Upload mixed_all_diff_v5_350k/checkpoint-3000

.gitattributes

@@ -224,3 +224,4 @@ mixed_all_v5_300k_noreach/checkpoint-2500/tokenizer.json filter=lfs diff=lfs mer
 toy_maze_2d_alt_v5_100k/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 toy_maze_3d_v5_100k/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 counting-mark_all_v5_100k/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mixed_all_diff_v5_350k/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

mixed_all_diff_v5_350k/checkpoint-3000/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
+}

mixed_all_diff_v5_350k/checkpoint-3000/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 %}"
+}

mixed_all_diff_v5_350k/checkpoint-3000/config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 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": "4.51.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

mixed_all_diff_v5_350k/checkpoint-3000/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.1"
+}

mixed_all_diff_v5_350k/checkpoint-3000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd74ad06b4e6a69c09c5eaa263b6d026a2729464f3ed04842360b5293b9b3f3
+size 4968243304

mixed_all_diff_v5_350k/checkpoint-3000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d34a9a6eee2f1a30ef5f1109e9f5271eb30800f0ad60c5f15a64913275ba3a
+size 4991495816

mixed_all_diff_v5_350k/checkpoint-3000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59628692e700be819bd3767c3f2b563da571b925b48709db66a5feb9a6c27ab8
+size 4932751040

mixed_all_diff_v5_350k/checkpoint-3000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84237f4d086ff2b599a6d2fb41a978e1e0a2dcd4f1128f42321231d93d5c8180
+size 1691924384

mixed_all_diff_v5_350k/checkpoint-3000/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"
+  }
+}

mixed_all_diff_v5_350k/checkpoint-3000/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

mixed_all_diff_v5_350k/checkpoint-3000/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
+  }
+}

mixed_all_diff_v5_350k/checkpoint-3000/tokenizer.json

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

mixed_all_diff_v5_350k/checkpoint-3000/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": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

mixed_all_diff_v5_350k/checkpoint-3000/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 13.095802307128906,
+      "learning_rate": 1.8e-07,
+      "loss": 0.5392,
+      "step": 10
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 12.536194801330566,
+      "learning_rate": 3.8e-07,
+      "loss": 0.5071,
+      "step": 20
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 3.061798334121704,
+      "learning_rate": 5.800000000000001e-07,
+      "loss": 0.402,
+      "step": 30
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 1.6354824304580688,
+      "learning_rate": 7.8e-07,
+      "loss": 0.3299,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 10.905953407287598,
+      "learning_rate": 9.800000000000001e-07,
+      "loss": 0.3229,
+      "step": 50
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 2.0208652019500732,
+      "learning_rate": 1.1800000000000001e-06,
+      "loss": 0.2655,
+      "step": 60
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 2.0658318996429443,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 0.266,
+      "step": 70
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 1.5789655447006226,
+      "learning_rate": 1.5800000000000001e-06,
+      "loss": 0.2769,
+      "step": 80
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 1.4777958393096924,
+      "learning_rate": 1.7800000000000001e-06,
+      "loss": 0.274,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.455391764640808,
+      "learning_rate": 1.98e-06,
+      "loss": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 2.4884302616119385,
+      "learning_rate": 2.1800000000000003e-06,
+      "loss": 0.2466,
+      "step": 110
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.5171929597854614,
+      "learning_rate": 2.38e-06,
+      "loss": 0.2556,
+      "step": 120
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 1.3378539085388184,
+      "learning_rate": 2.5800000000000003e-06,
+      "loss": 0.2621,
+      "step": 130
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 1.728003978729248,
+      "learning_rate": 2.7800000000000005e-06,
+      "loss": 0.2636,
+      "step": 140
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.905702829360962,
+      "learning_rate": 2.9800000000000003e-06,
+      "loss": 0.2426,
+      "step": 150
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 3.693586826324463,
+      "learning_rate": 3.1800000000000005e-06,
+      "loss": 0.2505,
+      "step": 160
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 5.392415523529053,
+      "learning_rate": 3.3800000000000007e-06,
+      "loss": 0.2244,
+      "step": 170
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 1.7138640880584717,
+      "learning_rate": 3.58e-06,
+      "loss": 0.2474,
+      "step": 180
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 1.1188080310821533,
+      "learning_rate": 3.7800000000000002e-06,
+      "loss": 0.225,
+      "step": 190
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9188288450241089,
+      "learning_rate": 3.980000000000001e-06,
+      "loss": 0.2397,
+      "step": 200
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.94315505027771,
+      "learning_rate": 4.18e-06,
+      "loss": 0.2471,
+      "step": 210
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 1.3686072826385498,
+      "learning_rate": 4.38e-06,
+      "loss": 0.258,
+      "step": 220
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 1.0444778203964233,
+      "learning_rate": 4.58e-06,
+      "loss": 0.2117,
+      "step": 230
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 1.1232186555862427,
+      "learning_rate": 4.78e-06,
+      "loss": 0.2201,
+      "step": 240
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.0262072086334229,
+      "learning_rate": 4.980000000000001e-06,
+      "loss": 0.2447,
+      "step": 250
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.8631378412246704,
+      "learning_rate": 5.18e-06,
+      "loss": 0.2259,
+      "step": 260
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 1.3098729848861694,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 0.2498,
+      "step": 270
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 1.2882674932479858,
+      "learning_rate": 5.580000000000001e-06,
+      "loss": 0.2292,
+      "step": 280
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 1.3000662326812744,
+      "learning_rate": 5.78e-06,
+      "loss": 0.2284,
+      "step": 290
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9703101515769958,
+      "learning_rate": 5.98e-06,
+      "loss": 0.2064,
+      "step": 300
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.8370521664619446,
+      "learning_rate": 6.18e-06,
+      "loss": 0.2346,
+      "step": 310
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 1.088594913482666,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 0.2287,
+      "step": 320
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 1.3646186590194702,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 0.2312,
+      "step": 330
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.9520092606544495,
+      "learning_rate": 6.780000000000001e-06,
+      "loss": 0.2217,
+      "step": 340
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8036158084869385,
+      "learning_rate": 6.98e-06,
+      "loss": 0.256,
+      "step": 350
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 1.1443321704864502,
+      "learning_rate": 7.180000000000001e-06,
+      "loss": 0.2265,
+      "step": 360
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 1.7764973640441895,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 0.2265,
+      "step": 370
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.7990925908088684,
+      "learning_rate": 7.58e-06,
+      "loss": 0.2279,
+      "step": 380
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.9590052366256714,
+      "learning_rate": 7.78e-06,
+      "loss": 0.2159,
+      "step": 390
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.711288332939148,
+      "learning_rate": 7.980000000000002e-06,
+      "loss": 0.2174,
+      "step": 400
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 1.4151089191436768,
+      "learning_rate": 8.18e-06,
+      "loss": 0.233,
+      "step": 410
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.8439831733703613,
+      "learning_rate": 8.380000000000001e-06,
+      "loss": 0.2245,
+      "step": 420
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.8315847516059875,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 0.2581,
+      "step": 430
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.7403279542922974,
+      "learning_rate": 8.78e-06,
+      "loss": 0.2342,
+      "step": 440
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.0904396772384644,
+      "learning_rate": 8.98e-06,
+      "loss": 0.2084,
+      "step": 450
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.7344077229499817,
+      "learning_rate": 9.180000000000002e-06,
+      "loss": 0.2033,
+      "step": 460
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 1.1634783744812012,
+      "learning_rate": 9.38e-06,
+      "loss": 0.22,
+      "step": 470
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.9504854083061218,
+      "learning_rate": 9.58e-06,
+      "loss": 0.2383,
+      "step": 480
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.9341325759887695,
+      "learning_rate": 9.780000000000001e-06,
+      "loss": 0.2273,
+      "step": 490
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.8410105109214783,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 0.2146,
+      "step": 500
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 1.1256098747253418,
+      "learning_rate": 9.999901304280686e-06,
+      "loss": 0.2205,
+      "step": 510
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.7720330357551575,
+      "learning_rate": 9.999560138895238e-06,
+      "loss": 0.2241,
+      "step": 520
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 0.847719669342041,
+      "learning_rate": 9.99897530200195e-06,
+      "loss": 0.2125,
+      "step": 530
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.5810734033584595,
+      "learning_rate": 9.998146822104943e-06,
+      "loss": 0.2257,
+      "step": 540
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.7734278440475464,
+      "learning_rate": 9.997074739583162e-06,
+      "loss": 0.2317,
+      "step": 550
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 2.187501907348633,
+      "learning_rate": 9.995759106688394e-06,
+      "loss": 0.2194,
+      "step": 560
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 0.8118548393249512,
+      "learning_rate": 9.99419998754273e-06,
+      "loss": 0.2295,
+      "step": 570
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 1.4760451316833496,
+      "learning_rate": 9.992397458135438e-06,
+      "loss": 0.2111,
+      "step": 580
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 2.314441204071045,
+      "learning_rate": 9.990351606319261e-06,
+      "loss": 0.2369,
+      "step": 590
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.6937255859375,
+      "learning_rate": 9.988062531806127e-06,
+      "loss": 0.2153,
+      "step": 600
+    },
+    {
+      "epoch": 0.122,
+      "grad_norm": 1.1676185131072998,
+      "learning_rate": 9.9855303461623e-06,
+      "loss": 0.219,
+      "step": 610
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.693009614944458,
+      "learning_rate": 9.982755172802933e-06,
+      "loss": 0.2251,
+      "step": 620
+    },
+    {
+      "epoch": 0.126,
+      "grad_norm": 0.6551271080970764,
+      "learning_rate": 9.979737146986064e-06,
+      "loss": 0.2516,
+      "step": 630
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.5076565146446228,
+      "learning_rate": 9.976476415806013e-06,
+      "loss": 0.2171,
+      "step": 640
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.7930055260658264,
+      "learning_rate": 9.972973138186217e-06,
+      "loss": 0.2292,
+      "step": 650
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.6024525761604309,
+      "learning_rate": 9.969227484871485e-06,
+      "loss": 0.2287,
+      "step": 660
+    },
+    {
+      "epoch": 0.134,
+      "grad_norm": 0.7125842571258545,
+      "learning_rate": 9.965239638419673e-06,
+      "loss": 0.2122,
+      "step": 670
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.9468246698379517,
+      "learning_rate": 9.961009793192793e-06,
+      "loss": 0.2348,
+      "step": 680
+    },
+    {
+      "epoch": 0.138,
+      "grad_norm": 0.4537997841835022,
+      "learning_rate": 9.956538155347534e-06,
+      "loss": 0.2103,
+      "step": 690
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5157951712608337,
+      "learning_rate": 9.951824942825215e-06,
+      "loss": 0.2217,
+      "step": 700
+    },
+    {
+      "epoch": 0.142,
+      "grad_norm": 4.510913372039795,
+      "learning_rate": 9.946870385341167e-06,
+      "loss": 0.2089,
+      "step": 710
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.5302438139915466,
+      "learning_rate": 9.94167472437353e-06,
+      "loss": 0.2382,
+      "step": 720
+    },
+    {
+      "epoch": 0.146,
+      "grad_norm": 0.6763765811920166,
+      "learning_rate": 9.936238213151491e-06,
+      "loss": 0.2105,
+      "step": 730
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.7090476751327515,
+      "learning_rate": 9.930561116642936e-06,
+      "loss": 0.2211,
+      "step": 740
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.017712116241455,
+      "learning_rate": 9.92464371154154e-06,
+      "loss": 0.2129,
+      "step": 750
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.9004446864128113,
+      "learning_rate": 9.918486286253279e-06,
+      "loss": 0.2236,
+      "step": 760
+    },
+    {
+      "epoch": 0.154,
+      "grad_norm": 0.7102458477020264,
+      "learning_rate": 9.912089140882377e-06,
+      "loss": 0.224,
+      "step": 770
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.46271249651908875,
+      "learning_rate": 9.90545258721667e-06,
+      "loss": 0.2064,
+      "step": 780
+    },
+    {
+      "epoch": 0.158,
+      "grad_norm": 0.7656673192977905,
+      "learning_rate": 9.898576948712427e-06,
+      "loss": 0.2294,
+      "step": 790
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6276375651359558,
+      "learning_rate": 9.891462560478562e-06,
+      "loss": 0.2167,
+      "step": 800
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 0.6398945450782776,
+      "learning_rate": 9.884109769260326e-06,
+      "loss": 0.2114,
+      "step": 810
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.6401175260543823,
+      "learning_rate": 9.876518933422385e-06,
+      "loss": 0.1955,
+      "step": 820
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 0.6360971331596375,
+      "learning_rate": 9.868690422931372e-06,
+      "loss": 0.1937,
+      "step": 830
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6253735423088074,
+      "learning_rate": 9.860624619337844e-06,
+      "loss": 0.217,
+      "step": 840
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.7517882585525513,
+      "learning_rate": 9.852321915757688e-06,
+      "loss": 0.2356,
+      "step": 850
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.5675958395004272,
+      "learning_rate": 9.843782716852963e-06,
+      "loss": 0.2115,
+      "step": 860
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 0.5538104176521301,
+      "learning_rate": 9.835007438812177e-06,
+      "loss": 0.2033,
+      "step": 870
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.655990481376648,
+      "learning_rate": 9.825996509330001e-06,
+      "loss": 0.2113,
+      "step": 880
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 0.7001035213470459,
+      "learning_rate": 9.816750367586424e-06,
+      "loss": 0.2196,
+      "step": 890
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6400002241134644,
+      "learning_rate": 9.807269464225355e-06,
+      "loss": 0.2368,
+      "step": 900
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 0.42175188660621643,
+      "learning_rate": 9.797554261332644e-06,
+      "loss": 0.2153,
+      "step": 910
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6213666200637817,
+      "learning_rate": 9.787605232413575e-06,
+      "loss": 0.1973,
+      "step": 920
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 0.6222795248031616,
+      "learning_rate": 9.777422862369782e-06,
+      "loss": 0.2277,
+      "step": 930
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.4923384487628937,
+      "learning_rate": 9.767007647475618e-06,
+      "loss": 0.2187,
+      "step": 940
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.5715153813362122,
+      "learning_rate": 9.756360095353957e-06,
+      "loss": 0.2179,
+      "step": 950
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.540091872215271,
+      "learning_rate": 9.745480724951473e-06,
+      "loss": 0.2253,
+      "step": 960
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 0.6585381031036377,
+      "learning_rate": 9.73437006651333e-06,
+      "loss": 0.2161,
+      "step": 970
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.5296498537063599,
+      "learning_rate": 9.723028661557345e-06,
+      "loss": 0.2004,
+      "step": 980
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 0.7658775448799133,
+      "learning_rate": 9.711457062847596e-06,
+      "loss": 0.2166,
+      "step": 990
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.637302577495575,
+      "learning_rate": 9.699655834367479e-06,
+      "loss": 0.221,
+      "step": 1000
+    },
+    {
+      "epoch": 0.202,
+      "grad_norm": 0.6880996823310852,
+      "learning_rate": 9.687625551292219e-06,
+      "loss": 0.2254,
+      "step": 1010
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.5935792326927185,
+      "learning_rate": 9.675366799960842e-06,
+      "loss": 0.1994,
+      "step": 1020
+    },
+    {
+      "epoch": 0.206,
+      "grad_norm": 0.6944608688354492,
+      "learning_rate": 9.662880177847595e-06,
+      "loss": 0.2095,
+      "step": 1030
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.5425838232040405,
+      "learning_rate": 9.650166293532822e-06,
+      "loss": 0.1937,
+      "step": 1040
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.7364100217819214,
+      "learning_rate": 9.637225766673309e-06,
+      "loss": 0.1795,
+      "step": 1050
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.5623259544372559,
+      "learning_rate": 9.624059227972077e-06,
+      "loss": 0.2077,
+      "step": 1060
+    },
+    {
+      "epoch": 0.214,
+      "grad_norm": 0.5999733209609985,
+      "learning_rate": 9.610667319147648e-06,
+      "loss": 0.2013,
+      "step": 1070
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.4067252278327942,
+      "learning_rate": 9.597050692902765e-06,
+      "loss": 0.2224,
+      "step": 1080
+    },
+    {
+      "epoch": 0.218,
+      "grad_norm": 0.533978283405304,
+      "learning_rate": 9.583210012892582e-06,
+      "loss": 0.2104,
+      "step": 1090
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.42421042919158936,
+      "learning_rate": 9.569145953692316e-06,
+      "loss": 0.218,
+      "step": 1100
+    },
+    {
+      "epoch": 0.222,
+      "grad_norm": 0.5804603695869446,
+      "learning_rate": 9.554859200764371e-06,
+      "loss": 0.2149,
+      "step": 1110
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.43277624249458313,
+      "learning_rate": 9.540350450424927e-06,
+      "loss": 0.2292,
+      "step": 1120
+    },
+    {
+      "epoch": 0.226,
+      "grad_norm": 0.8847249746322632,
+      "learning_rate": 9.525620409810009e-06,
+      "loss": 0.2106,
+      "step": 1130
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.4747106432914734,
+      "learning_rate": 9.510669796841014e-06,
+      "loss": 0.193,
+      "step": 1140
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.6094072461128235,
+      "learning_rate": 9.495499340189729e-06,
+      "loss": 0.2232,
+      "step": 1150
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.4681115448474884,
+      "learning_rate": 9.480109779242805e-06,
+      "loss": 0.2151,
+      "step": 1160
+    },
+    {
+      "epoch": 0.234,
+      "grad_norm": 0.680808961391449,
+      "learning_rate": 9.464501864065735e-06,
+      "loss": 0.2,
+      "step": 1170
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.7517663240432739,
+      "learning_rate": 9.448676355366282e-06,
+      "loss": 0.2237,
+      "step": 1180
+    },
+    {
+      "epoch": 0.238,
+      "grad_norm": 0.5416564345359802,
+      "learning_rate": 9.432634024457414e-06,
+      "loss": 0.2098,
+      "step": 1190
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5150811076164246,
+      "learning_rate": 9.41637565321971e-06,
+      "loss": 0.2061,
+      "step": 1200
+    },
+    {
+      "epoch": 0.242,
+      "grad_norm": 0.9107248783111572,
+      "learning_rate": 9.399902034063244e-06,
+      "loss": 0.2195,
+      "step": 1210
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 0.6879210472106934,
+      "learning_rate": 9.383213969888972e-06,
+      "loss": 0.2038,
+      "step": 1220
+    },
+    {
+      "epoch": 0.246,
+      "grad_norm": 0.5012656450271606,
+      "learning_rate": 9.366312274049602e-06,
+      "loss": 0.2094,
+      "step": 1230
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.7412648797035217,
+      "learning_rate": 9.349197770309942e-06,
+      "loss": 0.2091,
+      "step": 1240
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.41605156660079956,
+      "learning_rate": 9.33187129280676e-06,
+      "loss": 0.2132,
+      "step": 1250
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 0.4487737715244293,
+      "learning_rate": 9.314333686008125e-06,
+      "loss": 0.2101,
+      "step": 1260
+    },
+    {
+      "epoch": 0.254,
+      "grad_norm": 0.6217042207717896,
+      "learning_rate": 9.296585804672253e-06,
+      "loss": 0.2189,
+      "step": 1270
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.6217819452285767,
+      "learning_rate": 9.278628513805838e-06,
+      "loss": 0.2071,
+      "step": 1280
+    },
+    {
+      "epoch": 0.258,
+      "grad_norm": 0.5297917127609253,
+      "learning_rate": 9.260462688621906e-06,
+      "loss": 0.1955,
+      "step": 1290
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.9292225241661072,
+      "learning_rate": 9.242089214497146e-06,
+      "loss": 0.2235,
+      "step": 1300
+    },
+    {
+      "epoch": 0.262,
+      "grad_norm": 1.318722128868103,
+      "learning_rate": 9.223508986928766e-06,
+      "loss": 0.2089,
+      "step": 1310
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.5659732818603516,
+      "learning_rate": 9.204722911490847e-06,
+      "loss": 0.2117,
+      "step": 1320
+    },
+    {
+      "epoch": 0.266,
+      "grad_norm": 0.6121715903282166,
+      "learning_rate": 9.1857319037902e-06,
+      "loss": 0.2219,
+      "step": 1330
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 0.5208039879798889,
+      "learning_rate": 9.16653688942175e-06,
+      "loss": 0.1786,
+      "step": 1340
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5769920349121094,
+      "learning_rate": 9.147138803923417e-06,
+      "loss": 0.2123,
+      "step": 1350
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.5934658646583557,
+      "learning_rate": 9.12753859273052e-06,
+      "loss": 0.2052,
+      "step": 1360
+    },
+    {
+      "epoch": 0.274,
+      "grad_norm": 0.5169550776481628,
+      "learning_rate": 9.107737211129702e-06,
+      "loss": 0.2033,
+      "step": 1370
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 0.43102511763572693,
+      "learning_rate": 9.087735624212365e-06,
+      "loss": 0.2112,
+      "step": 1380
+    },
+    {
+      "epoch": 0.278,
+      "grad_norm": 0.7378923892974854,
+      "learning_rate": 9.06753480682764e-06,
+      "loss": 0.2407,
+      "step": 1390
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.7497076988220215,
+      "learning_rate": 9.047135743534866e-06,
+      "loss": 0.2222,
+      "step": 1400
+    },
+    {
+      "epoch": 0.282,
+      "grad_norm": 0.5095514059066772,
+      "learning_rate": 9.026539428555609e-06,
+      "loss": 0.2226,
+      "step": 1410
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 0.5478781461715698,
+      "learning_rate": 9.005746865725206e-06,
+      "loss": 0.1907,
+      "step": 1420
+    },
+    {
+      "epoch": 0.286,
+      "grad_norm": 0.4810701012611389,
+      "learning_rate": 8.984759068443832e-06,
+      "loss": 0.1994,
+      "step": 1430
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.9713486433029175,
+      "learning_rate": 8.963577059627117e-06,
+      "loss": 0.1909,
+      "step": 1440
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.8102449774742126,
+      "learning_rate": 8.942201871656292e-06,
+      "loss": 0.2242,
+      "step": 1450
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 0.47727829217910767,
+      "learning_rate": 8.920634546327857e-06,
+      "loss": 0.2414,
+      "step": 1460
+    },
+    {
+      "epoch": 0.294,
+      "grad_norm": 0.6131921410560608,
+      "learning_rate": 8.898876134802827e-06,
+      "loss": 0.2011,
+      "step": 1470
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6480145454406738,
+      "learning_rate": 8.87692769755548e-06,
+      "loss": 0.2066,
+      "step": 1480
+    },
+    {
+      "epoch": 0.298,
+      "grad_norm": 2.078758716583252,
+      "learning_rate": 8.854790304321682e-06,
+      "loss": 0.2173,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.40884819626808167,
+      "learning_rate": 8.83246503404675e-06,
+      "loss": 0.2071,
+      "step": 1500
+    },
+    {
+      "epoch": 0.302,
+      "grad_norm": 0.5149683952331543,
+      "learning_rate": 8.80995297483286e-06,
+      "loss": 0.2102,
+      "step": 1510
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 1.1087095737457275,
+      "learning_rate": 8.78725522388602e-06,
+      "loss": 0.2045,
+      "step": 1520
+    },
+    {
+      "epoch": 0.306,
+      "grad_norm": 0.6572810411453247,
+      "learning_rate": 8.764372887462587e-06,
+      "loss": 0.2223,
+      "step": 1530
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.6297303438186646,
+      "learning_rate": 8.741307080815357e-06,
+      "loss": 0.2153,
+      "step": 1540
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.5744212865829468,
+      "learning_rate": 8.718058928139205e-06,
+      "loss": 0.1852,
+      "step": 1550
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.5409930944442749,
+      "learning_rate": 8.694629562516295e-06,
+      "loss": 0.2224,
+      "step": 1560
+    },
+    {
+      "epoch": 0.314,
+      "grad_norm": 1.185879111289978,
+      "learning_rate": 8.671020125860851e-06,
+      "loss": 0.1934,
+      "step": 1570
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 0.5738818645477295,
+      "learning_rate": 8.647231768863513e-06,
+      "loss": 0.1942,
+      "step": 1580
+    },
+    {
+      "epoch": 0.318,
+      "grad_norm": 0.6859444975852966,
+      "learning_rate": 8.623265650935233e-06,
+      "loss": 0.1992,
+      "step": 1590
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4545342028141022,
+      "learning_rate": 8.599122940150795e-06,
+      "loss": 0.1871,
+      "step": 1600
+    },
+    {
+      "epoch": 0.322,
+      "grad_norm": 0.5511049032211304,
+      "learning_rate": 8.574804813191859e-06,
+      "loss": 0.2247,
+      "step": 1610
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 0.4010733664035797,
+      "learning_rate": 8.550312455289624e-06,
+      "loss": 0.2112,
+      "step": 1620
+    },
+    {
+      "epoch": 0.326,
+      "grad_norm": 0.5987499952316284,
+      "learning_rate": 8.525647060167063e-06,
+      "loss": 0.1989,
+      "step": 1630
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6073696613311768,
+      "learning_rate": 8.500809829980734e-06,
+      "loss": 0.1986,
+      "step": 1640
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.5286404490470886,
+      "learning_rate": 8.4758019752622e-06,
+      "loss": 0.2266,
+      "step": 1650
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 0.6704223155975342,
+      "learning_rate": 8.450624714859016e-06,
+      "loss": 0.2143,
+      "step": 1660
+    },
+    {
+      "epoch": 0.334,
+      "grad_norm": 0.47345027327537537,
+      "learning_rate": 8.425279275875336e-06,
+      "loss": 0.2195,
+      "step": 1670
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.8093699812889099,
+      "learning_rate": 8.399766893612096e-06,
+      "loss": 0.1883,
+      "step": 1680
+    },
+    {
+      "epoch": 0.338,
+      "grad_norm": 0.4623982310295105,
+      "learning_rate": 8.374088811506819e-06,
+      "loss": 0.2301,
+      "step": 1690
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4242282509803772,
+      "learning_rate": 8.348246281072998e-06,
+      "loss": 0.213,
+      "step": 1700
+    },
+    {
+      "epoch": 0.342,
+      "grad_norm": 0.5219111442565918,
+      "learning_rate": 8.32224056183911e-06,
+      "loss": 0.21,
+      "step": 1710
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5398066639900208,
+      "learning_rate": 8.296072921287217e-06,
+      "loss": 0.1822,
+      "step": 1720
+    },
+    {
+      "epoch": 0.346,
+      "grad_norm": 0.8422920107841492,
+      "learning_rate": 8.269744634791207e-06,
+      "loss": 0.1957,
+      "step": 1730
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 0.4480317533016205,
+      "learning_rate": 8.243256985554622e-06,
+      "loss": 0.2037,
+      "step": 1740
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.7563358545303345,
+      "learning_rate": 8.21661126454811e-06,
+      "loss": 0.2019,
+      "step": 1750
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 1.0024635791778564,
+      "learning_rate": 8.189808770446528e-06,
+      "loss": 0.1966,
+      "step": 1760
+    },
+    {
+      "epoch": 0.354,
+      "grad_norm": 0.5437222123146057,
+      "learning_rate": 8.162850809565623e-06,
+      "loss": 0.2021,
+      "step": 1770
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 1.7502257823944092,
+      "learning_rate": 8.135738695798377e-06,
+      "loss": 0.2106,
+      "step": 1780
+    },
+    {
+      "epoch": 0.358,
+      "grad_norm": 0.3269011974334717,
+      "learning_rate": 8.108473750550965e-06,
+      "loss": 0.188,
+      "step": 1790
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.49707913398742676,
+      "learning_rate": 8.081057302678352e-06,
+      "loss": 0.2354,
+      "step": 1800
+    },
+    {
+      "epoch": 0.362,
+      "grad_norm": 0.8653764724731445,
+      "learning_rate": 8.053490688419532e-06,
+      "loss": 0.2325,
+      "step": 1810
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 0.7088777422904968,
+      "learning_rate": 8.02577525133239e-06,
+      "loss": 0.1987,
+      "step": 1820
+    },
+    {
+      "epoch": 0.366,
+      "grad_norm": 0.9555034637451172,
+      "learning_rate": 7.997912342228232e-06,
+      "loss": 0.1952,
+      "step": 1830
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.4464254081249237,
+      "learning_rate": 7.969903319105935e-06,
+      "loss": 0.2173,
+      "step": 1840
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.8708261847496033,
+      "learning_rate": 7.941749547085778e-06,
+      "loss": 0.2115,
+      "step": 1850
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 0.47305262088775635,
+      "learning_rate": 7.913452398342882e-06,
+      "loss": 0.1974,
+      "step": 1860
+    },
+    {
+      "epoch": 0.374,
+      "grad_norm": 0.5733006596565247,
+      "learning_rate": 7.88501325204036e-06,
+      "loss": 0.1877,
+      "step": 1870
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.7463773488998413,
+      "learning_rate": 7.856433494262078e-06,
+      "loss": 0.2277,
+      "step": 1880
+    },
+    {
+      "epoch": 0.378,
+      "grad_norm": 0.47928038239479065,
+      "learning_rate": 7.827714517945116e-06,
+      "loss": 0.2225,
+      "step": 1890
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.8981123566627502,
+      "learning_rate": 7.798857722811857e-06,
+      "loss": 0.1872,
+      "step": 1900
+    },
+    {
+      "epoch": 0.382,
+      "grad_norm": 0.5608500838279724,
+      "learning_rate": 7.769864515301787e-06,
+      "loss": 0.23,
+      "step": 1910
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.6065028309822083,
+      "learning_rate": 7.740736308502939e-06,
+      "loss": 0.2107,
+      "step": 1920
+    },
+    {
+      "epoch": 0.386,
+      "grad_norm": 0.5508809685707092,
+      "learning_rate": 7.711474522083015e-06,
+      "loss": 0.2218,
+      "step": 1930
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 1.8120936155319214,
+      "learning_rate": 7.682080582220206e-06,
+      "loss": 0.2032,
+      "step": 1940
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.4027613401412964,
+      "learning_rate": 7.652555921533671e-06,
+      "loss": 0.1981,
+      "step": 1950
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.4585378170013428,
+      "learning_rate": 7.622901979013717e-06,
+      "loss": 0.1834,
+      "step": 1960
+    },
+    {
+      "epoch": 0.394,
+      "grad_norm": 0.5401368141174316,
+      "learning_rate": 7.5931201999516715e-06,
+      "loss": 0.2236,
+      "step": 1970
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 0.5511544346809387,
+      "learning_rate": 7.563212035869426e-06,
+      "loss": 0.2057,
+      "step": 1980
+    },
+    {
+      "epoch": 0.398,
+      "grad_norm": 0.6503185629844666,
+      "learning_rate": 7.533178944448705e-06,
+      "loss": 0.2298,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.49653172492980957,
+      "learning_rate": 7.503022389460014e-06,
+      "loss": 0.2024,
+      "step": 2000
+    },
+    {
+      "epoch": 0.402,
+      "grad_norm": 0.539131224155426,
+      "learning_rate": 7.4727438406912986e-06,
+      "loss": 0.2131,
+      "step": 2010
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 0.43545109033584595,
+      "learning_rate": 7.44234477387631e-06,
+      "loss": 0.2151,
+      "step": 2020
+    },
+    {
+      "epoch": 0.406,
+      "grad_norm": 0.5361935496330261,
+      "learning_rate": 7.411826670622676e-06,
+      "loss": 0.1915,
+      "step": 2030
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.7580951452255249,
+      "learning_rate": 7.381191018339697e-06,
+      "loss": 0.2,
+      "step": 2040
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.37760236859321594,
+      "learning_rate": 7.350439310165842e-06,
+      "loss": 0.2005,
+      "step": 2050
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 0.4977528154850006,
+      "learning_rate": 7.319573044895986e-06,
+      "loss": 0.2361,
+      "step": 2060
+    },
+    {
+      "epoch": 0.414,
+      "grad_norm": 0.6078364849090576,
+      "learning_rate": 7.288593726908351e-06,
+      "loss": 0.2097,
+      "step": 2070
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.862210750579834,
+      "learning_rate": 7.257502866091192e-06,
+      "loss": 0.2047,
+      "step": 2080
+    },
+    {
+      "epoch": 0.418,
+      "grad_norm": 0.6176338791847229,
+      "learning_rate": 7.226301977769199e-06,
+      "loss": 0.225,
+      "step": 2090
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.4122490882873535,
+      "learning_rate": 7.194992582629654e-06,
+      "loss": 0.1608,
+      "step": 2100
+    },
+    {
+      "epoch": 0.422,
+      "grad_norm": 0.6164351105690002,
+      "learning_rate": 7.1635762066483035e-06,
+      "loss": 0.1889,
+      "step": 2110
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.5966829061508179,
+      "learning_rate": 7.1320543810149945e-06,
+      "loss": 0.2019,
+      "step": 2120
+    },
+    {
+      "epoch": 0.426,
+      "grad_norm": 0.6083138585090637,
+      "learning_rate": 7.100428642059033e-06,
+      "loss": 0.2039,
+      "step": 2130
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 0.5304433703422546,
+      "learning_rate": 7.0687005311743195e-06,
+      "loss": 0.2035,
+      "step": 2140
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.46998482942581177,
+      "learning_rate": 7.036871594744218e-06,
+      "loss": 0.1756,
+      "step": 2150
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.45765066146850586,
+      "learning_rate": 7.0049433840661875e-06,
+      "loss": 0.2068,
+      "step": 2160
+    },
+    {
+      "epoch": 0.434,
+      "grad_norm": 0.6738960146903992,
+      "learning_rate": 6.97291745527617e-06,
+      "loss": 0.2014,
+      "step": 2170
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 0.5685421824455261,
+      "learning_rate": 6.940795369272754e-06,
+      "loss": 0.2175,
+      "step": 2180
+    },
+    {
+      "epoch": 0.438,
+      "grad_norm": 0.5707959532737732,
+      "learning_rate": 6.908578691641092e-06,
+      "loss": 0.2064,
+      "step": 2190
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.6234077215194702,
+      "learning_rate": 6.876268992576605e-06,
+      "loss": 0.1966,
+      "step": 2200
+    },
+    {
+      "epoch": 0.442,
+      "grad_norm": 0.4323161542415619,
+      "learning_rate": 6.843867846808438e-06,
+      "loss": 0.201,
+      "step": 2210
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 0.36042520403862,
+      "learning_rate": 6.811376833522729e-06,
+      "loss": 0.2169,
+      "step": 2220
+    },
+    {
+      "epoch": 0.446,
+      "grad_norm": 0.7480013966560364,
+      "learning_rate": 6.778797536285625e-06,
+      "loss": 0.2003,
+      "step": 2230
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6599050760269165,
+      "learning_rate": 6.746131542966112e-06,
+      "loss": 0.208,
+      "step": 2240
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.7218502759933472,
+      "learning_rate": 6.713380445658618e-06,
+      "loss": 0.2023,
+      "step": 2250
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 0.9130281209945679,
+      "learning_rate": 6.680545840605423e-06,
+      "loss": 0.2437,
+      "step": 2260
+    },
+    {
+      "epoch": 0.454,
+      "grad_norm": 0.7023181915283203,
+      "learning_rate": 6.647629328118852e-06,
+      "loss": 0.1964,
+      "step": 2270
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.6429183483123779,
+      "learning_rate": 6.614632512503289e-06,
+      "loss": 0.2004,
+      "step": 2280
+    },
+    {
+      "epoch": 0.458,
+      "grad_norm": 0.36535733938217163,
+      "learning_rate": 6.58155700197697e-06,
+      "loss": 0.1915,
+      "step": 2290
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.40294337272644043,
+      "learning_rate": 6.548404408593622e-06,
+      "loss": 0.1984,
+      "step": 2300
+    },
+    {
+      "epoch": 0.462,
+      "grad_norm": 0.6866839528083801,
+      "learning_rate": 6.5151763481638705e-06,
+      "loss": 0.194,
+      "step": 2310
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 1.0196442604064941,
+      "learning_rate": 6.481874440176506e-06,
+      "loss": 0.2093,
+      "step": 2320
+    },
+    {
+      "epoch": 0.466,
+      "grad_norm": 0.4467718005180359,
+      "learning_rate": 6.448500307719537e-06,
+      "loss": 0.1987,
+      "step": 2330
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 0.43939700722694397,
+      "learning_rate": 6.415055577401101e-06,
+      "loss": 0.1884,
+      "step": 2340
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.4825338125228882,
+      "learning_rate": 6.3815418792701686e-06,
+      "loss": 0.1894,
+      "step": 2350
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.521355152130127,
+      "learning_rate": 6.3479608467371055e-06,
+      "loss": 0.2115,
+      "step": 2360
+    },
+    {
+      "epoch": 0.474,
+      "grad_norm": 0.4725077748298645,
+      "learning_rate": 6.314314116494061e-06,
+      "loss": 0.2087,
+      "step": 2370
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 0.5473461747169495,
+      "learning_rate": 6.280603328435199e-06,
+      "loss": 0.191,
+      "step": 2380
+    },
+    {
+      "epoch": 0.478,
+      "grad_norm": 0.37884438037872314,
+      "learning_rate": 6.24683012557677e-06,
+      "loss": 0.2063,
+      "step": 2390
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5701774954795837,
+      "learning_rate": 6.212996153977038e-06,
+      "loss": 0.1898,
+      "step": 2400
+    },
+    {
+      "epoch": 0.482,
+      "grad_norm": 0.600486159324646,
+      "learning_rate": 6.179103062656042e-06,
+      "loss": 0.1859,
+      "step": 2410
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 0.5841310024261475,
+      "learning_rate": 6.145152503515239e-06,
+      "loss": 0.1965,
+      "step": 2420
+    },
+    {
+      "epoch": 0.486,
+      "grad_norm": 0.45909231901168823,
+      "learning_rate": 6.111146131256983e-06,
+      "loss": 0.1996,
+      "step": 2430
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.7758110165596008,
+      "learning_rate": 6.077085603303883e-06,
+      "loss": 0.2106,
+      "step": 2440
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.5263580083847046,
+      "learning_rate": 6.04297257971802e-06,
+      "loss": 0.198,
+      "step": 2450
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 0.4820482134819031,
+      "learning_rate": 6.008808723120035e-06,
+      "loss": 0.2092,
+      "step": 2460
+    },
+    {
+      "epoch": 0.494,
+      "grad_norm": 0.6834841370582581,
+      "learning_rate": 5.974595698608103e-06,
+      "loss": 0.2267,
+      "step": 2470
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.7375311851501465,
+      "learning_rate": 5.94033517367677e-06,
+      "loss": 0.195,
+      "step": 2480
+    },
+    {
+      "epoch": 0.498,
+      "grad_norm": 0.5285785794258118,
+      "learning_rate": 5.906028818135687e-06,
+      "loss": 0.2,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5123167634010315,
+      "learning_rate": 5.871678304028224e-06,
+      "loss": 0.1925,
+      "step": 2500
+    },
+    {
+      "epoch": 0.502,
+      "grad_norm": 0.4106605350971222,
+      "learning_rate": 5.837285305549978e-06,
+      "loss": 0.1976,
+      "step": 2510
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.6250925660133362,
+      "learning_rate": 5.802851498967173e-06,
+      "loss": 0.1999,
+      "step": 2520
+    },
+    {
+      "epoch": 0.506,
+      "grad_norm": 0.6659073829650879,
+      "learning_rate": 5.768378562534962e-06,
+      "loss": 0.195,
+      "step": 2530
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 0.5039531588554382,
+      "learning_rate": 5.733868176415633e-06,
+      "loss": 0.2104,
+      "step": 2540
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5067370533943176,
+      "learning_rate": 5.6993220225967214e-06,
+      "loss": 0.2102,
+      "step": 2550
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.6953091025352478,
+      "learning_rate": 5.6647417848090225e-06,
+      "loss": 0.1938,
+      "step": 2560
+    },
+    {
+      "epoch": 0.514,
+      "grad_norm": 0.44697320461273193,
+      "learning_rate": 5.630129148444543e-06,
+      "loss": 0.2048,
+      "step": 2570
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 0.6580470204353333,
+      "learning_rate": 5.59548580047435e-06,
+      "loss": 0.1863,
+      "step": 2580
+    },
+    {
+      "epoch": 0.518,
+      "grad_norm": 0.48705974221229553,
+      "learning_rate": 5.560813429366345e-06,
+      "loss": 0.1974,
+      "step": 2590
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.3834196925163269,
+      "learning_rate": 5.526113725002984e-06,
+      "loss": 0.1872,
+      "step": 2600
+    },
+    {
+      "epoch": 0.522,
+      "grad_norm": 0.4463801085948944,
+      "learning_rate": 5.491388378598899e-06,
+      "loss": 0.2085,
+      "step": 2610
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 0.5016642808914185,
+      "learning_rate": 5.456639082618489e-06,
+      "loss": 0.1995,
+      "step": 2620
+    },
+    {
+      "epoch": 0.526,
+      "grad_norm": 0.4537654519081116,
+      "learning_rate": 5.4218675306934145e-06,
+      "loss": 0.2,
+      "step": 2630
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5141882300376892,
+      "learning_rate": 5.3870754175400595e-06,
+      "loss": 0.216,
+      "step": 2640
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.45729729533195496,
+      "learning_rate": 5.352264438876935e-06,
+      "loss": 0.2095,
+      "step": 2650
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 0.5724127292633057,
+      "learning_rate": 5.317436291342031e-06,
+      "loss": 0.1822,
+      "step": 2660
+    },
+    {
+      "epoch": 0.534,
+      "grad_norm": 0.6312456130981445,
+      "learning_rate": 5.282592672410124e-06,
+      "loss": 0.1965,
+      "step": 2670
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.5352129340171814,
+      "learning_rate": 5.247735280310041e-06,
+      "loss": 0.2048,
+      "step": 2680
+    },
+    {
+      "epoch": 0.538,
+      "grad_norm": 0.4662453532218933,
+      "learning_rate": 5.212865813941899e-06,
+      "loss": 0.2084,
+      "step": 2690
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.6075883507728577,
+      "learning_rate": 5.177985972794293e-06,
+      "loss": 0.2036,
+      "step": 2700
+    },
+    {
+      "epoch": 0.542,
+      "grad_norm": 0.7556445598602295,
+      "learning_rate": 5.143097456861474e-06,
+      "loss": 0.1942,
+      "step": 2710
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5502372980117798,
+      "learning_rate": 5.1082019665604895e-06,
+      "loss": 0.1933,
+      "step": 2720
+    },
+    {
+      "epoch": 0.546,
+      "grad_norm": 0.5725846886634827,
+      "learning_rate": 5.073301202648304e-06,
+      "loss": 0.2159,
+      "step": 2730
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 0.5544567704200745,
+      "learning_rate": 5.038396866138915e-06,
+      "loss": 0.2091,
+      "step": 2740
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.44515323638916016,
+      "learning_rate": 5.003490658220438e-06,
+      "loss": 0.2305,
+      "step": 2750
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.5360667109489441,
+      "learning_rate": 4.968584280172206e-06,
+      "loss": 0.1834,
+      "step": 2760
+    },
+    {
+      "epoch": 0.554,
+      "grad_norm": 0.43725571036338806,
+      "learning_rate": 4.933679433281837e-06,
+      "loss": 0.1939,
+      "step": 2770
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 0.4926971197128296,
+      "learning_rate": 4.898777818762325e-06,
+      "loss": 0.2004,
+      "step": 2780
+    },
+    {
+      "epoch": 0.558,
+      "grad_norm": 0.37087735533714294,
+      "learning_rate": 4.863881137669123e-06,
+      "loss": 0.2014,
+      "step": 2790
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5057938694953918,
+      "learning_rate": 4.828991090817238e-06,
+      "loss": 0.2222,
+      "step": 2800
+    },
+    {
+      "epoch": 0.562,
+      "grad_norm": 0.5449190735816956,
+      "learning_rate": 4.794109378698327e-06,
+      "loss": 0.2197,
+      "step": 2810
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 0.5408329963684082,
+      "learning_rate": 4.759237701397831e-06,
+      "loss": 0.1852,
+      "step": 2820
+    },
+    {
+      "epoch": 0.566,
+      "grad_norm": 0.516157865524292,
+      "learning_rate": 4.7243777585121034e-06,
+      "loss": 0.2058,
+      "step": 2830
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 3.804839611053467,
+      "learning_rate": 4.689531249065581e-06,
+      "loss": 0.1852,
+      "step": 2840
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.4984581768512726,
+      "learning_rate": 4.654699871427972e-06,
+      "loss": 0.2166,
+      "step": 2850
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 0.41814857721328735,
+      "learning_rate": 4.619885323231484e-06,
+      "loss": 0.2333,
+      "step": 2860
+    },
+    {
+      "epoch": 0.574,
+      "grad_norm": 0.44143739342689514,
+      "learning_rate": 4.5850893012880806e-06,
+      "loss": 0.1998,
+      "step": 2870
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.5027006268501282,
+      "learning_rate": 4.5503135015067815e-06,
+      "loss": 0.2052,
+      "step": 2880
+    },
+    {
+      "epoch": 0.578,
+      "grad_norm": 0.39498865604400635,
+      "learning_rate": 4.5155596188110055e-06,
+      "loss": 0.2105,
+      "step": 2890
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.4368332624435425,
+      "learning_rate": 4.4808293470559645e-06,
+      "loss": 0.1964,
+      "step": 2900
+    },
+    {
+      "epoch": 0.582,
+      "grad_norm": 0.5614102482795715,
+      "learning_rate": 4.446124378946108e-06,
+      "loss": 0.2187,
+      "step": 2910
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.4517853260040283,
+      "learning_rate": 4.4114464059526185e-06,
+      "loss": 0.2072,
+      "step": 2920
+    },
+    {
+      "epoch": 0.586,
+      "grad_norm": 1.014604091644287,
+      "learning_rate": 4.376797118230978e-06,
+      "loss": 0.2059,
+      "step": 2930
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 0.43756169080734253,
+      "learning_rate": 4.342178204538588e-06,
+      "loss": 0.2145,
+      "step": 2940
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.5247812271118164,
+      "learning_rate": 4.307591352152459e-06,
+      "loss": 0.2223,
+      "step": 2950
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.508820652961731,
+      "learning_rate": 4.273038246786986e-06,
+      "loss": 0.2252,
+      "step": 2960
+    },
+    {
+      "epoch": 0.594,
+      "grad_norm": 0.6411089301109314,
+      "learning_rate": 4.238520572511773e-06,
+      "loss": 0.1987,
+      "step": 2970
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 0.5892416834831238,
+      "learning_rate": 4.204040011669567e-06,
+      "loss": 0.1932,
+      "step": 2980
+    },
+    {
+      "epoch": 0.598,
+      "grad_norm": 0.4998707175254822,
+      "learning_rate": 4.169598244794261e-06,
+      "loss": 0.1931,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6128420233726501,
+      "learning_rate": 4.135196950528982e-06,
+      "loss": 0.1927,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5776860181947744e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

mixed_all_diff_v5_350k/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2840099ebff8df937a59cc9c358c7cdca866a9a0799e8e4483789e8314fd4a50
+size 7416