": 0.333,
+      "grad_norm": 10.135064125061035,
+      "learning_rate": 6.67e-07,
+      "loss": -0.0178,
+      "step": 333
+    },
+    {
+      "epoch": 0.334,
+      "grad_norm": 1.3906151056289673,
+      "learning_rate": 6.66e-07,
+      "loss": -0.0203,
+      "step": 334
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 0.684467613697052,
+      "learning_rate": 6.65e-07,
+      "loss": -0.0167,
+      "step": 335
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 5.278614521026611,
+      "learning_rate": 6.64e-07,
+      "loss": -0.0242,
+      "step": 336
+    },
+    {
+      "epoch": 0.337,
+      "grad_norm": 18.03533172607422,
+      "learning_rate": 6.63e-07,
+      "loss": -0.0156,
+      "step": 337
+    },
+    {
+      "epoch": 0.338,
+      "grad_norm": 16.466930389404297,
+      "learning_rate": 6.62e-07,
+      "loss": -0.0159,
+      "step": 338
+    },
+    {
+      "epoch": 0.339,
+      "grad_norm": 0.2426922619342804,
+      "learning_rate": 6.61e-07,
+      "loss": -0.0155,
+      "step": 339
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.30216166377067566,
+      "learning_rate": 6.6e-07,
+      "loss": -0.0145,
+      "step": 340
+    },
+    {
+      "epoch": 0.341,
+      "grad_norm": 11.390799522399902,
+      "learning_rate": 6.59e-07,
+      "loss": -0.0166,
+      "step": 341
+    },
+    {
+      "epoch": 0.342,
+      "grad_norm": 13.057865142822266,
+      "learning_rate": 6.58e-07,
+      "loss": -0.0169,
+      "step": 342
+    },
+    {
+      "epoch": 0.343,
+      "grad_norm": 9.05225658416748,
+      "learning_rate": 6.57e-07,
+      "loss": -0.0196,
+      "step": 343
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.26592203974723816,
+      "learning_rate": 6.56e-07,
+      "loss": -0.0193,
+      "step": 344
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 25.080825805664062,
+      "learning_rate": 6.55e-07,
+      "loss": -0.0219,
+      "step": 345
+    },
+    {
+      "epoch": 0.346,
+      "grad_norm": 34.43766403198242,
+      "learning_rate": 6.54e-07,
+      "loss": -0.0196,
+      "step": 346
+    },
+    {
+      "epoch": 0.347,
+      "grad_norm": 21.205123901367188,
+      "learning_rate": 6.53e-07,
+      "loss": -0.0211,
+      "step": 347
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 50.17305374145508,
+      "learning_rate": 6.52e-07,
+      "loss": -0.0202,
+      "step": 348
+    },
+    {
+      "epoch": 0.349,
+      "grad_norm": 15.89778995513916,
+      "learning_rate": 6.51e-07,
+      "loss": -0.0193,
+      "step": 349
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.15921801328659058,
+      "learning_rate": 6.5e-07,
+      "loss": -0.0191,
+      "step": 350
+    },
+    {
+      "epoch": 0.351,
+      "grad_norm": 14.905006408691406,
+      "learning_rate": 6.49e-07,
+      "loss": -0.0202,
+      "step": 351
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 175.54844665527344,
+      "learning_rate": 6.48e-07,
+      "loss": -0.0203,
+      "step": 352
+    },
+    {
+      "epoch": 0.353,
+      "grad_norm": 0.37033963203430176,
+      "learning_rate": 6.47e-07,
+      "loss": -0.0216,
+      "step": 353
+    },
+    {
+      "epoch": 0.354,
+      "grad_norm": 10.350979804992676,
+      "learning_rate": 6.46e-07,
+      "loss": -0.0224,
+      "step": 354
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 0.29729995131492615,
+      "learning_rate": 6.45e-07,
+      "loss": -0.0203,
+      "step": 355
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 20.688861846923828,
+      "learning_rate": 6.44e-07,
+      "loss": -0.02,
+      "step": 356
+    },
+    {
+      "epoch": 0.357,
+      "grad_norm": 0.12461265176534653,
+      "learning_rate": 6.43e-07,
+      "loss": -0.021,
+      "step": 357
+    },
+    {
+      "epoch": 0.358,
+      "grad_norm": 2.2356441020965576,
+      "learning_rate": 6.42e-07,
+      "loss": -0.0221,
+      "step": 358
+    },
+    {
+      "epoch": 0.359,
+      "grad_norm": 0.5642574429512024,
+      "learning_rate": 6.41e-07,
+      "loss": -0.0207,
+      "step": 359
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.15112696588039398,
+      "learning_rate": 6.4e-07,
+      "loss": -0.0217,
+      "step": 360
+    },
+    {
+      "epoch": 0.361,
+      "grad_norm": 0.18292704224586487,
+      "learning_rate": 6.389999999999999e-07,
+      "loss": -0.0218,
+      "step": 361
+    },
+    {
+      "epoch": 0.362,
+      "grad_norm": 141.11273193359375,
+      "learning_rate": 6.38e-07,
+      "loss": -0.115,
+      "step": 362
+    },
+    {
+      "epoch": 0.363,
+      "grad_norm": 0.2881525456905365,
+      "learning_rate": 6.37e-07,
+      "loss": -0.0219,
+      "step": 363
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 25.778043746948242,
+      "learning_rate": 6.36e-07,
+      "loss": -0.0241,
+      "step": 364
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 35.09903335571289,
+      "learning_rate": 6.35e-07,
+      "loss": -0.0233,
+      "step": 365
+    },
+    {
+      "epoch": 0.366,
+      "grad_norm": 8.698143005371094,
+      "learning_rate": 6.34e-07,
+      "loss": -0.0218,
+      "step": 366
+    },
+    {
+      "epoch": 0.367,
+      "grad_norm": 0.4322740137577057,
+      "learning_rate": 6.33e-07,
+      "loss": -0.0214,
+      "step": 367
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 24.4484806060791,
+      "learning_rate": 6.319999999999999e-07,
+      "loss": -0.0219,
+      "step": 368
+    },
+    {
+      "epoch": 0.369,
+      "grad_norm": 23.30872344970703,
+      "learning_rate": 6.31e-07,
+      "loss": -0.0226,
+      "step": 369
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.18092481791973114,
+      "learning_rate": 6.3e-07,
+      "loss": -0.0213,
+      "step": 370
+    },
+    {
+      "epoch": 0.371,
+      "grad_norm": 26.777523040771484,
+      "learning_rate": 6.289999999999999e-07,
+      "loss": -0.0215,
+      "step": 371
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 18.544477462768555,
+      "learning_rate": 6.28e-07,
+      "loss": -0.0223,
+      "step": 372
+    },
+    {
+      "epoch": 0.373,
+      "grad_norm": 0.24665169417858124,
+      "learning_rate": 6.27e-07,
+      "loss": -0.0199,
+      "step": 373
+    },
+    {
+      "epoch": 0.374,
+      "grad_norm": 33.62397003173828,
+      "learning_rate": 6.26e-07,
+      "loss": -0.0223,
+      "step": 374
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.21498312056064606,
+      "learning_rate": 6.249999999999999e-07,
+      "loss": -0.0199,
+      "step": 375
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 20.38393211364746,
+      "learning_rate": 6.24e-07,
+      "loss": -0.0211,
+      "step": 376
+    },
+    {
+      "epoch": 0.377,
+      "grad_norm": 0.5792163610458374,
+      "learning_rate": 6.23e-07,
+      "loss": -0.0232,
+      "step": 377
+    },
+    {
+      "epoch": 0.378,
+      "grad_norm": 31.55739974975586,
+      "learning_rate": 6.219999999999999e-07,
+      "loss": -0.021,
+      "step": 378
+    },
+    {
+      "epoch": 0.379,
+      "grad_norm": 16.803035736083984,
+      "learning_rate": 6.21e-07,
+      "loss": -0.0207,
+      "step": 379
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.416060209274292,
+      "learning_rate": 6.2e-07,
+      "loss": -0.0215,
+      "step": 380
+    },
+    {
+      "epoch": 0.381,
+      "grad_norm": 28.01506233215332,
+      "learning_rate": 6.189999999999999e-07,
+      "loss": -0.0236,
+      "step": 381
+    },
+    {
+      "epoch": 0.382,
+      "grad_norm": 0.5498484373092651,
+      "learning_rate": 6.18e-07,
+      "loss": -0.0231,
+      "step": 382
+    },
+    {
+      "epoch": 0.383,
+      "grad_norm": 10.306578636169434,
+      "learning_rate": 6.17e-07,
+      "loss": -0.0201,
+      "step": 383
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 36.499473571777344,
+      "learning_rate": 6.16e-07,
+      "loss": -0.0196,
+      "step": 384
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 0.21647116541862488,
+      "learning_rate": 6.149999999999999e-07,
+      "loss": -0.0201,
+      "step": 385
+    },
+    {
+      "epoch": 0.386,
+      "grad_norm": 0.2499529868364334,
+      "learning_rate": 6.14e-07,
+      "loss": -0.021,
+      "step": 386
+    },
+    {
+      "epoch": 0.387,
+      "grad_norm": 1.084391474723816,
+      "learning_rate": 6.13e-07,
+      "loss": -0.0227,
+      "step": 387
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 0.9214080572128296,
+      "learning_rate": 6.119999999999999e-07,
+      "loss": -0.0238,
+      "step": 388
+    },
+    {
+      "epoch": 0.389,
+      "grad_norm": 19.250062942504883,
+      "learning_rate": 6.11e-07,
+      "loss": -0.022,
+      "step": 389
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.26802465319633484,
+      "learning_rate": 6.1e-07,
+      "loss": -0.0196,
+      "step": 390
+    },
+    {
+      "epoch": 0.391,
+      "grad_norm": 106.85203552246094,
+      "learning_rate": 6.089999999999999e-07,
+      "loss": -0.0224,
+      "step": 391
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.8422381281852722,
+      "learning_rate": 6.079999999999999e-07,
+      "loss": -0.0206,
+      "step": 392
+    },
+    {
+      "epoch": 0.393,
+      "grad_norm": 0.7585501670837402,
+      "learning_rate": 6.07e-07,
+      "loss": -0.0224,
+      "step": 393
+    },
+    {
+      "epoch": 0.394,
+      "grad_norm": 28.89423370361328,
+      "learning_rate": 6.06e-07,
+      "loss": -0.0227,
+      "step": 394
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 26.399568557739258,
+      "learning_rate": 6.049999999999999e-07,
+      "loss": -0.0411,
+      "step": 395
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 11.942886352539062,
+      "learning_rate": 6.04e-07,
+      "loss": -0.0217,
+      "step": 396
+    },
+    {
+      "epoch": 0.397,
+      "grad_norm": 0.28943026065826416,
+      "learning_rate": 6.03e-07,
+      "loss": -0.0208,
+      "step": 397
+    },
+    {
+      "epoch": 0.398,
+      "grad_norm": 0.08330436050891876,
+      "learning_rate": 6.019999999999999e-07,
+      "loss": -0.0213,
+      "step": 398
+    },
+    {
+      "epoch": 0.399,
+      "grad_norm": 30.01115608215332,
+      "learning_rate": 6.009999999999999e-07,
+      "loss": -0.0224,
+      "step": 399
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.371118187904358,
+      "learning_rate": 6e-07,
+      "loss": -0.0217,
+      "step": 400
+    },
+    {
+      "epoch": 0.401,
+      "grad_norm": 0.05491195619106293,
+      "learning_rate": 5.989999999999999e-07,
+      "loss": -0.0214,
+      "step": 401
+    },
+    {
+      "epoch": 0.402,
+      "grad_norm": 0.0758928507566452,
+      "learning_rate": 5.979999999999999e-07,
+      "loss": -0.0198,
+      "step": 402
+    },
+    {
+      "epoch": 0.403,
+      "grad_norm": 3.590472936630249,
+      "learning_rate": 5.97e-07,
+      "loss": -0.0241,
+      "step": 403
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 12.983104705810547,
+      "learning_rate": 5.96e-07,
+      "loss": -0.0223,
+      "step": 404
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 1.925836205482483,
+      "learning_rate": 5.949999999999999e-07,
+      "loss": -0.0222,
+      "step": 405
+    },
+    {
+      "epoch": 0.406,
+      "grad_norm": 0.14429360628128052,
+      "learning_rate": 5.939999999999999e-07,
+      "loss": -0.0209,
+      "step": 406
+    },
+    {
+      "epoch": 0.407,
+      "grad_norm": 0.0922478511929512,
+      "learning_rate": 5.93e-07,
+      "loss": -0.0213,
+      "step": 407
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.1684679090976715,
+      "learning_rate": 5.919999999999999e-07,
+      "loss": -0.0226,
+      "step": 408
+    },
+    {
+      "epoch": 0.409,
+      "grad_norm": 0.15818046033382416,
+      "learning_rate": 5.909999999999999e-07,
+      "loss": -0.021,
+      "step": 409
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 13.302352905273438,
+      "learning_rate": 5.9e-07,
+      "loss": -0.0233,
+      "step": 410
+    },
+    {
+      "epoch": 0.411,
+      "grad_norm": 1.632759928703308,
+      "learning_rate": 5.89e-07,
+      "loss": -0.0206,
+      "step": 411
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 4.784732341766357,
+      "learning_rate": 5.879999999999999e-07,
+      "loss": -0.0236,
+      "step": 412
+    },
+    {
+      "epoch": 0.413,
+      "grad_norm": 0.2627317011356354,
+      "learning_rate": 5.87e-07,
+      "loss": -0.0214,
+      "step": 413
+    },
+    {
+      "epoch": 0.414,
+      "grad_norm": 0.10862652212381363,
+      "learning_rate": 5.86e-07,
+      "loss": -0.021,
+      "step": 414
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 8.3672456741333,
+      "learning_rate": 5.849999999999999e-07,
+      "loss": -0.02,
+      "step": 415
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.09097602963447571,
+      "learning_rate": 5.839999999999999e-07,
+      "loss": -0.0229,
+      "step": 416
+    },
+    {
+      "epoch": 0.417,
+      "grad_norm": 1.1638470888137817,
+      "learning_rate": 5.83e-07,
+      "loss": -0.0195,
+      "step": 417
+    },
+    {
+      "epoch": 0.418,
+      "grad_norm": 35.60856628417969,
+      "learning_rate": 5.819999999999999e-07,
+      "loss": -0.0202,
+      "step": 418
+    },
+    {
+      "epoch": 0.419,
+      "grad_norm": 0.13040615618228912,
+      "learning_rate": 5.809999999999999e-07,
+      "loss": -0.0216,
+      "step": 419
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3730159401893616,
+      "learning_rate": 5.8e-07,
+      "loss": -0.0185,
+      "step": 420
+    },
+    {
+      "epoch": 0.421,
+      "grad_norm": 33.22984313964844,
+      "learning_rate": 5.79e-07,
+      "loss": -0.0214,
+      "step": 421
+    },
+    {
+      "epoch": 0.422,
+      "grad_norm": 23.419509887695312,
+      "learning_rate": 5.779999999999999e-07,
+      "loss": -0.0214,
+      "step": 422
+    },
+    {
+      "epoch": 0.423,
+      "grad_norm": 2.6873676776885986,
+      "learning_rate": 5.769999999999999e-07,
+      "loss": -0.0207,
+      "step": 423
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 8.351359367370605,
+      "learning_rate": 5.76e-07,
+      "loss": -0.0202,
+      "step": 424
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 18.850969314575195,
+      "learning_rate": 5.749999999999999e-07,
+      "loss": -0.0202,
+      "step": 425
+    },
+    {
+      "epoch": 0.426,
+      "grad_norm": 0.12487243115901947,
+      "learning_rate": 5.739999999999999e-07,
+      "loss": -0.0204,
+      "step": 426
+    },
+    {
+      "epoch": 0.427,
+      "grad_norm": 29.81341552734375,
+      "learning_rate": 5.73e-07,
+      "loss": -0.0206,
+      "step": 427
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 17.285696029663086,
+      "learning_rate": 5.719999999999999e-07,
+      "loss": -0.0219,
+      "step": 428
+    },
+    {
+      "epoch": 0.429,
+      "grad_norm": 0.01124389935284853,
+      "learning_rate": 5.709999999999999e-07,
+      "loss": -0.0204,
+      "step": 429
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 5.026052951812744,
+      "learning_rate": 5.699999999999999e-07,
+      "loss": -0.021,
+      "step": 430
+    },
+    {
+      "epoch": 0.431,
+      "grad_norm": 15.67419719696045,
+      "learning_rate": 5.69e-07,
+      "loss": -0.0214,
+      "step": 431
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 42.911834716796875,
+      "learning_rate": 5.679999999999999e-07,
+      "loss": -0.0215,
+      "step": 432
+    },
+    {
+      "epoch": 0.433,
+      "grad_norm": 11.09153938293457,
+      "learning_rate": 5.669999999999999e-07,
+      "loss": -0.0211,
+      "step": 433
+    },
+    {
+      "epoch": 0.434,
+      "grad_norm": 0.011223341338336468,
+      "learning_rate": 5.66e-07,
+      "loss": -0.0214,
+      "step": 434
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 0.057168252766132355,
+      "learning_rate": 5.649999999999999e-07,
+      "loss": -0.0218,
+      "step": 435
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 0.07865128666162491,
+      "learning_rate": 5.639999999999999e-07,
+      "loss": -0.0215,
+      "step": 436
+    },
+    {
+      "epoch": 0.437,
+      "grad_norm": 0.0804368183016777,
+      "learning_rate": 5.629999999999999e-07,
+      "loss": -0.0215,
+      "step": 437
+    },
+    {
+      "epoch": 0.438,
+      "grad_norm": 0.18600013852119446,
+      "learning_rate": 5.620000000000001e-07,
+      "loss": -0.0202,
+      "step": 438
+    },
+    {
+      "epoch": 0.439,
+      "grad_norm": 8.603721618652344,
+      "learning_rate": 5.61e-07,
+      "loss": -0.0219,
+      "step": 439
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.006383820436894894,
+      "learning_rate": 5.6e-07,
+      "loss": -0.0214,
+      "step": 440
+    },
+    {
+      "epoch": 0.441,
+      "grad_norm": 0.403230220079422,
+      "learning_rate": 5.590000000000001e-07,
+      "loss": -0.0228,
+      "step": 441
+    },
+    {
+      "epoch": 0.442,
+      "grad_norm": 0.011017720215022564,
+      "learning_rate": 5.58e-07,
+      "loss": -0.0213,
+      "step": 442
+    },
+    {
+      "epoch": 0.443,
+      "grad_norm": 0.005116923712193966,
+      "learning_rate": 5.57e-07,
+      "loss": -0.0202,
+      "step": 443
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 0.051764048635959625,
+      "learning_rate": 5.560000000000001e-07,
+      "loss": -0.0217,
+      "step": 444
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 0.012888140045106411,
+      "learning_rate": 5.55e-07,
+      "loss": -0.0218,
+      "step": 445
+    },
+    {
+      "epoch": 0.446,
+      "grad_norm": 0.10950469225645065,
+      "learning_rate": 5.54e-07,
+      "loss": -0.0201,
+      "step": 446
+    },
+    {
+      "epoch": 0.447,
+      "grad_norm": 0.004182915668934584,
+      "learning_rate": 5.53e-07,
+      "loss": -0.0212,
+      "step": 447
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 13.388778686523438,
+      "learning_rate": 5.520000000000001e-07,
+      "loss": -0.0207,
+      "step": 448
+    },
+    {
+      "epoch": 0.449,
+      "grad_norm": 0.005313895642757416,
+      "learning_rate": 5.51e-07,
+      "loss": -0.0209,
+      "step": 449
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.011246556416153908,
+      "learning_rate": 5.5e-07,
+      "loss": -0.0214,
+      "step": 450
+    },
+    {
+      "epoch": 0.451,
+      "grad_norm": 3.540335178375244,
+      "learning_rate": 5.490000000000001e-07,
+      "loss": -0.0223,
+      "step": 451
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 10.97947883605957,
+      "learning_rate": 5.48e-07,
+      "loss": -0.0221,
+      "step": 452
+    },
+    {
+      "epoch": 0.453,
+      "grad_norm": 0.025508947670459747,
+      "learning_rate": 5.47e-07,
+      "loss": -0.0215,
+      "step": 453
+    },
+    {
+      "epoch": 0.454,
+      "grad_norm": 4.389809608459473,
+      "learning_rate": 5.46e-07,
+      "loss": -0.0256,
+      "step": 454
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 22.6923828125,
+      "learning_rate": 5.45e-07,
+      "loss": -0.0201,
+      "step": 455
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.05772879347205162,
+      "learning_rate": 5.44e-07,
+      "loss": -0.0214,
+      "step": 456
+    },
+    {
+      "epoch": 0.457,
+      "grad_norm": 36.30032730102539,
+      "learning_rate": 5.43e-07,
+      "loss": -0.0209,
+      "step": 457
+    },
+    {
+      "epoch": 0.458,
+      "grad_norm": 20.58974266052246,
+      "learning_rate": 5.420000000000001e-07,
+      "loss": -0.0215,
+      "step": 458
+    },
+    {
+      "epoch": 0.459,
+      "grad_norm": 33.54576873779297,
+      "learning_rate": 5.41e-07,
+      "loss": -0.0199,
+      "step": 459
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 11.226568222045898,
+      "learning_rate": 5.4e-07,
+      "loss": -0.0215,
+      "step": 460
+    },
+    {
+      "epoch": 0.461,
+      "grad_norm": 14.77125072479248,
+      "learning_rate": 5.39e-07,
+      "loss": -0.0214,
+      "step": 461
+    },
+    {
+      "epoch": 0.462,
+      "grad_norm": 0.09918845444917679,
+      "learning_rate": 5.38e-07,
+      "loss": -0.0196,
+      "step": 462
+    },
+    {
+      "epoch": 0.463,
+      "grad_norm": 0.1098228320479393,
+      "learning_rate": 5.37e-07,
+      "loss": -0.021,
+      "step": 463
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.008116762153804302,
+      "learning_rate": 5.36e-07,
+      "loss": -0.0229,
+      "step": 464
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 2.2812070846557617,
+      "learning_rate": 5.35e-07,
+      "loss": -0.022,
+      "step": 465
+    },
+    {
+      "epoch": 0.466,
+      "grad_norm": 11.995945930480957,
+      "learning_rate": 5.34e-07,
+      "loss": -0.0217,
+      "step": 466
+    },
+    {
+      "epoch": 0.467,
+      "grad_norm": 0.003694022772833705,
+      "learning_rate": 5.33e-07,
+      "loss": -0.0206,
+      "step": 467
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 0.021653158590197563,
+      "learning_rate": 5.32e-07,
+      "loss": -0.0207,
+      "step": 468
+    },
+    {
+      "epoch": 0.469,
+      "grad_norm": 0.08230645209550858,
+      "learning_rate": 5.31e-07,
+      "loss": -0.0215,
+      "step": 469
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 20.44363784790039,
+      "learning_rate": 5.3e-07,
+      "loss": -0.0254,
+      "step": 470
+    },
+    {
+      "epoch": 0.471,
+      "grad_norm": 20.872936248779297,
+      "learning_rate": 5.29e-07,
+      "loss": -0.0216,
+      "step": 471
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.7526280283927917,
+      "learning_rate": 5.28e-07,
+      "loss": -0.0216,
+      "step": 472
+    },
+    {
+      "epoch": 0.473,
+      "grad_norm": 1.3575342893600464,
+      "learning_rate": 5.27e-07,
+      "loss": -0.0216,
+      "step": 473
+    },
+    {
+      "epoch": 0.474,
+      "grad_norm": 0.3029508888721466,
+      "learning_rate": 5.26e-07,
+      "loss": -0.0212,
+      "step": 474
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.0847870409488678,
+      "learning_rate": 5.25e-07,
+      "loss": -0.0222,
+      "step": 475
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 0.29451194405555725,
+      "learning_rate": 5.24e-07,
+      "loss": -0.0209,
+      "step": 476
+    },
+    {
+      "epoch": 0.477,
+      "grad_norm": 0.1121833547949791,
+      "learning_rate": 5.23e-07,
+      "loss": -0.0222,
+      "step": 477
+    },
+    {
+      "epoch": 0.478,
+      "grad_norm": 0.9485394358634949,
+      "learning_rate": 5.22e-07,
+      "loss": -0.0216,
+      "step": 478
+    },
+    {
+      "epoch": 0.479,
+      "grad_norm": 0.229567289352417,
+      "learning_rate": 5.21e-07,
+      "loss": -0.0207,
+      "step": 479
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.15580624341964722,
+      "learning_rate": 5.2e-07,
+      "loss": -0.021,
+      "step": 480
+    },
+    {
+      "epoch": 0.481,
+      "grad_norm": 2.089952230453491,
+      "learning_rate": 5.19e-07,
+      "loss": -0.0241,
+      "step": 481
+    },
+    {
+      "epoch": 0.482,
+      "grad_norm": 0.018858514726161957,
+      "learning_rate": 5.18e-07,
+      "loss": -0.0205,
+      "step": 482
+    },
+    {
+      "epoch": 0.483,
+      "grad_norm": 8.776660919189453,
+      "learning_rate": 5.17e-07,
+      "loss": -0.0258,
+      "step": 483
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 0.012773383408784866,
+      "learning_rate": 5.16e-07,
+      "loss": -0.0198,
+      "step": 484
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 31.97705078125,
+      "learning_rate": 5.149999999999999e-07,
+      "loss": -0.0233,
+      "step": 485
+    },
+    {
+      "epoch": 0.486,
+      "grad_norm": 0.004696122836321592,
+      "learning_rate": 5.14e-07,
+      "loss": -0.0197,
+      "step": 486
+    },
+    {
+      "epoch": 0.487,
+      "grad_norm": 0.04128094017505646,
+      "learning_rate": 5.13e-07,
+      "loss": -0.0214,
+      "step": 487
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 9.115206718444824,
+      "learning_rate": 5.12e-07,
+      "loss": -0.0284,
+      "step": 488
+    },
+    {
+      "epoch": 0.489,
+      "grad_norm": 28.6943416595459,
+      "learning_rate": 5.11e-07,
+      "loss": -0.0217,
+      "step": 489
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.030571995303034782,
+      "learning_rate": 5.1e-07,
+      "loss": -0.0234,
+      "step": 490
+    },
+    {
+      "epoch": 0.491,
+      "grad_norm": 28.605690002441406,
+      "learning_rate": 5.09e-07,
+      "loss": -0.0214,
+      "step": 491
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 0.0029869191348552704,
+      "learning_rate": 5.079999999999999e-07,
+      "loss": -0.0223,
+      "step": 492
+    },
+    {
+      "epoch": 0.493,
+      "grad_norm": 0.03462494909763336,
+      "learning_rate": 5.07e-07,
+      "loss": -0.0224,
+      "step": 493
+    },
+    {
+      "epoch": 0.494,
+      "grad_norm": 0.001028486411087215,
+      "learning_rate": 5.06e-07,
+      "loss": -0.0206,
+      "step": 494
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 0.001807240303605795,
+      "learning_rate": 5.049999999999999e-07,
+      "loss": -0.0204,
+      "step": 495
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.004462388344109058,
+      "learning_rate": 5.04e-07,
+      "loss": -0.0209,
+      "step": 496
+    },
+    {
+      "epoch": 0.497,
+      "grad_norm": 0.0032996328081935644,
+      "learning_rate": 5.03e-07,
+      "loss": -0.0214,
+      "step": 497
+    },
+    {
+      "epoch": 0.498,
+      "grad_norm": 0.002159065566956997,
+      "learning_rate": 5.02e-07,
+      "loss": -0.0209,
+      "step": 498
+    },
+    {
+      "epoch": 0.499,
+      "grad_norm": 0.07682286202907562,
+      "learning_rate": 5.009999999999999e-07,
+      "loss": -0.0224,
+      "step": 499
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.23552227020263672,
+      "learning_rate": 5e-07,
+      "loss": -0.022,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119a946d4a384acd516af0d4019416045f73f1e78a556987aacaad6578c07c41
+size 8440