Upload mixed_all_v5_300k_norefdot/checkpoint-4500

.gitattributes

@@ -263,3 +263,4 @@ mixed_all_v5_300k_nomatchmove/checkpoint-4500/tokenizer.json filter=lfs diff=lfs
 mixed_all_v5_300k_nomaze2d/checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 mixed_all_v5_300k_nopatch/checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 mixed_all_v5_300k_noreach/checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mixed_all_v5_300k_norefdot/checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

mixed_all_v5_300k_norefdot/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_norefdot/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_norefdot/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_norefdot/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_norefdot/checkpoint-4500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f249c6de45c01e9b7f116ec6e89d4afebeb3f09d80c7cf92ccd4c27b4ca203
+size 4968243304

mixed_all_v5_300k_norefdot/checkpoint-4500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e64dd9287aa4399857bde8340c05510b7c6c87fe11f2f80ae6c5a5a7c3490a
+size 4991495816

mixed_all_v5_300k_norefdot/checkpoint-4500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d2b96f114bd2ba755bdf94a388d942f9d175d58721cf4845542f844e3d4006
+size 4932751040

mixed_all_v5_300k_norefdot/checkpoint-4500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ff8c132758a619ccb6417a31fbc197a04f40010e1bf7c3d9ed6f0d24223e8b
+size 1691924384

mixed_all_v5_300k_norefdot/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_norefdot/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_norefdot/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_norefdot/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_norefdot/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_norefdot/checkpoint-4500/trainer_state.json

@@ -0,0 +1,3184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0666666666666667,
+  "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": 11.33369255065918,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.5576,
+      "step": 10
+    },
+    {
+      "epoch": 0.0044444444444444444,
+      "grad_norm": 10.669922828674316,
+      "learning_rate": 4.2222222222222226e-07,
+      "loss": 0.4922,
+      "step": 20
+    },
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.499049425125122,
+      "learning_rate": 6.444444444444445e-07,
+      "loss": 0.3864,
+      "step": 30
+    },
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 2.2912824153900146,
+      "learning_rate": 8.666666666666668e-07,
+      "loss": 0.3045,
+      "step": 40
+    },
+    {
+      "epoch": 0.011111111111111112,
+      "grad_norm": 1.8093018531799316,
+      "learning_rate": 1.0888888888888889e-06,
+      "loss": 0.3118,
+      "step": 50
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 2.3803558349609375,
+      "learning_rate": 1.3111111111111112e-06,
+      "loss": 0.2959,
+      "step": 60
+    },
+    {
+      "epoch": 0.015555555555555555,
+      "grad_norm": 1.5057625770568848,
+      "learning_rate": 1.5333333333333334e-06,
+      "loss": 0.2892,
+      "step": 70
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 2.2131848335266113,
+      "learning_rate": 1.7555555555555556e-06,
+      "loss": 0.2614,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.7370716333389282,
+      "learning_rate": 1.977777777777778e-06,
+      "loss": 0.288,
+      "step": 90
+    },
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 1.141723394393921,
+      "learning_rate": 2.2e-06,
+      "loss": 0.2712,
+      "step": 100
+    },
+    {
+      "epoch": 0.024444444444444446,
+      "grad_norm": 1.4614087343215942,
+      "learning_rate": 2.4222222222222223e-06,
+      "loss": 0.2576,
+      "step": 110
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.3950473070144653,
+      "learning_rate": 2.6444444444444444e-06,
+      "loss": 0.2488,
+      "step": 120
+    },
+    {
+      "epoch": 0.028888888888888888,
+      "grad_norm": 1.9712028503417969,
+      "learning_rate": 2.866666666666667e-06,
+      "loss": 0.2454,
+      "step": 130
+    },
+    {
+      "epoch": 0.03111111111111111,
+      "grad_norm": 1.4057611227035522,
+      "learning_rate": 3.088888888888889e-06,
+      "loss": 0.2635,
+      "step": 140
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 1.2727811336517334,
+      "learning_rate": 3.3111111111111118e-06,
+      "loss": 0.2614,
+      "step": 150
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 1.275658130645752,
+      "learning_rate": 3.5333333333333335e-06,
+      "loss": 0.2484,
+      "step": 160
+    },
+    {
+      "epoch": 0.03777777777777778,
+      "grad_norm": 0.9173070192337036,
+      "learning_rate": 3.7555555555555557e-06,
+      "loss": 0.2473,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.036001443862915,
+      "learning_rate": 3.977777777777778e-06,
+      "loss": 0.256,
+      "step": 180
+    },
+    {
+      "epoch": 0.042222222222222223,
+      "grad_norm": 1.074122667312622,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.2675,
+      "step": 190
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 1.2323079109191895,
+      "learning_rate": 4.422222222222223e-06,
+      "loss": 0.2404,
+      "step": 200
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 0.8814379572868347,
+      "learning_rate": 4.644444444444445e-06,
+      "loss": 0.2495,
+      "step": 210
+    },
+    {
+      "epoch": 0.04888888888888889,
+      "grad_norm": 1.1023792028427124,
+      "learning_rate": 4.866666666666667e-06,
+      "loss": 0.2377,
+      "step": 220
+    },
+    {
+      "epoch": 0.051111111111111114,
+      "grad_norm": 1.041581630706787,
+      "learning_rate": 5.088888888888889e-06,
+      "loss": 0.2408,
+      "step": 230
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.3396949768066406,
+      "learning_rate": 5.311111111111111e-06,
+      "loss": 0.2263,
+      "step": 240
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.8793016076087952,
+      "learning_rate": 5.533333333333334e-06,
+      "loss": 0.2409,
+      "step": 250
+    },
+    {
+      "epoch": 0.057777777777777775,
+      "grad_norm": 0.9513671398162842,
+      "learning_rate": 5.7555555555555564e-06,
+      "loss": 0.2326,
+      "step": 260
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.2494601011276245,
+      "learning_rate": 5.977777777777778e-06,
+      "loss": 0.2395,
+      "step": 270
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 1.6981801986694336,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 0.2294,
+      "step": 280
+    },
+    {
+      "epoch": 0.06444444444444444,
+      "grad_norm": 0.8790388107299805,
+      "learning_rate": 6.422222222222223e-06,
+      "loss": 0.2292,
+      "step": 290
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.7193958163261414,
+      "learning_rate": 6.644444444444444e-06,
+      "loss": 0.2266,
+      "step": 300
+    },
+    {
+      "epoch": 0.06888888888888889,
+      "grad_norm": 0.7859980463981628,
+      "learning_rate": 6.866666666666667e-06,
+      "loss": 0.2659,
+      "step": 310
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.9260739088058472,
+      "learning_rate": 7.0888888888888894e-06,
+      "loss": 0.2569,
+      "step": 320
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 5.169978141784668,
+      "learning_rate": 7.3111111111111125e-06,
+      "loss": 0.2086,
+      "step": 330
+    },
+    {
+      "epoch": 0.07555555555555556,
+      "grad_norm": 2.5789854526519775,
+      "learning_rate": 7.533333333333334e-06,
+      "loss": 0.2368,
+      "step": 340
+    },
+    {
+      "epoch": 0.07777777777777778,
+      "grad_norm": 0.8443690538406372,
+      "learning_rate": 7.755555555555557e-06,
+      "loss": 0.2161,
+      "step": 350
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.8808491230010986,
+      "learning_rate": 7.977777777777779e-06,
+      "loss": 0.2353,
+      "step": 360
+    },
+    {
+      "epoch": 0.08222222222222222,
+      "grad_norm": 0.5854344367980957,
+      "learning_rate": 8.2e-06,
+      "loss": 0.2418,
+      "step": 370
+    },
+    {
+      "epoch": 0.08444444444444445,
+      "grad_norm": 0.8184396624565125,
+      "learning_rate": 8.422222222222223e-06,
+      "loss": 0.2418,
+      "step": 380
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 0.792427659034729,
+      "learning_rate": 8.644444444444445e-06,
+      "loss": 0.2181,
+      "step": 390
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.140810489654541,
+      "learning_rate": 8.866666666666668e-06,
+      "loss": 0.2324,
+      "step": 400
+    },
+    {
+      "epoch": 0.09111111111111111,
+      "grad_norm": 0.7240546345710754,
+      "learning_rate": 9.08888888888889e-06,
+      "loss": 0.2168,
+      "step": 410
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 0.6173529028892517,
+      "learning_rate": 9.311111111111112e-06,
+      "loss": 0.245,
+      "step": 420
+    },
+    {
+      "epoch": 0.09555555555555556,
+      "grad_norm": 0.813779354095459,
+      "learning_rate": 9.533333333333334e-06,
+      "loss": 0.2354,
+      "step": 430
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 3.4472432136535645,
+      "learning_rate": 9.755555555555556e-06,
+      "loss": 0.2394,
+      "step": 440
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.953109860420227,
+      "learning_rate": 9.977777777777778e-06,
+      "loss": 0.2123,
+      "step": 450
+    },
+    {
+      "epoch": 0.10222222222222223,
+      "grad_norm": 0.7197315096855164,
+      "learning_rate": 9.999878153526974e-06,
+      "loss": 0.2253,
+      "step": 460
+    },
+    {
+      "epoch": 0.10444444444444445,
+      "grad_norm": 0.7617526650428772,
+      "learning_rate": 9.999456963466733e-06,
+      "loss": 0.2332,
+      "step": 470
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.6620506048202515,
+      "learning_rate": 9.99873495087924e-06,
+      "loss": 0.227,
+      "step": 480
+    },
+    {
+      "epoch": 0.10888888888888888,
+      "grad_norm": 1.400289535522461,
+      "learning_rate": 9.997712159208745e-06,
+      "loss": 0.2061,
+      "step": 490
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.8885228633880615,
+      "learning_rate": 9.996388649997687e-06,
+      "loss": 0.2372,
+      "step": 500
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 0.924054741859436,
+      "learning_rate": 9.99476450288299e-06,
+      "loss": 0.2324,
+      "step": 510
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 0.7079559564590454,
+      "learning_rate": 9.99283981559128e-06,
+      "loss": 0.2224,
+      "step": 520
+    },
+    {
+      "epoch": 0.11777777777777777,
+      "grad_norm": 0.6031741499900818,
+      "learning_rate": 9.990614703932991e-06,
+      "loss": 0.2452,
+      "step": 530
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.104919672012329,
+      "learning_rate": 9.988089301795406e-06,
+      "loss": 0.224,
+      "step": 540
+    },
+    {
+      "epoch": 0.12222222222222222,
+      "grad_norm": 0.9171038866043091,
+      "learning_rate": 9.985263761134602e-06,
+      "loss": 0.2381,
+      "step": 550
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 0.6996046304702759,
+      "learning_rate": 9.982138251966297e-06,
+      "loss": 0.2122,
+      "step": 560
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 0.640687882900238,
+      "learning_rate": 9.978712962355634e-06,
+      "loss": 0.2301,
+      "step": 570
+    },
+    {
+      "epoch": 0.1288888888888889,
+      "grad_norm": 1.0187742710113525,
+      "learning_rate": 9.97498809840585e-06,
+      "loss": 0.2158,
+      "step": 580
+    },
+    {
+      "epoch": 0.13111111111111112,
+      "grad_norm": 0.7564474940299988,
+      "learning_rate": 9.970963884245885e-06,
+      "loss": 0.222,
+      "step": 590
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.7258399724960327,
+      "learning_rate": 9.96664056201689e-06,
+      "loss": 0.2207,
+      "step": 600
+    },
+    {
+      "epoch": 0.13555555555555557,
+      "grad_norm": 1.1189857721328735,
+      "learning_rate": 9.962018391857665e-06,
+      "loss": 0.2367,
+      "step": 610
+    },
+    {
+      "epoch": 0.13777777777777778,
+      "grad_norm": 13.553669929504395,
+      "learning_rate": 9.957097651888996e-06,
+      "loss": 0.2178,
+      "step": 620
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.7234174013137817,
+      "learning_rate": 9.951878638196929e-06,
+      "loss": 0.2069,
+      "step": 630
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.29282808303833,
+      "learning_rate": 9.946361664814942e-06,
+      "loss": 0.2451,
+      "step": 640
+    },
+    {
+      "epoch": 0.14444444444444443,
+      "grad_norm": 0.6512086987495422,
+      "learning_rate": 9.940547063705071e-06,
+      "loss": 0.2012,
+      "step": 650
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 0.7376608848571777,
+      "learning_rate": 9.93443518473791e-06,
+      "loss": 0.2461,
+      "step": 660
+    },
+    {
+      "epoch": 0.14888888888888888,
+      "grad_norm": 0.7877892851829529,
+      "learning_rate": 9.928026395671577e-06,
+      "loss": 0.2082,
+      "step": 670
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 0.545399010181427,
+      "learning_rate": 9.921321082129578e-06,
+      "loss": 0.2308,
+      "step": 680
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 0.7691233158111572,
+      "learning_rate": 9.914319647577608e-06,
+      "loss": 0.2413,
+      "step": 690
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.5028457641601562,
+      "learning_rate": 9.907022513299264e-06,
+      "loss": 0.2161,
+      "step": 700
+    },
+    {
+      "epoch": 0.15777777777777777,
+      "grad_norm": 0.5077999234199524,
+      "learning_rate": 9.899430118370712e-06,
+      "loss": 0.231,
+      "step": 710
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8014217019081116,
+      "learning_rate": 9.891542919634252e-06,
+      "loss": 0.2193,
+      "step": 720
+    },
+    {
+      "epoch": 0.1622222222222222,
+      "grad_norm": 0.5127914547920227,
+      "learning_rate": 9.883361391670841e-06,
+      "loss": 0.2145,
+      "step": 730
+    },
+    {
+      "epoch": 0.16444444444444445,
+      "grad_norm": 0.8126584887504578,
+      "learning_rate": 9.874886026771526e-06,
+      "loss": 0.231,
+      "step": 740
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.7147446274757385,
+      "learning_rate": 9.866117334907832e-06,
+      "loss": 0.2222,
+      "step": 750
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 0.6180881261825562,
+      "learning_rate": 9.857055843701073e-06,
+      "loss": 0.2082,
+      "step": 760
+    },
+    {
+      "epoch": 0.1711111111111111,
+      "grad_norm": 1.0180305242538452,
+      "learning_rate": 9.847702098390603e-06,
+      "loss": 0.2161,
+      "step": 770
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 0.46449825167655945,
+      "learning_rate": 9.83805666180101e-06,
+      "loss": 0.2437,
+      "step": 780
+    },
+    {
+      "epoch": 0.17555555555555555,
+      "grad_norm": 0.7959275841712952,
+      "learning_rate": 9.828120114308248e-06,
+      "loss": 0.2623,
+      "step": 790
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6887152791023254,
+      "learning_rate": 9.817893053804719e-06,
+      "loss": 0.2361,
+      "step": 800
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6447773575782776,
+      "learning_rate": 9.807376095663294e-06,
+      "loss": 0.2361,
+      "step": 810
+    },
+    {
+      "epoch": 0.18222222222222223,
+      "grad_norm": 0.8348853588104248,
+      "learning_rate": 9.796569872700287e-06,
+      "loss": 0.2086,
+      "step": 820
+    },
+    {
+      "epoch": 0.18444444444444444,
+      "grad_norm": 0.6994556188583374,
+      "learning_rate": 9.78547503513738e-06,
+      "loss": 0.2352,
+      "step": 830
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.4774794280529022,
+      "learning_rate": 9.774092250562488e-06,
+      "loss": 0.2496,
+      "step": 840
+    },
+    {
+      "epoch": 0.18888888888888888,
+      "grad_norm": 1.1575181484222412,
+      "learning_rate": 9.762422203889604e-06,
+      "loss": 0.223,
+      "step": 850
+    },
+    {
+      "epoch": 0.19111111111111112,
+      "grad_norm": 0.5560621023178101,
+      "learning_rate": 9.75046559731758e-06,
+      "loss": 0.2412,
+      "step": 860
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 0.6625902056694031,
+      "learning_rate": 9.738223150287874e-06,
+      "loss": 0.2137,
+      "step": 870
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.7033166885375977,
+      "learning_rate": 9.72569559944126e-06,
+      "loss": 0.2235,
+      "step": 880
+    },
+    {
+      "epoch": 0.19777777777777777,
+      "grad_norm": 0.48002922534942627,
+      "learning_rate": 9.712883698573506e-06,
+      "loss": 0.2172,
+      "step": 890
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6284924149513245,
+      "learning_rate": 9.69978821859002e-06,
+      "loss": 0.2213,
+      "step": 900
+    },
+    {
+      "epoch": 0.20222222222222222,
+      "grad_norm": 0.620901346206665,
+      "learning_rate": 9.68640994745946e-06,
+      "loss": 0.2452,
+      "step": 910
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 0.7191984057426453,
+      "learning_rate": 9.672749690166312e-06,
+      "loss": 0.2063,
+      "step": 920
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 0.44102415442466736,
+      "learning_rate": 9.658808268662478e-06,
+      "loss": 0.2365,
+      "step": 930
+    },
+    {
+      "epoch": 0.2088888888888889,
+      "grad_norm": 0.5127256512641907,
+      "learning_rate": 9.644586521817792e-06,
+      "loss": 0.2062,
+      "step": 940
+    },
+    {
+      "epoch": 0.2111111111111111,
+      "grad_norm": 0.6389340758323669,
+      "learning_rate": 9.630085305369559e-06,
+      "loss": 0.2137,
+      "step": 950
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6132908463478088,
+      "learning_rate": 9.61530549187106e-06,
+      "loss": 0.2127,
+      "step": 960
+    },
+    {
+      "epoch": 0.21555555555555556,
+      "grad_norm": 0.5338010787963867,
+      "learning_rate": 9.600247970639053e-06,
+      "loss": 0.2483,
+      "step": 970
+    },
+    {
+      "epoch": 0.21777777777777776,
+      "grad_norm": 0.5087562203407288,
+      "learning_rate": 9.584913647700256e-06,
+      "loss": 0.2041,
+      "step": 980
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.5899208188056946,
+      "learning_rate": 9.569303445736836e-06,
+      "loss": 0.2257,
+      "step": 990
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.4776994585990906,
+      "learning_rate": 9.553418304030886e-06,
+      "loss": 0.2156,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22444444444444445,
+      "grad_norm": 0.6404227018356323,
+      "learning_rate": 9.53725917840791e-06,
+      "loss": 0.2319,
+      "step": 1010
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 0.48633572459220886,
+      "learning_rate": 9.520827041179314e-06,
+      "loss": 0.228,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2288888888888889,
+      "grad_norm": 0.5632798671722412,
+      "learning_rate": 9.504122881083886e-06,
+      "loss": 0.2321,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.4978937804698944,
+      "learning_rate": 9.487147703228323e-06,
+      "loss": 0.2212,
+      "step": 1040
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.5216785073280334,
+      "learning_rate": 9.469902529026736e-06,
+      "loss": 0.2207,
+      "step": 1050
+    },
+    {
+      "epoch": 0.23555555555555555,
+      "grad_norm": 0.5872246623039246,
+      "learning_rate": 9.452388396139202e-06,
+      "loss": 0.2404,
+      "step": 1060
+    },
+    {
+      "epoch": 0.23777777777777778,
+      "grad_norm": 0.7641334533691406,
+      "learning_rate": 9.43460635840932e-06,
+      "loss": 0.2131,
+      "step": 1070
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.7297215461730957,
+      "learning_rate": 9.416557485800796e-06,
+      "loss": 0.2119,
+      "step": 1080
+    },
+    {
+      "epoch": 0.24222222222222223,
+      "grad_norm": 0.7217341661453247,
+      "learning_rate": 9.398242864333084e-06,
+      "loss": 0.2445,
+      "step": 1090
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.7188194990158081,
+      "learning_rate": 9.379663596016004e-06,
+      "loss": 0.2164,
+      "step": 1100
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.6071985960006714,
+      "learning_rate": 9.360820798783469e-06,
+      "loss": 0.2207,
+      "step": 1110
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.4779536724090576,
+      "learning_rate": 9.34171560642619e-06,
+      "loss": 0.2143,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2511111111111111,
+      "grad_norm": 0.4994782507419586,
+      "learning_rate": 9.322349168523467e-06,
+      "loss": 0.2243,
+      "step": 1130
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 0.5922213196754456,
+      "learning_rate": 9.302722650374025e-06,
+      "loss": 0.2214,
+      "step": 1140
+    },
+    {
+      "epoch": 0.25555555555555554,
+      "grad_norm": 0.448760062456131,
+      "learning_rate": 9.282837232925876e-06,
+      "loss": 0.234,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 0.4707668721675873,
+      "learning_rate": 9.262694112705283e-06,
+      "loss": 0.2156,
+      "step": 1160
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5610018968582153,
+      "learning_rate": 9.242294501744743e-06,
+      "loss": 0.2328,
+      "step": 1170
+    },
+    {
+      "epoch": 0.26222222222222225,
+      "grad_norm": 0.6034278869628906,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 0.1977,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2644444444444444,
+      "grad_norm": 0.6561083197593689,
+      "learning_rate": 9.200730732826555e-06,
+      "loss": 0.2463,
+      "step": 1190
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.7015923857688904,
+      "learning_rate": 9.179569075804124e-06,
+      "loss": 0.21,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2688888888888889,
+      "grad_norm": 0.7460187673568726,
+      "learning_rate": 9.15815592976171e-06,
+      "loss": 0.2077,
+      "step": 1210
+    },
+    {
+      "epoch": 0.27111111111111114,
+      "grad_norm": 0.4673583209514618,
+      "learning_rate": 9.136492583150588e-06,
+      "loss": 0.2276,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 0.36275604367256165,
+      "learning_rate": 9.114580339476859e-06,
+      "loss": 0.228,
+      "step": 1230
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 0.7570303082466125,
+      "learning_rate": 9.09242051722303e-06,
+      "loss": 0.2175,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.4462106227874756,
+      "learning_rate": 9.07001444976866e-06,
+      "loss": 0.1925,
+      "step": 1250
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6511518955230713,
+      "learning_rate": 9.04736348531014e-06,
+      "loss": 0.2131,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2822222222222222,
+      "grad_norm": 0.4885598123073578,
+      "learning_rate": 9.02446898677957e-06,
+      "loss": 0.2312,
+      "step": 1270
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.5255832076072693,
+      "learning_rate": 9.001332331762748e-06,
+      "loss": 0.2321,
+      "step": 1280
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 0.4638875424861908,
+      "learning_rate": 8.977954912416278e-06,
+      "loss": 0.2372,
+      "step": 1290
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.4896669089794159,
+      "learning_rate": 8.954338135383804e-06,
+      "loss": 0.2201,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2911111111111111,
+      "grad_norm": 2.0014896392822266,
+      "learning_rate": 8.930483421711376e-06,
+      "loss": 0.2301,
+      "step": 1310
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.5638192892074585,
+      "learning_rate": 8.906392206761933e-06,
+      "loss": 0.2311,
+      "step": 1320
+    },
+    {
+      "epoch": 0.29555555555555557,
+      "grad_norm": 0.8357833027839661,
+      "learning_rate": 8.882065940128946e-06,
+      "loss": 0.2295,
+      "step": 1330
+    },
+    {
+      "epoch": 0.29777777777777775,
+      "grad_norm": 0.5070579051971436,
+      "learning_rate": 8.857506085549188e-06,
+      "loss": 0.2101,
+      "step": 1340
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.5315201282501221,
+      "learning_rate": 8.832714120814663e-06,
+      "loss": 0.2292,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 0.608734667301178,
+      "learning_rate": 8.807691537683685e-06,
+      "loss": 0.2117,
+      "step": 1360
+    },
+    {
+      "epoch": 0.30444444444444446,
+      "grad_norm": 0.5390174388885498,
+      "learning_rate": 8.782439841791115e-06,
+      "loss": 0.2105,
+      "step": 1370
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.6464143991470337,
+      "learning_rate": 8.756960552557769e-06,
+      "loss": 0.1987,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3088888888888889,
+      "grad_norm": 0.6428011059761047,
+      "learning_rate": 8.73125520309899e-06,
+      "loss": 0.2196,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.7456507086753845,
+      "learning_rate": 8.7053253401324e-06,
+      "loss": 0.2045,
+      "step": 1400
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 0.4864068329334259,
+      "learning_rate": 8.679172523884833e-06,
+      "loss": 0.2205,
+      "step": 1410
+    },
+    {
+      "epoch": 0.31555555555555553,
+      "grad_norm": 2.234358549118042,
+      "learning_rate": 8.652798327998458e-06,
+      "loss": 0.2156,
+      "step": 1420
+    },
+    {
+      "epoch": 0.31777777777777777,
+      "grad_norm": 0.7126372456550598,
+      "learning_rate": 8.626204339436075e-06,
+      "loss": 0.2516,
+      "step": 1430
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.9786515831947327,
+      "learning_rate": 8.599392158385651e-06,
+      "loss": 0.2176,
+      "step": 1440
+    },
+    {
+      "epoch": 0.32222222222222224,
+      "grad_norm": 0.5261818170547485,
+      "learning_rate": 8.572363398164017e-06,
+      "loss": 0.2083,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3244444444444444,
+      "grad_norm": 0.4807901382446289,
+      "learning_rate": 8.545119685119798e-06,
+      "loss": 0.2068,
+      "step": 1460
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.42613741755485535,
+      "learning_rate": 8.51766265853555e-06,
+      "loss": 0.197,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 0.4265085756778717,
+      "learning_rate": 8.489993970529137e-06,
+      "loss": 0.2034,
+      "step": 1480
+    },
+    {
+      "epoch": 0.33111111111111113,
+      "grad_norm": 0.6814882159233093,
+      "learning_rate": 8.462115285954299e-06,
+      "loss": 0.2356,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6597103476524353,
+      "learning_rate": 8.434028282300497e-06,
+      "loss": 0.2188,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33555555555555555,
+      "grad_norm": 0.5260792970657349,
+      "learning_rate": 8.405734649591964e-06,
+      "loss": 0.2216,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.6519996523857117,
+      "learning_rate": 8.377236090286016e-06,
+      "loss": 0.2207,
+      "step": 1520
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.41724681854248047,
+      "learning_rate": 8.34853431917062e-06,
+      "loss": 0.2041,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3422222222222222,
+      "grad_norm": 0.6121205687522888,
+      "learning_rate": 8.319631063261209e-06,
+      "loss": 0.1957,
+      "step": 1540
+    },
+    {
+      "epoch": 0.34444444444444444,
+      "grad_norm": 0.949219822883606,
+      "learning_rate": 8.290528061696761e-06,
+      "loss": 0.2196,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.4100121259689331,
+      "learning_rate": 8.261227065635162e-06,
+      "loss": 0.2206,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3488888888888889,
+      "grad_norm": 0.49160468578338623,
+      "learning_rate": 8.231729838147833e-06,
+      "loss": 0.2068,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3511111111111111,
+      "grad_norm": 0.6115289926528931,
+      "learning_rate": 8.202038154113641e-06,
+      "loss": 0.2334,
+      "step": 1580
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 0.8405654430389404,
+      "learning_rate": 8.172153800112107e-06,
+      "loss": 0.2282,
+      "step": 1590
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6662808060646057,
+      "learning_rate": 8.142078574315907e-06,
+      "loss": 0.23,
+      "step": 1600
+    },
+    {
+      "epoch": 0.35777777777777775,
+      "grad_norm": 0.5457441806793213,
+      "learning_rate": 8.111814286382667e-06,
+      "loss": 0.2306,
+      "step": 1610
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7779885530471802,
+      "learning_rate": 8.081362757346083e-06,
+      "loss": 0.1981,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3622222222222222,
+      "grad_norm": 0.5274958610534668,
+      "learning_rate": 8.05072581950634e-06,
+      "loss": 0.2011,
+      "step": 1630
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 0.5446702241897583,
+      "learning_rate": 8.019905316319863e-06,
+      "loss": 0.2281,
+      "step": 1640
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.5606325268745422,
+      "learning_rate": 7.988903102288399e-06,
+      "loss": 0.2179,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3688888888888889,
+      "grad_norm": 7.5567121505737305,
+      "learning_rate": 7.95772104284742e-06,
+      "loss": 0.2151,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3711111111111111,
+      "grad_norm": 0.38736268877983093,
+      "learning_rate": 7.92636101425389e-06,
+      "loss": 0.2122,
+      "step": 1670
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.47426578402519226,
+      "learning_rate": 7.894824903473356e-06,
+      "loss": 0.2113,
+      "step": 1680
+    },
+    {
+      "epoch": 0.37555555555555553,
+      "grad_norm": 0.4985625147819519,
+      "learning_rate": 7.863114608066417e-06,
+      "loss": 0.21,
+      "step": 1690
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.6098905205726624,
+      "learning_rate": 7.831232036074542e-06,
+      "loss": 0.211,
+      "step": 1700
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.2106733322143555,
+      "learning_rate": 7.799179105905255e-06,
+      "loss": 0.1896,
+      "step": 1710
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 0.6900057792663574,
+      "learning_rate": 7.76695774621672e-06,
+      "loss": 0.2169,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3844444444444444,
+      "grad_norm": 0.55312180519104,
+      "learning_rate": 7.734569895801675e-06,
+      "loss": 0.2166,
+      "step": 1730
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 0.5338639616966248,
+      "learning_rate": 7.702017503470773e-06,
+      "loss": 0.2115,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.43841829895973206,
+      "learning_rate": 7.669302527935334e-06,
+      "loss": 0.2193,
+      "step": 1750
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.7797672152519226,
+      "learning_rate": 7.636426937689476e-06,
+      "loss": 0.2219,
+      "step": 1760
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 0.46977758407592773,
+      "learning_rate": 7.603392710891665e-06,
+      "loss": 0.2081,
+      "step": 1770
+    },
+    {
+      "epoch": 0.39555555555555555,
+      "grad_norm": 0.6233215928077698,
+      "learning_rate": 7.570201835245703e-06,
+      "loss": 0.2207,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3977777777777778,
+      "grad_norm": 0.5074626207351685,
+      "learning_rate": 7.536856307881106e-06,
+      "loss": 0.2306,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5548232197761536,
+      "learning_rate": 7.503358135232959e-06,
+      "loss": 0.1978,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4022222222222222,
+      "grad_norm": 0.5380575060844421,
+      "learning_rate": 7.469709332921155e-06,
+      "loss": 0.1918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.40444444444444444,
+      "grad_norm": 0.5419725179672241,
+      "learning_rate": 7.435911925629146e-06,
+      "loss": 0.2195,
+      "step": 1820
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 0.6580492258071899,
+      "learning_rate": 7.401967946982089e-06,
+      "loss": 0.2129,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 0.40074673295021057,
+      "learning_rate": 7.3678794394245e-06,
+      "loss": 0.2197,
+      "step": 1840
+    },
+    {
+      "epoch": 0.4111111111111111,
+      "grad_norm": 0.4864460825920105,
+      "learning_rate": 7.333648454097347e-06,
+      "loss": 0.2189,
+      "step": 1850
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 1.0007145404815674,
+      "learning_rate": 7.299277050714631e-06,
+      "loss": 0.2308,
+      "step": 1860
+    },
+    {
+      "epoch": 0.41555555555555557,
+      "grad_norm": 0.574856162071228,
+      "learning_rate": 7.264767297439455e-06,
+      "loss": 0.2138,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 0.6101383566856384,
+      "learning_rate": 7.230121270759583e-06,
+      "loss": 0.203,
+      "step": 1880
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5229494571685791,
+      "learning_rate": 7.195341055362485e-06,
+      "loss": 0.1982,
+      "step": 1890
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.46096137166023254,
+      "learning_rate": 7.160428744009913e-06,
+      "loss": 0.1952,
+      "step": 1900
+    },
+    {
+      "epoch": 0.42444444444444446,
+      "grad_norm": 0.5301885604858398,
+      "learning_rate": 7.1253864374119615e-06,
+      "loss": 0.1779,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.6712138056755066,
+      "learning_rate": 7.090216244100683e-06,
+      "loss": 0.1933,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4288888888888889,
+      "grad_norm": 0.43138372898101807,
+      "learning_rate": 7.054920280303199e-06,
+      "loss": 0.2161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.4311111111111111,
+      "grad_norm": 0.547301173210144,
+      "learning_rate": 7.019500669814378e-06,
+      "loss": 0.2225,
+      "step": 1940
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.5402425527572632,
+      "learning_rate": 6.9839595438690345e-06,
+      "loss": 0.2064,
+      "step": 1950
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 0.7565062642097473,
+      "learning_rate": 6.948299041013695e-06,
+      "loss": 0.1872,
+      "step": 1960
+    },
+    {
+      "epoch": 0.43777777777777777,
+      "grad_norm": 0.5148667097091675,
+      "learning_rate": 6.912521306977922e-06,
+      "loss": 0.2003,
+      "step": 1970
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5977216958999634,
+      "learning_rate": 6.876628494545198e-06,
+      "loss": 0.1988,
+      "step": 1980
+    },
+    {
+      "epoch": 0.44222222222222224,
+      "grad_norm": 0.5444183945655823,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 0.1887,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.5000138282775879,
+      "learning_rate": 6.804506280114804e-06,
+      "loss": 0.2238,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 0.36713868379592896,
+      "learning_rate": 6.76828121778582e-06,
+      "loss": 0.195,
+      "step": 2010
+    },
+    {
+      "epoch": 0.4488888888888889,
+      "grad_norm": 0.40727663040161133,
+      "learning_rate": 6.7319497561361245e-06,
+      "loss": 0.2115,
+      "step": 2020
+    },
+    {
+      "epoch": 0.45111111111111113,
+      "grad_norm": 0.6632441878318787,
+      "learning_rate": 6.695514081267571e-06,
+      "loss": 0.2034,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.562683641910553,
+      "learning_rate": 6.658976385552625e-06,
+      "loss": 0.2372,
+      "step": 2040
+    },
+    {
+      "epoch": 0.45555555555555555,
+      "grad_norm": 0.5284994840621948,
+      "learning_rate": 6.622338867502452e-06,
+      "loss": 0.213,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4577777777777778,
+      "grad_norm": 0.590913712978363,
+      "learning_rate": 6.585603731634636e-06,
+      "loss": 0.2095,
+      "step": 2060
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.7636019587516785,
+      "learning_rate": 6.548773188340523e-06,
+      "loss": 0.2067,
+      "step": 2070
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.6471806764602661,
+      "learning_rate": 6.5118494537522235e-06,
+      "loss": 0.1996,
+      "step": 2080
+    },
+    {
+      "epoch": 0.46444444444444444,
+      "grad_norm": 0.46714213490486145,
+      "learning_rate": 6.474834749609266e-06,
+      "loss": 0.1876,
+      "step": 2090
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.3906289339065552,
+      "learning_rate": 6.4377313031249085e-06,
+      "loss": 0.2053,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4688888888888889,
+      "grad_norm": 0.4733579158782959,
+      "learning_rate": 6.400541346852136e-06,
+      "loss": 0.224,
+      "step": 2110
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 0.6433371901512146,
+      "learning_rate": 6.363267118549307e-06,
+      "loss": 0.1941,
+      "step": 2120
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.7840290069580078,
+      "learning_rate": 6.325910861045526e-06,
+      "loss": 0.1832,
+      "step": 2130
+    },
+    {
+      "epoch": 0.47555555555555556,
+      "grad_norm": 0.6022821664810181,
+      "learning_rate": 6.28847482210567e-06,
+      "loss": 0.2034,
+      "step": 2140
+    },
+    {
+      "epoch": 0.4777777777777778,
+      "grad_norm": 0.8734650015830994,
+      "learning_rate": 6.250961254295156e-06,
+      "loss": 0.2184,
+      "step": 2150
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5723605155944824,
+      "learning_rate": 6.21337241484439e-06,
+      "loss": 0.2382,
+      "step": 2160
+    },
+    {
+      "epoch": 0.4822222222222222,
+      "grad_norm": 0.4411050081253052,
+      "learning_rate": 6.17571056551295e-06,
+      "loss": 0.2232,
+      "step": 2170
+    },
+    {
+      "epoch": 0.48444444444444446,
+      "grad_norm": 0.5421409010887146,
+      "learning_rate": 6.137977972453499e-06,
+      "loss": 0.216,
+      "step": 2180
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 0.49950799345970154,
+      "learning_rate": 6.10017690607542e-06,
+      "loss": 0.2058,
+      "step": 2190
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.45395323634147644,
+      "learning_rate": 6.062309640908206e-06,
+      "loss": 0.2255,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4911111111111111,
+      "grad_norm": 0.5360926389694214,
+      "learning_rate": 6.024378455464603e-06,
+      "loss": 0.2152,
+      "step": 2210
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 0.7860808372497559,
+      "learning_rate": 5.986385632103505e-06,
+      "loss": 0.2221,
+      "step": 2220
+    },
+    {
+      "epoch": 0.4955555555555556,
+      "grad_norm": 0.47331491112709045,
+      "learning_rate": 5.948333456892624e-06,
+      "loss": 0.1963,
+      "step": 2230
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.9222210049629211,
+      "learning_rate": 5.910224219470935e-06,
+      "loss": 0.2068,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.38796505331993103,
+      "learning_rate": 5.872060212910903e-06,
+      "loss": 0.2075,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5022222222222222,
+      "grad_norm": 0.6094416379928589,
+      "learning_rate": 5.8338437335805124e-06,
+      "loss": 0.2074,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5044444444444445,
+      "grad_norm": 0.45269209146499634,
+      "learning_rate": 5.795577081005086e-06,
+      "loss": 0.2041,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.48547807335853577,
+      "learning_rate": 5.757262557728927e-06,
+      "loss": 0.2127,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5088888888888888,
+      "grad_norm": 0.5762115120887756,
+      "learning_rate": 5.718902469176765e-06,
+      "loss": 0.1874,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.9455215930938721,
+      "learning_rate": 5.680499123515039e-06,
+      "loss": 0.2324,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 0.5121821165084839,
+      "learning_rate": 5.6420548315130156e-06,
+      "loss": 0.2335,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.5269145369529724,
+      "learning_rate": 5.6035719064037446e-06,
+      "loss": 0.218,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5177777777777778,
+      "grad_norm": 0.4522016942501068,
+      "learning_rate": 5.56505266374487e-06,
+      "loss": 0.2052,
+      "step": 2330
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5505020022392273,
+      "learning_rate": 5.5264994212793e-06,
+      "loss": 0.2286,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5222222222222223,
+      "grad_norm": 0.6321388483047485,
+      "learning_rate": 5.487914498795748e-06,
+      "loss": 0.2364,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 0.3844665586948395,
+      "learning_rate": 5.4493002179891455e-06,
+      "loss": 0.1941,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 0.5325224995613098,
+      "learning_rate": 5.410658902320946e-06,
+      "loss": 0.2068,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5288888888888889,
+      "grad_norm": 0.3940238356590271,
+      "learning_rate": 5.371992876879318e-06,
+      "loss": 0.1995,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5311111111111111,
+      "grad_norm": 0.40742266178131104,
+      "learning_rate": 5.333304468239241e-06,
+      "loss": 0.2204,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.6924517750740051,
+      "learning_rate": 5.294596004322518e-06,
+      "loss": 0.206,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5355555555555556,
+      "grad_norm": 0.5800101161003113,
+      "learning_rate": 5.255869814257701e-06,
+      "loss": 0.2138,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5377777777777778,
+      "grad_norm": 0.5364833474159241,
+      "learning_rate": 5.217128228239934e-06,
+      "loss": 0.2014,
+      "step": 2420
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.41309791803359985,
+      "learning_rate": 5.178373577390763e-06,
+      "loss": 0.2067,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 0.4769889712333679,
+      "learning_rate": 5.139608193617846e-06,
+      "loss": 0.2248,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5444444444444444,
+      "grad_norm": 0.586300790309906,
+      "learning_rate": 5.100834409474661e-06,
+      "loss": 0.2122,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.47269368171691895,
+      "learning_rate": 5.062054558020145e-06,
+      "loss": 0.207,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5488888888888889,
+      "grad_norm": 0.606197714805603,
+      "learning_rate": 5.0232709726783065e-06,
+      "loss": 0.2279,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.8266254663467407,
+      "learning_rate": 4.984485987097829e-06,
+      "loss": 0.2037,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 1.2550374269485474,
+      "learning_rate": 4.945701935011651e-06,
+      "loss": 0.2192,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.44271695613861084,
+      "learning_rate": 4.906921150096538e-06,
+      "loss": 0.2242,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5577777777777778,
+      "grad_norm": 0.41325992345809937,
+      "learning_rate": 4.868145965832667e-06,
+      "loss": 0.2187,
+      "step": 2510
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.7073836922645569,
+      "learning_rate": 4.8293787153632245e-06,
+      "loss": 0.2293,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5622222222222222,
+      "grad_norm": 0.4135652184486389,
+      "learning_rate": 4.7906217313540035e-06,
+      "loss": 0.1818,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5644444444444444,
+      "grad_norm": 0.5508117079734802,
+      "learning_rate": 4.751877345853055e-06,
+      "loss": 0.1956,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.7012504935264587,
+      "learning_rate": 4.713147890150372e-06,
+      "loss": 0.2013,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.4391688108444214,
+      "learning_rate": 4.674435694637597e-06,
+      "loss": 0.2218,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5711111111111111,
+      "grad_norm": 0.3952424228191376,
+      "learning_rate": 4.635743088667815e-06,
+      "loss": 0.2084,
+      "step": 2570
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 0.4249865710735321,
+      "learning_rate": 4.597072400415383e-06,
+      "loss": 0.1789,
+      "step": 2580
+    },
+    {
+      "epoch": 0.5755555555555556,
+      "grad_norm": 0.3916455805301666,
+      "learning_rate": 4.5584259567358505e-06,
+      "loss": 0.2103,
+      "step": 2590
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.49334606528282166,
+      "learning_rate": 4.519806083025944e-06,
+      "loss": 0.1908,
+      "step": 2600
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4928642809391022,
+      "learning_rate": 4.481215103083646e-06,
+      "loss": 0.2044,
+      "step": 2610
+    },
+    {
+      "epoch": 0.5822222222222222,
+      "grad_norm": 0.39454615116119385,
+      "learning_rate": 4.442655338968373e-06,
+      "loss": 0.2238,
+      "step": 2620
+    },
+    {
+      "epoch": 0.5844444444444444,
+      "grad_norm": 0.44189751148223877,
+      "learning_rate": 4.404129110861254e-06,
+      "loss": 0.2124,
+      "step": 2630
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.39245477318763733,
+      "learning_rate": 4.365638736925512e-06,
+      "loss": 0.1872,
+      "step": 2640
+    },
+    {
+      "epoch": 0.5888888888888889,
+      "grad_norm": 0.44201573729515076,
+      "learning_rate": 4.3271865331670036e-06,
+      "loss": 0.2071,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5911111111111111,
+      "grad_norm": 0.9676383137702942,
+      "learning_rate": 4.288774813294833e-06,
+      "loss": 0.2071,
+      "step": 2660
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.5469398498535156,
+      "learning_rate": 4.2504058885821515e-06,
+      "loss": 0.2138,
+      "step": 2670
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 0.5392938852310181,
+      "learning_rate": 4.212082067727079e-06,
+      "loss": 0.1977,
+      "step": 2680
+    },
+    {
+      "epoch": 0.5977777777777777,
+      "grad_norm": 0.48335549235343933,
+      "learning_rate": 4.173805656713793e-06,
+      "loss": 0.1872,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6414911150932312,
+      "learning_rate": 4.13557895867377e-06,
+      "loss": 0.2146,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6022222222222222,
+      "grad_norm": 0.7016770839691162,
+      "learning_rate": 4.0974042737472005e-06,
+      "loss": 0.2041,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.910889744758606,
+      "learning_rate": 4.0592838989446e-06,
+      "loss": 0.1808,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 0.5011441707611084,
+      "learning_rate": 4.021220128008584e-06,
+      "loss": 0.2219,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6088888888888889,
+      "grad_norm": 0.5267744064331055,
+      "learning_rate": 3.983215251275847e-06,
+      "loss": 0.191,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.5419243574142456,
+      "learning_rate": 3.945271555539373e-06,
+      "loss": 0.2006,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.6747017502784729,
+      "learning_rate": 3.90739132391081e-06,
+      "loss": 0.1984,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6155555555555555,
+      "grad_norm": 0.52618008852005,
+      "learning_rate": 3.869576835683109e-06,
+      "loss": 0.1954,
+      "step": 2770
+    },
+    {
+      "epoch": 0.6177777777777778,
+      "grad_norm": 0.4393468499183655,
+      "learning_rate": 3.831830366193367e-06,
+      "loss": 0.2139,
+      "step": 2780
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5834131836891174,
+      "learning_rate": 3.7941541866859337e-06,
+      "loss": 0.2237,
+      "step": 2790
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.37476396560668945,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 0.2101,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6244444444444445,
+      "grad_norm": 0.6598880887031555,
+      "learning_rate": 3.7190217613118385e-06,
+      "loss": 0.2289,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 0.4706180691719055,
+      "learning_rate": 3.6815700362413855e-06,
+      "loss": 0.2142,
+      "step": 2820
+    },
+    {
+      "epoch": 0.6288888888888889,
+      "grad_norm": 0.46370431780815125,
+      "learning_rate": 3.6441976424736315e-06,
+      "loss": 0.1946,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 0.4361344873905182,
+      "learning_rate": 3.6069068287443932e-06,
+      "loss": 0.1984,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.5363613367080688,
+      "learning_rate": 3.569699838880735e-06,
+      "loss": 0.1948,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6355555555555555,
+      "grad_norm": 0.5266453623771667,
+      "learning_rate": 3.5325789116659493e-06,
+      "loss": 0.1887,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6377777777777778,
+      "grad_norm": 0.4433373510837555,
+      "learning_rate": 3.495546280704849e-06,
+      "loss": 0.2188,
+      "step": 2870
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4429185092449188,
+      "learning_rate": 3.458604174289367e-06,
+      "loss": 0.1995,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6422222222222222,
+      "grad_norm": 0.45663219690322876,
+      "learning_rate": 3.4217548152644887e-06,
+      "loss": 0.2037,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 0.43009230494499207,
+      "learning_rate": 3.3850004208944838e-06,
+      "loss": 0.1878,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 0.550760805606842,
+      "learning_rate": 3.3483432027295025e-06,
+      "loss": 0.2015,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 0.6194041967391968,
+      "learning_rate": 3.311785366472506e-06,
+      "loss": 0.2014,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6511111111111111,
+      "grad_norm": 0.4014096260070801,
+      "learning_rate": 3.275329111846536e-06,
+      "loss": 0.1905,
+      "step": 2930
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 0.4828612208366394,
+      "learning_rate": 3.238976632462364e-06,
+      "loss": 0.1798,
+      "step": 2940
+    },
+    {
+      "epoch": 0.6555555555555556,
+      "grad_norm": 0.38511934876441956,
+      "learning_rate": 3.2027301156865015e-06,
+      "loss": 0.212,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.6415356993675232,
+      "learning_rate": 3.166591742509575e-06,
+      "loss": 0.2254,
+      "step": 2960
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.669744610786438,
+      "learning_rate": 3.130563687415098e-06,
+      "loss": 0.1983,
+      "step": 2970
+    },
+    {
+      "epoch": 0.6622222222222223,
+      "grad_norm": 0.5774917602539062,
+      "learning_rate": 3.09464811824863e-06,
+      "loss": 0.2088,
+      "step": 2980
+    },
+    {
+      "epoch": 0.6644444444444444,
+      "grad_norm": 0.49747976660728455,
+      "learning_rate": 3.05884719608734e-06,
+      "loss": 0.2216,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.42713528871536255,
+      "learning_rate": 3.0231630751099628e-06,
+      "loss": 0.2141,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6688888888888889,
+      "grad_norm": 1.2869380712509155,
+      "learning_rate": 2.9875979024671846e-06,
+      "loss": 0.2205,
+      "step": 3010
+    },
+    {
+      "epoch": 0.6711111111111111,
+      "grad_norm": 0.5339882969856262,
+      "learning_rate": 2.9521538181524497e-06,
+      "loss": 0.207,
+      "step": 3020
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 0.4252525568008423,
+      "learning_rate": 2.9168329548731873e-06,
+      "loss": 0.2265,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.445364385843277,
+      "learning_rate": 2.8816374379224932e-06,
+      "loss": 0.2197,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6777777777777778,
+      "grad_norm": 0.6213434338569641,
+      "learning_rate": 2.846569385051241e-06,
+      "loss": 0.2047,
+      "step": 3050
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5438356995582581,
+      "learning_rate": 2.8116309063406593e-06,
+      "loss": 0.2365,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6822222222222222,
+      "grad_norm": 0.4693785607814789,
+      "learning_rate": 2.776824104075364e-06,
+      "loss": 0.2001,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 0.6357928514480591,
+      "learning_rate": 2.742151072616861e-06,
+      "loss": 0.2127,
+      "step": 3080
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 0.6603185534477234,
+      "learning_rate": 2.707613898277533e-06,
+      "loss": 0.2132,
+      "step": 3090
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.5123574137687683,
+      "learning_rate": 2.6732146591950924e-06,
+      "loss": 0.2163,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6911111111111111,
+      "grad_norm": 0.5603567957878113,
+      "learning_rate": 2.638955425207545e-06,
+      "loss": 0.2037,
+      "step": 3110
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.8993784785270691,
+      "learning_rate": 2.604838257728648e-06,
+      "loss": 0.2014,
+      "step": 3120
+    },
+    {
+      "epoch": 0.6955555555555556,
+      "grad_norm": 0.45358985662460327,
+      "learning_rate": 2.5708652096238674e-06,
+      "loss": 0.2328,
+      "step": 3130
+    },
+    {
+      "epoch": 0.6977777777777778,
+      "grad_norm": 0.6038041114807129,
+      "learning_rate": 2.5370383250868493e-06,
+      "loss": 0.1989,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5077185034751892,
+      "learning_rate": 2.503359639516437e-06,
+      "loss": 0.2215,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 0.4637431204319,
+      "learning_rate": 2.469831179394182e-06,
+      "loss": 0.1987,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7044444444444444,
+      "grad_norm": 0.598070502281189,
+      "learning_rate": 2.4364549621624124e-06,
+      "loss": 0.2459,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 0.7257698178291321,
+      "learning_rate": 2.40323299610285e-06,
+      "loss": 0.2263,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7088888888888889,
+      "grad_norm": 0.44860175251960754,
+      "learning_rate": 2.3701672802157567e-06,
+      "loss": 0.2053,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.5306028127670288,
+      "learning_rate": 2.3372598040996614e-06,
+      "loss": 0.2204,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 0.7388485074043274,
+      "learning_rate": 2.304512547831639e-06,
+      "loss": 0.193,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7155555555555555,
+      "grad_norm": 0.5636351108551025,
+      "learning_rate": 2.2719274818481767e-06,
+      "loss": 0.1956,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7177777777777777,
+      "grad_norm": 0.6284674406051636,
+      "learning_rate": 2.2395065668265943e-06,
+      "loss": 0.2162,
+      "step": 3230
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5573301315307617,
+      "learning_rate": 2.2072517535670795e-06,
+      "loss": 0.1955,
+      "step": 3240
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 0.7660098075866699,
+      "learning_rate": 2.175164982875311e-06,
+      "loss": 0.2315,
+      "step": 3250
+    },
+    {
+      "epoch": 0.7244444444444444,
+      "grad_norm": 0.6921658515930176,
+      "learning_rate": 2.1432481854456645e-06,
+      "loss": 0.2099,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 0.4891114830970764,
+      "learning_rate": 2.1115032817450476e-06,
+      "loss": 0.2119,
+      "step": 3270
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.8401778340339661,
+      "learning_rate": 2.0799321818973488e-06,
+      "loss": 0.2043,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7311111111111112,
+      "grad_norm": 0.6000136733055115,
+      "learning_rate": 2.0485367855684932e-06,
+      "loss": 0.2193,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.4936680197715759,
+      "learning_rate": 2.0173189818521442e-06,
+      "loss": 0.2064,
+      "step": 3300
+    },
+    {
+      "epoch": 0.7355555555555555,
+      "grad_norm": 0.5655127763748169,
+      "learning_rate": 1.9862806491560315e-06,
+      "loss": 0.1971,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 0.6277737021446228,
+      "learning_rate": 1.955423655088928e-06,
+      "loss": 0.2344,
+      "step": 3320
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.485286682844162,
+      "learning_rate": 1.9247498563482724e-06,
+      "loss": 0.2049,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7422222222222222,
+      "grad_norm": 0.622129499912262,
+      "learning_rate": 1.8942610986084487e-06,
+      "loss": 0.2259,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7444444444444445,
+      "grad_norm": 0.6010628938674927,
+      "learning_rate": 1.8639592164097348e-06,
+      "loss": 0.1823,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.5716583728790283,
+      "learning_rate": 1.8338460330479102e-06,
+      "loss": 0.2142,
+      "step": 3360
+    },
+    {
+      "epoch": 0.7488888888888889,
+      "grad_norm": 0.6274925470352173,
+      "learning_rate": 1.8039233604645468e-06,
+      "loss": 0.2237,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7511111111111111,
+      "grad_norm": 0.5479351878166199,
+      "learning_rate": 1.7741929991379914e-06,
+      "loss": 0.2115,
+      "step": 3380
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 0.5495596528053284,
+      "learning_rate": 1.7446567379750167e-06,
+      "loss": 0.2003,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.7401885390281677,
+      "learning_rate": 1.7153163542031881e-06,
+      "loss": 0.2055,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7577777777777778,
+      "grad_norm": 0.6181710958480835,
+      "learning_rate": 1.686173613263925e-06,
+      "loss": 0.188,
+      "step": 3410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.7485997080802917,
+      "learning_rate": 1.6572302687062718e-06,
+      "loss": 0.2123,
+      "step": 3420
+    },
+    {
+      "epoch": 0.7622222222222222,
+      "grad_norm": 0.5755326151847839,
+      "learning_rate": 1.6284880620813847e-06,
+      "loss": 0.1969,
+      "step": 3430
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.5471241474151611,
+      "learning_rate": 1.5999487228377398e-06,
+      "loss": 0.1683,
+      "step": 3440
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.7080233693122864,
+      "learning_rate": 1.5716139682170778e-06,
+      "loss": 0.2191,
+      "step": 3450
+    },
+    {
+      "epoch": 0.7688888888888888,
+      "grad_norm": 1.2081867456436157,
+      "learning_rate": 1.5434855031510626e-06,
+      "loss": 0.2122,
+      "step": 3460
+    },
+    {
+      "epoch": 0.7711111111111111,
+      "grad_norm": 0.6755123138427734,
+      "learning_rate": 1.515565020158703e-06,
+      "loss": 0.2002,
+      "step": 3470
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.739806592464447,
+      "learning_rate": 1.4878541992445144e-06,
+      "loss": 0.2552,
+      "step": 3480
+    },
+    {
+      "epoch": 0.7755555555555556,
+      "grad_norm": 0.5652565360069275,
+      "learning_rate": 1.4603547077974217e-06,
+      "loss": 0.1962,
+      "step": 3490
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.7767261266708374,
+      "learning_rate": 1.4330682004904367e-06,
+      "loss": 0.201,
+      "step": 3500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.8696750402450562,
+      "learning_rate": 1.4059963191810955e-06,
+      "loss": 0.2088,
+      "step": 3510
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.4759983420372009,
+      "learning_rate": 1.3791406928126638e-06,
+      "loss": 0.1948,
+      "step": 3520
+    },
+    {
+      "epoch": 0.7844444444444445,
+      "grad_norm": 0.7665895819664001,
+      "learning_rate": 1.352502937316122e-06,
+      "loss": 0.2099,
+      "step": 3530
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 0.8648385405540466,
+      "learning_rate": 1.3260846555129325e-06,
+      "loss": 0.1897,
+      "step": 3540
+    },
+    {
+      "epoch": 0.7888888888888889,
+      "grad_norm": 0.5879445672035217,
+      "learning_rate": 1.2998874370186026e-06,
+      "loss": 0.2051,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 0.6816076636314392,
+      "learning_rate": 1.273912858147024e-06,
+      "loss": 0.2036,
+      "step": 3560
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.8157027959823608,
+      "learning_rate": 1.2481624818156319e-06,
+      "loss": 0.2282,
+      "step": 3570
+    },
+    {
+      "epoch": 0.7955555555555556,
+      "grad_norm": 0.6209530830383301,
+      "learning_rate": 1.2226378574513654e-06,
+      "loss": 0.2002,
+      "step": 3580
+    },
+    {
+      "epoch": 0.7977777777777778,
+      "grad_norm": 0.671550989151001,
+      "learning_rate": 1.1973405208974282e-06,
+      "loss": 0.1899,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7487563490867615,
+      "learning_rate": 1.1722719943208822e-06,
+      "loss": 0.2017,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8022222222222222,
+      "grad_norm": 0.5452727675437927,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 0.1975,
+      "step": 3610
+    },
+    {
+      "epoch": 0.8044444444444444,
+      "grad_norm": 0.6567462086677551,
+      "learning_rate": 1.1228273908387756e-06,
+      "loss": 0.2004,
+      "step": 3620
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 0.8309646844863892,
+      "learning_rate": 1.0984542890664513e-06,
+      "loss": 0.2075,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 0.6340985894203186,
+      "learning_rate": 1.0743159473589738e-06,
+      "loss": 0.1898,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8111111111111111,
+      "grad_norm": 0.5178126692771912,
+      "learning_rate": 1.050413818145481e-06,
+      "loss": 0.199,
+      "step": 3650
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 0.9813441038131714,
+      "learning_rate": 1.0267493396419559e-06,
+      "loss": 0.2044,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8155555555555556,
+      "grad_norm": 0.6538034677505493,
+      "learning_rate": 1.0033239357646913e-06,
+      "loss": 0.2031,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.9272398352622986,
+      "learning_rate": 9.801390160446135e-07,
+      "loss": 0.2297,
+      "step": 3680
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.7015199065208435,
+      "learning_rate": 9.571959755424643e-07,
+      "loss": 0.22,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.6526545882225037,
+      "learning_rate": 9.344961947648624e-07,
+      "loss": 0.1935,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8244444444444444,
+      "grad_norm": 0.8535521626472473,
+      "learning_rate": 9.120410395812346e-07,
+      "loss": 0.2055,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.5749399662017822,
+      "learning_rate": 8.898318611416329e-07,
+      "loss": 0.2076,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8288888888888889,
+      "grad_norm": 0.49103567004203796,
+      "learning_rate": 8.678699957954323e-07,
+      "loss": 0.2446,
+      "step": 3730
+    },
+    {
+      "epoch": 0.8311111111111111,
+      "grad_norm": 0.7974038124084473,
+      "learning_rate": 8.461567650109187e-07,
+      "loss": 0.2119,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.8334592580795288,
+      "learning_rate": 8.246934752957835e-07,
+      "loss": 0.1786,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.9666873812675476,
+      "learning_rate": 8.034814181184996e-07,
+      "loss": 0.1986,
+      "step": 3760
+    },
+    {
+      "epoch": 0.8377777777777777,
+      "grad_norm": 0.6071197986602783,
+      "learning_rate": 7.825218698306164e-07,
+      "loss": 0.1827,
+      "step": 3770
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7532318234443665,
+      "learning_rate": 7.618160915899641e-07,
+      "loss": 0.2011,
+      "step": 3780
+    },
+    {
+      "epoch": 0.8422222222222222,
+      "grad_norm": 0.6244765520095825,
+      "learning_rate": 7.413653292847617e-07,
+      "loss": 0.2042,
+      "step": 3790
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.738523006439209,
+      "learning_rate": 7.211708134586565e-07,
+      "loss": 0.2156,
+      "step": 3800
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 0.6839056611061096,
+      "learning_rate": 7.012337592366764e-07,
+      "loss": 0.1885,
+      "step": 3810
+    },
+    {
+      "epoch": 0.8488888888888889,
+      "grad_norm": 0.9326360821723938,
+      "learning_rate": 6.815553662521185e-07,
+      "loss": 0.1992,
+      "step": 3820
+    },
+    {
+      "epoch": 0.8511111111111112,
+      "grad_norm": 0.7894675731658936,
+      "learning_rate": 6.621368185743626e-07,
+      "loss": 0.1808,
+      "step": 3830
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.213384747505188,
+      "learning_rate": 6.429792846376259e-07,
+      "loss": 0.2247,
+      "step": 3840
+    },
+    {
+      "epoch": 0.8555555555555555,
+      "grad_norm": 0.7277671694755554,
+      "learning_rate": 6.240839171706608e-07,
+      "loss": 0.1965,
+      "step": 3850
+    },
+    {
+      "epoch": 0.8577777777777778,
+      "grad_norm": 0.6237801313400269,
+      "learning_rate": 6.054518531273861e-07,
+      "loss": 0.2081,
+      "step": 3860
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.5130978226661682,
+      "learning_rate": 5.870842136184807e-07,
+      "loss": 0.1906,
+      "step": 3870
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 0.5112106204032898,
+      "learning_rate": 5.689821038439264e-07,
+      "loss": 0.1977,
+      "step": 3880
+    },
+    {
+      "epoch": 0.8644444444444445,
+      "grad_norm": 1.0289357900619507,
+      "learning_rate": 5.51146613026502e-07,
+      "loss": 0.2103,
+      "step": 3890
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 1.1599540710449219,
+      "learning_rate": 5.335788143462472e-07,
+      "loss": 0.2219,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8688888888888889,
+      "grad_norm": 0.5727497935295105,
+      "learning_rate": 5.162797648758877e-07,
+      "loss": 0.2289,
+      "step": 3910
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.894284188747406,
+      "learning_rate": 4.992505055172287e-07,
+      "loss": 0.2161,
+      "step": 3920
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 0.601863443851471,
+      "learning_rate": 4.824920609385242e-07,
+      "loss": 0.2087,
+      "step": 3930
+    },
+    {
+      "epoch": 0.8755555555555555,
+      "grad_norm": 1.0111278295516968,
+      "learning_rate": 4.6600543951281995e-07,
+      "loss": 0.1958,
+      "step": 3940
+    },
+    {
+      "epoch": 0.8777777777777778,
+      "grad_norm": 0.8098214268684387,
+      "learning_rate": 4.4979163325728324e-07,
+      "loss": 0.2053,
+      "step": 3950
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8319457769393921,
+      "learning_rate": 4.3385161777350527e-07,
+      "loss": 0.194,
+      "step": 3960
+    },
+    {
+      "epoch": 0.8822222222222222,
+      "grad_norm": 0.8957728743553162,
+      "learning_rate": 4.1818635218880186e-07,
+      "loss": 0.2026,
+      "step": 3970
+    },
+    {
+      "epoch": 0.8844444444444445,
+      "grad_norm": 0.6386129856109619,
+      "learning_rate": 4.027967790985038e-07,
+      "loss": 0.1989,
+      "step": 3980
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.6992731690406799,
+      "learning_rate": 3.876838245092357e-07,
+      "loss": 0.1961,
+      "step": 3990
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.6819199323654175,
+      "learning_rate": 3.728483977831998e-07,
+      "loss": 0.2088,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8911111111111111,
+      "grad_norm": 0.6888799071311951,
+      "learning_rate": 3.582913915834574e-07,
+      "loss": 0.203,
+      "step": 4010
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 0.6650670170783997,
+      "learning_rate": 3.440136818202183e-07,
+      "loss": 0.1944,
+      "step": 4020
+    },
+    {
+      "epoch": 0.8955555555555555,
+      "grad_norm": 0.7581616640090942,
+      "learning_rate": 3.30016127598134e-07,
+      "loss": 0.2076,
+      "step": 4030
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 0.6258016228675842,
+      "learning_rate": 3.162995711646055e-07,
+      "loss": 0.207,
+      "step": 4040
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.6250176429748535,
+      "learning_rate": 3.0286483785910594e-07,
+      "loss": 0.202,
+      "step": 4050
+    },
+    {
+      "epoch": 0.9022222222222223,
+      "grad_norm": 0.619933545589447,
+      "learning_rate": 2.8971273606351656e-07,
+      "loss": 0.1988,
+      "step": 4060
+    },
+    {
+      "epoch": 0.9044444444444445,
+      "grad_norm": 0.6950874328613281,
+      "learning_rate": 2.7684405715348585e-07,
+      "loss": 0.1964,
+      "step": 4070
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.5528272390365601,
+      "learning_rate": 2.642595754508143e-07,
+      "loss": 0.1879,
+      "step": 4080
+    },
+    {
+      "epoch": 0.9088888888888889,
+      "grad_norm": 0.555220365524292,
+      "learning_rate": 2.519600481768597e-07,
+      "loss": 0.214,
+      "step": 4090
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.6779254674911499,
+      "learning_rate": 2.3994621540697425e-07,
+      "loss": 0.1872,
+      "step": 4100
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 0.8899818658828735,
+      "learning_rate": 2.2821880002597662e-07,
+      "loss": 0.1907,
+      "step": 4110
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 0.521691083908081,
+      "learning_rate": 2.167785076846518e-07,
+      "loss": 0.1857,
+      "step": 4120
+    },
+    {
+      "epoch": 0.9177777777777778,
+      "grad_norm": 0.6602068543434143,
+      "learning_rate": 2.056260267572935e-07,
+      "loss": 0.181,
+      "step": 4130
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5623869895935059,
+      "learning_rate": 1.9476202830028213e-07,
+      "loss": 0.1835,
+      "step": 4140
+    },
+    {
+      "epoch": 0.9222222222222223,
+      "grad_norm": 0.8227715492248535,
+      "learning_rate": 1.841871660117095e-07,
+      "loss": 0.2003,
+      "step": 4150
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.1691772937774658,
+      "learning_rate": 1.739020761920418e-07,
+      "loss": 0.1847,
+      "step": 4160
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 0.7558993697166443,
+      "learning_rate": 1.639073777058342e-07,
+      "loss": 0.1771,
+      "step": 4170
+    },
+    {
+      "epoch": 0.9288888888888889,
+      "grad_norm": 0.9957707524299622,
+      "learning_rate": 1.5420367194449448e-07,
+      "loss": 0.207,
+      "step": 4180
+    },
+    {
+      "epoch": 0.9311111111111111,
+      "grad_norm": 1.27088463306427,
+      "learning_rate": 1.447915427900959e-07,
+      "loss": 0.1956,
+      "step": 4190
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.8207851052284241,
+      "learning_rate": 1.3567155658023967e-07,
+      "loss": 0.1807,
+      "step": 4200
+    },
+    {
+      "epoch": 1.0022222222222221,
+      "grad_norm": 0.7550169825553894,
+      "learning_rate": 1.268442620739868e-07,
+      "loss": 0.2081,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0044444444444445,
+      "grad_norm": 0.5855371356010437,
+      "learning_rate": 1.1831019041883273e-07,
+      "loss": 0.194,
+      "step": 4220
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 1.190290927886963,
+      "learning_rate": 1.1006985511874734e-07,
+      "loss": 0.2121,
+      "step": 4230
+    },
+    {
+      "epoch": 1.008888888888889,
+      "grad_norm": 0.7071307897567749,
+      "learning_rate": 1.0212375200327973e-07,
+      "loss": 0.1869,
+      "step": 4240
+    },
+    {
+      "epoch": 1.011111111111111,
+      "grad_norm": 0.6801832318305969,
+      "learning_rate": 9.447235919772202e-08,
+      "loss": 0.207,
+      "step": 4250
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.6869502663612366,
+      "learning_rate": 8.711613709434075e-08,
+      "loss": 0.2336,
+      "step": 4260
+    },
+    {
+      "epoch": 1.0155555555555555,
+      "grad_norm": 1.2630761861801147,
+      "learning_rate": 8.00555283246729e-08,
+      "loss": 0.2024,
+      "step": 4270
+    },
+    {
+      "epoch": 1.0177777777777777,
+      "grad_norm": 0.6952125430107117,
+      "learning_rate": 7.329095773289552e-08,
+      "loss": 0.2276,
+      "step": 4280
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.877948522567749,
+      "learning_rate": 6.682283235025844e-08,
+      "loss": 0.218,
+      "step": 4290
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 0.5656408667564392,
+      "learning_rate": 6.065154137059603e-08,
+      "loss": 0.1758,
+      "step": 4300
+    },
+    {
+      "epoch": 1.0244444444444445,
+      "grad_norm": 0.7789971232414246,
+      "learning_rate": 5.477745612690766e-08,
+      "loss": 0.206,
+      "step": 4310
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.6387847661972046,
+      "learning_rate": 4.9200930069014943e-08,
+      "loss": 0.2079,
+      "step": 4320
+    },
+    {
+      "epoch": 1.028888888888889,
+      "grad_norm": 1.0071361064910889,
+      "learning_rate": 4.392229874229159e-08,
+      "loss": 0.1832,
+      "step": 4330
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 0.889040470123291,
+      "learning_rate": 3.894187976747732e-08,
+      "loss": 0.2215,
+      "step": 4340
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.8084672689437866,
+      "learning_rate": 3.4259972821564236e-08,
+      "loss": 0.1991,
+      "step": 4350
+    },
+    {
+      "epoch": 1.0355555555555556,
+      "grad_norm": 0.6156975626945496,
+      "learning_rate": 2.9876859619764606e-08,
+      "loss": 0.2088,
+      "step": 4360
+    },
+    {
+      "epoch": 1.0377777777777777,
+      "grad_norm": 0.7236930131912231,
+      "learning_rate": 2.5792803898559425e-08,
+      "loss": 0.2095,
+      "step": 4370
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6219337582588196,
+      "learning_rate": 2.2008051399831643e-08,
+      "loss": 0.2032,
+      "step": 4380
+    },
+    {
+      "epoch": 1.0422222222222222,
+      "grad_norm": 0.6610362529754639,
+      "learning_rate": 1.8522829856076895e-08,
+      "loss": 0.1973,
+      "step": 4390
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 0.7610447406768799,
+      "learning_rate": 1.5337348976701137e-08,
+      "loss": 0.2056,
+      "step": 4400
+    },
+    {
+      "epoch": 1.0466666666666666,
+      "grad_norm": 0.6604824662208557,
+      "learning_rate": 1.2451800435403504e-08,
+      "loss": 0.2235,
+      "step": 4410
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 0.6615695357322693,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 0.191,
+      "step": 4420
+    },
+    {
+      "epoch": 1.051111111111111,
+      "grad_norm": 0.7280304431915283,
+      "learning_rate": 7.581176815187329e-09,
+      "loss": 0.2019,
+      "step": 4430
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.6365146040916443,
+      "learning_rate": 5.596394806759442e-09,
+      "loss": 0.2041,
+      "step": 4440
+    },
+    {
+      "epoch": 1.0555555555555556,
+      "grad_norm": 0.776874840259552,
+      "learning_rate": 3.912131259757313e-09,
+      "loss": 0.1791,
+      "step": 4450
+    },
+    {
+      "epoch": 1.0577777777777777,
+      "grad_norm": 1.013484239578247,
+      "learning_rate": 2.5284875180708878e-09,
+      "loss": 0.2065,
+      "step": 4460
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.7705738544464111,
+      "learning_rate": 1.4455468369845015e-09,
+      "loss": 0.1933,
+      "step": 4470
+    },
+    {
+      "epoch": 1.0622222222222222,
+      "grad_norm": 0.831679105758667,
+      "learning_rate": 6.633743781642166e-10,
+      "loss": 0.2035,
+      "step": 4480
+    },
+    {
+      "epoch": 1.0644444444444445,
+      "grad_norm": 0.642478346824646,
+      "learning_rate": 1.8201720574206884e-10,
+      "loss": 0.2263,
+      "step": 4490
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.6768687963485718,
+      "learning_rate": 1.504283478892532e-12,
+      "loss": 0.2121,
+      "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": 2.4268824839054164e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

mixed_all_v5_300k_norefdot/checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e044b52fa191ea3d02cd20876a02190b2cbae599ecb3162473314748c2921f
+size 7416