Upload mixed_all_v5_300k/checkpoint-4500

.gitattributes

@@ -254,3 +254,4 @@ mixed_all_v5_300k_nopatch/checkpoint-4000/tokenizer.json filter=lfs diff=lfs mer
 mixed_all_v5_300k_noreach/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 mixed_all_v5_300k_noreach/checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 mixed_all_v5_300k_noreach/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mixed_all_v5_300k/checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

mixed_all_v5_300k/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/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/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/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/checkpoint-4500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b4966846d79f3b8ab8134672191bb1329eb2952c5e6da75c4aef25ba28f3cf
+size 4968243304

mixed_all_v5_300k/checkpoint-4500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530d65cbfb32bc2d73504717ce6df23b9ae91e51ad3e86c41050a8d6edc69dd9
+size 4991495816

mixed_all_v5_300k/checkpoint-4500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a33a83efc21275747983f45e91f25a37c75069702cff83c99598534d04831b
+size 4932751040

mixed_all_v5_300k/checkpoint-4500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cab03b5766ae9f55ea8d05c39d4d3011d4f3311b33c6aa61f900d85242a1721
+size 1691924384

mixed_all_v5_300k/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/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/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/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/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/checkpoint-4500/trainer_state.json

@@ -0,0 +1,3184 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0002222222222221,
+  "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": 9.924181938171387,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.5626,
+      "step": 10
+    },
+    {
+      "epoch": 0.0044444444444444444,
+      "grad_norm": 11.688103675842285,
+      "learning_rate": 4.2222222222222226e-07,
+      "loss": 0.5276,
+      "step": 20
+    },
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 3.2598812580108643,
+      "learning_rate": 6.444444444444445e-07,
+      "loss": 0.3824,
+      "step": 30
+    },
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 2.0114388465881348,
+      "learning_rate": 8.666666666666668e-07,
+      "loss": 0.3443,
+      "step": 40
+    },
+    {
+      "epoch": 0.011111111111111112,
+      "grad_norm": 1.4809671640396118,
+      "learning_rate": 1.0888888888888889e-06,
+      "loss": 0.3004,
+      "step": 50
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.979543924331665,
+      "learning_rate": 1.3111111111111112e-06,
+      "loss": 0.2755,
+      "step": 60
+    },
+    {
+      "epoch": 0.015555555555555555,
+      "grad_norm": 1.2359498739242554,
+      "learning_rate": 1.5333333333333334e-06,
+      "loss": 0.2822,
+      "step": 70
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 3.338075637817383,
+      "learning_rate": 1.7555555555555556e-06,
+      "loss": 0.2849,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.8061875104904175,
+      "learning_rate": 1.977777777777778e-06,
+      "loss": 0.2671,
+      "step": 90
+    },
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 1.5001753568649292,
+      "learning_rate": 2.2e-06,
+      "loss": 0.2736,
+      "step": 100
+    },
+    {
+      "epoch": 0.024444444444444446,
+      "grad_norm": 6.0512471199035645,
+      "learning_rate": 2.4222222222222223e-06,
+      "loss": 0.2856,
+      "step": 110
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 2.0769591331481934,
+      "learning_rate": 2.6444444444444444e-06,
+      "loss": 0.2608,
+      "step": 120
+    },
+    {
+      "epoch": 0.028888888888888888,
+      "grad_norm": 1.4859682321548462,
+      "learning_rate": 2.866666666666667e-06,
+      "loss": 0.2575,
+      "step": 130
+    },
+    {
+      "epoch": 0.03111111111111111,
+      "grad_norm": 1.3658599853515625,
+      "learning_rate": 3.088888888888889e-06,
+      "loss": 0.2581,
+      "step": 140
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 1.2706785202026367,
+      "learning_rate": 3.3111111111111118e-06,
+      "loss": 0.264,
+      "step": 150
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 1.5977369546890259,
+      "learning_rate": 3.5333333333333335e-06,
+      "loss": 0.3132,
+      "step": 160
+    },
+    {
+      "epoch": 0.03777777777777778,
+      "grad_norm": 1.0276427268981934,
+      "learning_rate": 3.7555555555555557e-06,
+      "loss": 0.2678,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.3077694177627563,
+      "learning_rate": 3.977777777777778e-06,
+      "loss": 0.2613,
+      "step": 180
+    },
+    {
+      "epoch": 0.042222222222222223,
+      "grad_norm": 1.6265144348144531,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.2648,
+      "step": 190
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.9548312425613403,
+      "learning_rate": 4.422222222222223e-06,
+      "loss": 0.2391,
+      "step": 200
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 1.02474045753479,
+      "learning_rate": 4.644444444444445e-06,
+      "loss": 0.2555,
+      "step": 210
+    },
+    {
+      "epoch": 0.04888888888888889,
+      "grad_norm": 0.8681908249855042,
+      "learning_rate": 4.866666666666667e-06,
+      "loss": 0.2347,
+      "step": 220
+    },
+    {
+      "epoch": 0.051111111111111114,
+      "grad_norm": 1.0561692714691162,
+      "learning_rate": 5.088888888888889e-06,
+      "loss": 0.2606,
+      "step": 230
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.9467365145683289,
+      "learning_rate": 5.311111111111111e-06,
+      "loss": 0.2263,
+      "step": 240
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 1.156806230545044,
+      "learning_rate": 5.533333333333334e-06,
+      "loss": 0.2463,
+      "step": 250
+    },
+    {
+      "epoch": 0.057777777777777775,
+      "grad_norm": 0.9601301550865173,
+      "learning_rate": 5.7555555555555564e-06,
+      "loss": 0.235,
+      "step": 260
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0934863090515137,
+      "learning_rate": 5.977777777777778e-06,
+      "loss": 0.2528,
+      "step": 270
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 0.7502247095108032,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 0.2479,
+      "step": 280
+    },
+    {
+      "epoch": 0.06444444444444444,
+      "grad_norm": 1.0168192386627197,
+      "learning_rate": 6.422222222222223e-06,
+      "loss": 0.2389,
+      "step": 290
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 1.0070475339889526,
+      "learning_rate": 6.644444444444444e-06,
+      "loss": 0.2612,
+      "step": 300
+    },
+    {
+      "epoch": 0.06888888888888889,
+      "grad_norm": 1.0982449054718018,
+      "learning_rate": 6.866666666666667e-06,
+      "loss": 0.2459,
+      "step": 310
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.9444432854652405,
+      "learning_rate": 7.0888888888888894e-06,
+      "loss": 0.2538,
+      "step": 320
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 2.190020799636841,
+      "learning_rate": 7.3111111111111125e-06,
+      "loss": 0.2278,
+      "step": 330
+    },
+    {
+      "epoch": 0.07555555555555556,
+      "grad_norm": 2.1246378421783447,
+      "learning_rate": 7.533333333333334e-06,
+      "loss": 0.2134,
+      "step": 340
+    },
+    {
+      "epoch": 0.07777777777777778,
+      "grad_norm": 1.140108585357666,
+      "learning_rate": 7.755555555555557e-06,
+      "loss": 0.2575,
+      "step": 350
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.5251386165618896,
+      "learning_rate": 7.977777777777779e-06,
+      "loss": 0.2567,
+      "step": 360
+    },
+    {
+      "epoch": 0.08222222222222222,
+      "grad_norm": 1.4499849081039429,
+      "learning_rate": 8.2e-06,
+      "loss": 0.2427,
+      "step": 370
+    },
+    {
+      "epoch": 0.08444444444444445,
+      "grad_norm": 4.66734504699707,
+      "learning_rate": 8.422222222222223e-06,
+      "loss": 0.231,
+      "step": 380
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 0.9242591261863708,
+      "learning_rate": 8.644444444444445e-06,
+      "loss": 0.261,
+      "step": 390
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.9572818875312805,
+      "learning_rate": 8.866666666666668e-06,
+      "loss": 0.2569,
+      "step": 400
+    },
+    {
+      "epoch": 0.09111111111111111,
+      "grad_norm": 1.324184775352478,
+      "learning_rate": 9.08888888888889e-06,
+      "loss": 0.2613,
+      "step": 410
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 0.9304335117340088,
+      "learning_rate": 9.311111111111112e-06,
+      "loss": 0.2337,
+      "step": 420
+    },
+    {
+      "epoch": 0.09555555555555556,
+      "grad_norm": 1.1610562801361084,
+      "learning_rate": 9.533333333333334e-06,
+      "loss": 0.2221,
+      "step": 430
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 1.6304186582565308,
+      "learning_rate": 9.755555555555556e-06,
+      "loss": 0.233,
+      "step": 440
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.948921799659729,
+      "learning_rate": 9.977777777777778e-06,
+      "loss": 0.2178,
+      "step": 450
+    },
+    {
+      "epoch": 0.10222222222222223,
+      "grad_norm": 0.7488666772842407,
+      "learning_rate": 9.999878153526974e-06,
+      "loss": 0.2288,
+      "step": 460
+    },
+    {
+      "epoch": 0.10444444444444445,
+      "grad_norm": 2.3285465240478516,
+      "learning_rate": 9.999456963466733e-06,
+      "loss": 0.2192,
+      "step": 470
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.0879158973693848,
+      "learning_rate": 9.99873495087924e-06,
+      "loss": 0.2409,
+      "step": 480
+    },
+    {
+      "epoch": 0.10888888888888888,
+      "grad_norm": 0.7695150971412659,
+      "learning_rate": 9.997712159208745e-06,
+      "loss": 0.2364,
+      "step": 490
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.9298784136772156,
+      "learning_rate": 9.996388649997687e-06,
+      "loss": 0.2133,
+      "step": 500
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 0.857125461101532,
+      "learning_rate": 9.99476450288299e-06,
+      "loss": 0.2219,
+      "step": 510
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 1.0964268445968628,
+      "learning_rate": 9.99283981559128e-06,
+      "loss": 0.2382,
+      "step": 520
+    },
+    {
+      "epoch": 0.11777777777777777,
+      "grad_norm": 0.7096911668777466,
+      "learning_rate": 9.990614703932991e-06,
+      "loss": 0.2487,
+      "step": 530
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.7830138206481934,
+      "learning_rate": 9.988089301795406e-06,
+      "loss": 0.2423,
+      "step": 540
+    },
+    {
+      "epoch": 0.12222222222222222,
+      "grad_norm": 0.8286463022232056,
+      "learning_rate": 9.985263761134602e-06,
+      "loss": 0.2266,
+      "step": 550
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 0.9743831157684326,
+      "learning_rate": 9.982138251966297e-06,
+      "loss": 0.2298,
+      "step": 560
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 0.6821303963661194,
+      "learning_rate": 9.978712962355634e-06,
+      "loss": 0.2328,
+      "step": 570
+    },
+    {
+      "epoch": 0.1288888888888889,
+      "grad_norm": 0.8267591595649719,
+      "learning_rate": 9.97498809840585e-06,
+      "loss": 0.2349,
+      "step": 580
+    },
+    {
+      "epoch": 0.13111111111111112,
+      "grad_norm": 0.6285133361816406,
+      "learning_rate": 9.970963884245885e-06,
+      "loss": 0.2327,
+      "step": 590
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.0221643447875977,
+      "learning_rate": 9.96664056201689e-06,
+      "loss": 0.2361,
+      "step": 600
+    },
+    {
+      "epoch": 0.13555555555555557,
+      "grad_norm": 0.681692898273468,
+      "learning_rate": 9.962018391857665e-06,
+      "loss": 0.2299,
+      "step": 610
+    },
+    {
+      "epoch": 0.13777777777777778,
+      "grad_norm": 1.2295910120010376,
+      "learning_rate": 9.957097651888996e-06,
+      "loss": 0.2272,
+      "step": 620
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8763057589530945,
+      "learning_rate": 9.951878638196929e-06,
+      "loss": 0.2098,
+      "step": 630
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.6827264428138733,
+      "learning_rate": 9.946361664814942e-06,
+      "loss": 0.2315,
+      "step": 640
+    },
+    {
+      "epoch": 0.14444444444444443,
+      "grad_norm": 1.064443588256836,
+      "learning_rate": 9.940547063705071e-06,
+      "loss": 0.2322,
+      "step": 650
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 0.7289556264877319,
+      "learning_rate": 9.93443518473791e-06,
+      "loss": 0.2471,
+      "step": 660
+    },
+    {
+      "epoch": 0.14888888888888888,
+      "grad_norm": 0.8253892660140991,
+      "learning_rate": 9.928026395671577e-06,
+      "loss": 0.2009,
+      "step": 670
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 0.5132562518119812,
+      "learning_rate": 9.921321082129578e-06,
+      "loss": 0.2285,
+      "step": 680
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 0.7551118731498718,
+      "learning_rate": 9.914319647577608e-06,
+      "loss": 0.2288,
+      "step": 690
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.5669192671775818,
+      "learning_rate": 9.907022513299264e-06,
+      "loss": 0.2388,
+      "step": 700
+    },
+    {
+      "epoch": 0.15777777777777777,
+      "grad_norm": 1.347604751586914,
+      "learning_rate": 9.899430118370712e-06,
+      "loss": 0.2163,
+      "step": 710
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7553471326828003,
+      "learning_rate": 9.891542919634252e-06,
+      "loss": 0.2308,
+      "step": 720
+    },
+    {
+      "epoch": 0.1622222222222222,
+      "grad_norm": 2.6021807193756104,
+      "learning_rate": 9.883361391670841e-06,
+      "loss": 0.2232,
+      "step": 730
+    },
+    {
+      "epoch": 0.16444444444444445,
+      "grad_norm": 0.7035297155380249,
+      "learning_rate": 9.874886026771526e-06,
+      "loss": 0.2576,
+      "step": 740
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.7769802808761597,
+      "learning_rate": 9.866117334907832e-06,
+      "loss": 0.2295,
+      "step": 750
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 0.7617781758308411,
+      "learning_rate": 9.857055843701073e-06,
+      "loss": 0.2253,
+      "step": 760
+    },
+    {
+      "epoch": 0.1711111111111111,
+      "grad_norm": 0.610367476940155,
+      "learning_rate": 9.847702098390603e-06,
+      "loss": 0.2402,
+      "step": 770
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 0.7274327278137207,
+      "learning_rate": 9.83805666180101e-06,
+      "loss": 0.2424,
+      "step": 780
+    },
+    {
+      "epoch": 0.17555555555555555,
+      "grad_norm": 0.644281268119812,
+      "learning_rate": 9.828120114308248e-06,
+      "loss": 0.2105,
+      "step": 790
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6311648488044739,
+      "learning_rate": 9.817893053804719e-06,
+      "loss": 0.2151,
+      "step": 800
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5773924589157104,
+      "learning_rate": 9.807376095663294e-06,
+      "loss": 0.2261,
+      "step": 810
+    },
+    {
+      "epoch": 0.18222222222222223,
+      "grad_norm": 0.7182205319404602,
+      "learning_rate": 9.796569872700287e-06,
+      "loss": 0.2258,
+      "step": 820
+    },
+    {
+      "epoch": 0.18444444444444444,
+      "grad_norm": 0.6940751075744629,
+      "learning_rate": 9.78547503513738e-06,
+      "loss": 0.2216,
+      "step": 830
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.8167203068733215,
+      "learning_rate": 9.774092250562488e-06,
+      "loss": 0.2226,
+      "step": 840
+    },
+    {
+      "epoch": 0.18888888888888888,
+      "grad_norm": 0.8323789834976196,
+      "learning_rate": 9.762422203889604e-06,
+      "loss": 0.2275,
+      "step": 850
+    },
+    {
+      "epoch": 0.19111111111111112,
+      "grad_norm": 0.5814133286476135,
+      "learning_rate": 9.75046559731758e-06,
+      "loss": 0.2323,
+      "step": 860
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 0.5363942980766296,
+      "learning_rate": 9.738223150287874e-06,
+      "loss": 0.1942,
+      "step": 870
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.5470007061958313,
+      "learning_rate": 9.72569559944126e-06,
+      "loss": 0.2366,
+      "step": 880
+    },
+    {
+      "epoch": 0.19777777777777777,
+      "grad_norm": 0.6173815131187439,
+      "learning_rate": 9.712883698573506e-06,
+      "loss": 0.2239,
+      "step": 890
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.5648717880249023,
+      "learning_rate": 9.69978821859002e-06,
+      "loss": 0.2329,
+      "step": 900
+    },
+    {
+      "epoch": 0.20222222222222222,
+      "grad_norm": 1.0717254877090454,
+      "learning_rate": 9.68640994745946e-06,
+      "loss": 0.2057,
+      "step": 910
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 0.5438013076782227,
+      "learning_rate": 9.672749690166312e-06,
+      "loss": 0.2437,
+      "step": 920
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 0.6994393467903137,
+      "learning_rate": 9.658808268662478e-06,
+      "loss": 0.2271,
+      "step": 930
+    },
+    {
+      "epoch": 0.2088888888888889,
+      "grad_norm": 0.5521865487098694,
+      "learning_rate": 9.644586521817792e-06,
+      "loss": 0.2055,
+      "step": 940
+    },
+    {
+      "epoch": 0.2111111111111111,
+      "grad_norm": 0.8000915050506592,
+      "learning_rate": 9.630085305369559e-06,
+      "loss": 0.2287,
+      "step": 950
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6016538739204407,
+      "learning_rate": 9.61530549187106e-06,
+      "loss": 0.2372,
+      "step": 960
+    },
+    {
+      "epoch": 0.21555555555555556,
+      "grad_norm": 0.7297303080558777,
+      "learning_rate": 9.600247970639053e-06,
+      "loss": 0.2216,
+      "step": 970
+    },
+    {
+      "epoch": 0.21777777777777776,
+      "grad_norm": 0.6423630714416504,
+      "learning_rate": 9.584913647700256e-06,
+      "loss": 0.2159,
+      "step": 980
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.4872545599937439,
+      "learning_rate": 9.569303445736836e-06,
+      "loss": 0.2205,
+      "step": 990
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.6575105786323547,
+      "learning_rate": 9.553418304030886e-06,
+      "loss": 0.2393,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22444444444444445,
+      "grad_norm": 0.8463655710220337,
+      "learning_rate": 9.53725917840791e-06,
+      "loss": 0.2279,
+      "step": 1010
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 0.7961763143539429,
+      "learning_rate": 9.520827041179314e-06,
+      "loss": 0.2104,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2288888888888889,
+      "grad_norm": 0.9833681583404541,
+      "learning_rate": 9.504122881083886e-06,
+      "loss": 0.2326,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.5351530909538269,
+      "learning_rate": 9.487147703228323e-06,
+      "loss": 0.2355,
+      "step": 1040
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.6020206809043884,
+      "learning_rate": 9.469902529026736e-06,
+      "loss": 0.2212,
+      "step": 1050
+    },
+    {
+      "epoch": 0.23555555555555555,
+      "grad_norm": 0.5131970047950745,
+      "learning_rate": 9.452388396139202e-06,
+      "loss": 0.2036,
+      "step": 1060
+    },
+    {
+      "epoch": 0.23777777777777778,
+      "grad_norm": 1.3133710622787476,
+      "learning_rate": 9.43460635840932e-06,
+      "loss": 0.2308,
+      "step": 1070
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.6461527943611145,
+      "learning_rate": 9.416557485800796e-06,
+      "loss": 0.2144,
+      "step": 1080
+    },
+    {
+      "epoch": 0.24222222222222223,
+      "grad_norm": 0.7322333455085754,
+      "learning_rate": 9.398242864333084e-06,
+      "loss": 0.2196,
+      "step": 1090
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 3.4561572074890137,
+      "learning_rate": 9.379663596016004e-06,
+      "loss": 0.2201,
+      "step": 1100
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.6419399976730347,
+      "learning_rate": 9.360820798783469e-06,
+      "loss": 0.2407,
+      "step": 1110
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.3857824504375458,
+      "learning_rate": 9.34171560642619e-06,
+      "loss": 0.2202,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2511111111111111,
+      "grad_norm": 0.48406118154525757,
+      "learning_rate": 9.322349168523467e-06,
+      "loss": 0.2118,
+      "step": 1130
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 0.4081599712371826,
+      "learning_rate": 9.302722650374025e-06,
+      "loss": 0.2129,
+      "step": 1140
+    },
+    {
+      "epoch": 0.25555555555555554,
+      "grad_norm": 0.5763452053070068,
+      "learning_rate": 9.282837232925876e-06,
+      "loss": 0.2379,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 0.6393010020256042,
+      "learning_rate": 9.262694112705283e-06,
+      "loss": 0.211,
+      "step": 1160
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.57600998878479,
+      "learning_rate": 9.242294501744743e-06,
+      "loss": 0.2074,
+      "step": 1170
+    },
+    {
+      "epoch": 0.26222222222222225,
+      "grad_norm": 0.5989611148834229,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 0.2267,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2644444444444444,
+      "grad_norm": 0.5097178816795349,
+      "learning_rate": 9.200730732826555e-06,
+      "loss": 0.232,
+      "step": 1190
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.5838733315467834,
+      "learning_rate": 9.179569075804124e-06,
+      "loss": 0.2402,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2688888888888889,
+      "grad_norm": 0.722679615020752,
+      "learning_rate": 9.15815592976171e-06,
+      "loss": 0.2351,
+      "step": 1210
+    },
+    {
+      "epoch": 0.27111111111111114,
+      "grad_norm": 0.4932297468185425,
+      "learning_rate": 9.136492583150588e-06,
+      "loss": 0.1997,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 1.1461904048919678,
+      "learning_rate": 9.114580339476859e-06,
+      "loss": 0.2222,
+      "step": 1230
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 0.5406240224838257,
+      "learning_rate": 9.09242051722303e-06,
+      "loss": 0.2424,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.5069988965988159,
+      "learning_rate": 9.07001444976866e-06,
+      "loss": 0.222,
+      "step": 1250
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.9292587637901306,
+      "learning_rate": 9.04736348531014e-06,
+      "loss": 0.2196,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2822222222222222,
+      "grad_norm": 0.7752560377120972,
+      "learning_rate": 9.02446898677957e-06,
+      "loss": 0.2213,
+      "step": 1270
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.6626201272010803,
+      "learning_rate": 9.001332331762748e-06,
+      "loss": 0.2387,
+      "step": 1280
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 0.6038187742233276,
+      "learning_rate": 8.977954912416278e-06,
+      "loss": 0.2372,
+      "step": 1290
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.4917048215866089,
+      "learning_rate": 8.954338135383804e-06,
+      "loss": 0.23,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2911111111111111,
+      "grad_norm": 0.5198574662208557,
+      "learning_rate": 8.930483421711376e-06,
+      "loss": 0.2203,
+      "step": 1310
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.5830650329589844,
+      "learning_rate": 8.906392206761933e-06,
+      "loss": 0.2176,
+      "step": 1320
+    },
+    {
+      "epoch": 0.29555555555555557,
+      "grad_norm": 0.6417010426521301,
+      "learning_rate": 8.882065940128946e-06,
+      "loss": 0.2429,
+      "step": 1330
+    },
+    {
+      "epoch": 0.29777777777777775,
+      "grad_norm": 0.49336278438568115,
+      "learning_rate": 8.857506085549188e-06,
+      "loss": 0.2152,
+      "step": 1340
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.528846025466919,
+      "learning_rate": 8.832714120814663e-06,
+      "loss": 0.2263,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 0.5572819709777832,
+      "learning_rate": 8.807691537683685e-06,
+      "loss": 0.2028,
+      "step": 1360
+    },
+    {
+      "epoch": 0.30444444444444446,
+      "grad_norm": 0.634105920791626,
+      "learning_rate": 8.782439841791115e-06,
+      "loss": 0.2174,
+      "step": 1370
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.7402420043945312,
+      "learning_rate": 8.756960552557769e-06,
+      "loss": 0.2462,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3088888888888889,
+      "grad_norm": 0.5466001629829407,
+      "learning_rate": 8.73125520309899e-06,
+      "loss": 0.2245,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 1.1451408863067627,
+      "learning_rate": 8.7053253401324e-06,
+      "loss": 0.2293,
+      "step": 1400
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 0.8137235641479492,
+      "learning_rate": 8.679172523884833e-06,
+      "loss": 0.2319,
+      "step": 1410
+    },
+    {
+      "epoch": 0.31555555555555553,
+      "grad_norm": 0.6870085000991821,
+      "learning_rate": 8.652798327998458e-06,
+      "loss": 0.2214,
+      "step": 1420
+    },
+    {
+      "epoch": 0.31777777777777777,
+      "grad_norm": 1.126531720161438,
+      "learning_rate": 8.626204339436075e-06,
+      "loss": 0.2231,
+      "step": 1430
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5569244027137756,
+      "learning_rate": 8.599392158385651e-06,
+      "loss": 0.2227,
+      "step": 1440
+    },
+    {
+      "epoch": 0.32222222222222224,
+      "grad_norm": 0.6929180026054382,
+      "learning_rate": 8.572363398164017e-06,
+      "loss": 0.2117,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3244444444444444,
+      "grad_norm": 0.6341601014137268,
+      "learning_rate": 8.545119685119798e-06,
+      "loss": 0.2216,
+      "step": 1460
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.6216258406639099,
+      "learning_rate": 8.51766265853555e-06,
+      "loss": 0.2164,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 0.7235459685325623,
+      "learning_rate": 8.489993970529137e-06,
+      "loss": 0.2018,
+      "step": 1480
+    },
+    {
+      "epoch": 0.33111111111111113,
+      "grad_norm": 0.6330488920211792,
+      "learning_rate": 8.462115285954299e-06,
+      "loss": 0.2359,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6952196955680847,
+      "learning_rate": 8.434028282300497e-06,
+      "loss": 0.2361,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33555555555555555,
+      "grad_norm": 0.5741705298423767,
+      "learning_rate": 8.405734649591964e-06,
+      "loss": 0.2271,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.5972622036933899,
+      "learning_rate": 8.377236090286016e-06,
+      "loss": 0.2459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.6268580555915833,
+      "learning_rate": 8.34853431917062e-06,
+      "loss": 0.2318,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3422222222222222,
+      "grad_norm": 0.5555704832077026,
+      "learning_rate": 8.319631063261209e-06,
+      "loss": 0.2206,
+      "step": 1540
+    },
+    {
+      "epoch": 0.34444444444444444,
+      "grad_norm": 0.6367019414901733,
+      "learning_rate": 8.290528061696761e-06,
+      "loss": 0.202,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.45616430044174194,
+      "learning_rate": 8.261227065635162e-06,
+      "loss": 0.236,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3488888888888889,
+      "grad_norm": 0.504652738571167,
+      "learning_rate": 8.231729838147833e-06,
+      "loss": 0.2063,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3511111111111111,
+      "grad_norm": 0.604731023311615,
+      "learning_rate": 8.202038154113641e-06,
+      "loss": 0.2293,
+      "step": 1580
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 0.5620101690292358,
+      "learning_rate": 8.172153800112107e-06,
+      "loss": 0.2307,
+      "step": 1590
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.507335901260376,
+      "learning_rate": 8.142078574315907e-06,
+      "loss": 0.2004,
+      "step": 1600
+    },
+    {
+      "epoch": 0.35777777777777775,
+      "grad_norm": 0.5985124111175537,
+      "learning_rate": 8.111814286382667e-06,
+      "loss": 0.2151,
+      "step": 1610
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5698251128196716,
+      "learning_rate": 8.081362757346083e-06,
+      "loss": 0.2278,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3622222222222222,
+      "grad_norm": 0.5372495055198669,
+      "learning_rate": 8.05072581950634e-06,
+      "loss": 0.2269,
+      "step": 1630
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 0.6088298559188843,
+      "learning_rate": 8.019905316319863e-06,
+      "loss": 0.2397,
+      "step": 1640
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.4769972860813141,
+      "learning_rate": 7.988903102288399e-06,
+      "loss": 0.2098,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3688888888888889,
+      "grad_norm": 0.672837495803833,
+      "learning_rate": 7.95772104284742e-06,
+      "loss": 0.2123,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3711111111111111,
+      "grad_norm": 0.5442995429039001,
+      "learning_rate": 7.92636101425389e-06,
+      "loss": 0.2246,
+      "step": 1670
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.6181974411010742,
+      "learning_rate": 7.894824903473356e-06,
+      "loss": 0.204,
+      "step": 1680
+    },
+    {
+      "epoch": 0.37555555555555553,
+      "grad_norm": 0.6373948454856873,
+      "learning_rate": 7.863114608066417e-06,
+      "loss": 0.2327,
+      "step": 1690
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.5649070739746094,
+      "learning_rate": 7.831232036074542e-06,
+      "loss": 0.2488,
+      "step": 1700
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.7189968824386597,
+      "learning_rate": 7.799179105905255e-06,
+      "loss": 0.2297,
+      "step": 1710
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 0.9851977229118347,
+      "learning_rate": 7.76695774621672e-06,
+      "loss": 0.2185,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3844444444444444,
+      "grad_norm": 1.034421443939209,
+      "learning_rate": 7.734569895801675e-06,
+      "loss": 0.2161,
+      "step": 1730
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 0.6332741379737854,
+      "learning_rate": 7.702017503470773e-06,
+      "loss": 0.1988,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.4665151536464691,
+      "learning_rate": 7.669302527935334e-06,
+      "loss": 0.2091,
+      "step": 1750
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.6290430426597595,
+      "learning_rate": 7.636426937689476e-06,
+      "loss": 0.2327,
+      "step": 1760
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 0.4994640052318573,
+      "learning_rate": 7.603392710891665e-06,
+      "loss": 0.2117,
+      "step": 1770
+    },
+    {
+      "epoch": 0.39555555555555555,
+      "grad_norm": 0.59731525182724,
+      "learning_rate": 7.570201835245703e-06,
+      "loss": 0.2281,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3977777777777778,
+      "grad_norm": 0.44482335448265076,
+      "learning_rate": 7.536856307881106e-06,
+      "loss": 0.205,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4912755787372589,
+      "learning_rate": 7.503358135232959e-06,
+      "loss": 0.2077,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4022222222222222,
+      "grad_norm": 1.3179619312286377,
+      "learning_rate": 7.469709332921155e-06,
+      "loss": 0.2148,
+      "step": 1810
+    },
+    {
+      "epoch": 0.40444444444444444,
+      "grad_norm": 0.48789018392562866,
+      "learning_rate": 7.435911925629146e-06,
+      "loss": 0.2308,
+      "step": 1820
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 0.5717813968658447,
+      "learning_rate": 7.401967946982089e-06,
+      "loss": 0.2223,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 4.386058330535889,
+      "learning_rate": 7.3678794394245e-06,
+      "loss": 0.2113,
+      "step": 1840
+    },
+    {
+      "epoch": 0.4111111111111111,
+      "grad_norm": 0.758614718914032,
+      "learning_rate": 7.333648454097347e-06,
+      "loss": 0.2168,
+      "step": 1850
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 0.48516130447387695,
+      "learning_rate": 7.299277050714631e-06,
+      "loss": 0.2254,
+      "step": 1860
+    },
+    {
+      "epoch": 0.41555555555555557,
+      "grad_norm": 0.44800400733947754,
+      "learning_rate": 7.264767297439455e-06,
+      "loss": 0.2103,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 0.5340624451637268,
+      "learning_rate": 7.230121270759583e-06,
+      "loss": 0.2168,
+      "step": 1880
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.41869935393333435,
+      "learning_rate": 7.195341055362485e-06,
+      "loss": 0.2127,
+      "step": 1890
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.6609564423561096,
+      "learning_rate": 7.160428744009913e-06,
+      "loss": 0.2189,
+      "step": 1900
+    },
+    {
+      "epoch": 0.42444444444444446,
+      "grad_norm": 0.7715006470680237,
+      "learning_rate": 7.1253864374119615e-06,
+      "loss": 0.2385,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.4341668486595154,
+      "learning_rate": 7.090216244100683e-06,
+      "loss": 0.2177,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4288888888888889,
+      "grad_norm": 0.5809782147407532,
+      "learning_rate": 7.054920280303199e-06,
+      "loss": 0.1927,
+      "step": 1930
+    },
+    {
+      "epoch": 0.4311111111111111,
+      "grad_norm": 0.4711281359195709,
+      "learning_rate": 7.019500669814378e-06,
+      "loss": 0.2193,
+      "step": 1940
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.5338524580001831,
+      "learning_rate": 6.9839595438690345e-06,
+      "loss": 0.2097,
+      "step": 1950
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 0.5637155771255493,
+      "learning_rate": 6.948299041013695e-06,
+      "loss": 0.2265,
+      "step": 1960
+    },
+    {
+      "epoch": 0.43777777777777777,
+      "grad_norm": 0.5559911727905273,
+      "learning_rate": 6.912521306977922e-06,
+      "loss": 0.2429,
+      "step": 1970
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.44113731384277344,
+      "learning_rate": 6.876628494545198e-06,
+      "loss": 0.203,
+      "step": 1980
+    },
+    {
+      "epoch": 0.44222222222222224,
+      "grad_norm": 0.5687151551246643,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 0.2404,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.885344386100769,
+      "learning_rate": 6.804506280114804e-06,
+      "loss": 0.2337,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 0.7357438206672668,
+      "learning_rate": 6.76828121778582e-06,
+      "loss": 0.2292,
+      "step": 2010
+    },
+    {
+      "epoch": 0.4488888888888889,
+      "grad_norm": 0.4875304400920868,
+      "learning_rate": 6.7319497561361245e-06,
+      "loss": 0.2118,
+      "step": 2020
+    },
+    {
+      "epoch": 0.45111111111111113,
+      "grad_norm": 0.48754340410232544,
+      "learning_rate": 6.695514081267571e-06,
+      "loss": 0.2132,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.449505478143692,
+      "learning_rate": 6.658976385552625e-06,
+      "loss": 0.2006,
+      "step": 2040
+    },
+    {
+      "epoch": 0.45555555555555555,
+      "grad_norm": 0.5936020612716675,
+      "learning_rate": 6.622338867502452e-06,
+      "loss": 0.2329,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4577777777777778,
+      "grad_norm": 0.43800297379493713,
+      "learning_rate": 6.585603731634636e-06,
+      "loss": 0.1992,
+      "step": 2060
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5078200101852417,
+      "learning_rate": 6.548773188340523e-06,
+      "loss": 0.2341,
+      "step": 2070
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.4979291558265686,
+      "learning_rate": 6.5118494537522235e-06,
+      "loss": 0.225,
+      "step": 2080
+    },
+    {
+      "epoch": 0.46444444444444444,
+      "grad_norm": 0.7118539214134216,
+      "learning_rate": 6.474834749609266e-06,
+      "loss": 0.2154,
+      "step": 2090
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.6591707468032837,
+      "learning_rate": 6.4377313031249085e-06,
+      "loss": 0.2209,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4688888888888889,
+      "grad_norm": 1.314562201499939,
+      "learning_rate": 6.400541346852136e-06,
+      "loss": 0.2376,
+      "step": 2110
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 0.7785199880599976,
+      "learning_rate": 6.363267118549307e-06,
+      "loss": 0.2196,
+      "step": 2120
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.5423850417137146,
+      "learning_rate": 6.325910861045526e-06,
+      "loss": 0.2074,
+      "step": 2130
+    },
+    {
+      "epoch": 0.47555555555555556,
+      "grad_norm": 0.4341280162334442,
+      "learning_rate": 6.28847482210567e-06,
+      "loss": 0.2239,
+      "step": 2140
+    },
+    {
+      "epoch": 0.4777777777777778,
+      "grad_norm": 0.6796637177467346,
+      "learning_rate": 6.250961254295156e-06,
+      "loss": 0.1973,
+      "step": 2150
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.4732671082019806,
+      "learning_rate": 6.21337241484439e-06,
+      "loss": 0.2098,
+      "step": 2160
+    },
+    {
+      "epoch": 0.4822222222222222,
+      "grad_norm": 0.4725073575973511,
+      "learning_rate": 6.17571056551295e-06,
+      "loss": 0.2265,
+      "step": 2170
+    },
+    {
+      "epoch": 0.48444444444444446,
+      "grad_norm": 0.3642556071281433,
+      "learning_rate": 6.137977972453499e-06,
+      "loss": 0.2401,
+      "step": 2180
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 0.6184865832328796,
+      "learning_rate": 6.10017690607542e-06,
+      "loss": 0.2237,
+      "step": 2190
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.39165645837783813,
+      "learning_rate": 6.062309640908206e-06,
+      "loss": 0.2049,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4911111111111111,
+      "grad_norm": 0.5216869115829468,
+      "learning_rate": 6.024378455464603e-06,
+      "loss": 0.221,
+      "step": 2210
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 0.5703321695327759,
+      "learning_rate": 5.986385632103505e-06,
+      "loss": 0.2494,
+      "step": 2220
+    },
+    {
+      "epoch": 0.4955555555555556,
+      "grad_norm": 0.6099245548248291,
+      "learning_rate": 5.948333456892624e-06,
+      "loss": 0.2309,
+      "step": 2230
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.6665458083152771,
+      "learning_rate": 5.910224219470935e-06,
+      "loss": 0.2488,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5038465857505798,
+      "learning_rate": 5.872060212910903e-06,
+      "loss": 0.2058,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5022222222222222,
+      "grad_norm": 0.7212831974029541,
+      "learning_rate": 5.8338437335805124e-06,
+      "loss": 0.2061,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5044444444444445,
+      "grad_norm": 0.4945129156112671,
+      "learning_rate": 5.795577081005086e-06,
+      "loss": 0.2367,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.5349830985069275,
+      "learning_rate": 5.757262557728927e-06,
+      "loss": 0.2134,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5088888888888888,
+      "grad_norm": 1.2578166723251343,
+      "learning_rate": 5.718902469176765e-06,
+      "loss": 0.2266,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.46451711654663086,
+      "learning_rate": 5.680499123515039e-06,
+      "loss": 0.2464,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 0.5644308924674988,
+      "learning_rate": 5.6420548315130156e-06,
+      "loss": 0.2167,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.4930547773838043,
+      "learning_rate": 5.6035719064037446e-06,
+      "loss": 0.1943,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5177777777777778,
+      "grad_norm": 0.5735832452774048,
+      "learning_rate": 5.56505266374487e-06,
+      "loss": 0.2467,
+      "step": 2330
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.6241104006767273,
+      "learning_rate": 5.5264994212793e-06,
+      "loss": 0.215,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5222222222222223,
+      "grad_norm": 0.5817795991897583,
+      "learning_rate": 5.487914498795748e-06,
+      "loss": 0.2117,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 0.6174975633621216,
+      "learning_rate": 5.4493002179891455e-06,
+      "loss": 0.2313,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 0.4075397253036499,
+      "learning_rate": 5.410658902320946e-06,
+      "loss": 0.2339,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5288888888888889,
+      "grad_norm": 0.551929771900177,
+      "learning_rate": 5.371992876879318e-06,
+      "loss": 0.2319,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5311111111111111,
+      "grad_norm": 0.549560546875,
+      "learning_rate": 5.333304468239241e-06,
+      "loss": 0.1927,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.46545615792274475,
+      "learning_rate": 5.294596004322518e-06,
+      "loss": 0.2123,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5355555555555556,
+      "grad_norm": 0.5949607491493225,
+      "learning_rate": 5.255869814257701e-06,
+      "loss": 0.2031,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5377777777777778,
+      "grad_norm": 0.5138635635375977,
+      "learning_rate": 5.217128228239934e-06,
+      "loss": 0.2114,
+      "step": 2420
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.46768128871917725,
+      "learning_rate": 5.178373577390763e-06,
+      "loss": 0.2035,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 0.5480571389198303,
+      "learning_rate": 5.139608193617846e-06,
+      "loss": 0.201,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5444444444444444,
+      "grad_norm": 0.48850375413894653,
+      "learning_rate": 5.100834409474661e-06,
+      "loss": 0.2138,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.4850066006183624,
+      "learning_rate": 5.062054558020145e-06,
+      "loss": 0.2094,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5488888888888889,
+      "grad_norm": 0.47435295581817627,
+      "learning_rate": 5.0232709726783065e-06,
+      "loss": 0.2182,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.6518157124519348,
+      "learning_rate": 4.984485987097829e-06,
+      "loss": 0.2096,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 0.4830823838710785,
+      "learning_rate": 4.945701935011651e-06,
+      "loss": 0.2282,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.5129601955413818,
+      "learning_rate": 4.906921150096538e-06,
+      "loss": 0.2121,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5577777777777778,
+      "grad_norm": 0.6198655962944031,
+      "learning_rate": 4.868145965832667e-06,
+      "loss": 0.2164,
+      "step": 2510
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6033708453178406,
+      "learning_rate": 4.8293787153632245e-06,
+      "loss": 0.2066,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5622222222222222,
+      "grad_norm": 0.5549076795578003,
+      "learning_rate": 4.7906217313540035e-06,
+      "loss": 0.2044,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5644444444444444,
+      "grad_norm": 0.5874499678611755,
+      "learning_rate": 4.751877345853055e-06,
+      "loss": 0.1961,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.7137885689735413,
+      "learning_rate": 4.713147890150372e-06,
+      "loss": 0.2097,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.6060664653778076,
+      "learning_rate": 4.674435694637597e-06,
+      "loss": 0.2238,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5711111111111111,
+      "grad_norm": 0.47340139746665955,
+      "learning_rate": 4.635743088667815e-06,
+      "loss": 0.2124,
+      "step": 2570
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 0.4907388687133789,
+      "learning_rate": 4.597072400415383e-06,
+      "loss": 0.2242,
+      "step": 2580
+    },
+    {
+      "epoch": 0.5755555555555556,
+      "grad_norm": 0.7059533596038818,
+      "learning_rate": 4.5584259567358505e-06,
+      "loss": 0.1992,
+      "step": 2590
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.6504600644111633,
+      "learning_rate": 4.519806083025944e-06,
+      "loss": 0.2289,
+      "step": 2600
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.6024309396743774,
+      "learning_rate": 4.481215103083646e-06,
+      "loss": 0.2141,
+      "step": 2610
+    },
+    {
+      "epoch": 0.5822222222222222,
+      "grad_norm": 0.6088564991950989,
+      "learning_rate": 4.442655338968373e-06,
+      "loss": 0.212,
+      "step": 2620
+    },
+    {
+      "epoch": 0.5844444444444444,
+      "grad_norm": 0.5141090750694275,
+      "learning_rate": 4.404129110861254e-06,
+      "loss": 0.2502,
+      "step": 2630
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.6999302506446838,
+      "learning_rate": 4.365638736925512e-06,
+      "loss": 0.2328,
+      "step": 2640
+    },
+    {
+      "epoch": 0.5888888888888889,
+      "grad_norm": 0.6864138841629028,
+      "learning_rate": 4.3271865331670036e-06,
+      "loss": 0.2044,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5911111111111111,
+      "grad_norm": 0.7770395874977112,
+      "learning_rate": 4.288774813294833e-06,
+      "loss": 0.1901,
+      "step": 2660
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.6016991138458252,
+      "learning_rate": 4.2504058885821515e-06,
+      "loss": 0.2,
+      "step": 2670
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 2.2206220626831055,
+      "learning_rate": 4.212082067727079e-06,
+      "loss": 0.2304,
+      "step": 2680
+    },
+    {
+      "epoch": 0.5977777777777777,
+      "grad_norm": 0.4321691393852234,
+      "learning_rate": 4.173805656713793e-06,
+      "loss": 0.2318,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6187299489974976,
+      "learning_rate": 4.13557895867377e-06,
+      "loss": 0.2492,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6022222222222222,
+      "grad_norm": 0.6705717444419861,
+      "learning_rate": 4.0974042737472005e-06,
+      "loss": 0.2151,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.5393504500389099,
+      "learning_rate": 4.0592838989446e-06,
+      "loss": 0.232,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 0.5743488073348999,
+      "learning_rate": 4.021220128008584e-06,
+      "loss": 0.2059,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6088888888888889,
+      "grad_norm": 0.6187424063682556,
+      "learning_rate": 3.983215251275847e-06,
+      "loss": 0.2222,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.47079968452453613,
+      "learning_rate": 3.945271555539373e-06,
+      "loss": 0.2398,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.5697185397148132,
+      "learning_rate": 3.90739132391081e-06,
+      "loss": 0.232,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6155555555555555,
+      "grad_norm": 1.5167560577392578,
+      "learning_rate": 3.869576835683109e-06,
+      "loss": 0.2117,
+      "step": 2770
+    },
+    {
+      "epoch": 0.6177777777777778,
+      "grad_norm": 0.5479514002799988,
+      "learning_rate": 3.831830366193367e-06,
+      "loss": 0.214,
+      "step": 2780
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.993269681930542,
+      "learning_rate": 3.7941541866859337e-06,
+      "loss": 0.2382,
+      "step": 2790
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.7427210807800293,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 0.2313,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6244444444444445,
+      "grad_norm": 0.9641949534416199,
+      "learning_rate": 3.7190217613118385e-06,
+      "loss": 0.1994,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 0.6805160641670227,
+      "learning_rate": 3.6815700362413855e-06,
+      "loss": 0.2312,
+      "step": 2820
+    },
+    {
+      "epoch": 0.6288888888888889,
+      "grad_norm": 0.4689134359359741,
+      "learning_rate": 3.6441976424736315e-06,
+      "loss": 0.2034,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 0.5220444798469543,
+      "learning_rate": 3.6069068287443932e-06,
+      "loss": 0.2128,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.7826744914054871,
+      "learning_rate": 3.569699838880735e-06,
+      "loss": 0.1967,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6355555555555555,
+      "grad_norm": 0.6871840953826904,
+      "learning_rate": 3.5325789116659493e-06,
+      "loss": 0.186,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6377777777777778,
+      "grad_norm": 0.6477622389793396,
+      "learning_rate": 3.495546280704849e-06,
+      "loss": 0.2064,
+      "step": 2870
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5703286528587341,
+      "learning_rate": 3.458604174289367e-06,
+      "loss": 0.2166,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6422222222222222,
+      "grad_norm": 0.4790681302547455,
+      "learning_rate": 3.4217548152644887e-06,
+      "loss": 0.2103,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 0.5331887602806091,
+      "learning_rate": 3.3850004208944838e-06,
+      "loss": 0.2138,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 0.6076874136924744,
+      "learning_rate": 3.3483432027295025e-06,
+      "loss": 0.1831,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 0.6662538647651672,
+      "learning_rate": 3.311785366472506e-06,
+      "loss": 0.2058,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6511111111111111,
+      "grad_norm": 0.5907435417175293,
+      "learning_rate": 3.275329111846536e-06,
+      "loss": 0.1998,
+      "step": 2930
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 0.8563355803489685,
+      "learning_rate": 3.238976632462364e-06,
+      "loss": 0.2139,
+      "step": 2940
+    },
+    {
+      "epoch": 0.6555555555555556,
+      "grad_norm": 0.6290088891983032,
+      "learning_rate": 3.2027301156865015e-06,
+      "loss": 0.2255,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.5487999320030212,
+      "learning_rate": 3.166591742509575e-06,
+      "loss": 0.2004,
+      "step": 2960
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.6499339938163757,
+      "learning_rate": 3.130563687415098e-06,
+      "loss": 0.1937,
+      "step": 2970
+    },
+    {
+      "epoch": 0.6622222222222223,
+      "grad_norm": 0.5198572874069214,
+      "learning_rate": 3.09464811824863e-06,
+      "loss": 0.1932,
+      "step": 2980
+    },
+    {
+      "epoch": 0.6644444444444444,
+      "grad_norm": 0.5077383518218994,
+      "learning_rate": 3.05884719608734e-06,
+      "loss": 0.2142,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5301347970962524,
+      "learning_rate": 3.0231630751099628e-06,
+      "loss": 0.2062,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6688888888888889,
+      "grad_norm": 0.6551733016967773,
+      "learning_rate": 2.9875979024671846e-06,
+      "loss": 0.2173,
+      "step": 3010
+    },
+    {
+      "epoch": 0.6711111111111111,
+      "grad_norm": 0.5385633111000061,
+      "learning_rate": 2.9521538181524497e-06,
+      "loss": 0.2139,
+      "step": 3020
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 0.6124095916748047,
+      "learning_rate": 2.9168329548731873e-06,
+      "loss": 0.2122,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.720691442489624,
+      "learning_rate": 2.8816374379224932e-06,
+      "loss": 0.2328,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6777777777777778,
+      "grad_norm": 0.8918633460998535,
+      "learning_rate": 2.846569385051241e-06,
+      "loss": 0.1985,
+      "step": 3050
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.606036901473999,
+      "learning_rate": 2.8116309063406593e-06,
+      "loss": 0.2115,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6822222222222222,
+      "grad_norm": 0.595835268497467,
+      "learning_rate": 2.776824104075364e-06,
+      "loss": 0.2029,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 0.9692875742912292,
+      "learning_rate": 2.742151072616861e-06,
+      "loss": 0.2142,
+      "step": 3080
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 0.6808924674987793,
+      "learning_rate": 2.707613898277533e-06,
+      "loss": 0.1988,
+      "step": 3090
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.6407119035720825,
+      "learning_rate": 2.6732146591950924e-06,
+      "loss": 0.2203,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6911111111111111,
+      "grad_norm": 0.8610571622848511,
+      "learning_rate": 2.638955425207545e-06,
+      "loss": 0.2236,
+      "step": 3110
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.5613287091255188,
+      "learning_rate": 2.604838257728648e-06,
+      "loss": 0.2042,
+      "step": 3120
+    },
+    {
+      "epoch": 0.6955555555555556,
+      "grad_norm": 0.5763799548149109,
+      "learning_rate": 2.5708652096238674e-06,
+      "loss": 0.2112,
+      "step": 3130
+    },
+    {
+      "epoch": 0.6977777777777778,
+      "grad_norm": 0.5103434324264526,
+      "learning_rate": 2.5370383250868493e-06,
+      "loss": 0.2057,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4667283892631531,
+      "learning_rate": 2.503359639516437e-06,
+      "loss": 0.2263,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 0.7064809799194336,
+      "learning_rate": 2.469831179394182e-06,
+      "loss": 0.2356,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7044444444444444,
+      "grad_norm": 0.500585675239563,
+      "learning_rate": 2.4364549621624124e-06,
+      "loss": 0.221,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 0.8225744366645813,
+      "learning_rate": 2.40323299610285e-06,
+      "loss": 0.2144,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7088888888888889,
+      "grad_norm": 0.5574638843536377,
+      "learning_rate": 2.3701672802157567e-06,
+      "loss": 0.1851,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.5390077233314514,
+      "learning_rate": 2.3372598040996614e-06,
+      "loss": 0.201,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 0.7689483761787415,
+      "learning_rate": 2.304512547831639e-06,
+      "loss": 0.2173,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7155555555555555,
+      "grad_norm": 0.5512729287147522,
+      "learning_rate": 2.2719274818481767e-06,
+      "loss": 0.2135,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7177777777777777,
+      "grad_norm": 0.8316792845726013,
+      "learning_rate": 2.2395065668265943e-06,
+      "loss": 0.1868,
+      "step": 3230
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.7149350643157959,
+      "learning_rate": 2.2072517535670795e-06,
+      "loss": 0.2236,
+      "step": 3240
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 1.338810682296753,
+      "learning_rate": 2.175164982875311e-06,
+      "loss": 0.1988,
+      "step": 3250
+    },
+    {
+      "epoch": 0.7244444444444444,
+      "grad_norm": 0.8373861908912659,
+      "learning_rate": 2.1432481854456645e-06,
+      "loss": 0.1668,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 0.6652361750602722,
+      "learning_rate": 2.1115032817450476e-06,
+      "loss": 0.2202,
+      "step": 3270
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.7520272135734558,
+      "learning_rate": 2.0799321818973488e-06,
+      "loss": 0.2054,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7311111111111112,
+      "grad_norm": 1.2596155405044556,
+      "learning_rate": 2.0485367855684932e-06,
+      "loss": 0.2119,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.5658687949180603,
+      "learning_rate": 2.0173189818521442e-06,
+      "loss": 0.2334,
+      "step": 3300
+    },
+    {
+      "epoch": 0.7355555555555555,
+      "grad_norm": 0.8128467798233032,
+      "learning_rate": 1.9862806491560315e-06,
+      "loss": 0.2238,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 0.6476460099220276,
+      "learning_rate": 1.955423655088928e-06,
+      "loss": 0.2246,
+      "step": 3320
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7568962574005127,
+      "learning_rate": 1.9247498563482724e-06,
+      "loss": 0.2214,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7422222222222222,
+      "grad_norm": 1.4074445962905884,
+      "learning_rate": 1.8942610986084487e-06,
+      "loss": 0.2141,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7444444444444445,
+      "grad_norm": 0.7794123291969299,
+      "learning_rate": 1.8639592164097348e-06,
+      "loss": 0.2058,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.5494393110275269,
+      "learning_rate": 1.8338460330479102e-06,
+      "loss": 0.2123,
+      "step": 3360
+    },
+    {
+      "epoch": 0.7488888888888889,
+      "grad_norm": 1.0316509008407593,
+      "learning_rate": 1.8039233604645468e-06,
+      "loss": 0.2286,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7511111111111111,
+      "grad_norm": 0.5098915100097656,
+      "learning_rate": 1.7741929991379914e-06,
+      "loss": 0.2205,
+      "step": 3380
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 0.7158875465393066,
+      "learning_rate": 1.7446567379750167e-06,
+      "loss": 0.2295,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.7294540405273438,
+      "learning_rate": 1.7153163542031881e-06,
+      "loss": 0.2305,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7577777777777778,
+      "grad_norm": 0.6323444843292236,
+      "learning_rate": 1.686173613263925e-06,
+      "loss": 0.2047,
+      "step": 3410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.9141685366630554,
+      "learning_rate": 1.6572302687062718e-06,
+      "loss": 0.2265,
+      "step": 3420
+    },
+    {
+      "epoch": 0.7622222222222222,
+      "grad_norm": 0.6141507029533386,
+      "learning_rate": 1.6284880620813847e-06,
+      "loss": 0.2039,
+      "step": 3430
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.6586495637893677,
+      "learning_rate": 1.5999487228377398e-06,
+      "loss": 0.2147,
+      "step": 3440
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.7326564192771912,
+      "learning_rate": 1.5716139682170778e-06,
+      "loss": 0.2124,
+      "step": 3450
+    },
+    {
+      "epoch": 0.7688888888888888,
+      "grad_norm": 0.620236337184906,
+      "learning_rate": 1.5434855031510626e-06,
+      "loss": 0.2198,
+      "step": 3460
+    },
+    {
+      "epoch": 0.7711111111111111,
+      "grad_norm": 0.6801938414573669,
+      "learning_rate": 1.515565020158703e-06,
+      "loss": 0.21,
+      "step": 3470
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.7456125020980835,
+      "learning_rate": 1.4878541992445144e-06,
+      "loss": 0.2161,
+      "step": 3480
+    },
+    {
+      "epoch": 0.7755555555555556,
+      "grad_norm": 0.6374524235725403,
+      "learning_rate": 1.4603547077974217e-06,
+      "loss": 0.2139,
+      "step": 3490
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.9286184310913086,
+      "learning_rate": 1.4330682004904367e-06,
+      "loss": 0.2141,
+      "step": 3500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.8765749335289001,
+      "learning_rate": 1.4059963191810955e-06,
+      "loss": 0.2155,
+      "step": 3510
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.1142102479934692,
+      "learning_rate": 1.3791406928126638e-06,
+      "loss": 0.2022,
+      "step": 3520
+    },
+    {
+      "epoch": 0.7844444444444445,
+      "grad_norm": 0.7423458695411682,
+      "learning_rate": 1.352502937316122e-06,
+      "loss": 0.2033,
+      "step": 3530
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 0.5692638754844666,
+      "learning_rate": 1.3260846555129325e-06,
+      "loss": 0.2043,
+      "step": 3540
+    },
+    {
+      "epoch": 0.7888888888888889,
+      "grad_norm": 0.5001302361488342,
+      "learning_rate": 1.2998874370186026e-06,
+      "loss": 0.2201,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 0.7446277737617493,
+      "learning_rate": 1.273912858147024e-06,
+      "loss": 0.198,
+      "step": 3560
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.8999312520027161,
+      "learning_rate": 1.2481624818156319e-06,
+      "loss": 0.2124,
+      "step": 3570
+    },
+    {
+      "epoch": 0.7955555555555556,
+      "grad_norm": 0.6090630292892456,
+      "learning_rate": 1.2226378574513654e-06,
+      "loss": 0.2006,
+      "step": 3580
+    },
+    {
+      "epoch": 0.7977777777777778,
+      "grad_norm": 0.9677258729934692,
+      "learning_rate": 1.1973405208974282e-06,
+      "loss": 0.2085,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7128000855445862,
+      "learning_rate": 1.1722719943208822e-06,
+      "loss": 0.2061,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8022222222222222,
+      "grad_norm": 0.825572669506073,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 0.217,
+      "step": 3610
+    },
+    {
+      "epoch": 0.8044444444444444,
+      "grad_norm": 0.7483615279197693,
+      "learning_rate": 1.1228273908387756e-06,
+      "loss": 0.2105,
+      "step": 3620
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 0.5786201357841492,
+      "learning_rate": 1.0984542890664513e-06,
+      "loss": 0.1949,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 1.1126819849014282,
+      "learning_rate": 1.0743159473589738e-06,
+      "loss": 0.2291,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8111111111111111,
+      "grad_norm": 0.7378976941108704,
+      "learning_rate": 1.050413818145481e-06,
+      "loss": 0.2369,
+      "step": 3650
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 0.878474235534668,
+      "learning_rate": 1.0267493396419559e-06,
+      "loss": 0.2304,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8155555555555556,
+      "grad_norm": 0.7040265202522278,
+      "learning_rate": 1.0033239357646913e-06,
+      "loss": 0.2188,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.0113208293914795,
+      "learning_rate": 9.801390160446135e-07,
+      "loss": 0.2082,
+      "step": 3680
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.2628803253173828,
+      "learning_rate": 9.571959755424643e-07,
+      "loss": 0.2156,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.6413156986236572,
+      "learning_rate": 9.344961947648624e-07,
+      "loss": 0.2235,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8244444444444444,
+      "grad_norm": 0.7177358269691467,
+      "learning_rate": 9.120410395812346e-07,
+      "loss": 0.1963,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.6427916288375854,
+      "learning_rate": 8.898318611416329e-07,
+      "loss": 0.1927,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8288888888888889,
+      "grad_norm": 0.5534716248512268,
+      "learning_rate": 8.678699957954323e-07,
+      "loss": 0.2056,
+      "step": 3730
+    },
+    {
+      "epoch": 0.8311111111111111,
+      "grad_norm": 1.0947418212890625,
+      "learning_rate": 8.461567650109187e-07,
+      "loss": 0.1991,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.7426397204399109,
+      "learning_rate": 8.246934752957835e-07,
+      "loss": 0.1942,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.661493718624115,
+      "learning_rate": 8.034814181184996e-07,
+      "loss": 0.212,
+      "step": 3760
+    },
+    {
+      "epoch": 0.8377777777777777,
+      "grad_norm": 0.7180119156837463,
+      "learning_rate": 7.825218698306164e-07,
+      "loss": 0.1921,
+      "step": 3770
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.6054819822311401,
+      "learning_rate": 7.618160915899641e-07,
+      "loss": 0.2287,
+      "step": 3780
+    },
+    {
+      "epoch": 0.8422222222222222,
+      "grad_norm": 0.8168054819107056,
+      "learning_rate": 7.413653292847617e-07,
+      "loss": 0.1981,
+      "step": 3790
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.548618495464325,
+      "learning_rate": 7.211708134586565e-07,
+      "loss": 0.2228,
+      "step": 3800
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 0.5999671220779419,
+      "learning_rate": 7.012337592366764e-07,
+      "loss": 0.21,
+      "step": 3810
+    },
+    {
+      "epoch": 0.8488888888888889,
+      "grad_norm": 0.7660518288612366,
+      "learning_rate": 6.815553662521185e-07,
+      "loss": 0.1975,
+      "step": 3820
+    },
+    {
+      "epoch": 0.8511111111111112,
+      "grad_norm": 0.8853387236595154,
+      "learning_rate": 6.621368185743626e-07,
+      "loss": 0.1847,
+      "step": 3830
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.5182763338088989,
+      "learning_rate": 6.429792846376259e-07,
+      "loss": 0.2086,
+      "step": 3840
+    },
+    {
+      "epoch": 0.8555555555555555,
+      "grad_norm": 1.1235034465789795,
+      "learning_rate": 6.240839171706608e-07,
+      "loss": 0.2164,
+      "step": 3850
+    },
+    {
+      "epoch": 0.8577777777777778,
+      "grad_norm": 0.7863725423812866,
+      "learning_rate": 6.054518531273861e-07,
+      "loss": 0.1926,
+      "step": 3860
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.8976577520370483,
+      "learning_rate": 5.870842136184807e-07,
+      "loss": 0.2166,
+      "step": 3870
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 0.6538885235786438,
+      "learning_rate": 5.689821038439264e-07,
+      "loss": 0.2089,
+      "step": 3880
+    },
+    {
+      "epoch": 0.8644444444444445,
+      "grad_norm": 0.6148439645767212,
+      "learning_rate": 5.51146613026502e-07,
+      "loss": 0.1856,
+      "step": 3890
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.6208164691925049,
+      "learning_rate": 5.335788143462472e-07,
+      "loss": 0.2013,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8688888888888889,
+      "grad_norm": 0.5821053385734558,
+      "learning_rate": 5.162797648758877e-07,
+      "loss": 0.2076,
+      "step": 3910
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.7765588164329529,
+      "learning_rate": 4.992505055172287e-07,
+      "loss": 0.2143,
+      "step": 3920
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 1.0043152570724487,
+      "learning_rate": 4.824920609385242e-07,
+      "loss": 0.2289,
+      "step": 3930
+    },
+    {
+      "epoch": 0.8755555555555555,
+      "grad_norm": 0.737336277961731,
+      "learning_rate": 4.6600543951281995e-07,
+      "loss": 0.1861,
+      "step": 3940
+    },
+    {
+      "epoch": 0.8777777777777778,
+      "grad_norm": 0.5942501425743103,
+      "learning_rate": 4.4979163325728324e-07,
+      "loss": 0.2077,
+      "step": 3950
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8742725253105164,
+      "learning_rate": 4.3385161777350527e-07,
+      "loss": 0.2261,
+      "step": 3960
+    },
+    {
+      "epoch": 0.8822222222222222,
+      "grad_norm": 0.9254752993583679,
+      "learning_rate": 4.1818635218880186e-07,
+      "loss": 0.2003,
+      "step": 3970
+    },
+    {
+      "epoch": 0.8844444444444445,
+      "grad_norm": 0.6978368163108826,
+      "learning_rate": 4.027967790985038e-07,
+      "loss": 0.216,
+      "step": 3980
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.8893056511878967,
+      "learning_rate": 3.876838245092357e-07,
+      "loss": 0.2081,
+      "step": 3990
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.6782008409500122,
+      "learning_rate": 3.728483977831998e-07,
+      "loss": 0.2104,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8911111111111111,
+      "grad_norm": 0.6253308653831482,
+      "learning_rate": 3.582913915834574e-07,
+      "loss": 0.1878,
+      "step": 4010
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 0.7457274794578552,
+      "learning_rate": 3.440136818202183e-07,
+      "loss": 0.1975,
+      "step": 4020
+    },
+    {
+      "epoch": 0.8955555555555555,
+      "grad_norm": 0.7316535115242004,
+      "learning_rate": 3.30016127598134e-07,
+      "loss": 0.2382,
+      "step": 4030
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 0.6126384735107422,
+      "learning_rate": 3.162995711646055e-07,
+      "loss": 0.1964,
+      "step": 4040
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.7700461745262146,
+      "learning_rate": 3.0286483785910594e-07,
+      "loss": 0.225,
+      "step": 4050
+    },
+    {
+      "epoch": 0.9022222222222223,
+      "grad_norm": 0.6118504405021667,
+      "learning_rate": 2.8971273606351656e-07,
+      "loss": 0.1786,
+      "step": 4060
+    },
+    {
+      "epoch": 0.9044444444444445,
+      "grad_norm": 0.5702471733093262,
+      "learning_rate": 2.7684405715348585e-07,
+      "loss": 0.1949,
+      "step": 4070
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.7140989899635315,
+      "learning_rate": 2.642595754508143e-07,
+      "loss": 0.2086,
+      "step": 4080
+    },
+    {
+      "epoch": 0.9088888888888889,
+      "grad_norm": 0.7439819574356079,
+      "learning_rate": 2.519600481768597e-07,
+      "loss": 0.2149,
+      "step": 4090
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.6804289221763611,
+      "learning_rate": 2.3994621540697425e-07,
+      "loss": 0.2002,
+      "step": 4100
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 0.6358819007873535,
+      "learning_rate": 2.2821880002597662e-07,
+      "loss": 0.2143,
+      "step": 4110
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 0.6164494752883911,
+      "learning_rate": 2.167785076846518e-07,
+      "loss": 0.2269,
+      "step": 4120
+    },
+    {
+      "epoch": 0.9177777777777778,
+      "grad_norm": 0.571231484413147,
+      "learning_rate": 2.056260267572935e-07,
+      "loss": 0.1974,
+      "step": 4130
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.567934513092041,
+      "learning_rate": 1.9476202830028213e-07,
+      "loss": 0.215,
+      "step": 4140
+    },
+    {
+      "epoch": 0.9222222222222223,
+      "grad_norm": 0.9265458583831787,
+      "learning_rate": 1.841871660117095e-07,
+      "loss": 0.208,
+      "step": 4150
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.8160156607627869,
+      "learning_rate": 1.739020761920418e-07,
+      "loss": 0.2346,
+      "step": 4160
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 0.8809767961502075,
+      "learning_rate": 1.639073777058342e-07,
+      "loss": 0.1922,
+      "step": 4170
+    },
+    {
+      "epoch": 0.9288888888888889,
+      "grad_norm": 0.841490626335144,
+      "learning_rate": 1.5420367194449448e-07,
+      "loss": 0.2224,
+      "step": 4180
+    },
+    {
+      "epoch": 0.9311111111111111,
+      "grad_norm": 0.630286455154419,
+      "learning_rate": 1.447915427900959e-07,
+      "loss": 0.2071,
+      "step": 4190
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.682261049747467,
+      "learning_rate": 1.3567155658023967e-07,
+      "loss": 0.1956,
+      "step": 4200
+    },
+    {
+      "epoch": 0.9355555555555556,
+      "grad_norm": 0.768012285232544,
+      "learning_rate": 1.268442620739868e-07,
+      "loss": 0.211,
+      "step": 4210
+    },
+    {
+      "epoch": 0.9377777777777778,
+      "grad_norm": 0.7140825986862183,
+      "learning_rate": 1.1831019041883273e-07,
+      "loss": 0.2003,
+      "step": 4220
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7665072679519653,
+      "learning_rate": 1.1006985511874734e-07,
+      "loss": 0.2021,
+      "step": 4230
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 0.6483919024467468,
+      "learning_rate": 1.0212375200327973e-07,
+      "loss": 0.2155,
+      "step": 4240
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 0.6706344485282898,
+      "learning_rate": 9.447235919772202e-08,
+      "loss": 0.1982,
+      "step": 4250
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 0.8224043250083923,
+      "learning_rate": 8.711613709434075e-08,
+      "loss": 0.2204,
+      "step": 4260
+    },
+    {
+      "epoch": 0.9488888888888889,
+      "grad_norm": 0.8311476707458496,
+      "learning_rate": 8.00555283246729e-08,
+      "loss": 0.2145,
+      "step": 4270
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 0.8523874878883362,
+      "learning_rate": 7.329095773289552e-08,
+      "loss": 0.1939,
+      "step": 4280
+    },
+    {
+      "epoch": 0.9533333333333334,
+      "grad_norm": 0.8444700837135315,
+      "learning_rate": 6.682283235025844e-08,
+      "loss": 0.2213,
+      "step": 4290
+    },
+    {
+      "epoch": 0.9555555555555556,
+      "grad_norm": 0.46966105699539185,
+      "learning_rate": 6.065154137059603e-08,
+      "loss": 0.2151,
+      "step": 4300
+    },
+    {
+      "epoch": 0.9577777777777777,
+      "grad_norm": 0.6799271106719971,
+      "learning_rate": 5.477745612690766e-08,
+      "loss": 0.1831,
+      "step": 4310
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6573999524116516,
+      "learning_rate": 4.9200930069014943e-08,
+      "loss": 0.2308,
+      "step": 4320
+    },
+    {
+      "epoch": 0.9622222222222222,
+      "grad_norm": 0.5156139135360718,
+      "learning_rate": 4.392229874229159e-08,
+      "loss": 0.2125,
+      "step": 4330
+    },
+    {
+      "epoch": 0.9644444444444444,
+      "grad_norm": 0.894886314868927,
+      "learning_rate": 3.894187976747732e-08,
+      "loss": 0.205,
+      "step": 4340
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.7663149833679199,
+      "learning_rate": 3.4259972821564236e-08,
+      "loss": 0.2072,
+      "step": 4350
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 1.0722953081130981,
+      "learning_rate": 2.9876859619764606e-08,
+      "loss": 0.1991,
+      "step": 4360
+    },
+    {
+      "epoch": 0.9711111111111111,
+      "grad_norm": 0.6166538596153259,
+      "learning_rate": 2.5792803898559425e-08,
+      "loss": 0.2137,
+      "step": 4370
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 0.700756847858429,
+      "learning_rate": 2.2008051399831643e-08,
+      "loss": 0.1935,
+      "step": 4380
+    },
+    {
+      "epoch": 0.9755555555555555,
+      "grad_norm": 0.7113191485404968,
+      "learning_rate": 1.8522829856076895e-08,
+      "loss": 0.2028,
+      "step": 4390
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.8005170226097107,
+      "learning_rate": 1.5337348976701137e-08,
+      "loss": 0.2197,
+      "step": 4400
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.102728247642517,
+      "learning_rate": 1.2451800435403504e-08,
+      "loss": 0.2037,
+      "step": 4410
+    },
+    {
+      "epoch": 0.9822222222222222,
+      "grad_norm": 0.6093318462371826,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 0.2015,
+      "step": 4420
+    },
+    {
+      "epoch": 0.9844444444444445,
+      "grad_norm": 0.958145797252655,
+      "learning_rate": 7.581176815187329e-09,
+      "loss": 0.2265,
+      "step": 4430
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.559722363948822,
+      "learning_rate": 5.596394806759442e-09,
+      "loss": 0.185,
+      "step": 4440
+    },
+    {
+      "epoch": 0.9888888888888889,
+      "grad_norm": 1.0361049175262451,
+      "learning_rate": 3.912131259757313e-09,
+      "loss": 0.1873,
+      "step": 4450
+    },
+    {
+      "epoch": 0.9911111111111112,
+      "grad_norm": 0.6513498425483704,
+      "learning_rate": 2.5284875180708878e-09,
+      "loss": 0.1924,
+      "step": 4460
+    },
+    {
+      "epoch": 0.9933333333333333,
+      "grad_norm": 1.0283327102661133,
+      "learning_rate": 1.4455468369845015e-09,
+      "loss": 0.2117,
+      "step": 4470
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.8018894195556641,
+      "learning_rate": 6.633743781642166e-10,
+      "loss": 0.1965,
+      "step": 4480
+    },
+    {
+      "epoch": 0.9977777777777778,
+      "grad_norm": 0.888047993183136,
+      "learning_rate": 1.8201720574206884e-10,
+      "loss": 0.2112,
+      "step": 4490
+    },
+    {
+      "epoch": 1.0002222222222221,
+      "grad_norm": 0.9756260514259338,
+      "learning_rate": 1.504283478892532e-12,
+      "loss": 0.2199,
+      "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": 2.3423136385378288e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

mixed_all_v5_300k/checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9184d0daf1196cec31d441770f25f67bc27d4ceb23be60bf975420c87f1da573
+size 7416