Upload folder using huggingface_hub

.gitattributes

@@ -46,3 +46,4 @@ grpo-procthor-sequence-1105-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs
 grpo-clevr-1105-1epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 grpo-procthor-1105-5epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 sft-procthor-1108-7epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+sft-procthor-1108-20epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text

sft-procthor-1108-20epoch/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
+}

sft-procthor-1108-20epoch/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 %}"
+}

sft-procthor-1108-20epoch/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "model_type": "qwen2_5_vl",
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

sft-procthor-1108-20epoch/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": "4.49.0",
+  "use_cache": false
+}

sft-procthor-1108-20epoch/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d39bb20217d0965ff6161af27797dde96f347e6dcb067a8b104748369d6819
+size 4968243304

sft-procthor-1108-20epoch/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a40f93c95b1b484994a256d0ea32a9103e55dcbc6d2defaa64822d612aac68
+size 4991495816

sft-procthor-1108-20epoch/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3fa8908f2978af530b961e42ee8a8add4227c95c3187dbf0dfabdcebcc67af
+size 4932751040

sft-procthor-1108-20epoch/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931c541eadd4a2c8a2b1d55184a8e30ba7509a3aac126fa95f28d3198e4aef64
+size 1691924384

sft-procthor-1108-20epoch/model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

sft-procthor-1108-20epoch/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
+}

sft-procthor-1108-20epoch/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
+  }
+}

sft-procthor-1108-20epoch/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0c439f7be467bf47d12a7e6f9adc6116201056fc60c67f431c679b7c16afc8
+size 11422064

sft-procthor-1108-20epoch/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
+}

sft-procthor-1108-20epoch/trainer_state.json

@@ -0,0 +1,1449 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 1180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "step": 0,
+      "train/loss": 1.4470248222351074
+    },
+    {
+      "epoch": 0.1694915254237288,
+      "grad_norm": 5.84375,
+      "learning_rate": 1.9830508474576275e-05,
+      "loss": 0.6419,
+      "step": 10
+    },
+    {
+      "epoch": 0.1694915254237288,
+      "step": 10,
+      "train/loss": 0.47170916199684143
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 3.984375,
+      "learning_rate": 1.9661016949152545e-05,
+      "loss": 0.4504,
+      "step": 20
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "step": 20,
+      "train/loss": 0.3966394364833832
+    },
+    {
+      "epoch": 0.5084745762711864,
+      "grad_norm": 4.0,
+      "learning_rate": 1.9491525423728814e-05,
+      "loss": 0.4089,
+      "step": 30
+    },
+    {
+      "epoch": 0.5084745762711864,
+      "step": 30,
+      "train/loss": 0.37289565801620483
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.9322033898305087e-05,
+      "loss": 0.3761,
+      "step": 40
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "step": 40,
+      "train/loss": 0.35740864276885986
+    },
+    {
+      "epoch": 0.847457627118644,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.9152542372881357e-05,
+      "loss": 0.3713,
+      "step": 50
+    },
+    {
+      "epoch": 0.847457627118644,
+      "step": 50,
+      "train/loss": 0.3621162176132202
+    },
+    {
+      "epoch": 1.0169491525423728,
+      "grad_norm": 3.0,
+      "learning_rate": 1.898305084745763e-05,
+      "loss": 0.3672,
+      "step": 60
+    },
+    {
+      "epoch": 1.0169491525423728,
+      "step": 60,
+      "train/loss": 0.31411823630332947
+    },
+    {
+      "epoch": 1.1864406779661016,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.88135593220339e-05,
+      "loss": 0.3532,
+      "step": 70
+    },
+    {
+      "epoch": 1.1864406779661016,
+      "step": 70,
+      "train/loss": 0.3259919285774231
+    },
+    {
+      "epoch": 1.3559322033898304,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.864406779661017e-05,
+      "loss": 0.3605,
+      "step": 80
+    },
+    {
+      "epoch": 1.3559322033898304,
+      "step": 80,
+      "train/loss": 0.3220116198062897
+    },
+    {
+      "epoch": 1.5254237288135593,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.8474576271186443e-05,
+      "loss": 0.3491,
+      "step": 90
+    },
+    {
+      "epoch": 1.5254237288135593,
+      "step": 90,
+      "train/loss": 0.3267311751842499
+    },
+    {
+      "epoch": 1.694915254237288,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.8305084745762713e-05,
+      "loss": 0.3457,
+      "step": 100
+    },
+    {
+      "epoch": 1.694915254237288,
+      "step": 100,
+      "train/loss": 0.3065634071826935
+    },
+    {
+      "epoch": 1.8644067796610169,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.8135593220338986e-05,
+      "loss": 0.3407,
+      "step": 110
+    },
+    {
+      "epoch": 1.8644067796610169,
+      "step": 110,
+      "train/loss": 0.32794389128685
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.7966101694915256e-05,
+      "loss": 0.337,
+      "step": 120
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "step": 120,
+      "train/loss": 0.3475218117237091
+    },
+    {
+      "epoch": 2.2033898305084745,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.7796610169491526e-05,
+      "loss": 0.3288,
+      "step": 130
+    },
+    {
+      "epoch": 2.2033898305084745,
+      "step": 130,
+      "train/loss": 0.31640565395355225
+    },
+    {
+      "epoch": 2.3728813559322033,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.76271186440678e-05,
+      "loss": 0.3254,
+      "step": 140
+    },
+    {
+      "epoch": 2.3728813559322033,
+      "step": 140,
+      "train/loss": 0.3183189630508423
+    },
+    {
+      "epoch": 2.542372881355932,
+      "grad_norm": 2.5,
+      "learning_rate": 1.745762711864407e-05,
+      "loss": 0.3193,
+      "step": 150
+    },
+    {
+      "epoch": 2.542372881355932,
+      "step": 150,
+      "train/loss": 0.3277460038661957
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.728813559322034e-05,
+      "loss": 0.3221,
+      "step": 160
+    },
+    {
+      "epoch": 2.711864406779661,
+      "step": 160,
+      "train/loss": 0.30371442437171936
+    },
+    {
+      "epoch": 2.8813559322033897,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.711864406779661e-05,
+      "loss": 0.3174,
+      "step": 170
+    },
+    {
+      "epoch": 2.8813559322033897,
+      "step": 170,
+      "train/loss": 0.31250590085983276
+    },
+    {
+      "epoch": 3.0508474576271185,
+      "grad_norm": 2.875,
+      "learning_rate": 1.694915254237288e-05,
+      "loss": 0.3085,
+      "step": 180
+    },
+    {
+      "epoch": 3.0508474576271185,
+      "step": 180,
+      "train/loss": 0.32504305243492126
+    },
+    {
+      "epoch": 3.2203389830508473,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.6779661016949154e-05,
+      "loss": 0.2895,
+      "step": 190
+    },
+    {
+      "epoch": 3.2203389830508473,
+      "step": 190,
+      "train/loss": 0.28471484780311584
+    },
+    {
+      "epoch": 3.389830508474576,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.6610169491525424e-05,
+      "loss": 0.2949,
+      "step": 200
+    },
+    {
+      "epoch": 3.389830508474576,
+      "step": 200,
+      "train/loss": 0.2855951189994812
+    },
+    {
+      "epoch": 3.559322033898305,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.6440677966101697e-05,
+      "loss": 0.2967,
+      "step": 210
+    },
+    {
+      "epoch": 3.559322033898305,
+      "step": 210,
+      "train/loss": 0.2883809208869934
+    },
+    {
+      "epoch": 3.7288135593220337,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.6271186440677967e-05,
+      "loss": 0.2994,
+      "step": 220
+    },
+    {
+      "epoch": 3.7288135593220337,
+      "step": 220,
+      "train/loss": 0.2865351736545563
+    },
+    {
+      "epoch": 3.898305084745763,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.6101694915254237e-05,
+      "loss": 0.2993,
+      "step": 230
+    },
+    {
+      "epoch": 3.898305084745763,
+      "step": 230,
+      "train/loss": 0.29260143637657166
+    },
+    {
+      "epoch": 4.067796610169491,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.593220338983051e-05,
+      "loss": 0.2767,
+      "step": 240
+    },
+    {
+      "epoch": 4.067796610169491,
+      "step": 240,
+      "train/loss": 0.2667180597782135
+    },
+    {
+      "epoch": 4.237288135593221,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.576271186440678e-05,
+      "loss": 0.2598,
+      "step": 250
+    },
+    {
+      "epoch": 4.237288135593221,
+      "step": 250,
+      "train/loss": 0.25305286049842834
+    },
+    {
+      "epoch": 4.406779661016949,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.5593220338983053e-05,
+      "loss": 0.2588,
+      "step": 260
+    },
+    {
+      "epoch": 4.406779661016949,
+      "step": 260,
+      "train/loss": 0.24407540261745453
+    },
+    {
+      "epoch": 4.576271186440678,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.5423728813559326e-05,
+      "loss": 0.2597,
+      "step": 270
+    },
+    {
+      "epoch": 4.576271186440678,
+      "step": 270,
+      "train/loss": 0.2666082978248596
+    },
+    {
+      "epoch": 4.745762711864407,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.5254237288135594e-05,
+      "loss": 0.259,
+      "step": 280
+    },
+    {
+      "epoch": 4.745762711864407,
+      "step": 280,
+      "train/loss": 0.24160327017307281
+    },
+    {
+      "epoch": 4.915254237288136,
+      "grad_norm": 2.75,
+      "learning_rate": 1.5084745762711865e-05,
+      "loss": 0.2665,
+      "step": 290
+    },
+    {
+      "epoch": 4.915254237288136,
+      "step": 290,
+      "train/loss": 0.24594742059707642
+    },
+    {
+      "epoch": 5.084745762711864,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.4915254237288137e-05,
+      "loss": 0.2471,
+      "step": 300
+    },
+    {
+      "epoch": 5.084745762711864,
+      "step": 300,
+      "train/loss": 0.22457915544509888
+    },
+    {
+      "epoch": 5.254237288135593,
+      "grad_norm": 3.875,
+      "learning_rate": 1.4745762711864408e-05,
+      "loss": 0.2233,
+      "step": 310
+    },
+    {
+      "epoch": 5.254237288135593,
+      "step": 310,
+      "train/loss": 0.2522847056388855
+    },
+    {
+      "epoch": 5.423728813559322,
+      "grad_norm": 3.890625,
+      "learning_rate": 1.4576271186440678e-05,
+      "loss": 0.2285,
+      "step": 320
+    },
+    {
+      "epoch": 5.423728813559322,
+      "step": 320,
+      "train/loss": 0.21290698647499084
+    },
+    {
+      "epoch": 5.593220338983051,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.440677966101695e-05,
+      "loss": 0.228,
+      "step": 330
+    },
+    {
+      "epoch": 5.593220338983051,
+      "step": 330,
+      "train/loss": 0.23090802133083344
+    },
+    {
+      "epoch": 5.762711864406779,
+      "grad_norm": 3.875,
+      "learning_rate": 1.4237288135593221e-05,
+      "loss": 0.224,
+      "step": 340
+    },
+    {
+      "epoch": 5.762711864406779,
+      "step": 340,
+      "train/loss": 0.24016369879245758
+    },
+    {
+      "epoch": 5.932203389830509,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.4067796610169493e-05,
+      "loss": 0.2267,
+      "step": 350
+    },
+    {
+      "epoch": 5.932203389830509,
+      "step": 350,
+      "train/loss": 0.21689116954803467
+    },
+    {
+      "epoch": 6.101694915254237,
+      "grad_norm": 3.625,
+      "learning_rate": 1.3898305084745764e-05,
+      "loss": 0.1993,
+      "step": 360
+    },
+    {
+      "epoch": 6.101694915254237,
+      "step": 360,
+      "train/loss": 0.17973674833774567
+    },
+    {
+      "epoch": 6.271186440677966,
+      "grad_norm": 4.28125,
+      "learning_rate": 1.3728813559322034e-05,
+      "loss": 0.1772,
+      "step": 370
+    },
+    {
+      "epoch": 6.271186440677966,
+      "step": 370,
+      "train/loss": 0.15253561735153198
+    },
+    {
+      "epoch": 6.440677966101695,
+      "grad_norm": 3.1875,
+      "learning_rate": 1.3559322033898305e-05,
+      "loss": 0.1761,
+      "step": 380
+    },
+    {
+      "epoch": 6.440677966101695,
+      "step": 380,
+      "train/loss": 0.17003832757472992
+    },
+    {
+      "epoch": 6.610169491525424,
+      "grad_norm": 4.34375,
+      "learning_rate": 1.3389830508474577e-05,
+      "loss": 0.1746,
+      "step": 390
+    },
+    {
+      "epoch": 6.610169491525424,
+      "step": 390,
+      "train/loss": 0.15967515110969543
+    },
+    {
+      "epoch": 6.779661016949152,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.3220338983050848e-05,
+      "loss": 0.1764,
+      "step": 400
+    },
+    {
+      "epoch": 6.779661016949152,
+      "step": 400,
+      "train/loss": 0.1983628273010254
+    },
+    {
+      "epoch": 6.9491525423728815,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.305084745762712e-05,
+      "loss": 0.1743,
+      "step": 410
+    },
+    {
+      "epoch": 6.9491525423728815,
+      "step": 410,
+      "train/loss": 0.1475476771593094
+    },
+    {
+      "epoch": 7.11864406779661,
+      "grad_norm": 4.40625,
+      "learning_rate": 1.288135593220339e-05,
+      "loss": 0.1423,
+      "step": 420
+    },
+    {
+      "epoch": 7.11864406779661,
+      "step": 420,
+      "train/loss": 0.10199220478534698
+    },
+    {
+      "epoch": 7.288135593220339,
+      "grad_norm": 3.703125,
+      "learning_rate": 1.2711864406779661e-05,
+      "loss": 0.1188,
+      "step": 430
+    },
+    {
+      "epoch": 7.288135593220339,
+      "step": 430,
+      "train/loss": 0.09074366837739944
+    },
+    {
+      "epoch": 7.4576271186440675,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.2542372881355932e-05,
+      "loss": 0.1307,
+      "step": 440
+    },
+    {
+      "epoch": 7.4576271186440675,
+      "step": 440,
+      "train/loss": 0.10294702649116516
+    },
+    {
+      "epoch": 7.627118644067797,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.2372881355932205e-05,
+      "loss": 0.1214,
+      "step": 450
+    },
+    {
+      "epoch": 7.627118644067797,
+      "step": 450,
+      "train/loss": 0.16743707656860352
+    },
+    {
+      "epoch": 7.796610169491525,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.2203389830508477e-05,
+      "loss": 0.1283,
+      "step": 460
+    },
+    {
+      "epoch": 7.796610169491525,
+      "step": 460,
+      "train/loss": 0.1334034651517868
+    },
+    {
+      "epoch": 7.966101694915254,
+      "grad_norm": 3.609375,
+      "learning_rate": 1.2033898305084745e-05,
+      "loss": 0.1233,
+      "step": 470
+    },
+    {
+      "epoch": 7.966101694915254,
+      "step": 470,
+      "train/loss": 0.10844478756189346
+    },
+    {
+      "epoch": 8.135593220338983,
+      "grad_norm": 5.0,
+      "learning_rate": 1.1864406779661018e-05,
+      "loss": 0.0817,
+      "step": 480
+    },
+    {
+      "epoch": 8.135593220338983,
+      "step": 480,
+      "train/loss": 0.12947241961956024
+    },
+    {
+      "epoch": 8.305084745762711,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.169491525423729e-05,
+      "loss": 0.0718,
+      "step": 490
+    },
+    {
+      "epoch": 8.305084745762711,
+      "step": 490,
+      "train/loss": 0.12831160426139832
+    },
+    {
+      "epoch": 8.474576271186441,
+      "grad_norm": 3.640625,
+      "learning_rate": 1.1525423728813561e-05,
+      "loss": 0.0766,
+      "step": 500
+    },
+    {
+      "epoch": 8.474576271186441,
+      "step": 500,
+      "train/loss": 0.07453884929418564
+    },
+    {
+      "epoch": 8.64406779661017,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.1355932203389833e-05,
+      "loss": 0.0742,
+      "step": 510
+    },
+    {
+      "epoch": 8.64406779661017,
+      "step": 510,
+      "train/loss": 0.06703273206949234
+    },
+    {
+      "epoch": 8.813559322033898,
+      "grad_norm": 4.625,
+      "learning_rate": 1.1186440677966102e-05,
+      "loss": 0.07,
+      "step": 520
+    },
+    {
+      "epoch": 8.813559322033898,
+      "step": 520,
+      "train/loss": 0.09600033611059189
+    },
+    {
+      "epoch": 8.983050847457626,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.1016949152542374e-05,
+      "loss": 0.0716,
+      "step": 530
+    },
+    {
+      "epoch": 8.983050847457626,
+      "step": 530,
+      "train/loss": 0.07930044829845428
+    },
+    {
+      "epoch": 9.152542372881356,
+      "grad_norm": 4.3125,
+      "learning_rate": 1.0847457627118645e-05,
+      "loss": 0.0366,
+      "step": 540
+    },
+    {
+      "epoch": 9.152542372881356,
+      "step": 540,
+      "train/loss": 0.053484052419662476
+    },
+    {
+      "epoch": 9.322033898305085,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.0677966101694917e-05,
+      "loss": 0.0361,
+      "step": 550
+    },
+    {
+      "epoch": 9.322033898305085,
+      "step": 550,
+      "train/loss": 0.04231259971857071
+    },
+    {
+      "epoch": 9.491525423728813,
+      "grad_norm": 4.125,
+      "learning_rate": 1.0508474576271188e-05,
+      "loss": 0.0453,
+      "step": 560
+    },
+    {
+      "epoch": 9.491525423728813,
+      "step": 560,
+      "train/loss": 0.02207000181078911
+    },
+    {
+      "epoch": 9.661016949152543,
+      "grad_norm": 3.828125,
+      "learning_rate": 1.0338983050847458e-05,
+      "loss": 0.0394,
+      "step": 570
+    },
+    {
+      "epoch": 9.661016949152543,
+      "step": 570,
+      "train/loss": 0.04616210609674454
+    },
+    {
+      "epoch": 9.830508474576272,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.016949152542373e-05,
+      "loss": 0.0361,
+      "step": 580
+    },
+    {
+      "epoch": 9.830508474576272,
+      "step": 580,
+      "train/loss": 0.03096621483564377
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.15625,
+      "learning_rate": 1e-05,
+      "loss": 0.0322,
+      "step": 590
+    },
+    {
+      "epoch": 10.0,
+      "step": 590,
+      "train/loss": 0.018048249185085297
+    },
+    {
+      "epoch": 10.169491525423728,
+      "grad_norm": 2.390625,
+      "learning_rate": 9.830508474576272e-06,
+      "loss": 0.0172,
+      "step": 600
+    },
+    {
+      "epoch": 10.169491525423728,
+      "step": 600,
+      "train/loss": 0.010340224020183086
+    },
+    {
+      "epoch": 10.338983050847457,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.661016949152544e-06,
+      "loss": 0.014,
+      "step": 610
+    },
+    {
+      "epoch": 10.338983050847457,
+      "step": 610,
+      "train/loss": 0.007396917324513197
+    },
+    {
+      "epoch": 10.508474576271187,
+      "grad_norm": 2.9375,
+      "learning_rate": 9.491525423728815e-06,
+      "loss": 0.014,
+      "step": 620
+    },
+    {
+      "epoch": 10.508474576271187,
+      "step": 620,
+      "train/loss": 0.0389031246304512
+    },
+    {
+      "epoch": 10.677966101694915,
+      "grad_norm": 2.578125,
+      "learning_rate": 9.322033898305085e-06,
+      "loss": 0.0174,
+      "step": 630
+    },
+    {
+      "epoch": 10.677966101694915,
+      "step": 630,
+      "train/loss": 0.01295383833348751
+    },
+    {
+      "epoch": 10.847457627118644,
+      "grad_norm": 3.40625,
+      "learning_rate": 9.152542372881356e-06,
+      "loss": 0.0172,
+      "step": 640
+    },
+    {
+      "epoch": 10.847457627118644,
+      "step": 640,
+      "train/loss": 0.06287191808223724
+    },
+    {
+      "epoch": 11.016949152542374,
+      "grad_norm": 2.5625,
+      "learning_rate": 8.983050847457628e-06,
+      "loss": 0.0182,
+      "step": 650
+    },
+    {
+      "epoch": 11.016949152542374,
+      "step": 650,
+      "train/loss": 0.005611178930848837
+    },
+    {
+      "epoch": 11.186440677966102,
+      "grad_norm": 2.0,
+      "learning_rate": 8.8135593220339e-06,
+      "loss": 0.0097,
+      "step": 660
+    },
+    {
+      "epoch": 11.186440677966102,
+      "step": 660,
+      "train/loss": 0.006666500121355057
+    },
+    {
+      "epoch": 11.35593220338983,
+      "grad_norm": 2.3125,
+      "learning_rate": 8.64406779661017e-06,
+      "loss": 0.0088,
+      "step": 670
+    },
+    {
+      "epoch": 11.35593220338983,
+      "step": 670,
+      "train/loss": 0.012775097973644733
+    },
+    {
+      "epoch": 11.525423728813559,
+      "grad_norm": 1.234375,
+      "learning_rate": 8.47457627118644e-06,
+      "loss": 0.0097,
+      "step": 680
+    },
+    {
+      "epoch": 11.525423728813559,
+      "step": 680,
+      "train/loss": 0.04204524680972099
+    },
+    {
+      "epoch": 11.694915254237289,
+      "grad_norm": 2.3125,
+      "learning_rate": 8.305084745762712e-06,
+      "loss": 0.01,
+      "step": 690
+    },
+    {
+      "epoch": 11.694915254237289,
+      "step": 690,
+      "train/loss": 0.017657611519098282
+    },
+    {
+      "epoch": 11.864406779661017,
+      "grad_norm": 1.7421875,
+      "learning_rate": 8.135593220338983e-06,
+      "loss": 0.0083,
+      "step": 700
+    },
+    {
+      "epoch": 11.864406779661017,
+      "step": 700,
+      "train/loss": 0.003771095769479871
+    },
+    {
+      "epoch": 12.033898305084746,
+      "grad_norm": 0.75,
+      "learning_rate": 7.966101694915255e-06,
+      "loss": 0.0077,
+      "step": 710
+    },
+    {
+      "epoch": 12.033898305084746,
+      "step": 710,
+      "train/loss": 0.002517550252377987
+    },
+    {
+      "epoch": 12.203389830508474,
+      "grad_norm": 1.265625,
+      "learning_rate": 7.796610169491526e-06,
+      "loss": 0.0041,
+      "step": 720
+    },
+    {
+      "epoch": 12.203389830508474,
+      "step": 720,
+      "train/loss": 0.0025206583086401224
+    },
+    {
+      "epoch": 12.372881355932204,
+      "grad_norm": 0.359375,
+      "learning_rate": 7.627118644067797e-06,
+      "loss": 0.0039,
+      "step": 730
+    },
+    {
+      "epoch": 12.372881355932204,
+      "step": 730,
+      "train/loss": 0.0028069019317626953
+    },
+    {
+      "epoch": 12.542372881355933,
+      "grad_norm": 0.61328125,
+      "learning_rate": 7.4576271186440685e-06,
+      "loss": 0.0028,
+      "step": 740
+    },
+    {
+      "epoch": 12.542372881355933,
+      "step": 740,
+      "train/loss": 0.008937366306781769
+    },
+    {
+      "epoch": 12.711864406779661,
+      "grad_norm": 2.484375,
+      "learning_rate": 7.288135593220339e-06,
+      "loss": 0.0028,
+      "step": 750
+    },
+    {
+      "epoch": 12.711864406779661,
+      "step": 750,
+      "train/loss": 0.004732430912554264
+    },
+    {
+      "epoch": 12.88135593220339,
+      "grad_norm": 2.734375,
+      "learning_rate": 7.1186440677966106e-06,
+      "loss": 0.0044,
+      "step": 760
+    },
+    {
+      "epoch": 12.88135593220339,
+      "step": 760,
+      "train/loss": 0.001620347029529512
+    },
+    {
+      "epoch": 13.05084745762712,
+      "grad_norm": 0.61328125,
+      "learning_rate": 6.949152542372882e-06,
+      "loss": 0.0035,
+      "step": 770
+    },
+    {
+      "epoch": 13.05084745762712,
+      "step": 770,
+      "train/loss": 0.002415319439023733
+    },
+    {
+      "epoch": 13.220338983050848,
+      "grad_norm": 1.3125,
+      "learning_rate": 6.779661016949153e-06,
+      "loss": 0.0016,
+      "step": 780
+    },
+    {
+      "epoch": 13.220338983050848,
+      "step": 780,
+      "train/loss": 0.0016408833907917142
+    },
+    {
+      "epoch": 13.389830508474576,
+      "grad_norm": 0.306640625,
+      "learning_rate": 6.610169491525424e-06,
+      "loss": 0.0012,
+      "step": 790
+    },
+    {
+      "epoch": 13.389830508474576,
+      "step": 790,
+      "train/loss": 0.0010705557651817799
+    },
+    {
+      "epoch": 13.559322033898304,
+      "grad_norm": 0.390625,
+      "learning_rate": 6.440677966101695e-06,
+      "loss": 0.0016,
+      "step": 800
+    },
+    {
+      "epoch": 13.559322033898304,
+      "step": 800,
+      "train/loss": 0.0011124921729788184
+    },
+    {
+      "epoch": 13.728813559322035,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 6.271186440677966e-06,
+      "loss": 0.0012,
+      "step": 810
+    },
+    {
+      "epoch": 13.728813559322035,
+      "step": 810,
+      "train/loss": 0.004729266744107008
+    },
+    {
+      "epoch": 13.898305084745763,
+      "grad_norm": 0.671875,
+      "learning_rate": 6.1016949152542385e-06,
+      "loss": 0.0013,
+      "step": 820
+    },
+    {
+      "epoch": 13.898305084745763,
+      "step": 820,
+      "train/loss": 0.0020668096840381622
+    },
+    {
+      "epoch": 14.067796610169491,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 5.932203389830509e-06,
+      "loss": 0.0012,
+      "step": 830
+    },
+    {
+      "epoch": 14.067796610169491,
+      "step": 830,
+      "train/loss": 0.0006283410475589335
+    },
+    {
+      "epoch": 14.23728813559322,
+      "grad_norm": 0.109375,
+      "learning_rate": 5.7627118644067805e-06,
+      "loss": 0.0007,
+      "step": 840
+    },
+    {
+      "epoch": 14.23728813559322,
+      "step": 840,
+      "train/loss": 0.0009114898275583982
+    },
+    {
+      "epoch": 14.40677966101695,
+      "grad_norm": 0.1484375,
+      "learning_rate": 5.593220338983051e-06,
+      "loss": 0.0008,
+      "step": 850
+    },
+    {
+      "epoch": 14.40677966101695,
+      "step": 850,
+      "train/loss": 0.0006412779912352562
+    },
+    {
+      "epoch": 14.576271186440678,
+      "grad_norm": 0.09375,
+      "learning_rate": 5.423728813559323e-06,
+      "loss": 0.0007,
+      "step": 860
+    },
+    {
+      "epoch": 14.576271186440678,
+      "step": 860,
+      "train/loss": 0.00044277351116761565
+    },
+    {
+      "epoch": 14.745762711864407,
+      "grad_norm": 0.125,
+      "learning_rate": 5.254237288135594e-06,
+      "loss": 0.0007,
+      "step": 870
+    },
+    {
+      "epoch": 14.745762711864407,
+      "step": 870,
+      "train/loss": 0.0006639361381530762
+    },
+    {
+      "epoch": 14.915254237288135,
+      "grad_norm": 0.125,
+      "learning_rate": 5.084745762711865e-06,
+      "loss": 0.0007,
+      "step": 880
+    },
+    {
+      "epoch": 14.915254237288135,
+      "step": 880,
+      "train/loss": 0.0010526160476729274
+    },
+    {
+      "epoch": 15.084745762711865,
+      "grad_norm": 0.140625,
+      "learning_rate": 4.915254237288136e-06,
+      "loss": 0.0007,
+      "step": 890
+    },
+    {
+      "epoch": 15.084745762711865,
+      "step": 890,
+      "train/loss": 0.0008953613578341901
+    },
+    {
+      "epoch": 15.254237288135593,
+      "grad_norm": 0.11328125,
+      "learning_rate": 4.745762711864408e-06,
+      "loss": 0.0007,
+      "step": 900
+    },
+    {
+      "epoch": 15.254237288135593,
+      "step": 900,
+      "train/loss": 0.0005881416727788746
+    },
+    {
+      "epoch": 15.423728813559322,
+      "grad_norm": 0.111328125,
+      "learning_rate": 4.576271186440678e-06,
+      "loss": 0.0007,
+      "step": 910
+    },
+    {
+      "epoch": 15.423728813559322,
+      "step": 910,
+      "train/loss": 0.0006380457780323923
+    },
+    {
+      "epoch": 15.59322033898305,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 4.40677966101695e-06,
+      "loss": 0.0007,
+      "step": 920
+    },
+    {
+      "epoch": 15.59322033898305,
+      "step": 920,
+      "train/loss": 0.0011346661485731602
+    },
+    {
+      "epoch": 15.76271186440678,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 4.23728813559322e-06,
+      "loss": 0.0007,
+      "step": 930
+    },
+    {
+      "epoch": 15.76271186440678,
+      "step": 930,
+      "train/loss": 0.0006046256748959422
+    },
+    {
+      "epoch": 15.932203389830509,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 4.067796610169492e-06,
+      "loss": 0.0007,
+      "step": 940
+    },
+    {
+      "epoch": 15.932203389830509,
+      "step": 940,
+      "train/loss": 0.0011196370469406247
+    },
+    {
+      "epoch": 16.10169491525424,
+      "grad_norm": 0.078125,
+      "learning_rate": 3.898305084745763e-06,
+      "loss": 0.0006,
+      "step": 950
+    },
+    {
+      "epoch": 16.10169491525424,
+      "step": 950,
+      "train/loss": 0.00043817225378006697
+    },
+    {
+      "epoch": 16.271186440677965,
+      "grad_norm": 0.11474609375,
+      "learning_rate": 3.7288135593220342e-06,
+      "loss": 0.0007,
+      "step": 960
+    },
+    {
+      "epoch": 16.271186440677965,
+      "step": 960,
+      "train/loss": 0.000769623089581728
+    },
+    {
+      "epoch": 16.440677966101696,
+      "grad_norm": 0.1015625,
+      "learning_rate": 3.5593220338983053e-06,
+      "loss": 0.0007,
+      "step": 970
+    },
+    {
+      "epoch": 16.440677966101696,
+      "step": 970,
+      "train/loss": 0.00038810240221209824
+    },
+    {
+      "epoch": 16.610169491525422,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 3.3898305084745763e-06,
+      "loss": 0.0007,
+      "step": 980
+    },
+    {
+      "epoch": 16.610169491525422,
+      "step": 980,
+      "train/loss": 0.0009182461071759462
+    },
+    {
+      "epoch": 16.779661016949152,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 3.2203389830508473e-06,
+      "loss": 0.0007,
+      "step": 990
+    },
+    {
+      "epoch": 16.779661016949152,
+      "step": 990,
+      "train/loss": 0.00038518159999512136
+    },
+    {
+      "epoch": 16.949152542372882,
+      "grad_norm": 0.07373046875,
+      "learning_rate": 3.0508474576271192e-06,
+      "loss": 0.0006,
+      "step": 1000
+    },
+    {
+      "epoch": 16.949152542372882,
+      "step": 1000,
+      "train/loss": 0.0008729099063202739
+    },
+    {
+      "epoch": 17.11864406779661,
+      "grad_norm": 0.11474609375,
+      "learning_rate": 2.8813559322033903e-06,
+      "loss": 0.0007,
+      "step": 1010
+    },
+    {
+      "epoch": 17.11864406779661,
+      "step": 1010,
+      "train/loss": 0.00036369499866850674
+    },
+    {
+      "epoch": 17.28813559322034,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 2.7118644067796613e-06,
+      "loss": 0.0007,
+      "step": 1020
+    },
+    {
+      "epoch": 17.28813559322034,
+      "step": 1020,
+      "train/loss": 0.0008040030370466411
+    },
+    {
+      "epoch": 17.45762711864407,
+      "grad_norm": 0.09375,
+      "learning_rate": 2.5423728813559323e-06,
+      "loss": 0.0006,
+      "step": 1030
+    },
+    {
+      "epoch": 17.45762711864407,
+      "step": 1030,
+      "train/loss": 0.00033714919118210673
+    },
+    {
+      "epoch": 17.627118644067796,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 2.372881355932204e-06,
+      "loss": 0.0007,
+      "step": 1040
+    },
+    {
+      "epoch": 17.627118644067796,
+      "step": 1040,
+      "train/loss": 0.0011265197535976768
+    },
+    {
+      "epoch": 17.796610169491526,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 2.203389830508475e-06,
+      "loss": 0.0007,
+      "step": 1050
+    },
+    {
+      "epoch": 17.796610169491526,
+      "step": 1050,
+      "train/loss": 0.0007198441890068352
+    },
+    {
+      "epoch": 17.966101694915253,
+      "grad_norm": 0.10546875,
+      "learning_rate": 2.033898305084746e-06,
+      "loss": 0.0006,
+      "step": 1060
+    },
+    {
+      "epoch": 17.966101694915253,
+      "step": 1060,
+      "train/loss": 0.0005593463429249823
+    },
+    {
+      "epoch": 18.135593220338983,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 1.8644067796610171e-06,
+      "loss": 0.0006,
+      "step": 1070
+    },
+    {
+      "epoch": 18.135593220338983,
+      "step": 1070,
+      "train/loss": 0.0006793233915232122
+    },
+    {
+      "epoch": 18.305084745762713,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 1.6949152542372882e-06,
+      "loss": 0.0006,
+      "step": 1080
+    },
+    {
+      "epoch": 18.305084745762713,
+      "step": 1080,
+      "train/loss": 0.0007857573218643665
+    },
+    {
+      "epoch": 18.47457627118644,
+      "grad_norm": 0.123046875,
+      "learning_rate": 1.5254237288135596e-06,
+      "loss": 0.0007,
+      "step": 1090
+    },
+    {
+      "epoch": 18.47457627118644,
+      "step": 1090,
+      "train/loss": 0.0008864915580488741
+    },
+    {
+      "epoch": 18.64406779661017,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 1.3559322033898307e-06,
+      "loss": 0.0007,
+      "step": 1100
+    },
+    {
+      "epoch": 18.64406779661017,
+      "step": 1100,
+      "train/loss": 0.0009428944322280586
+    },
+    {
+      "epoch": 18.8135593220339,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 1.186440677966102e-06,
+      "loss": 0.0007,
+      "step": 1110
+    },
+    {
+      "epoch": 18.8135593220339,
+      "step": 1110,
+      "train/loss": 0.0007030675187706947
+    },
+    {
+      "epoch": 18.983050847457626,
+      "grad_norm": 0.11181640625,
+      "learning_rate": 1.016949152542373e-06,
+      "loss": 0.0006,
+      "step": 1120
+    },
+    {
+      "epoch": 18.983050847457626,
+      "step": 1120,
+      "train/loss": 0.0005212921532802284
+    },
+    {
+      "epoch": 19.152542372881356,
+      "grad_norm": 0.1162109375,
+      "learning_rate": 8.474576271186441e-07,
+      "loss": 0.0007,
+      "step": 1130
+    },
+    {
+      "epoch": 19.152542372881356,
+      "step": 1130,
+      "train/loss": 0.000918982143048197
+    },
+    {
+      "epoch": 19.322033898305083,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 6.779661016949153e-07,
+      "loss": 0.0007,
+      "step": 1140
+    },
+    {
+      "epoch": 19.322033898305083,
+      "step": 1140,
+      "train/loss": 0.0006755354697816074
+    },
+    {
+      "epoch": 19.491525423728813,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 5.084745762711865e-07,
+      "loss": 0.0007,
+      "step": 1150
+    },
+    {
+      "epoch": 19.491525423728813,
+      "step": 1150,
+      "train/loss": 0.0004047738912049681
+    },
+    {
+      "epoch": 19.661016949152543,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 3.3898305084745766e-07,
+      "loss": 0.0006,
+      "step": 1160
+    },
+    {
+      "epoch": 19.661016949152543,
+      "step": 1160,
+      "train/loss": 0.0006619080086238682
+    },
+    {
+      "epoch": 19.83050847457627,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 1.6949152542372883e-07,
+      "loss": 0.0006,
+      "step": 1170
+    },
+    {
+      "epoch": 19.83050847457627,
+      "step": 1170,
+      "train/loss": 0.0008306258241645992
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.0,
+      "loss": 0.0006,
+      "step": 1180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

sft-procthor-1108-20epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b9aa7d34c75f987198e038015aa3ce760af19342c0f05b60870704cd7e507d
+size 5841