Training in progress, step 1884, checkpoint

checkpoint-1884/added_tokens.json

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

checkpoint-1884/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 %}"
+}

checkpoint-1884/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": "4.50.0.dev0",
+  "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
+}

checkpoint-1884/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.50.0.dev0"
+}

checkpoint-1884/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1430d132535f75a24819817a796ac6dc149c98696959f21768e26cbffd2acb
+size 4968243304

checkpoint-1884/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:469e83040a9b4dfef560ac829e3ab05e534376680d0de467e5969e436040be99
+size 4991495816

checkpoint-1884/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b136a9953d061780b07b0ceb09cb1fe0bff83ceac259c49901e3e5119fc3e3
+size 4932751040

checkpoint-1884/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c91e56ca10acc1a16d05c456fcf909cee62c5ab244b2393cd66637e3a375b0
+size 1691924384

checkpoint-1884/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"
+  }
+}

checkpoint-1884/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
+}

checkpoint-1884/special_tokens_map.json

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

checkpoint-1884/tokenizer.json

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

checkpoint-1884/tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "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": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1884/trainer_state.json

@@ -0,0 +1,1349 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1884,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01592356687898089,
+      "grad_norm": 5.938978672027588,
+      "learning_rate": 1.0582010582010582e-06,
+      "loss": 0.5588,
+      "step": 10
+    },
+    {
+      "epoch": 0.03184713375796178,
+      "grad_norm": 2.5084874629974365,
+      "learning_rate": 2.1164021164021164e-06,
+      "loss": 0.4422,
+      "step": 20
+    },
+    {
+      "epoch": 0.04777070063694268,
+      "grad_norm": 0.9098156690597534,
+      "learning_rate": 3.1746031746031746e-06,
+      "loss": 0.3842,
+      "step": 30
+    },
+    {
+      "epoch": 0.06369426751592357,
+      "grad_norm": 0.7925612330436707,
+      "learning_rate": 4.232804232804233e-06,
+      "loss": 0.3481,
+      "step": 40
+    },
+    {
+      "epoch": 0.07961783439490445,
+      "grad_norm": 0.7580339312553406,
+      "learning_rate": 5.291005291005291e-06,
+      "loss": 0.3313,
+      "step": 50
+    },
+    {
+      "epoch": 0.09554140127388536,
+      "grad_norm": 1.1035263538360596,
+      "learning_rate": 6.349206349206349e-06,
+      "loss": 0.3168,
+      "step": 60
+    },
+    {
+      "epoch": 0.11146496815286625,
+      "grad_norm": 0.576166033744812,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.3109,
+      "step": 70
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "grad_norm": 0.6099635362625122,
+      "learning_rate": 8.465608465608466e-06,
+      "loss": 0.3068,
+      "step": 80
+    },
+    {
+      "epoch": 0.14331210191082802,
+      "grad_norm": 0.7660859823226929,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.302,
+      "step": 90
+    },
+    {
+      "epoch": 0.1592356687898089,
+      "grad_norm": 1.0273711681365967,
+      "learning_rate": 1.0582010582010582e-05,
+      "loss": 0.3053,
+      "step": 100
+    },
+    {
+      "epoch": 0.1751592356687898,
+      "grad_norm": 0.7934479713439941,
+      "learning_rate": 1.1640211640211641e-05,
+      "loss": 0.3055,
+      "step": 110
+    },
+    {
+      "epoch": 0.1910828025477707,
+      "grad_norm": 1.4802435636520386,
+      "learning_rate": 1.2698412698412699e-05,
+      "loss": 0.3012,
+      "step": 120
+    },
+    {
+      "epoch": 0.2070063694267516,
+      "grad_norm": 1.150119423866272,
+      "learning_rate": 1.3756613756613758e-05,
+      "loss": 0.3041,
+      "step": 130
+    },
+    {
+      "epoch": 0.2229299363057325,
+      "grad_norm": 1.2672383785247803,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.3048,
+      "step": 140
+    },
+    {
+      "epoch": 0.23885350318471338,
+      "grad_norm": 0.7314700484275818,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.2997,
+      "step": 150
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 1.1569265127182007,
+      "learning_rate": 1.693121693121693e-05,
+      "loss": 0.3017,
+      "step": 160
+    },
+    {
+      "epoch": 0.27070063694267515,
+      "grad_norm": 0.8508642911911011,
+      "learning_rate": 1.798941798941799e-05,
+      "loss": 0.2936,
+      "step": 170
+    },
+    {
+      "epoch": 0.28662420382165604,
+      "grad_norm": 0.8888178467750549,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.2959,
+      "step": 180
+    },
+    {
+      "epoch": 0.30254777070063693,
+      "grad_norm": 0.9090297818183899,
+      "learning_rate": 1.9999982823676135e-05,
+      "loss": 0.293,
+      "step": 190
+    },
+    {
+      "epoch": 0.3184713375796178,
+      "grad_norm": 1.0700126886367798,
+      "learning_rate": 1.9997921736207435e-05,
+      "loss": 0.2927,
+      "step": 200
+    },
+    {
+      "epoch": 0.3343949044585987,
+      "grad_norm": 1.2329490184783936,
+      "learning_rate": 1.9992426195241246e-05,
+      "loss": 0.2935,
+      "step": 210
+    },
+    {
+      "epoch": 0.3503184713375796,
+      "grad_norm": 0.6014856100082397,
+      "learning_rate": 1.9983498088587904e-05,
+      "loss": 0.2875,
+      "step": 220
+    },
+    {
+      "epoch": 0.3662420382165605,
+      "grad_norm": 0.5173149108886719,
+      "learning_rate": 1.9971140483201507e-05,
+      "loss": 0.2865,
+      "step": 230
+    },
+    {
+      "epoch": 0.3821656050955414,
+      "grad_norm": 0.4913546144962311,
+      "learning_rate": 1.995535762412639e-05,
+      "loss": 0.2842,
+      "step": 240
+    },
+    {
+      "epoch": 0.3980891719745223,
+      "grad_norm": 0.6859982013702393,
+      "learning_rate": 1.9936154933038882e-05,
+      "loss": 0.2825,
+      "step": 250
+    },
+    {
+      "epoch": 0.4140127388535032,
+      "grad_norm": 0.836473286151886,
+      "learning_rate": 1.991353900638485e-05,
+      "loss": 0.2807,
+      "step": 260
+    },
+    {
+      "epoch": 0.4299363057324841,
+      "grad_norm": 0.7169066667556763,
+      "learning_rate": 1.988751761311373e-05,
+      "loss": 0.2776,
+      "step": 270
+    },
+    {
+      "epoch": 0.445859872611465,
+      "grad_norm": 0.7342332601547241,
+      "learning_rate": 1.9858099692009746e-05,
+      "loss": 0.2768,
+      "step": 280
+    },
+    {
+      "epoch": 0.46178343949044587,
+      "grad_norm": 0.5076990723609924,
+      "learning_rate": 1.9825295348621303e-05,
+      "loss": 0.2736,
+      "step": 290
+    },
+    {
+      "epoch": 0.47770700636942676,
+      "grad_norm": 0.4993409514427185,
+      "learning_rate": 1.978911585178955e-05,
+      "loss": 0.2687,
+      "step": 300
+    },
+    {
+      "epoch": 0.49363057324840764,
+      "grad_norm": 0.8263068795204163,
+      "learning_rate": 1.974957362977735e-05,
+      "loss": 0.2698,
+      "step": 310
+    },
+    {
+      "epoch": 0.5095541401273885,
+      "grad_norm": 0.5373275279998779,
+      "learning_rate": 1.970668226599997e-05,
+      "loss": 0.2669,
+      "step": 320
+    },
+    {
+      "epoch": 0.5254777070063694,
+      "grad_norm": 0.7009662985801697,
+      "learning_rate": 1.966045649435893e-05,
+      "loss": 0.2644,
+      "step": 330
+    },
+    {
+      "epoch": 0.5414012738853503,
+      "grad_norm": 0.7370754480361938,
+      "learning_rate": 1.9610912194180685e-05,
+      "loss": 0.264,
+      "step": 340
+    },
+    {
+      "epoch": 0.5573248407643312,
+      "grad_norm": 0.5792177319526672,
+      "learning_rate": 1.9558066384761794e-05,
+      "loss": 0.259,
+      "step": 350
+    },
+    {
+      "epoch": 0.5732484076433121,
+      "grad_norm": 0.7904641032218933,
+      "learning_rate": 1.950193721952252e-05,
+      "loss": 0.259,
+      "step": 360
+    },
+    {
+      "epoch": 0.589171974522293,
+      "grad_norm": 0.57305908203125,
+      "learning_rate": 1.944254397977081e-05,
+      "loss": 0.2527,
+      "step": 370
+    },
+    {
+      "epoch": 0.6050955414012739,
+      "grad_norm": 0.6305221319198608,
+      "learning_rate": 1.9379907068078857e-05,
+      "loss": 0.2516,
+      "step": 380
+    },
+    {
+      "epoch": 0.6210191082802548,
+      "grad_norm": 0.5892254710197449,
+      "learning_rate": 1.931404800127447e-05,
+      "loss": 0.252,
+      "step": 390
+    },
+    {
+      "epoch": 0.6369426751592356,
+      "grad_norm": 0.5180689692497253,
+      "learning_rate": 1.9244989403049677e-05,
+      "loss": 0.2459,
+      "step": 400
+    },
+    {
+      "epoch": 0.6528662420382165,
+      "grad_norm": 0.5340262055397034,
+      "learning_rate": 1.9172754996189125e-05,
+      "loss": 0.2427,
+      "step": 410
+    },
+    {
+      "epoch": 0.6687898089171974,
+      "grad_norm": 0.6435000896453857,
+      "learning_rate": 1.9097369594420888e-05,
+      "loss": 0.2387,
+      "step": 420
+    },
+    {
+      "epoch": 0.6847133757961783,
+      "grad_norm": 0.9354584217071533,
+      "learning_rate": 1.9018859093892538e-05,
+      "loss": 0.2366,
+      "step": 430
+    },
+    {
+      "epoch": 0.7006369426751592,
+      "grad_norm": 0.7087671160697937,
+      "learning_rate": 1.8937250464275407e-05,
+      "loss": 0.2315,
+      "step": 440
+    },
+    {
+      "epoch": 0.7165605095541401,
+      "grad_norm": 1.0769435167312622,
+      "learning_rate": 1.8852571739500025e-05,
+      "loss": 0.2279,
+      "step": 450
+    },
+    {
+      "epoch": 0.732484076433121,
+      "grad_norm": 1.0389244556427002,
+      "learning_rate": 1.8764852008126e-05,
+      "loss": 0.2259,
+      "step": 460
+    },
+    {
+      "epoch": 0.7484076433121019,
+      "grad_norm": 0.6885454058647156,
+      "learning_rate": 1.8674121403349634e-05,
+      "loss": 0.2199,
+      "step": 470
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 1.4660230875015259,
+      "learning_rate": 1.858041109265264e-05,
+      "loss": 0.215,
+      "step": 480
+    },
+    {
+      "epoch": 0.7802547770700637,
+      "grad_norm": 0.8413995504379272,
+      "learning_rate": 1.8483753267095606e-05,
+      "loss": 0.2134,
+      "step": 490
+    },
+    {
+      "epoch": 0.7961783439490446,
+      "grad_norm": 0.687028169631958,
+      "learning_rate": 1.8384181130259814e-05,
+      "loss": 0.207,
+      "step": 500
+    },
+    {
+      "epoch": 0.8121019108280255,
+      "grad_norm": 0.7690938115119934,
+      "learning_rate": 1.8281728886841258e-05,
+      "loss": 0.2009,
+      "step": 510
+    },
+    {
+      "epoch": 0.8280254777070064,
+      "grad_norm": 0.882749080657959,
+      "learning_rate": 1.8176431730900772e-05,
+      "loss": 0.1951,
+      "step": 520
+    },
+    {
+      "epoch": 0.8439490445859873,
+      "grad_norm": 0.6659705638885498,
+      "learning_rate": 1.8068325833774262e-05,
+      "loss": 0.194,
+      "step": 530
+    },
+    {
+      "epoch": 0.8598726114649682,
+      "grad_norm": 0.7047539949417114,
+      "learning_rate": 1.7957448331647253e-05,
+      "loss": 0.1857,
+      "step": 540
+    },
+    {
+      "epoch": 0.8757961783439491,
+      "grad_norm": 0.7337578535079956,
+      "learning_rate": 1.784383731279799e-05,
+      "loss": 0.1829,
+      "step": 550
+    },
+    {
+      "epoch": 0.89171974522293,
+      "grad_norm": 0.8769313097000122,
+      "learning_rate": 1.7727531804513483e-05,
+      "loss": 0.1746,
+      "step": 560
+    },
+    {
+      "epoch": 0.9076433121019108,
+      "grad_norm": 0.7639766335487366,
+      "learning_rate": 1.7608571759682963e-05,
+      "loss": 0.1736,
+      "step": 570
+    },
+    {
+      "epoch": 0.9235668789808917,
+      "grad_norm": 0.8756518363952637,
+      "learning_rate": 1.748699804307341e-05,
+      "loss": 0.1675,
+      "step": 580
+    },
+    {
+      "epoch": 0.9394904458598726,
+      "grad_norm": 0.7969843745231628,
+      "learning_rate": 1.7362852417291813e-05,
+      "loss": 0.1645,
+      "step": 590
+    },
+    {
+      "epoch": 0.9554140127388535,
+      "grad_norm": 1.0977206230163574,
+      "learning_rate": 1.7236177528439027e-05,
+      "loss": 0.1581,
+      "step": 600
+    },
+    {
+      "epoch": 0.9713375796178344,
+      "grad_norm": 1.1576684713363647,
+      "learning_rate": 1.7107016891460118e-05,
+      "loss": 0.1563,
+      "step": 610
+    },
+    {
+      "epoch": 0.9872611464968153,
+      "grad_norm": 0.8371659517288208,
+      "learning_rate": 1.697541487519623e-05,
+      "loss": 0.1475,
+      "step": 620
+    },
+    {
+      "epoch": 1.0031847133757963,
+      "grad_norm": 0.7080691456794739,
+      "learning_rate": 1.684141668714318e-05,
+      "loss": 0.1397,
+      "step": 630
+    },
+    {
+      "epoch": 1.019108280254777,
+      "grad_norm": 0.9583333730697632,
+      "learning_rate": 1.6705068357921913e-05,
+      "loss": 0.1137,
+      "step": 640
+    },
+    {
+      "epoch": 1.035031847133758,
+      "grad_norm": 0.6917926073074341,
+      "learning_rate": 1.6566416725466198e-05,
+      "loss": 0.1108,
+      "step": 650
+    },
+    {
+      "epoch": 1.0509554140127388,
+      "grad_norm": 0.7164482474327087,
+      "learning_rate": 1.6425509418933038e-05,
+      "loss": 0.1106,
+      "step": 660
+    },
+    {
+      "epoch": 1.0668789808917198,
+      "grad_norm": 0.6723839044570923,
+      "learning_rate": 1.6282394842341234e-05,
+      "loss": 0.1068,
+      "step": 670
+    },
+    {
+      "epoch": 1.0828025477707006,
+      "grad_norm": 0.7010757327079773,
+      "learning_rate": 1.613712215794381e-05,
+      "loss": 0.1034,
+      "step": 680
+    },
+    {
+      "epoch": 1.0987261146496816,
+      "grad_norm": 0.7355757355690002,
+      "learning_rate": 1.5989741269339956e-05,
+      "loss": 0.1011,
+      "step": 690
+    },
+    {
+      "epoch": 1.1146496815286624,
+      "grad_norm": 0.720433235168457,
+      "learning_rate": 1.5840302804332295e-05,
+      "loss": 0.1001,
+      "step": 700
+    },
+    {
+      "epoch": 1.1305732484076434,
+      "grad_norm": 0.7248522639274597,
+      "learning_rate": 1.5688858097535403e-05,
+      "loss": 0.0948,
+      "step": 710
+    },
+    {
+      "epoch": 1.1464968152866242,
+      "grad_norm": 0.7236132025718689,
+      "learning_rate": 1.5535459172741475e-05,
+      "loss": 0.0906,
+      "step": 720
+    },
+    {
+      "epoch": 1.1624203821656052,
+      "grad_norm": 0.6846908330917358,
+      "learning_rate": 1.538015872504933e-05,
+      "loss": 0.0881,
+      "step": 730
+    },
+    {
+      "epoch": 1.178343949044586,
+      "grad_norm": 0.6623250246047974,
+      "learning_rate": 1.5223010102762725e-05,
+      "loss": 0.0848,
+      "step": 740
+    },
+    {
+      "epoch": 1.194267515923567,
+      "grad_norm": 0.807305097579956,
+      "learning_rate": 1.5064067289064332e-05,
+      "loss": 0.0819,
+      "step": 750
+    },
+    {
+      "epoch": 1.2101910828025477,
+      "grad_norm": 0.6570079326629639,
+      "learning_rate": 1.4903384883471608e-05,
+      "loss": 0.0821,
+      "step": 760
+    },
+    {
+      "epoch": 1.2261146496815287,
+      "grad_norm": 0.6224232912063599,
+      "learning_rate": 1.474101808308096e-05,
+      "loss": 0.0781,
+      "step": 770
+    },
+    {
+      "epoch": 1.2420382165605095,
+      "grad_norm": 0.6488759517669678,
+      "learning_rate": 1.4577022663606592e-05,
+      "loss": 0.0756,
+      "step": 780
+    },
+    {
+      "epoch": 1.2579617834394905,
+      "grad_norm": 0.6796790957450867,
+      "learning_rate": 1.4411454960220647e-05,
+      "loss": 0.0739,
+      "step": 790
+    },
+    {
+      "epoch": 1.2738853503184713,
+      "grad_norm": 0.6596919298171997,
+      "learning_rate": 1.42443718482011e-05,
+      "loss": 0.0691,
+      "step": 800
+    },
+    {
+      "epoch": 1.2898089171974523,
+      "grad_norm": 0.6160626411437988,
+      "learning_rate": 1.4075830723394164e-05,
+      "loss": 0.0676,
+      "step": 810
+    },
+    {
+      "epoch": 1.305732484076433,
+      "grad_norm": 0.5704523324966431,
+      "learning_rate": 1.3905889482497858e-05,
+      "loss": 0.0647,
+      "step": 820
+    },
+    {
+      "epoch": 1.321656050955414,
+      "grad_norm": 0.5561860203742981,
+      "learning_rate": 1.3734606503173522e-05,
+      "loss": 0.0623,
+      "step": 830
+    },
+    {
+      "epoch": 1.3375796178343948,
+      "grad_norm": 0.681788444519043,
+      "learning_rate": 1.3562040623992092e-05,
+      "loss": 0.0611,
+      "step": 840
+    },
+    {
+      "epoch": 1.3535031847133758,
+      "grad_norm": 0.6568078994750977,
+      "learning_rate": 1.3388251124222104e-05,
+      "loss": 0.0588,
+      "step": 850
+    },
+    {
+      "epoch": 1.3694267515923566,
+      "grad_norm": 0.5263776183128357,
+      "learning_rate": 1.3213297703466237e-05,
+      "loss": 0.0564,
+      "step": 860
+    },
+    {
+      "epoch": 1.3853503184713376,
+      "grad_norm": 0.5988286733627319,
+      "learning_rate": 1.303724046115352e-05,
+      "loss": 0.0543,
+      "step": 870
+    },
+    {
+      "epoch": 1.4012738853503186,
+      "grad_norm": 0.5688588619232178,
+      "learning_rate": 1.2860139875894163e-05,
+      "loss": 0.0574,
+      "step": 880
+    },
+    {
+      "epoch": 1.4171974522292994,
+      "grad_norm": 0.6649556159973145,
+      "learning_rate": 1.2682056784704151e-05,
+      "loss": 0.0529,
+      "step": 890
+    },
+    {
+      "epoch": 1.4331210191082802,
+      "grad_norm": 0.5984866619110107,
+      "learning_rate": 1.2503052362106698e-05,
+      "loss": 0.0517,
+      "step": 900
+    },
+    {
+      "epoch": 1.4490445859872612,
+      "grad_norm": 0.5580580234527588,
+      "learning_rate": 1.2323188099117791e-05,
+      "loss": 0.0474,
+      "step": 910
+    },
+    {
+      "epoch": 1.4649681528662422,
+      "grad_norm": 0.5219546556472778,
+      "learning_rate": 1.2142525782122974e-05,
+      "loss": 0.0464,
+      "step": 920
+    },
+    {
+      "epoch": 1.480891719745223,
+      "grad_norm": 0.5171259641647339,
+      "learning_rate": 1.196112747165271e-05,
+      "loss": 0.0444,
+      "step": 930
+    },
+    {
+      "epoch": 1.4968152866242037,
+      "grad_norm": 0.5057135224342346,
+      "learning_rate": 1.1779055481063545e-05,
+      "loss": 0.042,
+      "step": 940
+    },
+    {
+      "epoch": 1.5127388535031847,
+      "grad_norm": 0.5676354765892029,
+      "learning_rate": 1.1596372355132422e-05,
+      "loss": 0.0405,
+      "step": 950
+    },
+    {
+      "epoch": 1.5286624203821657,
+      "grad_norm": 0.5014776587486267,
+      "learning_rate": 1.1413140848571495e-05,
+      "loss": 0.0409,
+      "step": 960
+    },
+    {
+      "epoch": 1.5445859872611465,
+      "grad_norm": 0.4629918038845062,
+      "learning_rate": 1.1229423904470864e-05,
+      "loss": 0.0405,
+      "step": 970
+    },
+    {
+      "epoch": 1.5605095541401273,
+      "grad_norm": 0.562461256980896,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0401,
+      "step": 980
+    },
+    {
+      "epoch": 1.5764331210191083,
+      "grad_norm": 0.5296617150306702,
+      "learning_rate": 1.0860786288111158e-05,
+      "loss": 0.0386,
+      "step": 990
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "grad_norm": 0.4665983021259308,
+      "learning_rate": 1.0675992249044882e-05,
+      "loss": 0.0352,
+      "step": 1000
+    },
+    {
+      "epoch": 1.60828025477707,
+      "grad_norm": 0.5495542287826538,
+      "learning_rate": 1.0490965995323879e-05,
+      "loss": 0.0339,
+      "step": 1010
+    },
+    {
+      "epoch": 1.6242038216560508,
+      "grad_norm": 0.47773268818855286,
+      "learning_rate": 1.0305771086563927e-05,
+      "loss": 0.032,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6401273885350318,
+      "grad_norm": 0.43807661533355713,
+      "learning_rate": 1.0120471140316647e-05,
+      "loss": 0.0346,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560509554140128,
+      "grad_norm": 0.4941099286079407,
+      "learning_rate": 9.935129810215793e-06,
+      "loss": 0.0329,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6719745222929936,
+      "grad_norm": 0.4290195405483246,
+      "learning_rate": 9.749810764111156e-06,
+      "loss": 0.0317,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6878980891719744,
+      "grad_norm": 0.4538203477859497,
+      "learning_rate": 9.564577662197612e-06,
+      "loss": 0.0325,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7038216560509554,
+      "grad_norm": 0.3967364430427551,
+      "learning_rate": 9.379494135146769e-06,
+      "loss": 0.0307,
+      "step": 1070
+    },
+    {
+      "epoch": 1.7197452229299364,
+      "grad_norm": 0.4934009611606598,
+      "learning_rate": 9.194623762248755e-06,
+      "loss": 0.0309,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7356687898089171,
+      "grad_norm": 0.4300677478313446,
+      "learning_rate": 9.010030049571686e-06,
+      "loss": 0.0298,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7515923566878981,
+      "grad_norm": 0.42275470495224,
+      "learning_rate": 8.825776408146262e-06,
+      "loss": 0.0289,
+      "step": 1100
+    },
+    {
+      "epoch": 1.767515923566879,
+      "grad_norm": 0.43387818336486816,
+      "learning_rate": 8.641926132183005e-06,
+      "loss": 0.0275,
+      "step": 1110
+    },
+    {
+      "epoch": 1.78343949044586,
+      "grad_norm": 0.4539569616317749,
+      "learning_rate": 8.458542377329661e-06,
+      "loss": 0.0267,
+      "step": 1120
+    },
+    {
+      "epoch": 1.799363057324841,
+      "grad_norm": 0.4254033863544464,
+      "learning_rate": 8.275688138976151e-06,
+      "loss": 0.0257,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8152866242038217,
+      "grad_norm": 0.3466563820838928,
+      "learning_rate": 8.093426230614627e-06,
+      "loss": 0.0256,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8312101910828025,
+      "grad_norm": 0.46024608612060547,
+      "learning_rate": 7.911819262261961e-06,
+      "loss": 0.0253,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8471337579617835,
+      "grad_norm": 0.3775930404663086,
+      "learning_rate": 7.73092961895217e-06,
+      "loss": 0.0249,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8630573248407645,
+      "grad_norm": 0.4123600125312805,
+      "learning_rate": 7.550819439306113e-06,
+      "loss": 0.0245,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8789808917197452,
+      "grad_norm": 0.3415584862232208,
+      "learning_rate": 7.37155059418583e-06,
+      "loss": 0.0234,
+      "step": 1180
+    },
+    {
+      "epoch": 1.894904458598726,
+      "grad_norm": 0.33297714591026306,
+      "learning_rate": 7.193184665440865e-06,
+      "loss": 0.0209,
+      "step": 1190
+    },
+    {
+      "epoch": 1.910828025477707,
+      "grad_norm": 0.39130252599716187,
+      "learning_rate": 7.015782924753871e-06,
+      "loss": 0.0228,
+      "step": 1200
+    },
+    {
+      "epoch": 1.926751592356688,
+      "grad_norm": 0.32679814100265503,
+      "learning_rate": 6.839406312592755e-06,
+      "loss": 0.0206,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9426751592356688,
+      "grad_norm": 0.40562936663627625,
+      "learning_rate": 6.664115417276629e-06,
+      "loss": 0.0202,
+      "step": 1220
+    },
+    {
+      "epoch": 1.9585987261146496,
+      "grad_norm": 0.4119989275932312,
+      "learning_rate": 6.489970454162677e-06,
+      "loss": 0.0181,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9745222929936306,
+      "grad_norm": 0.31588155031204224,
+      "learning_rate": 6.317031244961193e-06,
+      "loss": 0.0186,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9904458598726116,
+      "grad_norm": 0.3445233702659607,
+      "learning_rate": 6.1453571971858095e-06,
+      "loss": 0.0189,
+      "step": 1250
+    },
+    {
+      "epoch": 2.0063694267515926,
+      "grad_norm": 0.18995656073093414,
+      "learning_rate": 5.9750072837460436e-06,
+      "loss": 0.0134,
+      "step": 1260
+    },
+    {
+      "epoch": 2.022292993630573,
+      "grad_norm": 0.21353577077388763,
+      "learning_rate": 5.806040022689083e-06,
+      "loss": 0.0067,
+      "step": 1270
+    },
+    {
+      "epoch": 2.038216560509554,
+      "grad_norm": 0.2473672330379486,
+      "learning_rate": 5.638513457097887e-06,
+      "loss": 0.0067,
+      "step": 1280
+    },
+    {
+      "epoch": 2.054140127388535,
+      "grad_norm": 0.25051358342170715,
+      "learning_rate": 5.472485135152391e-06,
+      "loss": 0.0063,
+      "step": 1290
+    },
+    {
+      "epoch": 2.070063694267516,
+      "grad_norm": 0.2428949475288391,
+      "learning_rate": 5.3080120903607635e-06,
+      "loss": 0.0061,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0859872611464967,
+      "grad_norm": 0.2344033420085907,
+      "learning_rate": 5.14515082196743e-06,
+      "loss": 0.0065,
+      "step": 1310
+    },
+    {
+      "epoch": 2.1019108280254777,
+      "grad_norm": 0.18941205739974976,
+      "learning_rate": 4.983957275544645e-06,
+      "loss": 0.0059,
+      "step": 1320
+    },
+    {
+      "epoch": 2.1178343949044587,
+      "grad_norm": 0.312821626663208,
+      "learning_rate": 4.8244868237742325e-06,
+      "loss": 0.006,
+      "step": 1330
+    },
+    {
+      "epoch": 2.1337579617834397,
+      "grad_norm": 0.278249591588974,
+      "learning_rate": 4.666794247426169e-06,
+      "loss": 0.0058,
+      "step": 1340
+    },
+    {
+      "epoch": 2.1496815286624202,
+      "grad_norm": 0.23995652794837952,
+      "learning_rate": 4.510933716540459e-06,
+      "loss": 0.0055,
+      "step": 1350
+    },
+    {
+      "epoch": 2.1656050955414012,
+      "grad_norm": 0.27266427874565125,
+      "learning_rate": 4.356958771818804e-06,
+      "loss": 0.0058,
+      "step": 1360
+    },
+    {
+      "epoch": 2.1815286624203822,
+      "grad_norm": 0.15857194364070892,
+      "learning_rate": 4.204922306232508e-06,
+      "loss": 0.0046,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1974522292993632,
+      "grad_norm": 0.22888706624507904,
+      "learning_rate": 4.054876546852832e-06,
+      "loss": 0.0054,
+      "step": 1380
+    },
+    {
+      "epoch": 2.213375796178344,
+      "grad_norm": 0.2679773271083832,
+      "learning_rate": 3.906873036910128e-06,
+      "loss": 0.0061,
+      "step": 1390
+    },
+    {
+      "epoch": 2.229299363057325,
+      "grad_norm": 0.20967616140842438,
+      "learning_rate": 3.760962618087871e-06,
+      "loss": 0.0054,
+      "step": 1400
+    },
+    {
+      "epoch": 2.245222929936306,
+      "grad_norm": 0.24804317951202393,
+      "learning_rate": 3.6171954130577004e-06,
+      "loss": 0.0048,
+      "step": 1410
+    },
+    {
+      "epoch": 2.261146496815287,
+      "grad_norm": 0.2076551765203476,
+      "learning_rate": 3.4756208082614375e-06,
+      "loss": 0.005,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2770700636942673,
+      "grad_norm": 0.19931840896606445,
+      "learning_rate": 3.3362874369460154e-06,
+      "loss": 0.0044,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2929936305732483,
+      "grad_norm": 0.18009555339813232,
+      "learning_rate": 3.1992431624571364e-06,
+      "loss": 0.0045,
+      "step": 1440
+    },
+    {
+      "epoch": 2.3089171974522293,
+      "grad_norm": 0.3000176250934601,
+      "learning_rate": 3.06453506179743e-06,
+      "loss": 0.0053,
+      "step": 1450
+    },
+    {
+      "epoch": 2.3248407643312103,
+      "grad_norm": 0.28960147500038147,
+      "learning_rate": 2.9322094094547006e-06,
+      "loss": 0.0046,
+      "step": 1460
+    },
+    {
+      "epoch": 2.340764331210191,
+      "grad_norm": 0.1789318174123764,
+      "learning_rate": 2.802311661505873e-06,
+      "loss": 0.0051,
+      "step": 1470
+    },
+    {
+      "epoch": 2.356687898089172,
+      "grad_norm": 0.21748697757720947,
+      "learning_rate": 2.6748864400020557e-06,
+      "loss": 0.0048,
+      "step": 1480
+    },
+    {
+      "epoch": 2.372611464968153,
+      "grad_norm": 0.27882322669029236,
+      "learning_rate": 2.54997751764014e-06,
+      "loss": 0.0049,
+      "step": 1490
+    },
+    {
+      "epoch": 2.388535031847134,
+      "grad_norm": 0.2235172539949417,
+      "learning_rate": 2.42762780272613e-06,
+      "loss": 0.0044,
+      "step": 1500
+    },
+    {
+      "epoch": 2.404458598726115,
+      "grad_norm": 0.26929816603660583,
+      "learning_rate": 2.3078793244354303e-06,
+      "loss": 0.0049,
+      "step": 1510
+    },
+    {
+      "epoch": 2.4203821656050954,
+      "grad_norm": 0.19245010614395142,
+      "learning_rate": 2.1907732183751084e-06,
+      "loss": 0.0041,
+      "step": 1520
+    },
+    {
+      "epoch": 2.4363057324840764,
+      "grad_norm": 0.21086634695529938,
+      "learning_rate": 2.076349712453141e-06,
+      "loss": 0.0045,
+      "step": 1530
+    },
+    {
+      "epoch": 2.4522292993630574,
+      "grad_norm": 0.21319827437400818,
+      "learning_rate": 1.964648113059442e-06,
+      "loss": 0.0037,
+      "step": 1540
+    },
+    {
+      "epoch": 2.468152866242038,
+      "grad_norm": 0.22776374220848083,
+      "learning_rate": 1.8557067915634707e-06,
+      "loss": 0.0039,
+      "step": 1550
+    },
+    {
+      "epoch": 2.484076433121019,
+      "grad_norm": 0.24752478301525116,
+      "learning_rate": 1.7495631711330052e-06,
+      "loss": 0.0044,
+      "step": 1560
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.19484113156795502,
+      "learning_rate": 1.6462537138786793e-06,
+      "loss": 0.0044,
+      "step": 1570
+    },
+    {
+      "epoch": 2.515923566878981,
+      "grad_norm": 0.16486898064613342,
+      "learning_rate": 1.545813908328624e-06,
+      "loss": 0.0036,
+      "step": 1580
+    },
+    {
+      "epoch": 2.531847133757962,
+      "grad_norm": 0.15153397619724274,
+      "learning_rate": 1.4482782572375698e-06,
+      "loss": 0.0044,
+      "step": 1590
+    },
+    {
+      "epoch": 2.5477707006369426,
+      "grad_norm": 0.15440870821475983,
+      "learning_rate": 1.353680265734565e-06,
+      "loss": 0.0038,
+      "step": 1600
+    },
+    {
+      "epoch": 2.5636942675159236,
+      "grad_norm": 0.17342127859592438,
+      "learning_rate": 1.2620524298134117e-06,
+      "loss": 0.0044,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5796178343949046,
+      "grad_norm": 0.18218614161014557,
+      "learning_rate": 1.1734262251697458e-06,
+      "loss": 0.0038,
+      "step": 1620
+    },
+    {
+      "epoch": 2.595541401273885,
+      "grad_norm": 0.19614370167255402,
+      "learning_rate": 1.087832096388608e-06,
+      "loss": 0.0039,
+      "step": 1630
+    },
+    {
+      "epoch": 2.611464968152866,
+      "grad_norm": 0.12302397936582565,
+      "learning_rate": 1.005299446486211e-06,
+      "loss": 0.0036,
+      "step": 1640
+    },
+    {
+      "epoch": 2.627388535031847,
+      "grad_norm": 0.2053324580192566,
+      "learning_rate": 9.258566268095281e-07,
+      "loss": 0.0039,
+      "step": 1650
+    },
+    {
+      "epoch": 2.643312101910828,
+      "grad_norm": 0.17470555007457733,
+      "learning_rate": 8.495309272971175e-07,
+      "loss": 0.0041,
+      "step": 1660
+    },
+    {
+      "epoch": 2.659235668789809,
+      "grad_norm": 0.13682498037815094,
+      "learning_rate": 7.763485671045723e-07,
+      "loss": 0.0034,
+      "step": 1670
+    },
+    {
+      "epoch": 2.6751592356687897,
+      "grad_norm": 0.24173220992088318,
+      "learning_rate": 7.063346855978092e-07,
+      "loss": 0.0036,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6910828025477707,
+      "grad_norm": 0.19215670228004456,
+      "learning_rate": 6.395133337172699e-07,
+      "loss": 0.0039,
+      "step": 1690
+    },
+    {
+      "epoch": 2.7070063694267517,
+      "grad_norm": 0.15766797959804535,
+      "learning_rate": 5.759074657160213e-07,
+      "loss": 0.0033,
+      "step": 1700
+    },
+    {
+      "epoch": 2.722929936305732,
+      "grad_norm": 0.17200110852718353,
+      "learning_rate": 5.15538931274584e-07,
+      "loss": 0.0036,
+      "step": 1710
+    },
+    {
+      "epoch": 2.738853503184713,
+      "grad_norm": 0.20934487879276276,
+      "learning_rate": 4.5842846799520337e-07,
+      "loss": 0.0039,
+      "step": 1720
+    },
+    {
+      "epoch": 2.754777070063694,
+      "grad_norm": 0.18075595796108246,
+      "learning_rate": 4.0459569427813593e-07,
+      "loss": 0.0038,
+      "step": 1730
+    },
+    {
+      "epoch": 2.770700636942675,
+      "grad_norm": 0.22637341916561127,
+      "learning_rate": 3.540591025824025e-07,
+      "loss": 0.0037,
+      "step": 1740
+    },
+    {
+      "epoch": 2.786624203821656,
+      "grad_norm": 0.4421471357345581,
+      "learning_rate": 3.0683605307331053e-07,
+      "loss": 0.0038,
+      "step": 1750
+    },
+    {
+      "epoch": 2.802547770700637,
+      "grad_norm": 0.18272390961647034,
+      "learning_rate": 2.6294276765895577e-07,
+      "loss": 0.0035,
+      "step": 1760
+    },
+    {
+      "epoch": 2.8184713375796178,
+      "grad_norm": 0.1819288283586502,
+      "learning_rate": 2.223943244177207e-07,
+      "loss": 0.0035,
+      "step": 1770
+    },
+    {
+      "epoch": 2.8343949044585988,
+      "grad_norm": 0.20315492153167725,
+      "learning_rate": 1.852046524187068e-07,
+      "loss": 0.0037,
+      "step": 1780
+    },
+    {
+      "epoch": 2.8503184713375798,
+      "grad_norm": 0.12796497344970703,
+      "learning_rate": 1.5138652693685751e-07,
+      "loss": 0.0027,
+      "step": 1790
+    },
+    {
+      "epoch": 2.8662420382165603,
+      "grad_norm": 0.2990235984325409,
+      "learning_rate": 1.209515650644455e-07,
+      "loss": 0.0032,
+      "step": 1800
+    },
+    {
+      "epoch": 2.8821656050955413,
+      "grad_norm": 0.11842101812362671,
+      "learning_rate": 9.391022172040243e-08,
+      "loss": 0.0034,
+      "step": 1810
+    },
+    {
+      "epoch": 2.8980891719745223,
+      "grad_norm": 0.23246175050735474,
+      "learning_rate": 7.02717860588853e-08,
+      "loss": 0.0037,
+      "step": 1820
+    },
+    {
+      "epoch": 2.9140127388535033,
+      "grad_norm": 0.14524857699871063,
+      "learning_rate": 5.0044378278286675e-08,
+      "loss": 0.0035,
+      "step": 1830
+    },
+    {
+      "epoch": 2.9299363057324843,
+      "grad_norm": 0.21137791872024536,
+      "learning_rate": 3.323494683181716e-08,
+      "loss": 0.0039,
+      "step": 1840
+    },
+    {
+      "epoch": 2.945859872611465,
+      "grad_norm": 0.14681434631347656,
+      "learning_rate": 1.9849266040596893e-08,
+      "loss": 0.0035,
+      "step": 1850
+    },
+    {
+      "epoch": 2.961783439490446,
+      "grad_norm": 0.1578862965106964,
+      "learning_rate": 9.891934110075606e-09,
+      "loss": 0.0034,
+      "step": 1860
+    },
+    {
+      "epoch": 2.977707006369427,
+      "grad_norm": 0.16527986526489258,
+      "learning_rate": 3.366371550470593e-09,
+      "loss": 0.0031,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9936305732484074,
+      "grad_norm": 0.15652863681316376,
+      "learning_rate": 2.74820001772147e-10,
+      "loss": 0.0031,
+      "step": 1880
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1884,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.981483631879022e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1884/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fdcd187e003f4b9b5da9e9ce4b6b1f9e7edda6b65838c4d409702a576606f16
+size 7352