Upload mixed_all_v5_300k_nomatchmove/checkpoint-4500

.gitattributes

@@ -259,3 +259,4 @@ mixed_all_v5_300k_norefdot/checkpoint-3500/tokenizer.json filter=lfs diff=lfs me
 mixed_all_v5_300k_norefdot/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 toy_maze_2d_alt_v5_100k/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 mixed_all_diff_v5_350k/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mixed_all_v5_300k_nomatchmove/checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

mixed_all_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4811cc16aedfa46cf6748cd7d6c3890f6fe51f70ada6f4cf6cf57ceebad1199
+size 4968243304

mixed_all_v5_300k_nomatchmove/checkpoint-4500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8175a2ff7c481f4310008c84c92065e4a0c01126d35b6aa47a4f53fc86e1f8a3
+size 4991495816

mixed_all_v5_300k_nomatchmove/checkpoint-4500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e187ae474cf92ce45d28429927bbcb2ff0e52d7fcc2d9293393e6e76897a729c
+size 4932751040

mixed_all_v5_300k_nomatchmove/checkpoint-4500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffad4a6954859922b6149e0d81e4dfeb43b4ee9584889eeb712f0900c9416c0
+size 1691924384

mixed_all_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/tokenizer.json

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

mixed_all_v5_300k_nomatchmove/checkpoint-4500/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_v5_300k_nomatchmove/checkpoint-4500/trainer_state.json

@@ -0,0 +1,3184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0695555555555556,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0022222222222222222,
+      "grad_norm": 10.522222518920898,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.467,
+      "step": 10
+    },
+    {
+      "epoch": 0.0044444444444444444,
+      "grad_norm": 13.63652229309082,
+      "learning_rate": 4.2222222222222226e-07,
+      "loss": 0.436,
+      "step": 20
+    },
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 3.974196672439575,
+      "learning_rate": 6.444444444444445e-07,
+      "loss": 0.3025,
+      "step": 30
+    },
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 2.521632194519043,
+      "learning_rate": 8.666666666666668e-07,
+      "loss": 0.2574,
+      "step": 40
+    },
+    {
+      "epoch": 0.011111111111111112,
+      "grad_norm": 2.2161519527435303,
+      "learning_rate": 1.0888888888888889e-06,
+      "loss": 0.2197,
+      "step": 50
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 2.021404504776001,
+      "learning_rate": 1.3111111111111112e-06,
+      "loss": 0.2052,
+      "step": 60
+    },
+    {
+      "epoch": 0.015555555555555555,
+      "grad_norm": 1.4266228675842285,
+      "learning_rate": 1.5333333333333334e-06,
+      "loss": 0.1918,
+      "step": 70
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 1.5360816717147827,
+      "learning_rate": 1.7555555555555556e-06,
+      "loss": 0.1787,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.606668710708618,
+      "learning_rate": 1.977777777777778e-06,
+      "loss": 0.1803,
+      "step": 90
+    },
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 1.3905670642852783,
+      "learning_rate": 2.2e-06,
+      "loss": 0.1827,
+      "step": 100
+    },
+    {
+      "epoch": 0.024444444444444446,
+      "grad_norm": 2.099238157272339,
+      "learning_rate": 2.4222222222222223e-06,
+      "loss": 0.1726,
+      "step": 110
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 3.662956953048706,
+      "learning_rate": 2.6444444444444444e-06,
+      "loss": 0.1734,
+      "step": 120
+    },
+    {
+      "epoch": 0.028888888888888888,
+      "grad_norm": 1.5281059741973877,
+      "learning_rate": 2.866666666666667e-06,
+      "loss": 0.1764,
+      "step": 130
+    },
+    {
+      "epoch": 0.03111111111111111,
+      "grad_norm": 1.9996986389160156,
+      "learning_rate": 3.088888888888889e-06,
+      "loss": 0.1689,
+      "step": 140
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 3.4614593982696533,
+      "learning_rate": 3.3111111111111118e-06,
+      "loss": 0.1666,
+      "step": 150
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 1.5874890089035034,
+      "learning_rate": 3.5333333333333335e-06,
+      "loss": 0.1558,
+      "step": 160
+    },
+    {
+      "epoch": 0.03777777777777778,
+      "grad_norm": 1.7089293003082275,
+      "learning_rate": 3.7555555555555557e-06,
+      "loss": 0.1633,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.156266689300537,
+      "learning_rate": 3.977777777777778e-06,
+      "loss": 0.1619,
+      "step": 180
+    },
+    {
+      "epoch": 0.042222222222222223,
+      "grad_norm": 1.0367568731307983,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.1633,
+      "step": 190
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.6750001907348633,
+      "learning_rate": 4.422222222222223e-06,
+      "loss": 0.1595,
+      "step": 200
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 1.4754925966262817,
+      "learning_rate": 4.644444444444445e-06,
+      "loss": 0.16,
+      "step": 210
+    },
+    {
+      "epoch": 0.04888888888888889,
+      "grad_norm": 1.0825167894363403,
+      "learning_rate": 4.866666666666667e-06,
+      "loss": 0.1594,
+      "step": 220
+    },
+    {
+      "epoch": 0.051111111111111114,
+      "grad_norm": 1.1046106815338135,
+      "learning_rate": 5.088888888888889e-06,
+      "loss": 0.1534,
+      "step": 230
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.0096616744995117,
+      "learning_rate": 5.311111111111111e-06,
+      "loss": 0.1714,
+      "step": 240
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.7882689833641052,
+      "learning_rate": 5.533333333333334e-06,
+      "loss": 0.1578,
+      "step": 250
+    },
+    {
+      "epoch": 0.057777777777777775,
+      "grad_norm": 0.9213883876800537,
+      "learning_rate": 5.7555555555555564e-06,
+      "loss": 0.1648,
+      "step": 260
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.695729672908783,
+      "learning_rate": 5.977777777777778e-06,
+      "loss": 0.1545,
+      "step": 270
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 2.4778518676757812,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 0.157,
+      "step": 280
+    },
+    {
+      "epoch": 0.06444444444444444,
+      "grad_norm": 0.8597226738929749,
+      "learning_rate": 6.422222222222223e-06,
+      "loss": 0.1549,
+      "step": 290
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.9908995628356934,
+      "learning_rate": 6.644444444444444e-06,
+      "loss": 0.1568,
+      "step": 300
+    },
+    {
+      "epoch": 0.06888888888888889,
+      "grad_norm": 1.5490816831588745,
+      "learning_rate": 6.866666666666667e-06,
+      "loss": 0.1535,
+      "step": 310
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.7554294466972351,
+      "learning_rate": 7.0888888888888894e-06,
+      "loss": 0.1608,
+      "step": 320
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 0.7459516525268555,
+      "learning_rate": 7.3111111111111125e-06,
+      "loss": 0.1528,
+      "step": 330
+    },
+    {
+      "epoch": 0.07555555555555556,
+      "grad_norm": 0.7941413521766663,
+      "learning_rate": 7.533333333333334e-06,
+      "loss": 0.1599,
+      "step": 340
+    },
+    {
+      "epoch": 0.07777777777777778,
+      "grad_norm": 1.4148682355880737,
+      "learning_rate": 7.755555555555557e-06,
+      "loss": 0.149,
+      "step": 350
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6914868354797363,
+      "learning_rate": 7.977777777777779e-06,
+      "loss": 0.1524,
+      "step": 360
+    },
+    {
+      "epoch": 0.08222222222222222,
+      "grad_norm": 0.9896220564842224,
+      "learning_rate": 8.2e-06,
+      "loss": 0.1451,
+      "step": 370
+    },
+    {
+      "epoch": 0.08444444444444445,
+      "grad_norm": 0.8491429090499878,
+      "learning_rate": 8.422222222222223e-06,
+      "loss": 0.1517,
+      "step": 380
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.205206274986267,
+      "learning_rate": 8.644444444444445e-06,
+      "loss": 0.1535,
+      "step": 390
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.715539813041687,
+      "learning_rate": 8.866666666666668e-06,
+      "loss": 0.1479,
+      "step": 400
+    },
+    {
+      "epoch": 0.09111111111111111,
+      "grad_norm": 0.8184739947319031,
+      "learning_rate": 9.08888888888889e-06,
+      "loss": 0.1466,
+      "step": 410
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 0.7908129096031189,
+      "learning_rate": 9.311111111111112e-06,
+      "loss": 0.147,
+      "step": 420
+    },
+    {
+      "epoch": 0.09555555555555556,
+      "grad_norm": 0.8047763705253601,
+      "learning_rate": 9.533333333333334e-06,
+      "loss": 0.1473,
+      "step": 430
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 0.9746688604354858,
+      "learning_rate": 9.755555555555556e-06,
+      "loss": 0.1448,
+      "step": 440
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.1361509561538696,
+      "learning_rate": 9.977777777777778e-06,
+      "loss": 0.1478,
+      "step": 450
+    },
+    {
+      "epoch": 0.10222222222222223,
+      "grad_norm": 1.2025489807128906,
+      "learning_rate": 9.999878153526974e-06,
+      "loss": 0.1585,
+      "step": 460
+    },
+    {
+      "epoch": 0.10444444444444445,
+      "grad_norm": 0.6513128876686096,
+      "learning_rate": 9.999456963466733e-06,
+      "loss": 0.1531,
+      "step": 470
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.6371820569038391,
+      "learning_rate": 9.99873495087924e-06,
+      "loss": 0.1569,
+      "step": 480
+    },
+    {
+      "epoch": 0.10888888888888888,
+      "grad_norm": 0.5029793977737427,
+      "learning_rate": 9.997712159208745e-06,
+      "loss": 0.1419,
+      "step": 490
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.7396547794342041,
+      "learning_rate": 9.996388649997687e-06,
+      "loss": 0.1391,
+      "step": 500
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 0.6746697425842285,
+      "learning_rate": 9.99476450288299e-06,
+      "loss": 0.1409,
+      "step": 510
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 0.8636688590049744,
+      "learning_rate": 9.99283981559128e-06,
+      "loss": 0.1379,
+      "step": 520
+    },
+    {
+      "epoch": 0.11777777777777777,
+      "grad_norm": 0.584563136100769,
+      "learning_rate": 9.990614703932991e-06,
+      "loss": 0.1462,
+      "step": 530
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.6983034014701843,
+      "learning_rate": 9.988089301795406e-06,
+      "loss": 0.1356,
+      "step": 540
+    },
+    {
+      "epoch": 0.12222222222222222,
+      "grad_norm": 0.6839672327041626,
+      "learning_rate": 9.985263761134602e-06,
+      "loss": 0.1533,
+      "step": 550
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 0.5411971807479858,
+      "learning_rate": 9.982138251966297e-06,
+      "loss": 0.1447,
+      "step": 560
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 0.5902636647224426,
+      "learning_rate": 9.978712962355634e-06,
+      "loss": 0.1445,
+      "step": 570
+    },
+    {
+      "epoch": 0.1288888888888889,
+      "grad_norm": 0.5362726449966431,
+      "learning_rate": 9.97498809840585e-06,
+      "loss": 0.1398,
+      "step": 580
+    },
+    {
+      "epoch": 0.13111111111111112,
+      "grad_norm": 0.9063095450401306,
+      "learning_rate": 9.970963884245885e-06,
+      "loss": 0.1385,
+      "step": 590
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.4838777482509613,
+      "learning_rate": 9.96664056201689e-06,
+      "loss": 0.1404,
+      "step": 600
+    },
+    {
+      "epoch": 0.13555555555555557,
+      "grad_norm": 0.5629948973655701,
+      "learning_rate": 9.962018391857665e-06,
+      "loss": 0.1464,
+      "step": 610
+    },
+    {
+      "epoch": 0.13777777777777778,
+      "grad_norm": 0.6711680293083191,
+      "learning_rate": 9.957097651888996e-06,
+      "loss": 0.1363,
+      "step": 620
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.674533486366272,
+      "learning_rate": 9.951878638196929e-06,
+      "loss": 0.1376,
+      "step": 630
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.5592389106750488,
+      "learning_rate": 9.946361664814942e-06,
+      "loss": 0.1318,
+      "step": 640
+    },
+    {
+      "epoch": 0.14444444444444443,
+      "grad_norm": 0.5026865005493164,
+      "learning_rate": 9.940547063705071e-06,
+      "loss": 0.1433,
+      "step": 650
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 1.006273627281189,
+      "learning_rate": 9.93443518473791e-06,
+      "loss": 0.1399,
+      "step": 660
+    },
+    {
+      "epoch": 0.14888888888888888,
+      "grad_norm": 0.6140262484550476,
+      "learning_rate": 9.928026395671577e-06,
+      "loss": 0.1454,
+      "step": 670
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 1.98528254032135,
+      "learning_rate": 9.921321082129578e-06,
+      "loss": 0.1407,
+      "step": 680
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 1.0097556114196777,
+      "learning_rate": 9.914319647577608e-06,
+      "loss": 0.1501,
+      "step": 690
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.5728423595428467,
+      "learning_rate": 9.907022513299264e-06,
+      "loss": 0.1438,
+      "step": 700
+    },
+    {
+      "epoch": 0.15777777777777777,
+      "grad_norm": 0.9357684254646301,
+      "learning_rate": 9.899430118370712e-06,
+      "loss": 0.1497,
+      "step": 710
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5802273750305176,
+      "learning_rate": 9.891542919634252e-06,
+      "loss": 0.14,
+      "step": 720
+    },
+    {
+      "epoch": 0.1622222222222222,
+      "grad_norm": 0.5472957491874695,
+      "learning_rate": 9.883361391670841e-06,
+      "loss": 0.1434,
+      "step": 730
+    },
+    {
+      "epoch": 0.16444444444444445,
+      "grad_norm": 0.5894752740859985,
+      "learning_rate": 9.874886026771526e-06,
+      "loss": 0.143,
+      "step": 740
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.43565526604652405,
+      "learning_rate": 9.866117334907832e-06,
+      "loss": 0.1428,
+      "step": 750
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 0.47574561834335327,
+      "learning_rate": 9.857055843701073e-06,
+      "loss": 0.1321,
+      "step": 760
+    },
+    {
+      "epoch": 0.1711111111111111,
+      "grad_norm": 0.6405529379844666,
+      "learning_rate": 9.847702098390603e-06,
+      "loss": 0.1446,
+      "step": 770
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 0.4669484496116638,
+      "learning_rate": 9.83805666180101e-06,
+      "loss": 0.1331,
+      "step": 780
+    },
+    {
+      "epoch": 0.17555555555555555,
+      "grad_norm": 0.4057002067565918,
+      "learning_rate": 9.828120114308248e-06,
+      "loss": 0.1265,
+      "step": 790
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.7520941495895386,
+      "learning_rate": 9.817893053804719e-06,
+      "loss": 0.1439,
+      "step": 800
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5733896493911743,
+      "learning_rate": 9.807376095663294e-06,
+      "loss": 0.1331,
+      "step": 810
+    },
+    {
+      "epoch": 0.18222222222222223,
+      "grad_norm": 0.95039963722229,
+      "learning_rate": 9.796569872700287e-06,
+      "loss": 0.1357,
+      "step": 820
+    },
+    {
+      "epoch": 0.18444444444444444,
+      "grad_norm": 0.6228389143943787,
+      "learning_rate": 9.78547503513738e-06,
+      "loss": 0.1412,
+      "step": 830
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.6047731637954712,
+      "learning_rate": 9.774092250562488e-06,
+      "loss": 0.1377,
+      "step": 840
+    },
+    {
+      "epoch": 0.18888888888888888,
+      "grad_norm": 0.6079733967781067,
+      "learning_rate": 9.762422203889604e-06,
+      "loss": 0.1395,
+      "step": 850
+    },
+    {
+      "epoch": 0.19111111111111112,
+      "grad_norm": 0.6733460426330566,
+      "learning_rate": 9.75046559731758e-06,
+      "loss": 0.1494,
+      "step": 860
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 0.5680997371673584,
+      "learning_rate": 9.738223150287874e-06,
+      "loss": 0.1378,
+      "step": 870
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.5302682518959045,
+      "learning_rate": 9.72569559944126e-06,
+      "loss": 0.1381,
+      "step": 880
+    },
+    {
+      "epoch": 0.19777777777777777,
+      "grad_norm": 0.8905564546585083,
+      "learning_rate": 9.712883698573506e-06,
+      "loss": 0.1415,
+      "step": 890
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.685844361782074,
+      "learning_rate": 9.69978821859002e-06,
+      "loss": 0.1469,
+      "step": 900
+    },
+    {
+      "epoch": 0.20222222222222222,
+      "grad_norm": 0.5813329219818115,
+      "learning_rate": 9.68640994745946e-06,
+      "loss": 0.1447,
+      "step": 910
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 0.5627347826957703,
+      "learning_rate": 9.672749690166312e-06,
+      "loss": 0.1448,
+      "step": 920
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 0.4253447651863098,
+      "learning_rate": 9.658808268662478e-06,
+      "loss": 0.1339,
+      "step": 930
+    },
+    {
+      "epoch": 0.2088888888888889,
+      "grad_norm": 0.6289127469062805,
+      "learning_rate": 9.644586521817792e-06,
+      "loss": 0.1326,
+      "step": 940
+    },
+    {
+      "epoch": 0.2111111111111111,
+      "grad_norm": 0.4510696232318878,
+      "learning_rate": 9.630085305369559e-06,
+      "loss": 0.1268,
+      "step": 950
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.46679437160491943,
+      "learning_rate": 9.61530549187106e-06,
+      "loss": 0.1249,
+      "step": 960
+    },
+    {
+      "epoch": 0.21555555555555556,
+      "grad_norm": 0.533315122127533,
+      "learning_rate": 9.600247970639053e-06,
+      "loss": 0.1456,
+      "step": 970
+    },
+    {
+      "epoch": 0.21777777777777776,
+      "grad_norm": 0.5679814219474792,
+      "learning_rate": 9.584913647700256e-06,
+      "loss": 0.1304,
+      "step": 980
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7942007780075073,
+      "learning_rate": 9.569303445736836e-06,
+      "loss": 0.1357,
+      "step": 990
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.423073947429657,
+      "learning_rate": 9.553418304030886e-06,
+      "loss": 0.1269,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22444444444444445,
+      "grad_norm": 0.3851460814476013,
+      "learning_rate": 9.53725917840791e-06,
+      "loss": 0.1302,
+      "step": 1010
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 0.5507360696792603,
+      "learning_rate": 9.520827041179314e-06,
+      "loss": 0.128,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2288888888888889,
+      "grad_norm": 0.5385289788246155,
+      "learning_rate": 9.504122881083886e-06,
+      "loss": 0.1403,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.46596479415893555,
+      "learning_rate": 9.487147703228323e-06,
+      "loss": 0.1404,
+      "step": 1040
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.531572699546814,
+      "learning_rate": 9.469902529026736e-06,
+      "loss": 0.1329,
+      "step": 1050
+    },
+    {
+      "epoch": 0.23555555555555555,
+      "grad_norm": 0.703842282295227,
+      "learning_rate": 9.452388396139202e-06,
+      "loss": 0.1499,
+      "step": 1060
+    },
+    {
+      "epoch": 0.23777777777777778,
+      "grad_norm": 0.5137466192245483,
+      "learning_rate": 9.43460635840932e-06,
+      "loss": 0.1328,
+      "step": 1070
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5926620364189148,
+      "learning_rate": 9.416557485800796e-06,
+      "loss": 0.1374,
+      "step": 1080
+    },
+    {
+      "epoch": 0.24222222222222223,
+      "grad_norm": 0.6610704660415649,
+      "learning_rate": 9.398242864333084e-06,
+      "loss": 0.1396,
+      "step": 1090
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.43482649326324463,
+      "learning_rate": 9.379663596016004e-06,
+      "loss": 0.1344,
+      "step": 1100
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.47033923864364624,
+      "learning_rate": 9.360820798783469e-06,
+      "loss": 0.144,
+      "step": 1110
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.5374391674995422,
+      "learning_rate": 9.34171560642619e-06,
+      "loss": 0.1437,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2511111111111111,
+      "grad_norm": 0.5337796807289124,
+      "learning_rate": 9.322349168523467e-06,
+      "loss": 0.1363,
+      "step": 1130
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 0.5602109432220459,
+      "learning_rate": 9.302722650374025e-06,
+      "loss": 0.1344,
+      "step": 1140
+    },
+    {
+      "epoch": 0.25555555555555554,
+      "grad_norm": 0.8421133756637573,
+      "learning_rate": 9.282837232925876e-06,
+      "loss": 0.1423,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 0.5271303653717041,
+      "learning_rate": 9.262694112705283e-06,
+      "loss": 0.1361,
+      "step": 1160
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.6597898602485657,
+      "learning_rate": 9.242294501744743e-06,
+      "loss": 0.136,
+      "step": 1170
+    },
+    {
+      "epoch": 0.26222222222222225,
+      "grad_norm": 0.5394992232322693,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 0.1303,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2644444444444444,
+      "grad_norm": 0.4665914475917816,
+      "learning_rate": 9.200730732826555e-06,
+      "loss": 0.1323,
+      "step": 1190
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.4937392473220825,
+      "learning_rate": 9.179569075804124e-06,
+      "loss": 0.1319,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2688888888888889,
+      "grad_norm": 0.7416235208511353,
+      "learning_rate": 9.15815592976171e-06,
+      "loss": 0.1367,
+      "step": 1210
+    },
+    {
+      "epoch": 0.27111111111111114,
+      "grad_norm": 0.5438522696495056,
+      "learning_rate": 9.136492583150588e-06,
+      "loss": 0.1424,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 0.5193430781364441,
+      "learning_rate": 9.114580339476859e-06,
+      "loss": 0.1344,
+      "step": 1230
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 0.43237102031707764,
+      "learning_rate": 9.09242051722303e-06,
+      "loss": 0.142,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.5811928510665894,
+      "learning_rate": 9.07001444976866e-06,
+      "loss": 0.1457,
+      "step": 1250
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6087477803230286,
+      "learning_rate": 9.04736348531014e-06,
+      "loss": 0.1385,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2822222222222222,
+      "grad_norm": 0.4690982699394226,
+      "learning_rate": 9.02446898677957e-06,
+      "loss": 0.1404,
+      "step": 1270
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.5810984373092651,
+      "learning_rate": 9.001332331762748e-06,
+      "loss": 0.1251,
+      "step": 1280
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 0.5011066198348999,
+      "learning_rate": 8.977954912416278e-06,
+      "loss": 0.1331,
+      "step": 1290
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.5115669369697571,
+      "learning_rate": 8.954338135383804e-06,
+      "loss": 0.1299,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2911111111111111,
+      "grad_norm": 0.5805801153182983,
+      "learning_rate": 8.930483421711376e-06,
+      "loss": 0.1336,
+      "step": 1310
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.5647376775741577,
+      "learning_rate": 8.906392206761933e-06,
+      "loss": 0.1424,
+      "step": 1320
+    },
+    {
+      "epoch": 0.29555555555555557,
+      "grad_norm": 0.48366662859916687,
+      "learning_rate": 8.882065940128946e-06,
+      "loss": 0.1266,
+      "step": 1330
+    },
+    {
+      "epoch": 0.29777777777777775,
+      "grad_norm": 0.4465792775154114,
+      "learning_rate": 8.857506085549188e-06,
+      "loss": 0.1456,
+      "step": 1340
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4951059818267822,
+      "learning_rate": 8.832714120814663e-06,
+      "loss": 0.1389,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 0.5515382289886475,
+      "learning_rate": 8.807691537683685e-06,
+      "loss": 0.1357,
+      "step": 1360
+    },
+    {
+      "epoch": 0.30444444444444446,
+      "grad_norm": 0.4512007534503937,
+      "learning_rate": 8.782439841791115e-06,
+      "loss": 0.1369,
+      "step": 1370
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.6332638263702393,
+      "learning_rate": 8.756960552557769e-06,
+      "loss": 0.1389,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3088888888888889,
+      "grad_norm": 0.4105481207370758,
+      "learning_rate": 8.73125520309899e-06,
+      "loss": 0.1289,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.521911084651947,
+      "learning_rate": 8.7053253401324e-06,
+      "loss": 0.1364,
+      "step": 1400
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 0.5571779012680054,
+      "learning_rate": 8.679172523884833e-06,
+      "loss": 0.1309,
+      "step": 1410
+    },
+    {
+      "epoch": 0.31555555555555553,
+      "grad_norm": 0.6620376110076904,
+      "learning_rate": 8.652798327998458e-06,
+      "loss": 0.1329,
+      "step": 1420
+    },
+    {
+      "epoch": 0.31777777777777777,
+      "grad_norm": 0.5116106271743774,
+      "learning_rate": 8.626204339436075e-06,
+      "loss": 0.1259,
+      "step": 1430
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5097830891609192,
+      "learning_rate": 8.599392158385651e-06,
+      "loss": 0.1372,
+      "step": 1440
+    },
+    {
+      "epoch": 0.32222222222222224,
+      "grad_norm": 0.46004724502563477,
+      "learning_rate": 8.572363398164017e-06,
+      "loss": 0.1344,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3244444444444444,
+      "grad_norm": 0.465842604637146,
+      "learning_rate": 8.545119685119798e-06,
+      "loss": 0.1296,
+      "step": 1460
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.5300207138061523,
+      "learning_rate": 8.51766265853555e-06,
+      "loss": 0.1411,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 0.5274574160575867,
+      "learning_rate": 8.489993970529137e-06,
+      "loss": 0.1374,
+      "step": 1480
+    },
+    {
+      "epoch": 0.33111111111111113,
+      "grad_norm": 0.5240089297294617,
+      "learning_rate": 8.462115285954299e-06,
+      "loss": 0.1354,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.49891042709350586,
+      "learning_rate": 8.434028282300497e-06,
+      "loss": 0.1308,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33555555555555555,
+      "grad_norm": 0.5182827711105347,
+      "learning_rate": 8.405734649591964e-06,
+      "loss": 0.1297,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.5908147096633911,
+      "learning_rate": 8.377236090286016e-06,
+      "loss": 0.128,
+      "step": 1520
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5379282832145691,
+      "learning_rate": 8.34853431917062e-06,
+      "loss": 0.1357,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3422222222222222,
+      "grad_norm": 0.4943932890892029,
+      "learning_rate": 8.319631063261209e-06,
+      "loss": 0.1302,
+      "step": 1540
+    },
+    {
+      "epoch": 0.34444444444444444,
+      "grad_norm": 0.5225602388381958,
+      "learning_rate": 8.290528061696761e-06,
+      "loss": 0.1364,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.7498347759246826,
+      "learning_rate": 8.261227065635162e-06,
+      "loss": 0.1367,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3488888888888889,
+      "grad_norm": 0.5052734017372131,
+      "learning_rate": 8.231729838147833e-06,
+      "loss": 0.1405,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3511111111111111,
+      "grad_norm": 0.6217142343521118,
+      "learning_rate": 8.202038154113641e-06,
+      "loss": 0.1292,
+      "step": 1580
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 0.8158513307571411,
+      "learning_rate": 8.172153800112107e-06,
+      "loss": 0.1357,
+      "step": 1590
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.7563758492469788,
+      "learning_rate": 8.142078574315907e-06,
+      "loss": 0.1349,
+      "step": 1600
+    },
+    {
+      "epoch": 0.35777777777777775,
+      "grad_norm": 0.526100754737854,
+      "learning_rate": 8.111814286382667e-06,
+      "loss": 0.1252,
+      "step": 1610
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5793340802192688,
+      "learning_rate": 8.081362757346083e-06,
+      "loss": 0.1395,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3622222222222222,
+      "grad_norm": 0.4999346435070038,
+      "learning_rate": 8.05072581950634e-06,
+      "loss": 0.1248,
+      "step": 1630
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 0.5740838050842285,
+      "learning_rate": 8.019905316319863e-06,
+      "loss": 0.138,
+      "step": 1640
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.4553135633468628,
+      "learning_rate": 7.988903102288399e-06,
+      "loss": 0.1318,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3688888888888889,
+      "grad_norm": 1.5525007247924805,
+      "learning_rate": 7.95772104284742e-06,
+      "loss": 0.1372,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3711111111111111,
+      "grad_norm": 0.4879726469516754,
+      "learning_rate": 7.92636101425389e-06,
+      "loss": 0.1243,
+      "step": 1670
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.8027045726776123,
+      "learning_rate": 7.894824903473356e-06,
+      "loss": 0.1342,
+      "step": 1680
+    },
+    {
+      "epoch": 0.37555555555555553,
+      "grad_norm": 0.6526128649711609,
+      "learning_rate": 7.863114608066417e-06,
+      "loss": 0.1351,
+      "step": 1690
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.5237405896186829,
+      "learning_rate": 7.831232036074542e-06,
+      "loss": 0.1276,
+      "step": 1700
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.4994458258152008,
+      "learning_rate": 7.799179105905255e-06,
+      "loss": 0.1205,
+      "step": 1710
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 0.7934996485710144,
+      "learning_rate": 7.76695774621672e-06,
+      "loss": 0.1297,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3844444444444444,
+      "grad_norm": 0.7720109224319458,
+      "learning_rate": 7.734569895801675e-06,
+      "loss": 0.1322,
+      "step": 1730
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 0.4088926315307617,
+      "learning_rate": 7.702017503470773e-06,
+      "loss": 0.1279,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.5283262729644775,
+      "learning_rate": 7.669302527935334e-06,
+      "loss": 0.1364,
+      "step": 1750
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.5855908989906311,
+      "learning_rate": 7.636426937689476e-06,
+      "loss": 0.1338,
+      "step": 1760
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 0.6968936920166016,
+      "learning_rate": 7.603392710891665e-06,
+      "loss": 0.1351,
+      "step": 1770
+    },
+    {
+      "epoch": 0.39555555555555555,
+      "grad_norm": 0.5120360255241394,
+      "learning_rate": 7.570201835245703e-06,
+      "loss": 0.1387,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3977777777777778,
+      "grad_norm": 0.5173698663711548,
+      "learning_rate": 7.536856307881106e-06,
+      "loss": 0.1291,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4176649749279022,
+      "learning_rate": 7.503358135232959e-06,
+      "loss": 0.1339,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4022222222222222,
+      "grad_norm": 0.5139445066452026,
+      "learning_rate": 7.469709332921155e-06,
+      "loss": 0.1328,
+      "step": 1810
+    },
+    {
+      "epoch": 0.40444444444444444,
+      "grad_norm": 0.4628847539424896,
+      "learning_rate": 7.435911925629146e-06,
+      "loss": 0.1353,
+      "step": 1820
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 0.448440819978714,
+      "learning_rate": 7.401967946982089e-06,
+      "loss": 0.1351,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 0.562682032585144,
+      "learning_rate": 7.3678794394245e-06,
+      "loss": 0.1401,
+      "step": 1840
+    },
+    {
+      "epoch": 0.4111111111111111,
+      "grad_norm": 0.5423503518104553,
+      "learning_rate": 7.333648454097347e-06,
+      "loss": 0.1279,
+      "step": 1850
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 0.6223042011260986,
+      "learning_rate": 7.299277050714631e-06,
+      "loss": 0.1338,
+      "step": 1860
+    },
+    {
+      "epoch": 0.41555555555555557,
+      "grad_norm": 0.7407760620117188,
+      "learning_rate": 7.264767297439455e-06,
+      "loss": 0.1315,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 0.5277490019798279,
+      "learning_rate": 7.230121270759583e-06,
+      "loss": 0.127,
+      "step": 1880
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5846096873283386,
+      "learning_rate": 7.195341055362485e-06,
+      "loss": 0.1401,
+      "step": 1890
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.643839418888092,
+      "learning_rate": 7.160428744009913e-06,
+      "loss": 0.1229,
+      "step": 1900
+    },
+    {
+      "epoch": 0.42444444444444446,
+      "grad_norm": 0.5103057622909546,
+      "learning_rate": 7.1253864374119615e-06,
+      "loss": 0.1359,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.41724714636802673,
+      "learning_rate": 7.090216244100683e-06,
+      "loss": 0.1337,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4288888888888889,
+      "grad_norm": 0.41765230894088745,
+      "learning_rate": 7.054920280303199e-06,
+      "loss": 0.1282,
+      "step": 1930
+    },
+    {
+      "epoch": 0.4311111111111111,
+      "grad_norm": 0.49584460258483887,
+      "learning_rate": 7.019500669814378e-06,
+      "loss": 0.1313,
+      "step": 1940
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.5620400905609131,
+      "learning_rate": 6.9839595438690345e-06,
+      "loss": 0.1315,
+      "step": 1950
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 0.4478455185890198,
+      "learning_rate": 6.948299041013695e-06,
+      "loss": 0.1257,
+      "step": 1960
+    },
+    {
+      "epoch": 0.43777777777777777,
+      "grad_norm": 0.42052263021469116,
+      "learning_rate": 6.912521306977922e-06,
+      "loss": 0.1331,
+      "step": 1970
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4376496374607086,
+      "learning_rate": 6.876628494545198e-06,
+      "loss": 0.1254,
+      "step": 1980
+    },
+    {
+      "epoch": 0.44222222222222224,
+      "grad_norm": 0.6542510986328125,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 0.1362,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.6131172180175781,
+      "learning_rate": 6.804506280114804e-06,
+      "loss": 0.1385,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 0.4077327847480774,
+      "learning_rate": 6.76828121778582e-06,
+      "loss": 0.1265,
+      "step": 2010
+    },
+    {
+      "epoch": 0.4488888888888889,
+      "grad_norm": 0.42534321546554565,
+      "learning_rate": 6.7319497561361245e-06,
+      "loss": 0.1357,
+      "step": 2020
+    },
+    {
+      "epoch": 0.45111111111111113,
+      "grad_norm": 0.4628627896308899,
+      "learning_rate": 6.695514081267571e-06,
+      "loss": 0.1335,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.5614607334136963,
+      "learning_rate": 6.658976385552625e-06,
+      "loss": 0.1271,
+      "step": 2040
+    },
+    {
+      "epoch": 0.45555555555555555,
+      "grad_norm": 0.5273529887199402,
+      "learning_rate": 6.622338867502452e-06,
+      "loss": 0.1296,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4577777777777778,
+      "grad_norm": 0.5007169246673584,
+      "learning_rate": 6.585603731634636e-06,
+      "loss": 0.1313,
+      "step": 2060
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.6672019958496094,
+      "learning_rate": 6.548773188340523e-06,
+      "loss": 0.1248,
+      "step": 2070
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.5103129148483276,
+      "learning_rate": 6.5118494537522235e-06,
+      "loss": 0.1289,
+      "step": 2080
+    },
+    {
+      "epoch": 0.46444444444444444,
+      "grad_norm": 0.488765150308609,
+      "learning_rate": 6.474834749609266e-06,
+      "loss": 0.1268,
+      "step": 2090
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.4071212410926819,
+      "learning_rate": 6.4377313031249085e-06,
+      "loss": 0.1279,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4688888888888889,
+      "grad_norm": 0.469017893075943,
+      "learning_rate": 6.400541346852136e-06,
+      "loss": 0.1163,
+      "step": 2110
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 0.5014274716377258,
+      "learning_rate": 6.363267118549307e-06,
+      "loss": 0.1232,
+      "step": 2120
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.7158067226409912,
+      "learning_rate": 6.325910861045526e-06,
+      "loss": 0.1219,
+      "step": 2130
+    },
+    {
+      "epoch": 0.47555555555555556,
+      "grad_norm": 1.0783941745758057,
+      "learning_rate": 6.28847482210567e-06,
+      "loss": 0.134,
+      "step": 2140
+    },
+    {
+      "epoch": 0.4777777777777778,
+      "grad_norm": 0.6058904528617859,
+      "learning_rate": 6.250961254295156e-06,
+      "loss": 0.1392,
+      "step": 2150
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.42984646558761597,
+      "learning_rate": 6.21337241484439e-06,
+      "loss": 0.1248,
+      "step": 2160
+    },
+    {
+      "epoch": 0.4822222222222222,
+      "grad_norm": 1.3943397998809814,
+      "learning_rate": 6.17571056551295e-06,
+      "loss": 0.1273,
+      "step": 2170
+    },
+    {
+      "epoch": 0.48444444444444446,
+      "grad_norm": 0.3724241256713867,
+      "learning_rate": 6.137977972453499e-06,
+      "loss": 0.1414,
+      "step": 2180
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 0.5437288284301758,
+      "learning_rate": 6.10017690607542e-06,
+      "loss": 0.1338,
+      "step": 2190
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.45755183696746826,
+      "learning_rate": 6.062309640908206e-06,
+      "loss": 0.1292,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4911111111111111,
+      "grad_norm": 0.42334744334220886,
+      "learning_rate": 6.024378455464603e-06,
+      "loss": 0.1351,
+      "step": 2210
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 0.6708598136901855,
+      "learning_rate": 5.986385632103505e-06,
+      "loss": 0.1368,
+      "step": 2220
+    },
+    {
+      "epoch": 0.4955555555555556,
+      "grad_norm": 0.5554172992706299,
+      "learning_rate": 5.948333456892624e-06,
+      "loss": 0.133,
+      "step": 2230
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.41030314564704895,
+      "learning_rate": 5.910224219470935e-06,
+      "loss": 0.1364,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6109494566917419,
+      "learning_rate": 5.872060212910903e-06,
+      "loss": 0.1252,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5022222222222222,
+      "grad_norm": 0.5004986524581909,
+      "learning_rate": 5.8338437335805124e-06,
+      "loss": 0.1292,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5044444444444445,
+      "grad_norm": 1.1509629487991333,
+      "learning_rate": 5.795577081005086e-06,
+      "loss": 0.1304,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.46142834424972534,
+      "learning_rate": 5.757262557728927e-06,
+      "loss": 0.1252,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5088888888888888,
+      "grad_norm": 0.5413756966590881,
+      "learning_rate": 5.718902469176765e-06,
+      "loss": 0.1302,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.9259752631187439,
+      "learning_rate": 5.680499123515039e-06,
+      "loss": 0.1249,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 0.5130056738853455,
+      "learning_rate": 5.6420548315130156e-06,
+      "loss": 0.1335,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.42946282029151917,
+      "learning_rate": 5.6035719064037446e-06,
+      "loss": 0.1261,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5177777777777778,
+      "grad_norm": 0.6130263805389404,
+      "learning_rate": 5.56505266374487e-06,
+      "loss": 0.1358,
+      "step": 2330
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5312575697898865,
+      "learning_rate": 5.5264994212793e-06,
+      "loss": 0.1413,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5222222222222223,
+      "grad_norm": 0.4449516534805298,
+      "learning_rate": 5.487914498795748e-06,
+      "loss": 0.1262,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 0.6157702803611755,
+      "learning_rate": 5.4493002179891455e-06,
+      "loss": 0.1215,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 0.47227975726127625,
+      "learning_rate": 5.410658902320946e-06,
+      "loss": 0.1284,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5288888888888889,
+      "grad_norm": 0.47837525606155396,
+      "learning_rate": 5.371992876879318e-06,
+      "loss": 0.1222,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5311111111111111,
+      "grad_norm": 0.459592342376709,
+      "learning_rate": 5.333304468239241e-06,
+      "loss": 0.117,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.5647178292274475,
+      "learning_rate": 5.294596004322518e-06,
+      "loss": 0.1269,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5355555555555556,
+      "grad_norm": 0.41013428568840027,
+      "learning_rate": 5.255869814257701e-06,
+      "loss": 0.126,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5377777777777778,
+      "grad_norm": 0.38870328664779663,
+      "learning_rate": 5.217128228239934e-06,
+      "loss": 0.1179,
+      "step": 2420
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.459900826215744,
+      "learning_rate": 5.178373577390763e-06,
+      "loss": 0.1381,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 0.4623456299304962,
+      "learning_rate": 5.139608193617846e-06,
+      "loss": 0.1328,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5444444444444444,
+      "grad_norm": 0.4781836271286011,
+      "learning_rate": 5.100834409474661e-06,
+      "loss": 0.141,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.42533552646636963,
+      "learning_rate": 5.062054558020145e-06,
+      "loss": 0.1254,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5488888888888889,
+      "grad_norm": 1.3037346601486206,
+      "learning_rate": 5.0232709726783065e-06,
+      "loss": 0.1346,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.41636577248573303,
+      "learning_rate": 4.984485987097829e-06,
+      "loss": 0.1164,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 0.3753834068775177,
+      "learning_rate": 4.945701935011651e-06,
+      "loss": 0.1314,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.3136790692806244,
+      "learning_rate": 4.906921150096538e-06,
+      "loss": 0.1249,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5577777777777778,
+      "grad_norm": 0.4153110980987549,
+      "learning_rate": 4.868145965832667e-06,
+      "loss": 0.13,
+      "step": 2510
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6937836408615112,
+      "learning_rate": 4.8293787153632245e-06,
+      "loss": 0.1188,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5622222222222222,
+      "grad_norm": 0.5110385417938232,
+      "learning_rate": 4.7906217313540035e-06,
+      "loss": 0.1136,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5644444444444444,
+      "grad_norm": 0.3897841274738312,
+      "learning_rate": 4.751877345853055e-06,
+      "loss": 0.1282,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.46912264823913574,
+      "learning_rate": 4.713147890150372e-06,
+      "loss": 0.1278,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.46359360218048096,
+      "learning_rate": 4.674435694637597e-06,
+      "loss": 0.1151,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5711111111111111,
+      "grad_norm": 0.3676185607910156,
+      "learning_rate": 4.635743088667815e-06,
+      "loss": 0.1253,
+      "step": 2570
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 0.48425039649009705,
+      "learning_rate": 4.597072400415383e-06,
+      "loss": 0.1249,
+      "step": 2580
+    },
+    {
+      "epoch": 0.5755555555555556,
+      "grad_norm": 0.5913789868354797,
+      "learning_rate": 4.5584259567358505e-06,
+      "loss": 0.1308,
+      "step": 2590
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.49626192450523376,
+      "learning_rate": 4.519806083025944e-06,
+      "loss": 0.1204,
+      "step": 2600
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.5290204286575317,
+      "learning_rate": 4.481215103083646e-06,
+      "loss": 0.1288,
+      "step": 2610
+    },
+    {
+      "epoch": 0.5822222222222222,
+      "grad_norm": 0.6516179442405701,
+      "learning_rate": 4.442655338968373e-06,
+      "loss": 0.1262,
+      "step": 2620
+    },
+    {
+      "epoch": 0.5844444444444444,
+      "grad_norm": 0.7752233147621155,
+      "learning_rate": 4.404129110861254e-06,
+      "loss": 0.1243,
+      "step": 2630
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.6277996897697449,
+      "learning_rate": 4.365638736925512e-06,
+      "loss": 0.1246,
+      "step": 2640
+    },
+    {
+      "epoch": 0.5888888888888889,
+      "grad_norm": 0.8977844715118408,
+      "learning_rate": 4.3271865331670036e-06,
+      "loss": 0.1271,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5911111111111111,
+      "grad_norm": 0.5043493509292603,
+      "learning_rate": 4.288774813294833e-06,
+      "loss": 0.1287,
+      "step": 2660
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.4894304871559143,
+      "learning_rate": 4.2504058885821515e-06,
+      "loss": 0.1219,
+      "step": 2670
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 0.6554384827613831,
+      "learning_rate": 4.212082067727079e-06,
+      "loss": 0.1227,
+      "step": 2680
+    },
+    {
+      "epoch": 0.5977777777777777,
+      "grad_norm": 0.41011008620262146,
+      "learning_rate": 4.173805656713793e-06,
+      "loss": 0.1232,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1687465906143188,
+      "learning_rate": 4.13557895867377e-06,
+      "loss": 0.1211,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6022222222222222,
+      "grad_norm": 0.4009821116924286,
+      "learning_rate": 4.0974042737472005e-06,
+      "loss": 0.1248,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.4431607723236084,
+      "learning_rate": 4.0592838989446e-06,
+      "loss": 0.1224,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 1.3813080787658691,
+      "learning_rate": 4.021220128008584e-06,
+      "loss": 0.1257,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6088888888888889,
+      "grad_norm": 0.5191195011138916,
+      "learning_rate": 3.983215251275847e-06,
+      "loss": 0.1272,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.4447929263114929,
+      "learning_rate": 3.945271555539373e-06,
+      "loss": 0.1122,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.7146754860877991,
+      "learning_rate": 3.90739132391081e-06,
+      "loss": 0.121,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6155555555555555,
+      "grad_norm": 0.4215879738330841,
+      "learning_rate": 3.869576835683109e-06,
+      "loss": 0.1302,
+      "step": 2770
+    },
+    {
+      "epoch": 0.6177777777777778,
+      "grad_norm": 0.46832576394081116,
+      "learning_rate": 3.831830366193367e-06,
+      "loss": 0.1389,
+      "step": 2780
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.46786370873451233,
+      "learning_rate": 3.7941541866859337e-06,
+      "loss": 0.1252,
+      "step": 2790
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.5450805425643921,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 0.1219,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6244444444444445,
+      "grad_norm": 0.4638458490371704,
+      "learning_rate": 3.7190217613118385e-06,
+      "loss": 0.1219,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 0.4239422082901001,
+      "learning_rate": 3.6815700362413855e-06,
+      "loss": 0.1177,
+      "step": 2820
+    },
+    {
+      "epoch": 0.6288888888888889,
+      "grad_norm": 0.38469424843788147,
+      "learning_rate": 3.6441976424736315e-06,
+      "loss": 0.1215,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 0.48512521386146545,
+      "learning_rate": 3.6069068287443932e-06,
+      "loss": 0.131,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.4969252943992615,
+      "learning_rate": 3.569699838880735e-06,
+      "loss": 0.1241,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6355555555555555,
+      "grad_norm": 0.5221054553985596,
+      "learning_rate": 3.5325789116659493e-06,
+      "loss": 0.1216,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6377777777777778,
+      "grad_norm": 0.4684975743293762,
+      "learning_rate": 3.495546280704849e-06,
+      "loss": 0.1311,
+      "step": 2870
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.46615827083587646,
+      "learning_rate": 3.458604174289367e-06,
+      "loss": 0.1317,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6422222222222222,
+      "grad_norm": 0.4777681827545166,
+      "learning_rate": 3.4217548152644887e-06,
+      "loss": 0.1224,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 1.4527010917663574,
+      "learning_rate": 3.3850004208944838e-06,
+      "loss": 0.1325,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 0.3793092370033264,
+      "learning_rate": 3.3483432027295025e-06,
+      "loss": 0.1256,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 0.509833812713623,
+      "learning_rate": 3.311785366472506e-06,
+      "loss": 0.1277,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6511111111111111,
+      "grad_norm": 2.4946773052215576,
+      "learning_rate": 3.275329111846536e-06,
+      "loss": 0.1241,
+      "step": 2930
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 0.45981544256210327,
+      "learning_rate": 3.238976632462364e-06,
+      "loss": 0.1301,
+      "step": 2940
+    },
+    {
+      "epoch": 0.6555555555555556,
+      "grad_norm": 0.5723235607147217,
+      "learning_rate": 3.2027301156865015e-06,
+      "loss": 0.1269,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.45066529512405396,
+      "learning_rate": 3.166591742509575e-06,
+      "loss": 0.1263,
+      "step": 2960
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4456508457660675,
+      "learning_rate": 3.130563687415098e-06,
+      "loss": 0.1241,
+      "step": 2970
+    },
+    {
+      "epoch": 0.6622222222222223,
+      "grad_norm": 0.41982248425483704,
+      "learning_rate": 3.09464811824863e-06,
+      "loss": 0.13,
+      "step": 2980
+    },
+    {
+      "epoch": 0.6644444444444444,
+      "grad_norm": 0.5135678648948669,
+      "learning_rate": 3.05884719608734e-06,
+      "loss": 0.1233,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.4681214988231659,
+      "learning_rate": 3.0231630751099628e-06,
+      "loss": 0.133,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6688888888888889,
+      "grad_norm": 0.5704535841941833,
+      "learning_rate": 2.9875979024671846e-06,
+      "loss": 0.1254,
+      "step": 3010
+    },
+    {
+      "epoch": 0.6711111111111111,
+      "grad_norm": 0.40682005882263184,
+      "learning_rate": 2.9521538181524497e-06,
+      "loss": 0.1289,
+      "step": 3020
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 0.8277516961097717,
+      "learning_rate": 2.9168329548731873e-06,
+      "loss": 0.1279,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.3758750259876251,
+      "learning_rate": 2.8816374379224932e-06,
+      "loss": 0.1209,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6777777777777778,
+      "grad_norm": 0.4904175102710724,
+      "learning_rate": 2.846569385051241e-06,
+      "loss": 0.1158,
+      "step": 3050
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.44825479388237,
+      "learning_rate": 2.8116309063406593e-06,
+      "loss": 0.1306,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6822222222222222,
+      "grad_norm": 0.5725351572036743,
+      "learning_rate": 2.776824104075364e-06,
+      "loss": 0.1137,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 0.48397278785705566,
+      "learning_rate": 2.742151072616861e-06,
+      "loss": 0.1292,
+      "step": 3080
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 0.42874976992607117,
+      "learning_rate": 2.707613898277533e-06,
+      "loss": 0.142,
+      "step": 3090
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.6222420930862427,
+      "learning_rate": 2.6732146591950924e-06,
+      "loss": 0.1191,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6911111111111111,
+      "grad_norm": 0.4810314178466797,
+      "learning_rate": 2.638955425207545e-06,
+      "loss": 0.1288,
+      "step": 3110
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.5672168731689453,
+      "learning_rate": 2.604838257728648e-06,
+      "loss": 0.1178,
+      "step": 3120
+    },
+    {
+      "epoch": 0.6955555555555556,
+      "grad_norm": 0.5603622794151306,
+      "learning_rate": 2.5708652096238674e-06,
+      "loss": 0.1229,
+      "step": 3130
+    },
+    {
+      "epoch": 0.6977777777777778,
+      "grad_norm": 0.5577692985534668,
+      "learning_rate": 2.5370383250868493e-06,
+      "loss": 0.1166,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5470733642578125,
+      "learning_rate": 2.503359639516437e-06,
+      "loss": 0.1213,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 0.5103570222854614,
+      "learning_rate": 2.469831179394182e-06,
+      "loss": 0.1252,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7044444444444444,
+      "grad_norm": 0.6304283142089844,
+      "learning_rate": 2.4364549621624124e-06,
+      "loss": 0.1349,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 0.39297375082969666,
+      "learning_rate": 2.40323299610285e-06,
+      "loss": 0.1328,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7088888888888889,
+      "grad_norm": 0.39203497767448425,
+      "learning_rate": 2.3701672802157567e-06,
+      "loss": 0.1157,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.43473339080810547,
+      "learning_rate": 2.3372598040996614e-06,
+      "loss": 0.1273,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 0.5477563738822937,
+      "learning_rate": 2.304512547831639e-06,
+      "loss": 0.1352,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7155555555555555,
+      "grad_norm": 0.5483164191246033,
+      "learning_rate": 2.2719274818481767e-06,
+      "loss": 0.1173,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7177777777777777,
+      "grad_norm": 0.42467671632766724,
+      "learning_rate": 2.2395065668265943e-06,
+      "loss": 0.1281,
+      "step": 3230
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5613691806793213,
+      "learning_rate": 2.2072517535670795e-06,
+      "loss": 0.1189,
+      "step": 3240
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 0.3560629189014435,
+      "learning_rate": 2.175164982875311e-06,
+      "loss": 0.1235,
+      "step": 3250
+    },
+    {
+      "epoch": 0.7244444444444444,
+      "grad_norm": 0.38252389430999756,
+      "learning_rate": 2.1432481854456645e-06,
+      "loss": 0.1206,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 0.37806108593940735,
+      "learning_rate": 2.1115032817450476e-06,
+      "loss": 0.1165,
+      "step": 3270
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.49917393922805786,
+      "learning_rate": 2.0799321818973488e-06,
+      "loss": 0.1225,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7311111111111112,
+      "grad_norm": 0.43930304050445557,
+      "learning_rate": 2.0485367855684932e-06,
+      "loss": 0.128,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.5267101526260376,
+      "learning_rate": 2.0173189818521442e-06,
+      "loss": 0.1284,
+      "step": 3300
+    },
+    {
+      "epoch": 0.7355555555555555,
+      "grad_norm": 0.8096630573272705,
+      "learning_rate": 1.9862806491560315e-06,
+      "loss": 0.1238,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 0.41826507449150085,
+      "learning_rate": 1.955423655088928e-06,
+      "loss": 0.1176,
+      "step": 3320
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.45546630024909973,
+      "learning_rate": 1.9247498563482724e-06,
+      "loss": 0.1269,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7422222222222222,
+      "grad_norm": 0.3588191270828247,
+      "learning_rate": 1.8942610986084487e-06,
+      "loss": 0.1195,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7444444444444445,
+      "grad_norm": 0.5131126642227173,
+      "learning_rate": 1.8639592164097348e-06,
+      "loss": 0.1224,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.43253767490386963,
+      "learning_rate": 1.8338460330479102e-06,
+      "loss": 0.1303,
+      "step": 3360
+    },
+    {
+      "epoch": 0.7488888888888889,
+      "grad_norm": 0.4448409676551819,
+      "learning_rate": 1.8039233604645468e-06,
+      "loss": 0.1214,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7511111111111111,
+      "grad_norm": 1.8995914459228516,
+      "learning_rate": 1.7741929991379914e-06,
+      "loss": 0.1254,
+      "step": 3380
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 0.3588748574256897,
+      "learning_rate": 1.7446567379750167e-06,
+      "loss": 0.1186,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.4503515362739563,
+      "learning_rate": 1.7153163542031881e-06,
+      "loss": 0.1224,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7577777777777778,
+      "grad_norm": 0.4588978588581085,
+      "learning_rate": 1.686173613263925e-06,
+      "loss": 0.1183,
+      "step": 3410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.6858009099960327,
+      "learning_rate": 1.6572302687062718e-06,
+      "loss": 0.1225,
+      "step": 3420
+    },
+    {
+      "epoch": 0.7622222222222222,
+      "grad_norm": 0.8419854640960693,
+      "learning_rate": 1.6284880620813847e-06,
+      "loss": 0.1368,
+      "step": 3430
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.5079745650291443,
+      "learning_rate": 1.5999487228377398e-06,
+      "loss": 0.1223,
+      "step": 3440
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.4775300621986389,
+      "learning_rate": 1.5716139682170778e-06,
+      "loss": 0.1153,
+      "step": 3450
+    },
+    {
+      "epoch": 0.7688888888888888,
+      "grad_norm": 0.5589256882667542,
+      "learning_rate": 1.5434855031510626e-06,
+      "loss": 0.1236,
+      "step": 3460
+    },
+    {
+      "epoch": 0.7711111111111111,
+      "grad_norm": 0.4977892339229584,
+      "learning_rate": 1.515565020158703e-06,
+      "loss": 0.1234,
+      "step": 3470
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.5662384629249573,
+      "learning_rate": 1.4878541992445144e-06,
+      "loss": 0.1217,
+      "step": 3480
+    },
+    {
+      "epoch": 0.7755555555555556,
+      "grad_norm": 0.5906858444213867,
+      "learning_rate": 1.4603547077974217e-06,
+      "loss": 0.1245,
+      "step": 3490
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.60472172498703,
+      "learning_rate": 1.4330682004904367e-06,
+      "loss": 0.1272,
+      "step": 3500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.5190643072128296,
+      "learning_rate": 1.4059963191810955e-06,
+      "loss": 0.1312,
+      "step": 3510
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.6410015225410461,
+      "learning_rate": 1.3791406928126638e-06,
+      "loss": 0.1099,
+      "step": 3520
+    },
+    {
+      "epoch": 0.7844444444444445,
+      "grad_norm": 0.5300442576408386,
+      "learning_rate": 1.352502937316122e-06,
+      "loss": 0.1166,
+      "step": 3530
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 0.39025187492370605,
+      "learning_rate": 1.3260846555129325e-06,
+      "loss": 0.1255,
+      "step": 3540
+    },
+    {
+      "epoch": 0.7888888888888889,
+      "grad_norm": 0.5863329172134399,
+      "learning_rate": 1.2998874370186026e-06,
+      "loss": 0.1323,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 0.5212305188179016,
+      "learning_rate": 1.273912858147024e-06,
+      "loss": 0.1242,
+      "step": 3560
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.49098682403564453,
+      "learning_rate": 1.2481624818156319e-06,
+      "loss": 0.1127,
+      "step": 3570
+    },
+    {
+      "epoch": 0.7955555555555556,
+      "grad_norm": 0.6025397181510925,
+      "learning_rate": 1.2226378574513654e-06,
+      "loss": 0.1271,
+      "step": 3580
+    },
+    {
+      "epoch": 0.7977777777777778,
+      "grad_norm": 0.619203507900238,
+      "learning_rate": 1.1973405208974282e-06,
+      "loss": 0.13,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.43608346581459045,
+      "learning_rate": 1.1722719943208822e-06,
+      "loss": 0.1178,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8022222222222222,
+      "grad_norm": 1.086074948310852,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 0.125,
+      "step": 3610
+    },
+    {
+      "epoch": 0.8044444444444444,
+      "grad_norm": 0.5459340810775757,
+      "learning_rate": 1.1228273908387756e-06,
+      "loss": 0.1187,
+      "step": 3620
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 0.5029457211494446,
+      "learning_rate": 1.0984542890664513e-06,
+      "loss": 0.1228,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 0.5576343536376953,
+      "learning_rate": 1.0743159473589738e-06,
+      "loss": 0.1257,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8111111111111111,
+      "grad_norm": 0.43286800384521484,
+      "learning_rate": 1.050413818145481e-06,
+      "loss": 0.1204,
+      "step": 3650
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 0.47997763752937317,
+      "learning_rate": 1.0267493396419559e-06,
+      "loss": 0.1272,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8155555555555556,
+      "grad_norm": 0.972852349281311,
+      "learning_rate": 1.0033239357646913e-06,
+      "loss": 0.1211,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.3954049348831177,
+      "learning_rate": 9.801390160446135e-07,
+      "loss": 0.1177,
+      "step": 3680
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.599972128868103,
+      "learning_rate": 9.571959755424643e-07,
+      "loss": 0.1327,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.5212435126304626,
+      "learning_rate": 9.344961947648624e-07,
+      "loss": 0.1172,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8244444444444444,
+      "grad_norm": 0.4189106225967407,
+      "learning_rate": 9.120410395812346e-07,
+      "loss": 0.1172,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.45671314001083374,
+      "learning_rate": 8.898318611416329e-07,
+      "loss": 0.1251,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8288888888888889,
+      "grad_norm": 0.7642732262611389,
+      "learning_rate": 8.678699957954323e-07,
+      "loss": 0.1235,
+      "step": 3730
+    },
+    {
+      "epoch": 0.8311111111111111,
+      "grad_norm": 0.5783189535140991,
+      "learning_rate": 8.461567650109187e-07,
+      "loss": 0.1218,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.6543021202087402,
+      "learning_rate": 8.246934752957835e-07,
+      "loss": 0.1158,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.6368153691291809,
+      "learning_rate": 8.034814181184996e-07,
+      "loss": 0.1232,
+      "step": 3760
+    },
+    {
+      "epoch": 0.8377777777777777,
+      "grad_norm": 0.4983493387699127,
+      "learning_rate": 7.825218698306164e-07,
+      "loss": 0.1262,
+      "step": 3770
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.291187763214111,
+      "learning_rate": 7.618160915899641e-07,
+      "loss": 0.1223,
+      "step": 3780
+    },
+    {
+      "epoch": 0.8422222222222222,
+      "grad_norm": 0.47691014409065247,
+      "learning_rate": 7.413653292847617e-07,
+      "loss": 0.1303,
+      "step": 3790
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.5762483477592468,
+      "learning_rate": 7.211708134586565e-07,
+      "loss": 0.1143,
+      "step": 3800
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 0.5406270623207092,
+      "learning_rate": 7.012337592366764e-07,
+      "loss": 0.1144,
+      "step": 3810
+    },
+    {
+      "epoch": 0.8488888888888889,
+      "grad_norm": 0.5029114484786987,
+      "learning_rate": 6.815553662521185e-07,
+      "loss": 0.1198,
+      "step": 3820
+    },
+    {
+      "epoch": 0.8511111111111112,
+      "grad_norm": 0.6894350051879883,
+      "learning_rate": 6.621368185743626e-07,
+      "loss": 0.1243,
+      "step": 3830
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.5964691638946533,
+      "learning_rate": 6.429792846376259e-07,
+      "loss": 0.1245,
+      "step": 3840
+    },
+    {
+      "epoch": 0.8555555555555555,
+      "grad_norm": 0.628639817237854,
+      "learning_rate": 6.240839171706608e-07,
+      "loss": 0.1224,
+      "step": 3850
+    },
+    {
+      "epoch": 0.8577777777777778,
+      "grad_norm": 0.5169044733047485,
+      "learning_rate": 6.054518531273861e-07,
+      "loss": 0.1212,
+      "step": 3860
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.4869803190231323,
+      "learning_rate": 5.870842136184807e-07,
+      "loss": 0.1203,
+      "step": 3870
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 0.5320403575897217,
+      "learning_rate": 5.689821038439264e-07,
+      "loss": 0.1109,
+      "step": 3880
+    },
+    {
+      "epoch": 0.8644444444444445,
+      "grad_norm": 0.47311726212501526,
+      "learning_rate": 5.51146613026502e-07,
+      "loss": 0.1237,
+      "step": 3890
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.5362553596496582,
+      "learning_rate": 5.335788143462472e-07,
+      "loss": 0.125,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8688888888888889,
+      "grad_norm": 0.5812503099441528,
+      "learning_rate": 5.162797648758877e-07,
+      "loss": 0.1174,
+      "step": 3910
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.6182624697685242,
+      "learning_rate": 4.992505055172287e-07,
+      "loss": 0.119,
+      "step": 3920
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 0.5862412452697754,
+      "learning_rate": 4.824920609385242e-07,
+      "loss": 0.1089,
+      "step": 3930
+    },
+    {
+      "epoch": 0.8755555555555555,
+      "grad_norm": 0.5310211181640625,
+      "learning_rate": 4.6600543951281995e-07,
+      "loss": 0.1201,
+      "step": 3940
+    },
+    {
+      "epoch": 0.8777777777777778,
+      "grad_norm": 1.0204393863677979,
+      "learning_rate": 4.4979163325728324e-07,
+      "loss": 0.1259,
+      "step": 3950
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.6370622515678406,
+      "learning_rate": 4.3385161777350527e-07,
+      "loss": 0.124,
+      "step": 3960
+    },
+    {
+      "epoch": 0.8822222222222222,
+      "grad_norm": 0.6685206294059753,
+      "learning_rate": 4.1818635218880186e-07,
+      "loss": 0.1243,
+      "step": 3970
+    },
+    {
+      "epoch": 0.8844444444444445,
+      "grad_norm": 0.48257893323898315,
+      "learning_rate": 4.027967790985038e-07,
+      "loss": 0.1243,
+      "step": 3980
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.564773678779602,
+      "learning_rate": 3.876838245092357e-07,
+      "loss": 0.1153,
+      "step": 3990
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.4452403783798218,
+      "learning_rate": 3.728483977831998e-07,
+      "loss": 0.1144,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8911111111111111,
+      "grad_norm": 0.5338154435157776,
+      "learning_rate": 3.582913915834574e-07,
+      "loss": 0.1245,
+      "step": 4010
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 0.6422798037528992,
+      "learning_rate": 3.440136818202183e-07,
+      "loss": 0.1177,
+      "step": 4020
+    },
+    {
+      "epoch": 0.8955555555555555,
+      "grad_norm": 0.6522313952445984,
+      "learning_rate": 3.30016127598134e-07,
+      "loss": 0.1242,
+      "step": 4030
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 0.7125803828239441,
+      "learning_rate": 3.162995711646055e-07,
+      "loss": 0.1152,
+      "step": 4040
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4683825671672821,
+      "learning_rate": 3.0286483785910594e-07,
+      "loss": 0.1139,
+      "step": 4050
+    },
+    {
+      "epoch": 0.9022222222222223,
+      "grad_norm": 0.5882189273834229,
+      "learning_rate": 2.8971273606351656e-07,
+      "loss": 0.1224,
+      "step": 4060
+    },
+    {
+      "epoch": 0.9044444444444445,
+      "grad_norm": 0.7701581716537476,
+      "learning_rate": 2.7684405715348585e-07,
+      "loss": 0.1273,
+      "step": 4070
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.2797367572784424,
+      "learning_rate": 2.642595754508143e-07,
+      "loss": 0.1301,
+      "step": 4080
+    },
+    {
+      "epoch": 0.9088888888888889,
+      "grad_norm": 0.6263494491577148,
+      "learning_rate": 2.519600481768597e-07,
+      "loss": 0.1295,
+      "step": 4090
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.6285766959190369,
+      "learning_rate": 2.3994621540697425e-07,
+      "loss": 0.1115,
+      "step": 4100
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 0.44935739040374756,
+      "learning_rate": 2.2821880002597662e-07,
+      "loss": 0.1238,
+      "step": 4110
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 0.6543552279472351,
+      "learning_rate": 2.167785076846518e-07,
+      "loss": 0.1214,
+      "step": 4120
+    },
+    {
+      "epoch": 0.9177777777777778,
+      "grad_norm": 0.5090396404266357,
+      "learning_rate": 2.056260267572935e-07,
+      "loss": 0.1097,
+      "step": 4130
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.6067215800285339,
+      "learning_rate": 1.9476202830028213e-07,
+      "loss": 0.1153,
+      "step": 4140
+    },
+    {
+      "epoch": 0.9222222222222223,
+      "grad_norm": 1.6740268468856812,
+      "learning_rate": 1.841871660117095e-07,
+      "loss": 0.1282,
+      "step": 4150
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.5789941549301147,
+      "learning_rate": 1.739020761920418e-07,
+      "loss": 0.1082,
+      "step": 4160
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 0.7019000053405762,
+      "learning_rate": 1.639073777058342e-07,
+      "loss": 0.1244,
+      "step": 4170
+    },
+    {
+      "epoch": 0.9288888888888889,
+      "grad_norm": 0.6132505536079407,
+      "learning_rate": 1.5420367194449448e-07,
+      "loss": 0.1233,
+      "step": 4180
+    },
+    {
+      "epoch": 1.0006666666666666,
+      "grad_norm": 0.7383943796157837,
+      "learning_rate": 1.447915427900959e-07,
+      "loss": 0.1187,
+      "step": 4190
+    },
+    {
+      "epoch": 1.002888888888889,
+      "grad_norm": 0.5389364957809448,
+      "learning_rate": 1.3567155658023967e-07,
+      "loss": 0.1211,
+      "step": 4200
+    },
+    {
+      "epoch": 1.005111111111111,
+      "grad_norm": 0.5625196695327759,
+      "learning_rate": 1.268442620739868e-07,
+      "loss": 0.1123,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0073333333333334,
+      "grad_norm": 0.5088879466056824,
+      "learning_rate": 1.1831019041883273e-07,
+      "loss": 0.1166,
+      "step": 4220
+    },
+    {
+      "epoch": 1.0095555555555555,
+      "grad_norm": 0.5298504829406738,
+      "learning_rate": 1.1006985511874734e-07,
+      "loss": 0.1219,
+      "step": 4230
+    },
+    {
+      "epoch": 1.0117777777777779,
+      "grad_norm": 0.6784808039665222,
+      "learning_rate": 1.0212375200327973e-07,
+      "loss": 0.1222,
+      "step": 4240
+    },
+    {
+      "epoch": 1.014,
+      "grad_norm": 1.9344289302825928,
+      "learning_rate": 9.447235919772202e-08,
+      "loss": 0.1219,
+      "step": 4250
+    },
+    {
+      "epoch": 1.0162222222222221,
+      "grad_norm": 0.49869051575660706,
+      "learning_rate": 8.711613709434075e-08,
+      "loss": 0.118,
+      "step": 4260
+    },
+    {
+      "epoch": 1.0184444444444445,
+      "grad_norm": 0.5450420379638672,
+      "learning_rate": 8.00555283246729e-08,
+      "loss": 0.1112,
+      "step": 4270
+    },
+    {
+      "epoch": 1.0206666666666666,
+      "grad_norm": 0.5447321534156799,
+      "learning_rate": 7.329095773289552e-08,
+      "loss": 0.1232,
+      "step": 4280
+    },
+    {
+      "epoch": 1.022888888888889,
+      "grad_norm": 1.069838285446167,
+      "learning_rate": 6.682283235025844e-08,
+      "loss": 0.1285,
+      "step": 4290
+    },
+    {
+      "epoch": 1.025111111111111,
+      "grad_norm": 0.633292555809021,
+      "learning_rate": 6.065154137059603e-08,
+      "loss": 0.1297,
+      "step": 4300
+    },
+    {
+      "epoch": 1.0273333333333334,
+      "grad_norm": 0.7669098377227783,
+      "learning_rate": 5.477745612690766e-08,
+      "loss": 0.1204,
+      "step": 4310
+    },
+    {
+      "epoch": 1.0295555555555556,
+      "grad_norm": 0.6470752358436584,
+      "learning_rate": 4.9200930069014943e-08,
+      "loss": 0.1235,
+      "step": 4320
+    },
+    {
+      "epoch": 1.0317777777777777,
+      "grad_norm": 0.5270395278930664,
+      "learning_rate": 4.392229874229159e-08,
+      "loss": 0.1111,
+      "step": 4330
+    },
+    {
+      "epoch": 1.034,
+      "grad_norm": 0.41077911853790283,
+      "learning_rate": 3.894187976747732e-08,
+      "loss": 0.1138,
+      "step": 4340
+    },
+    {
+      "epoch": 1.0362222222222222,
+      "grad_norm": 0.508041262626648,
+      "learning_rate": 3.4259972821564236e-08,
+      "loss": 0.1244,
+      "step": 4350
+    },
+    {
+      "epoch": 1.0384444444444445,
+      "grad_norm": 0.3871985971927643,
+      "learning_rate": 2.9876859619764606e-08,
+      "loss": 0.1167,
+      "step": 4360
+    },
+    {
+      "epoch": 1.0406666666666666,
+      "grad_norm": 0.523582935333252,
+      "learning_rate": 2.5792803898559425e-08,
+      "loss": 0.123,
+      "step": 4370
+    },
+    {
+      "epoch": 1.042888888888889,
+      "grad_norm": 0.5492421388626099,
+      "learning_rate": 2.2008051399831643e-08,
+      "loss": 0.1146,
+      "step": 4380
+    },
+    {
+      "epoch": 1.045111111111111,
+      "grad_norm": 0.524429440498352,
+      "learning_rate": 1.8522829856076895e-08,
+      "loss": 0.1194,
+      "step": 4390
+    },
+    {
+      "epoch": 1.0473333333333332,
+      "grad_norm": 0.48922428488731384,
+      "learning_rate": 1.5337348976701137e-08,
+      "loss": 0.1182,
+      "step": 4400
+    },
+    {
+      "epoch": 1.0495555555555556,
+      "grad_norm": 0.470022976398468,
+      "learning_rate": 1.2451800435403504e-08,
+      "loss": 0.12,
+      "step": 4410
+    },
+    {
+      "epoch": 1.0517777777777777,
+      "grad_norm": 0.6413763761520386,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 0.1223,
+      "step": 4420
+    },
+    {
+      "epoch": 1.054,
+      "grad_norm": 0.4441639184951782,
+      "learning_rate": 7.581176815187329e-09,
+      "loss": 0.1169,
+      "step": 4430
+    },
+    {
+      "epoch": 1.0562222222222222,
+      "grad_norm": 0.657249927520752,
+      "learning_rate": 5.596394806759442e-09,
+      "loss": 0.1233,
+      "step": 4440
+    },
+    {
+      "epoch": 1.0584444444444445,
+      "grad_norm": 0.43894001841545105,
+      "learning_rate": 3.912131259757313e-09,
+      "loss": 0.1208,
+      "step": 4450
+    },
+    {
+      "epoch": 1.0606666666666666,
+      "grad_norm": 0.5758664608001709,
+      "learning_rate": 2.5284875180708878e-09,
+      "loss": 0.121,
+      "step": 4460
+    },
+    {
+      "epoch": 1.0628888888888888,
+      "grad_norm": 0.5076351761817932,
+      "learning_rate": 1.4455468369845015e-09,
+      "loss": 0.1248,
+      "step": 4470
+    },
+    {
+      "epoch": 1.0651111111111111,
+      "grad_norm": 0.587946355342865,
+      "learning_rate": 6.633743781642166e-10,
+      "loss": 0.1207,
+      "step": 4480
+    },
+    {
+      "epoch": 1.0673333333333332,
+      "grad_norm": 0.4501682221889496,
+      "learning_rate": 1.8201720574206884e-10,
+      "loss": 0.1178,
+      "step": 4490
+    },
+    {
+      "epoch": 1.0695555555555556,
+      "grad_norm": 0.5845088362693787,
+      "learning_rate": 1.504283478892532e-12,
+      "loss": 0.1254,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4500,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3343292990590288e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

mixed_all_v5_300k_nomatchmove/checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2febe7ad4ba0362c50c5d1cb29ac11ae3c0fce1eaf77e8c0b4d9f0d9c8979b5d
+size 7416