Upload mixed_all_v5_300k_noreach/checkpoint-4000

.gitattributes

@@ -253,3 +253,4 @@ mixed_all_v5_300k_nomaze2d/checkpoint-4000/tokenizer.json filter=lfs diff=lfs me
 mixed_all_v5_300k_nopatch/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 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_noreach/checkpoint-4000/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_noreach/checkpoint-4000/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_noreach/checkpoint-4000/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_noreach/checkpoint-4000/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_noreach/checkpoint-4000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e78abf02e86df7fba5789fcd26be9edcc9d3527c0996ff5119c7c043943f6b5
+size 4968243304

mixed_all_v5_300k_noreach/checkpoint-4000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf99af22804759f211a2407a85091e9bec5f181fc32f2fd55f9fa0aeddce9fd
+size 4991495816

mixed_all_v5_300k_noreach/checkpoint-4000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62eb07b0a5ff4a9badd0f746f4aaadb38d58d90dba8e7d19f8ac5a5be8cd9f2
+size 4932751040

mixed_all_v5_300k_noreach/checkpoint-4000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7677d7adaded6b9aa1c0fc61a225c93217d59c6f50a25b0ceef7d44b2f6e21
+size 1691924384

mixed_all_v5_300k_noreach/checkpoint-4000/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_noreach/checkpoint-4000/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_noreach/checkpoint-4000/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_noreach/checkpoint-4000/tokenizer.json

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

mixed_all_v5_300k_noreach/checkpoint-4000/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_noreach/checkpoint-4000/trainer_state.json

@@ -0,0 +1,2834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8888888888888888,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0022222222222222222,
+      "grad_norm": 11.935153007507324,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.5719,
+      "step": 10
+    },
+    {
+      "epoch": 0.0044444444444444444,
+      "grad_norm": 11.1741943359375,
+      "learning_rate": 4.2222222222222226e-07,
+      "loss": 0.5678,
+      "step": 20
+    },
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.459104299545288,
+      "learning_rate": 6.444444444444445e-07,
+      "loss": 0.4443,
+      "step": 30
+    },
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 1.632906198501587,
+      "learning_rate": 8.666666666666668e-07,
+      "loss": 0.3524,
+      "step": 40
+    },
+    {
+      "epoch": 0.011111111111111112,
+      "grad_norm": 5.870563507080078,
+      "learning_rate": 1.0888888888888889e-06,
+      "loss": 0.3536,
+      "step": 50
+    },
+    {
+      "epoch": 0.013333333333333334,
+      "grad_norm": 1.5167757272720337,
+      "learning_rate": 1.3111111111111112e-06,
+      "loss": 0.3007,
+      "step": 60
+    },
+    {
+      "epoch": 0.015555555555555555,
+      "grad_norm": 1.3979564905166626,
+      "learning_rate": 1.5333333333333334e-06,
+      "loss": 0.3075,
+      "step": 70
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 1.7612028121948242,
+      "learning_rate": 1.7555555555555556e-06,
+      "loss": 0.2994,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.5764000415802002,
+      "learning_rate": 1.977777777777778e-06,
+      "loss": 0.2645,
+      "step": 90
+    },
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 3.539851665496826,
+      "learning_rate": 2.2e-06,
+      "loss": 0.3009,
+      "step": 100
+    },
+    {
+      "epoch": 0.024444444444444446,
+      "grad_norm": 1.9442254304885864,
+      "learning_rate": 2.4222222222222223e-06,
+      "loss": 0.2946,
+      "step": 110
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.135090947151184,
+      "learning_rate": 2.6444444444444444e-06,
+      "loss": 0.2554,
+      "step": 120
+    },
+    {
+      "epoch": 0.028888888888888888,
+      "grad_norm": 1.8086374998092651,
+      "learning_rate": 2.866666666666667e-06,
+      "loss": 0.2708,
+      "step": 130
+    },
+    {
+      "epoch": 0.03111111111111111,
+      "grad_norm": 1.5638153553009033,
+      "learning_rate": 3.088888888888889e-06,
+      "loss": 0.2743,
+      "step": 140
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 1.862868070602417,
+      "learning_rate": 3.3111111111111118e-06,
+      "loss": 0.2741,
+      "step": 150
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 1.2769384384155273,
+      "learning_rate": 3.5333333333333335e-06,
+      "loss": 0.2371,
+      "step": 160
+    },
+    {
+      "epoch": 0.03777777777777778,
+      "grad_norm": 1.0571855306625366,
+      "learning_rate": 3.7555555555555557e-06,
+      "loss": 0.2728,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.4909420013427734,
+      "learning_rate": 3.977777777777778e-06,
+      "loss": 0.2826,
+      "step": 180
+    },
+    {
+      "epoch": 0.042222222222222223,
+      "grad_norm": 1.4698913097381592,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.2817,
+      "step": 190
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 1.0643539428710938,
+      "learning_rate": 4.422222222222223e-06,
+      "loss": 0.2701,
+      "step": 200
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 1.7701481580734253,
+      "learning_rate": 4.644444444444445e-06,
+      "loss": 0.2493,
+      "step": 210
+    },
+    {
+      "epoch": 0.04888888888888889,
+      "grad_norm": 1.0646620988845825,
+      "learning_rate": 4.866666666666667e-06,
+      "loss": 0.2732,
+      "step": 220
+    },
+    {
+      "epoch": 0.051111111111111114,
+      "grad_norm": 1.2875831127166748,
+      "learning_rate": 5.088888888888889e-06,
+      "loss": 0.2606,
+      "step": 230
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.1123046875,
+      "learning_rate": 5.311111111111111e-06,
+      "loss": 0.2704,
+      "step": 240
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 1.150532603263855,
+      "learning_rate": 5.533333333333334e-06,
+      "loss": 0.2525,
+      "step": 250
+    },
+    {
+      "epoch": 0.057777777777777775,
+      "grad_norm": 1.363961935043335,
+      "learning_rate": 5.7555555555555564e-06,
+      "loss": 0.2613,
+      "step": 260
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9745206236839294,
+      "learning_rate": 5.977777777777778e-06,
+      "loss": 0.2703,
+      "step": 270
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 1.5302971601486206,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 0.2482,
+      "step": 280
+    },
+    {
+      "epoch": 0.06444444444444444,
+      "grad_norm": 1.7488389015197754,
+      "learning_rate": 6.422222222222223e-06,
+      "loss": 0.2688,
+      "step": 290
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 1.121248722076416,
+      "learning_rate": 6.644444444444444e-06,
+      "loss": 0.2597,
+      "step": 300
+    },
+    {
+      "epoch": 0.06888888888888889,
+      "grad_norm": 1.1401336193084717,
+      "learning_rate": 6.866666666666667e-06,
+      "loss": 0.2406,
+      "step": 310
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.8919104933738708,
+      "learning_rate": 7.0888888888888894e-06,
+      "loss": 0.2585,
+      "step": 320
+    },
+    {
+      "epoch": 0.07333333333333333,
+      "grad_norm": 1.1204718351364136,
+      "learning_rate": 7.3111111111111125e-06,
+      "loss": 0.2538,
+      "step": 330
+    },
+    {
+      "epoch": 0.07555555555555556,
+      "grad_norm": 0.9152598977088928,
+      "learning_rate": 7.533333333333334e-06,
+      "loss": 0.2558,
+      "step": 340
+    },
+    {
+      "epoch": 0.07777777777777778,
+      "grad_norm": 1.179988145828247,
+      "learning_rate": 7.755555555555557e-06,
+      "loss": 0.2519,
+      "step": 350
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.8173415064811707,
+      "learning_rate": 7.977777777777779e-06,
+      "loss": 0.2571,
+      "step": 360
+    },
+    {
+      "epoch": 0.08222222222222222,
+      "grad_norm": 1.209908366203308,
+      "learning_rate": 8.2e-06,
+      "loss": 0.247,
+      "step": 370
+    },
+    {
+      "epoch": 0.08444444444444445,
+      "grad_norm": 0.939825713634491,
+      "learning_rate": 8.422222222222223e-06,
+      "loss": 0.2722,
+      "step": 380
+    },
+    {
+      "epoch": 0.08666666666666667,
+      "grad_norm": 1.0540449619293213,
+      "learning_rate": 8.644444444444445e-06,
+      "loss": 0.2493,
+      "step": 390
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.1151156425476074,
+      "learning_rate": 8.866666666666668e-06,
+      "loss": 0.2385,
+      "step": 400
+    },
+    {
+      "epoch": 0.09111111111111111,
+      "grad_norm": 0.9593901634216309,
+      "learning_rate": 9.08888888888889e-06,
+      "loss": 0.2643,
+      "step": 410
+    },
+    {
+      "epoch": 0.09333333333333334,
+      "grad_norm": 0.950873851776123,
+      "learning_rate": 9.311111111111112e-06,
+      "loss": 0.2453,
+      "step": 420
+    },
+    {
+      "epoch": 0.09555555555555556,
+      "grad_norm": 0.9747631549835205,
+      "learning_rate": 9.533333333333334e-06,
+      "loss": 0.239,
+      "step": 430
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 0.8782416582107544,
+      "learning_rate": 9.755555555555556e-06,
+      "loss": 0.2619,
+      "step": 440
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.8192035555839539,
+      "learning_rate": 9.977777777777778e-06,
+      "loss": 0.2526,
+      "step": 450
+    },
+    {
+      "epoch": 0.10222222222222223,
+      "grad_norm": 0.7931861877441406,
+      "learning_rate": 9.999878153526974e-06,
+      "loss": 0.2503,
+      "step": 460
+    },
+    {
+      "epoch": 0.10444444444444445,
+      "grad_norm": 1.1188077926635742,
+      "learning_rate": 9.999456963466733e-06,
+      "loss": 0.2549,
+      "step": 470
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.6315785646438599,
+      "learning_rate": 9.99873495087924e-06,
+      "loss": 0.2613,
+      "step": 480
+    },
+    {
+      "epoch": 0.10888888888888888,
+      "grad_norm": 0.8032658696174622,
+      "learning_rate": 9.997712159208745e-06,
+      "loss": 0.238,
+      "step": 490
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.7566089034080505,
+      "learning_rate": 9.996388649997687e-06,
+      "loss": 0.2562,
+      "step": 500
+    },
+    {
+      "epoch": 0.11333333333333333,
+      "grad_norm": 1.462567687034607,
+      "learning_rate": 9.99476450288299e-06,
+      "loss": 0.239,
+      "step": 510
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 0.8008801937103271,
+      "learning_rate": 9.99283981559128e-06,
+      "loss": 0.2323,
+      "step": 520
+    },
+    {
+      "epoch": 0.11777777777777777,
+      "grad_norm": 0.9862453937530518,
+      "learning_rate": 9.990614703932991e-06,
+      "loss": 0.2685,
+      "step": 530
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1226696968078613,
+      "learning_rate": 9.988089301795406e-06,
+      "loss": 0.2484,
+      "step": 540
+    },
+    {
+      "epoch": 0.12222222222222222,
+      "grad_norm": 0.9309948682785034,
+      "learning_rate": 9.985263761134602e-06,
+      "loss": 0.2422,
+      "step": 550
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 0.7939280271530151,
+      "learning_rate": 9.982138251966297e-06,
+      "loss": 0.2537,
+      "step": 560
+    },
+    {
+      "epoch": 0.12666666666666668,
+      "grad_norm": 0.7078467011451721,
+      "learning_rate": 9.978712962355634e-06,
+      "loss": 0.245,
+      "step": 570
+    },
+    {
+      "epoch": 0.1288888888888889,
+      "grad_norm": 0.6874547004699707,
+      "learning_rate": 9.97498809840585e-06,
+      "loss": 0.255,
+      "step": 580
+    },
+    {
+      "epoch": 0.13111111111111112,
+      "grad_norm": 0.7818899750709534,
+      "learning_rate": 9.970963884245885e-06,
+      "loss": 0.2183,
+      "step": 590
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.8907263875007629,
+      "learning_rate": 9.96664056201689e-06,
+      "loss": 0.2487,
+      "step": 600
+    },
+    {
+      "epoch": 0.13555555555555557,
+      "grad_norm": 0.8063980937004089,
+      "learning_rate": 9.962018391857665e-06,
+      "loss": 0.2721,
+      "step": 610
+    },
+    {
+      "epoch": 0.13777777777777778,
+      "grad_norm": 0.5637244582176208,
+      "learning_rate": 9.957097651888996e-06,
+      "loss": 0.2377,
+      "step": 620
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.7864395380020142,
+      "learning_rate": 9.951878638196929e-06,
+      "loss": 0.2429,
+      "step": 630
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 2.0207912921905518,
+      "learning_rate": 9.946361664814942e-06,
+      "loss": 0.2177,
+      "step": 640
+    },
+    {
+      "epoch": 0.14444444444444443,
+      "grad_norm": 0.789048433303833,
+      "learning_rate": 9.940547063705071e-06,
+      "loss": 0.2674,
+      "step": 650
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 0.738323986530304,
+      "learning_rate": 9.93443518473791e-06,
+      "loss": 0.2404,
+      "step": 660
+    },
+    {
+      "epoch": 0.14888888888888888,
+      "grad_norm": 0.7731937766075134,
+      "learning_rate": 9.928026395671577e-06,
+      "loss": 0.2551,
+      "step": 670
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 0.7536585330963135,
+      "learning_rate": 9.921321082129578e-06,
+      "loss": 0.2318,
+      "step": 680
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 0.5649324655532837,
+      "learning_rate": 9.914319647577608e-06,
+      "loss": 0.2614,
+      "step": 690
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.9135245680809021,
+      "learning_rate": 9.907022513299264e-06,
+      "loss": 0.263,
+      "step": 700
+    },
+    {
+      "epoch": 0.15777777777777777,
+      "grad_norm": 0.5732267498970032,
+      "learning_rate": 9.899430118370712e-06,
+      "loss": 0.2403,
+      "step": 710
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2682362794876099,
+      "learning_rate": 9.891542919634252e-06,
+      "loss": 0.2392,
+      "step": 720
+    },
+    {
+      "epoch": 0.1622222222222222,
+      "grad_norm": 0.7436350584030151,
+      "learning_rate": 9.883361391670841e-06,
+      "loss": 0.2456,
+      "step": 730
+    },
+    {
+      "epoch": 0.16444444444444445,
+      "grad_norm": 0.9578115940093994,
+      "learning_rate": 9.874886026771526e-06,
+      "loss": 0.2535,
+      "step": 740
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.663854718208313,
+      "learning_rate": 9.866117334907832e-06,
+      "loss": 0.2486,
+      "step": 750
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 0.6800159215927124,
+      "learning_rate": 9.857055843701073e-06,
+      "loss": 0.3019,
+      "step": 760
+    },
+    {
+      "epoch": 0.1711111111111111,
+      "grad_norm": 0.652099072933197,
+      "learning_rate": 9.847702098390603e-06,
+      "loss": 0.2646,
+      "step": 770
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 0.6285194158554077,
+      "learning_rate": 9.83805666180101e-06,
+      "loss": 0.242,
+      "step": 780
+    },
+    {
+      "epoch": 0.17555555555555555,
+      "grad_norm": 1.1205041408538818,
+      "learning_rate": 9.828120114308248e-06,
+      "loss": 0.248,
+      "step": 790
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.7202767729759216,
+      "learning_rate": 9.817893053804719e-06,
+      "loss": 0.2495,
+      "step": 800
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6055144667625427,
+      "learning_rate": 9.807376095663294e-06,
+      "loss": 0.2211,
+      "step": 810
+    },
+    {
+      "epoch": 0.18222222222222223,
+      "grad_norm": 0.8455381989479065,
+      "learning_rate": 9.796569872700287e-06,
+      "loss": 0.2571,
+      "step": 820
+    },
+    {
+      "epoch": 0.18444444444444444,
+      "grad_norm": 0.6304262280464172,
+      "learning_rate": 9.78547503513738e-06,
+      "loss": 0.2377,
+      "step": 830
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.5813708305358887,
+      "learning_rate": 9.774092250562488e-06,
+      "loss": 0.2179,
+      "step": 840
+    },
+    {
+      "epoch": 0.18888888888888888,
+      "grad_norm": 0.6618791222572327,
+      "learning_rate": 9.762422203889604e-06,
+      "loss": 0.2585,
+      "step": 850
+    },
+    {
+      "epoch": 0.19111111111111112,
+      "grad_norm": 0.6583630442619324,
+      "learning_rate": 9.75046559731758e-06,
+      "loss": 0.2574,
+      "step": 860
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 0.8397955298423767,
+      "learning_rate": 9.738223150287874e-06,
+      "loss": 0.2384,
+      "step": 870
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.7914876341819763,
+      "learning_rate": 9.72569559944126e-06,
+      "loss": 0.2449,
+      "step": 880
+    },
+    {
+      "epoch": 0.19777777777777777,
+      "grad_norm": 0.7022516131401062,
+      "learning_rate": 9.712883698573506e-06,
+      "loss": 0.2486,
+      "step": 890
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6290777921676636,
+      "learning_rate": 9.69978821859002e-06,
+      "loss": 0.2518,
+      "step": 900
+    },
+    {
+      "epoch": 0.20222222222222222,
+      "grad_norm": 0.6342347264289856,
+      "learning_rate": 9.68640994745946e-06,
+      "loss": 0.2354,
+      "step": 910
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 1.0882257223129272,
+      "learning_rate": 9.672749690166312e-06,
+      "loss": 0.2358,
+      "step": 920
+    },
+    {
+      "epoch": 0.20666666666666667,
+      "grad_norm": 0.6573370099067688,
+      "learning_rate": 9.658808268662478e-06,
+      "loss": 0.2286,
+      "step": 930
+    },
+    {
+      "epoch": 0.2088888888888889,
+      "grad_norm": 0.6233929991722107,
+      "learning_rate": 9.644586521817792e-06,
+      "loss": 0.2242,
+      "step": 940
+    },
+    {
+      "epoch": 0.2111111111111111,
+      "grad_norm": 0.7514392733573914,
+      "learning_rate": 9.630085305369559e-06,
+      "loss": 0.2501,
+      "step": 950
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.5216835737228394,
+      "learning_rate": 9.61530549187106e-06,
+      "loss": 0.2675,
+      "step": 960
+    },
+    {
+      "epoch": 0.21555555555555556,
+      "grad_norm": 0.6454413533210754,
+      "learning_rate": 9.600247970639053e-06,
+      "loss": 0.2409,
+      "step": 970
+    },
+    {
+      "epoch": 0.21777777777777776,
+      "grad_norm": 0.4984878599643707,
+      "learning_rate": 9.584913647700256e-06,
+      "loss": 0.2298,
+      "step": 980
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6576786041259766,
+      "learning_rate": 9.569303445736836e-06,
+      "loss": 0.2351,
+      "step": 990
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.6296005249023438,
+      "learning_rate": 9.553418304030886e-06,
+      "loss": 0.2356,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22444444444444445,
+      "grad_norm": 0.5381527543067932,
+      "learning_rate": 9.53725917840791e-06,
+      "loss": 0.2456,
+      "step": 1010
+    },
+    {
+      "epoch": 0.22666666666666666,
+      "grad_norm": 0.5423462390899658,
+      "learning_rate": 9.520827041179314e-06,
+      "loss": 0.2337,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2288888888888889,
+      "grad_norm": 0.6082004308700562,
+      "learning_rate": 9.504122881083886e-06,
+      "loss": 0.2277,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.5773634910583496,
+      "learning_rate": 9.487147703228323e-06,
+      "loss": 0.2682,
+      "step": 1040
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.5538159012794495,
+      "learning_rate": 9.469902529026736e-06,
+      "loss": 0.2367,
+      "step": 1050
+    },
+    {
+      "epoch": 0.23555555555555555,
+      "grad_norm": 0.4995594322681427,
+      "learning_rate": 9.452388396139202e-06,
+      "loss": 0.218,
+      "step": 1060
+    },
+    {
+      "epoch": 0.23777777777777778,
+      "grad_norm": 0.49008551239967346,
+      "learning_rate": 9.43460635840932e-06,
+      "loss": 0.2371,
+      "step": 1070
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.45274797081947327,
+      "learning_rate": 9.416557485800796e-06,
+      "loss": 0.2214,
+      "step": 1080
+    },
+    {
+      "epoch": 0.24222222222222223,
+      "grad_norm": 0.5752720832824707,
+      "learning_rate": 9.398242864333084e-06,
+      "loss": 0.2463,
+      "step": 1090
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.497204452753067,
+      "learning_rate": 9.379663596016004e-06,
+      "loss": 0.2479,
+      "step": 1100
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.7408638000488281,
+      "learning_rate": 9.360820798783469e-06,
+      "loss": 0.2367,
+      "step": 1110
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.4845982789993286,
+      "learning_rate": 9.34171560642619e-06,
+      "loss": 0.2442,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2511111111111111,
+      "grad_norm": 0.6029704213142395,
+      "learning_rate": 9.322349168523467e-06,
+      "loss": 0.2404,
+      "step": 1130
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 0.709968090057373,
+      "learning_rate": 9.302722650374025e-06,
+      "loss": 0.2438,
+      "step": 1140
+    },
+    {
+      "epoch": 0.25555555555555554,
+      "grad_norm": 2.07013201713562,
+      "learning_rate": 9.282837232925876e-06,
+      "loss": 0.2289,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 0.7255764603614807,
+      "learning_rate": 9.262694112705283e-06,
+      "loss": 0.2506,
+      "step": 1160
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5754784345626831,
+      "learning_rate": 9.242294501744743e-06,
+      "loss": 0.2339,
+      "step": 1170
+    },
+    {
+      "epoch": 0.26222222222222225,
+      "grad_norm": 0.5370100140571594,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 0.2392,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2644444444444444,
+      "grad_norm": 0.5608746409416199,
+      "learning_rate": 9.200730732826555e-06,
+      "loss": 0.2473,
+      "step": 1190
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.2223387956619263,
+      "learning_rate": 9.179569075804124e-06,
+      "loss": 0.2699,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2688888888888889,
+      "grad_norm": 0.8413452506065369,
+      "learning_rate": 9.15815592976171e-06,
+      "loss": 0.228,
+      "step": 1210
+    },
+    {
+      "epoch": 0.27111111111111114,
+      "grad_norm": 0.7279114723205566,
+      "learning_rate": 9.136492583150588e-06,
+      "loss": 0.2495,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 0.5452325940132141,
+      "learning_rate": 9.114580339476859e-06,
+      "loss": 0.2621,
+      "step": 1230
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 0.600328803062439,
+      "learning_rate": 9.09242051722303e-06,
+      "loss": 0.2456,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.7233782410621643,
+      "learning_rate": 9.07001444976866e-06,
+      "loss": 0.2421,
+      "step": 1250
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6281599402427673,
+      "learning_rate": 9.04736348531014e-06,
+      "loss": 0.2503,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2822222222222222,
+      "grad_norm": 0.7944521903991699,
+      "learning_rate": 9.02446898677957e-06,
+      "loss": 0.2337,
+      "step": 1270
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.7317690253257751,
+      "learning_rate": 9.001332331762748e-06,
+      "loss": 0.2465,
+      "step": 1280
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 0.7070778608322144,
+      "learning_rate": 8.977954912416278e-06,
+      "loss": 0.2542,
+      "step": 1290
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.4883306324481964,
+      "learning_rate": 8.954338135383804e-06,
+      "loss": 0.2258,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2911111111111111,
+      "grad_norm": 0.6024297475814819,
+      "learning_rate": 8.930483421711376e-06,
+      "loss": 0.2342,
+      "step": 1310
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.6627012491226196,
+      "learning_rate": 8.906392206761933e-06,
+      "loss": 0.2452,
+      "step": 1320
+    },
+    {
+      "epoch": 0.29555555555555557,
+      "grad_norm": 0.6280615329742432,
+      "learning_rate": 8.882065940128946e-06,
+      "loss": 0.2275,
+      "step": 1330
+    },
+    {
+      "epoch": 0.29777777777777775,
+      "grad_norm": 0.5541442632675171,
+      "learning_rate": 8.857506085549188e-06,
+      "loss": 0.23,
+      "step": 1340
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.7187899947166443,
+      "learning_rate": 8.832714120814663e-06,
+      "loss": 0.238,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 0.7954230308532715,
+      "learning_rate": 8.807691537683685e-06,
+      "loss": 0.2371,
+      "step": 1360
+    },
+    {
+      "epoch": 0.30444444444444446,
+      "grad_norm": 0.7210007905960083,
+      "learning_rate": 8.782439841791115e-06,
+      "loss": 0.2303,
+      "step": 1370
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.6461169123649597,
+      "learning_rate": 8.756960552557769e-06,
+      "loss": 0.2322,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3088888888888889,
+      "grad_norm": 0.6190142631530762,
+      "learning_rate": 8.73125520309899e-06,
+      "loss": 0.2618,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.5950425863265991,
+      "learning_rate": 8.7053253401324e-06,
+      "loss": 0.252,
+      "step": 1400
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 0.6483864784240723,
+      "learning_rate": 8.679172523884833e-06,
+      "loss": 0.2376,
+      "step": 1410
+    },
+    {
+      "epoch": 0.31555555555555553,
+      "grad_norm": 0.5700867176055908,
+      "learning_rate": 8.652798327998458e-06,
+      "loss": 0.2398,
+      "step": 1420
+    },
+    {
+      "epoch": 0.31777777777777777,
+      "grad_norm": 0.6297434568405151,
+      "learning_rate": 8.626204339436075e-06,
+      "loss": 0.2144,
+      "step": 1430
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.6893297433853149,
+      "learning_rate": 8.599392158385651e-06,
+      "loss": 0.2401,
+      "step": 1440
+    },
+    {
+      "epoch": 0.32222222222222224,
+      "grad_norm": 0.5975915193557739,
+      "learning_rate": 8.572363398164017e-06,
+      "loss": 0.2276,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3244444444444444,
+      "grad_norm": 0.8578329086303711,
+      "learning_rate": 8.545119685119798e-06,
+      "loss": 0.2439,
+      "step": 1460
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.5509724020957947,
+      "learning_rate": 8.51766265853555e-06,
+      "loss": 0.2337,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 0.5381113290786743,
+      "learning_rate": 8.489993970529137e-06,
+      "loss": 0.2551,
+      "step": 1480
+    },
+    {
+      "epoch": 0.33111111111111113,
+      "grad_norm": 0.48399072885513306,
+      "learning_rate": 8.462115285954299e-06,
+      "loss": 0.2255,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.5049117803573608,
+      "learning_rate": 8.434028282300497e-06,
+      "loss": 0.2321,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33555555555555555,
+      "grad_norm": 0.6357067823410034,
+      "learning_rate": 8.405734649591964e-06,
+      "loss": 0.262,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.4836282730102539,
+      "learning_rate": 8.377236090286016e-06,
+      "loss": 0.2383,
+      "step": 1520
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.7071205377578735,
+      "learning_rate": 8.34853431917062e-06,
+      "loss": 0.2369,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3422222222222222,
+      "grad_norm": 1.08063805103302,
+      "learning_rate": 8.319631063261209e-06,
+      "loss": 0.2555,
+      "step": 1540
+    },
+    {
+      "epoch": 0.34444444444444444,
+      "grad_norm": 0.6078683733940125,
+      "learning_rate": 8.290528061696761e-06,
+      "loss": 0.2137,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.8036940097808838,
+      "learning_rate": 8.261227065635162e-06,
+      "loss": 0.2277,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3488888888888889,
+      "grad_norm": 0.4736039936542511,
+      "learning_rate": 8.231729838147833e-06,
+      "loss": 0.2408,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3511111111111111,
+      "grad_norm": 0.649137556552887,
+      "learning_rate": 8.202038154113641e-06,
+      "loss": 0.2541,
+      "step": 1580
+    },
+    {
+      "epoch": 0.35333333333333333,
+      "grad_norm": 1.1798919439315796,
+      "learning_rate": 8.172153800112107e-06,
+      "loss": 0.2486,
+      "step": 1590
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.9178785085678101,
+      "learning_rate": 8.142078574315907e-06,
+      "loss": 0.2556,
+      "step": 1600
+    },
+    {
+      "epoch": 0.35777777777777775,
+      "grad_norm": 0.5806071162223816,
+      "learning_rate": 8.111814286382667e-06,
+      "loss": 0.2276,
+      "step": 1610
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.447551965713501,
+      "learning_rate": 8.081362757346083e-06,
+      "loss": 0.2315,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3622222222222222,
+      "grad_norm": 0.6877042055130005,
+      "learning_rate": 8.05072581950634e-06,
+      "loss": 0.2529,
+      "step": 1630
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 0.48793140053749084,
+      "learning_rate": 8.019905316319863e-06,
+      "loss": 0.2413,
+      "step": 1640
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.6241080164909363,
+      "learning_rate": 7.988903102288399e-06,
+      "loss": 0.1942,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3688888888888889,
+      "grad_norm": 0.5032159686088562,
+      "learning_rate": 7.95772104284742e-06,
+      "loss": 0.2577,
+      "step": 1660
+    },
+    {
+      "epoch": 0.3711111111111111,
+      "grad_norm": 0.8827240467071533,
+      "learning_rate": 7.92636101425389e-06,
+      "loss": 0.2464,
+      "step": 1670
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.8194811940193176,
+      "learning_rate": 7.894824903473356e-06,
+      "loss": 0.241,
+      "step": 1680
+    },
+    {
+      "epoch": 0.37555555555555553,
+      "grad_norm": 0.5342280268669128,
+      "learning_rate": 7.863114608066417e-06,
+      "loss": 0.2196,
+      "step": 1690
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.46870356798171997,
+      "learning_rate": 7.831232036074542e-06,
+      "loss": 0.2434,
+      "step": 1700
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.7307283282279968,
+      "learning_rate": 7.799179105905255e-06,
+      "loss": 0.2257,
+      "step": 1710
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 0.4963550567626953,
+      "learning_rate": 7.76695774621672e-06,
+      "loss": 0.2328,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3844444444444444,
+      "grad_norm": 0.5179299116134644,
+      "learning_rate": 7.734569895801675e-06,
+      "loss": 0.2271,
+      "step": 1730
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 0.8800008296966553,
+      "learning_rate": 7.702017503470773e-06,
+      "loss": 0.2355,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.5152933597564697,
+      "learning_rate": 7.669302527935334e-06,
+      "loss": 0.2525,
+      "step": 1750
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.6789291501045227,
+      "learning_rate": 7.636426937689476e-06,
+      "loss": 0.2195,
+      "step": 1760
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 0.5838199853897095,
+      "learning_rate": 7.603392710891665e-06,
+      "loss": 0.2435,
+      "step": 1770
+    },
+    {
+      "epoch": 0.39555555555555555,
+      "grad_norm": 1.0570043325424194,
+      "learning_rate": 7.570201835245703e-06,
+      "loss": 0.2358,
+      "step": 1780
+    },
+    {
+      "epoch": 0.3977777777777778,
+      "grad_norm": 0.5464975237846375,
+      "learning_rate": 7.536856307881106e-06,
+      "loss": 0.2385,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4945601224899292,
+      "learning_rate": 7.503358135232959e-06,
+      "loss": 0.2479,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4022222222222222,
+      "grad_norm": 0.9876905083656311,
+      "learning_rate": 7.469709332921155e-06,
+      "loss": 0.2276,
+      "step": 1810
+    },
+    {
+      "epoch": 0.40444444444444444,
+      "grad_norm": 0.7718654274940491,
+      "learning_rate": 7.435911925629146e-06,
+      "loss": 0.2405,
+      "step": 1820
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 0.8102084398269653,
+      "learning_rate": 7.401967946982089e-06,
+      "loss": 0.2408,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 0.4835777282714844,
+      "learning_rate": 7.3678794394245e-06,
+      "loss": 0.2338,
+      "step": 1840
+    },
+    {
+      "epoch": 0.4111111111111111,
+      "grad_norm": 0.6379567980766296,
+      "learning_rate": 7.333648454097347e-06,
+      "loss": 0.2465,
+      "step": 1850
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 0.5484440922737122,
+      "learning_rate": 7.299277050714631e-06,
+      "loss": 0.2121,
+      "step": 1860
+    },
+    {
+      "epoch": 0.41555555555555557,
+      "grad_norm": 0.5078845620155334,
+      "learning_rate": 7.264767297439455e-06,
+      "loss": 0.2035,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 0.8418991565704346,
+      "learning_rate": 7.230121270759583e-06,
+      "loss": 0.2338,
+      "step": 1880
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.859330415725708,
+      "learning_rate": 7.195341055362485e-06,
+      "loss": 0.2561,
+      "step": 1890
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.5570971369743347,
+      "learning_rate": 7.160428744009913e-06,
+      "loss": 0.2146,
+      "step": 1900
+    },
+    {
+      "epoch": 0.42444444444444446,
+      "grad_norm": 0.5831572413444519,
+      "learning_rate": 7.1253864374119615e-06,
+      "loss": 0.2328,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.5856032371520996,
+      "learning_rate": 7.090216244100683e-06,
+      "loss": 0.2428,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4288888888888889,
+      "grad_norm": 0.6182511448860168,
+      "learning_rate": 7.054920280303199e-06,
+      "loss": 0.2048,
+      "step": 1930
+    },
+    {
+      "epoch": 0.4311111111111111,
+      "grad_norm": 0.4959850013256073,
+      "learning_rate": 7.019500669814378e-06,
+      "loss": 0.2357,
+      "step": 1940
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.5951399207115173,
+      "learning_rate": 6.9839595438690345e-06,
+      "loss": 0.1973,
+      "step": 1950
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 0.5738755464553833,
+      "learning_rate": 6.948299041013695e-06,
+      "loss": 0.2388,
+      "step": 1960
+    },
+    {
+      "epoch": 0.43777777777777777,
+      "grad_norm": 0.7726308107376099,
+      "learning_rate": 6.912521306977922e-06,
+      "loss": 0.2317,
+      "step": 1970
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.6541021466255188,
+      "learning_rate": 6.876628494545198e-06,
+      "loss": 0.2288,
+      "step": 1980
+    },
+    {
+      "epoch": 0.44222222222222224,
+      "grad_norm": 0.4881785213947296,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 0.241,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.4665493965148926,
+      "learning_rate": 6.804506280114804e-06,
+      "loss": 0.223,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44666666666666666,
+      "grad_norm": 0.5558962821960449,
+      "learning_rate": 6.76828121778582e-06,
+      "loss": 0.226,
+      "step": 2010
+    },
+    {
+      "epoch": 0.4488888888888889,
+      "grad_norm": 0.5440465807914734,
+      "learning_rate": 6.7319497561361245e-06,
+      "loss": 0.2458,
+      "step": 2020
+    },
+    {
+      "epoch": 0.45111111111111113,
+      "grad_norm": 0.5264802575111389,
+      "learning_rate": 6.695514081267571e-06,
+      "loss": 0.2341,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.5955103635787964,
+      "learning_rate": 6.658976385552625e-06,
+      "loss": 0.2252,
+      "step": 2040
+    },
+    {
+      "epoch": 0.45555555555555555,
+      "grad_norm": 0.5731228590011597,
+      "learning_rate": 6.622338867502452e-06,
+      "loss": 0.238,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4577777777777778,
+      "grad_norm": 0.6660656332969666,
+      "learning_rate": 6.585603731634636e-06,
+      "loss": 0.2088,
+      "step": 2060
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5183016061782837,
+      "learning_rate": 6.548773188340523e-06,
+      "loss": 0.2048,
+      "step": 2070
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.5029473900794983,
+      "learning_rate": 6.5118494537522235e-06,
+      "loss": 0.2134,
+      "step": 2080
+    },
+    {
+      "epoch": 0.46444444444444444,
+      "grad_norm": 0.5297090411186218,
+      "learning_rate": 6.474834749609266e-06,
+      "loss": 0.2099,
+      "step": 2090
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.5621345043182373,
+      "learning_rate": 6.4377313031249085e-06,
+      "loss": 0.2318,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4688888888888889,
+      "grad_norm": 0.49249330163002014,
+      "learning_rate": 6.400541346852136e-06,
+      "loss": 0.2358,
+      "step": 2110
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 0.6385971903800964,
+      "learning_rate": 6.363267118549307e-06,
+      "loss": 0.2262,
+      "step": 2120
+    },
+    {
+      "epoch": 0.47333333333333333,
+      "grad_norm": 0.41663241386413574,
+      "learning_rate": 6.325910861045526e-06,
+      "loss": 0.2381,
+      "step": 2130
+    },
+    {
+      "epoch": 0.47555555555555556,
+      "grad_norm": 0.7673817276954651,
+      "learning_rate": 6.28847482210567e-06,
+      "loss": 0.2076,
+      "step": 2140
+    },
+    {
+      "epoch": 0.4777777777777778,
+      "grad_norm": 0.4361864924430847,
+      "learning_rate": 6.250961254295156e-06,
+      "loss": 0.2382,
+      "step": 2150
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.7437453866004944,
+      "learning_rate": 6.21337241484439e-06,
+      "loss": 0.2415,
+      "step": 2160
+    },
+    {
+      "epoch": 0.4822222222222222,
+      "grad_norm": 0.4662710130214691,
+      "learning_rate": 6.17571056551295e-06,
+      "loss": 0.2477,
+      "step": 2170
+    },
+    {
+      "epoch": 0.48444444444444446,
+      "grad_norm": 0.45837879180908203,
+      "learning_rate": 6.137977972453499e-06,
+      "loss": 0.2255,
+      "step": 2180
+    },
+    {
+      "epoch": 0.4866666666666667,
+      "grad_norm": 0.5218656063079834,
+      "learning_rate": 6.10017690607542e-06,
+      "loss": 0.2355,
+      "step": 2190
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.4350171685218811,
+      "learning_rate": 6.062309640908206e-06,
+      "loss": 0.2139,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4911111111111111,
+      "grad_norm": 1.2192610502243042,
+      "learning_rate": 6.024378455464603e-06,
+      "loss": 0.2186,
+      "step": 2210
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 0.5528021454811096,
+      "learning_rate": 5.986385632103505e-06,
+      "loss": 0.2279,
+      "step": 2220
+    },
+    {
+      "epoch": 0.4955555555555556,
+      "grad_norm": 0.5733168721199036,
+      "learning_rate": 5.948333456892624e-06,
+      "loss": 0.2171,
+      "step": 2230
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.7069255113601685,
+      "learning_rate": 5.910224219470935e-06,
+      "loss": 0.229,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5340228080749512,
+      "learning_rate": 5.872060212910903e-06,
+      "loss": 0.2229,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5022222222222222,
+      "grad_norm": 0.5726852416992188,
+      "learning_rate": 5.8338437335805124e-06,
+      "loss": 0.2516,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5044444444444445,
+      "grad_norm": 0.5481095314025879,
+      "learning_rate": 5.795577081005086e-06,
+      "loss": 0.211,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.7434238195419312,
+      "learning_rate": 5.757262557728927e-06,
+      "loss": 0.2389,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5088888888888888,
+      "grad_norm": 0.533612847328186,
+      "learning_rate": 5.718902469176765e-06,
+      "loss": 0.2153,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.4836199879646301,
+      "learning_rate": 5.680499123515039e-06,
+      "loss": 0.2392,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 0.5625936388969421,
+      "learning_rate": 5.6420548315130156e-06,
+      "loss": 0.2221,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.5190809965133667,
+      "learning_rate": 5.6035719064037446e-06,
+      "loss": 0.2116,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5177777777777778,
+      "grad_norm": 0.4456705152988434,
+      "learning_rate": 5.56505266374487e-06,
+      "loss": 0.2131,
+      "step": 2330
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.7487488985061646,
+      "learning_rate": 5.5264994212793e-06,
+      "loss": 0.2475,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5222222222222223,
+      "grad_norm": 0.4860404431819916,
+      "learning_rate": 5.487914498795748e-06,
+      "loss": 0.2404,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 0.5812284350395203,
+      "learning_rate": 5.4493002179891455e-06,
+      "loss": 0.2105,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 0.5378413200378418,
+      "learning_rate": 5.410658902320946e-06,
+      "loss": 0.2257,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5288888888888889,
+      "grad_norm": 0.47278687357902527,
+      "learning_rate": 5.371992876879318e-06,
+      "loss": 0.227,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5311111111111111,
+      "grad_norm": 0.516788125038147,
+      "learning_rate": 5.333304468239241e-06,
+      "loss": 0.2135,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.5576591491699219,
+      "learning_rate": 5.294596004322518e-06,
+      "loss": 0.263,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5355555555555556,
+      "grad_norm": 0.7135146856307983,
+      "learning_rate": 5.255869814257701e-06,
+      "loss": 0.2276,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5377777777777778,
+      "grad_norm": 0.6495805978775024,
+      "learning_rate": 5.217128228239934e-06,
+      "loss": 0.236,
+      "step": 2420
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8253788948059082,
+      "learning_rate": 5.178373577390763e-06,
+      "loss": 0.2305,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 0.8396733403205872,
+      "learning_rate": 5.139608193617846e-06,
+      "loss": 0.2433,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5444444444444444,
+      "grad_norm": 0.6592555046081543,
+      "learning_rate": 5.100834409474661e-06,
+      "loss": 0.2163,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.60608971118927,
+      "learning_rate": 5.062054558020145e-06,
+      "loss": 0.2463,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5488888888888889,
+      "grad_norm": 0.5089678168296814,
+      "learning_rate": 5.0232709726783065e-06,
+      "loss": 0.2316,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.49585267901420593,
+      "learning_rate": 4.984485987097829e-06,
+      "loss": 0.218,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 0.48399657011032104,
+      "learning_rate": 4.945701935011651e-06,
+      "loss": 0.2341,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.5765243768692017,
+      "learning_rate": 4.906921150096538e-06,
+      "loss": 0.2291,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5577777777777778,
+      "grad_norm": 0.6511385440826416,
+      "learning_rate": 4.868145965832667e-06,
+      "loss": 0.2011,
+      "step": 2510
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.4851745367050171,
+      "learning_rate": 4.8293787153632245e-06,
+      "loss": 0.2406,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5622222222222222,
+      "grad_norm": 0.53596431016922,
+      "learning_rate": 4.7906217313540035e-06,
+      "loss": 0.2127,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5644444444444444,
+      "grad_norm": 0.6848158836364746,
+      "learning_rate": 4.751877345853055e-06,
+      "loss": 0.2048,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.7368415594100952,
+      "learning_rate": 4.713147890150372e-06,
+      "loss": 0.2216,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.4864996373653412,
+      "learning_rate": 4.674435694637597e-06,
+      "loss": 0.2239,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5711111111111111,
+      "grad_norm": 0.5134068727493286,
+      "learning_rate": 4.635743088667815e-06,
+      "loss": 0.2374,
+      "step": 2570
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 0.4680314064025879,
+      "learning_rate": 4.597072400415383e-06,
+      "loss": 0.2167,
+      "step": 2580
+    },
+    {
+      "epoch": 0.5755555555555556,
+      "grad_norm": 0.5015770196914673,
+      "learning_rate": 4.5584259567358505e-06,
+      "loss": 0.2218,
+      "step": 2590
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.5194075107574463,
+      "learning_rate": 4.519806083025944e-06,
+      "loss": 0.201,
+      "step": 2600
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.43954020738601685,
+      "learning_rate": 4.481215103083646e-06,
+      "loss": 0.2307,
+      "step": 2610
+    },
+    {
+      "epoch": 0.5822222222222222,
+      "grad_norm": 0.6641078591346741,
+      "learning_rate": 4.442655338968373e-06,
+      "loss": 0.2511,
+      "step": 2620
+    },
+    {
+      "epoch": 0.5844444444444444,
+      "grad_norm": 0.6749869585037231,
+      "learning_rate": 4.404129110861254e-06,
+      "loss": 0.1974,
+      "step": 2630
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.7704310417175293,
+      "learning_rate": 4.365638736925512e-06,
+      "loss": 0.2257,
+      "step": 2640
+    },
+    {
+      "epoch": 0.5888888888888889,
+      "grad_norm": 0.7620184421539307,
+      "learning_rate": 4.3271865331670036e-06,
+      "loss": 0.2209,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5911111111111111,
+      "grad_norm": 0.6936331987380981,
+      "learning_rate": 4.288774813294833e-06,
+      "loss": 0.2169,
+      "step": 2660
+    },
+    {
+      "epoch": 0.5933333333333334,
+      "grad_norm": 0.7116475105285645,
+      "learning_rate": 4.2504058885821515e-06,
+      "loss": 0.237,
+      "step": 2670
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 0.5770586133003235,
+      "learning_rate": 4.212082067727079e-06,
+      "loss": 0.2445,
+      "step": 2680
+    },
+    {
+      "epoch": 0.5977777777777777,
+      "grad_norm": 0.7257152795791626,
+      "learning_rate": 4.173805656713793e-06,
+      "loss": 0.2176,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.807619571685791,
+      "learning_rate": 4.13557895867377e-06,
+      "loss": 0.2324,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6022222222222222,
+      "grad_norm": 0.5045626163482666,
+      "learning_rate": 4.0974042737472005e-06,
+      "loss": 0.2289,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.6968899965286255,
+      "learning_rate": 4.0592838989446e-06,
+      "loss": 0.2551,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6066666666666667,
+      "grad_norm": 0.7338456511497498,
+      "learning_rate": 4.021220128008584e-06,
+      "loss": 0.2099,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6088888888888889,
+      "grad_norm": 0.616070032119751,
+      "learning_rate": 3.983215251275847e-06,
+      "loss": 0.2261,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.466467022895813,
+      "learning_rate": 3.945271555539373e-06,
+      "loss": 0.2224,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.7739804983139038,
+      "learning_rate": 3.90739132391081e-06,
+      "loss": 0.2198,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6155555555555555,
+      "grad_norm": 0.5310224294662476,
+      "learning_rate": 3.869576835683109e-06,
+      "loss": 0.2299,
+      "step": 2770
+    },
+    {
+      "epoch": 0.6177777777777778,
+      "grad_norm": 0.5864322781562805,
+      "learning_rate": 3.831830366193367e-06,
+      "loss": 0.2031,
+      "step": 2780
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.503046989440918,
+      "learning_rate": 3.7941541866859337e-06,
+      "loss": 0.211,
+      "step": 2790
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.5578895211219788,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 0.1965,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6244444444444445,
+      "grad_norm": 0.5403327345848083,
+      "learning_rate": 3.7190217613118385e-06,
+      "loss": 0.249,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 0.48486825823783875,
+      "learning_rate": 3.6815700362413855e-06,
+      "loss": 0.2194,
+      "step": 2820
+    },
+    {
+      "epoch": 0.6288888888888889,
+      "grad_norm": 1.0061817169189453,
+      "learning_rate": 3.6441976424736315e-06,
+      "loss": 0.2367,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 0.6847549676895142,
+      "learning_rate": 3.6069068287443932e-06,
+      "loss": 0.2228,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.6903135180473328,
+      "learning_rate": 3.569699838880735e-06,
+      "loss": 0.2257,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6355555555555555,
+      "grad_norm": 0.5248664021492004,
+      "learning_rate": 3.5325789116659493e-06,
+      "loss": 0.215,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6377777777777778,
+      "grad_norm": 0.6344507932662964,
+      "learning_rate": 3.495546280704849e-06,
+      "loss": 0.2207,
+      "step": 2870
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6156448125839233,
+      "learning_rate": 3.458604174289367e-06,
+      "loss": 0.2032,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6422222222222222,
+      "grad_norm": 0.5697433948516846,
+      "learning_rate": 3.4217548152644887e-06,
+      "loss": 0.2092,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 0.7283775806427002,
+      "learning_rate": 3.3850004208944838e-06,
+      "loss": 0.2349,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6466666666666666,
+      "grad_norm": 0.6243658065795898,
+      "learning_rate": 3.3483432027295025e-06,
+      "loss": 0.2526,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 0.6870917677879333,
+      "learning_rate": 3.311785366472506e-06,
+      "loss": 0.2163,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6511111111111111,
+      "grad_norm": 0.5320258736610413,
+      "learning_rate": 3.275329111846536e-06,
+      "loss": 0.2186,
+      "step": 2930
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 0.7291749715805054,
+      "learning_rate": 3.238976632462364e-06,
+      "loss": 0.2464,
+      "step": 2940
+    },
+    {
+      "epoch": 0.6555555555555556,
+      "grad_norm": 0.7033562660217285,
+      "learning_rate": 3.2027301156865015e-06,
+      "loss": 0.233,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.6965799331665039,
+      "learning_rate": 3.166591742509575e-06,
+      "loss": 0.2112,
+      "step": 2960
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.5640952587127686,
+      "learning_rate": 3.130563687415098e-06,
+      "loss": 0.243,
+      "step": 2970
+    },
+    {
+      "epoch": 0.6622222222222223,
+      "grad_norm": 0.4882139265537262,
+      "learning_rate": 3.09464811824863e-06,
+      "loss": 0.2196,
+      "step": 2980
+    },
+    {
+      "epoch": 0.6644444444444444,
+      "grad_norm": 0.3836524486541748,
+      "learning_rate": 3.05884719608734e-06,
+      "loss": 0.2346,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.6721084117889404,
+      "learning_rate": 3.0231630751099628e-06,
+      "loss": 0.2429,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6688888888888889,
+      "grad_norm": 0.6006462574005127,
+      "learning_rate": 2.9875979024671846e-06,
+      "loss": 0.2472,
+      "step": 3010
+    },
+    {
+      "epoch": 0.6711111111111111,
+      "grad_norm": 0.5289439558982849,
+      "learning_rate": 2.9521538181524497e-06,
+      "loss": 0.2321,
+      "step": 3020
+    },
+    {
+      "epoch": 0.6733333333333333,
+      "grad_norm": 0.6664814352989197,
+      "learning_rate": 2.9168329548731873e-06,
+      "loss": 0.2245,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.6002072095870972,
+      "learning_rate": 2.8816374379224932e-06,
+      "loss": 0.253,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6777777777777778,
+      "grad_norm": 0.6766952276229858,
+      "learning_rate": 2.846569385051241e-06,
+      "loss": 0.2442,
+      "step": 3050
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5962438583374023,
+      "learning_rate": 2.8116309063406593e-06,
+      "loss": 0.2275,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6822222222222222,
+      "grad_norm": 0.5721535086631775,
+      "learning_rate": 2.776824104075364e-06,
+      "loss": 0.1964,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 1.182945728302002,
+      "learning_rate": 2.742151072616861e-06,
+      "loss": 0.2401,
+      "step": 3080
+    },
+    {
+      "epoch": 0.6866666666666666,
+      "grad_norm": 0.6877291202545166,
+      "learning_rate": 2.707613898277533e-06,
+      "loss": 0.2249,
+      "step": 3090
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.5899962782859802,
+      "learning_rate": 2.6732146591950924e-06,
+      "loss": 0.2354,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6911111111111111,
+      "grad_norm": 0.8089621067047119,
+      "learning_rate": 2.638955425207545e-06,
+      "loss": 0.2466,
+      "step": 3110
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.802108883857727,
+      "learning_rate": 2.604838257728648e-06,
+      "loss": 0.2209,
+      "step": 3120
+    },
+    {
+      "epoch": 0.6955555555555556,
+      "grad_norm": 0.5903416872024536,
+      "learning_rate": 2.5708652096238674e-06,
+      "loss": 0.2174,
+      "step": 3130
+    },
+    {
+      "epoch": 0.6977777777777778,
+      "grad_norm": 0.7151070237159729,
+      "learning_rate": 2.5370383250868493e-06,
+      "loss": 0.2392,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5183787941932678,
+      "learning_rate": 2.503359639516437e-06,
+      "loss": 0.229,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 0.4839763045310974,
+      "learning_rate": 2.469831179394182e-06,
+      "loss": 0.2331,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7044444444444444,
+      "grad_norm": 0.6388260722160339,
+      "learning_rate": 2.4364549621624124e-06,
+      "loss": 0.2457,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 1.7699531316757202,
+      "learning_rate": 2.40323299610285e-06,
+      "loss": 0.2145,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7088888888888889,
+      "grad_norm": 0.7154451608657837,
+      "learning_rate": 2.3701672802157567e-06,
+      "loss": 0.2346,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.649513840675354,
+      "learning_rate": 2.3372598040996614e-06,
+      "loss": 0.2329,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 1.1018325090408325,
+      "learning_rate": 2.304512547831639e-06,
+      "loss": 0.2247,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7155555555555555,
+      "grad_norm": 0.6996004581451416,
+      "learning_rate": 2.2719274818481767e-06,
+      "loss": 0.2366,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7177777777777777,
+      "grad_norm": 0.5865346193313599,
+      "learning_rate": 2.2395065668265943e-06,
+      "loss": 0.255,
+      "step": 3230
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.744001567363739,
+      "learning_rate": 2.2072517535670795e-06,
+      "loss": 0.2356,
+      "step": 3240
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 0.5543341040611267,
+      "learning_rate": 2.175164982875311e-06,
+      "loss": 0.2355,
+      "step": 3250
+    },
+    {
+      "epoch": 0.7244444444444444,
+      "grad_norm": 0.5818354487419128,
+      "learning_rate": 2.1432481854456645e-06,
+      "loss": 0.2191,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 0.4707711637020111,
+      "learning_rate": 2.1115032817450476e-06,
+      "loss": 0.2363,
+      "step": 3270
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.7600942850112915,
+      "learning_rate": 2.0799321818973488e-06,
+      "loss": 0.246,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7311111111111112,
+      "grad_norm": 0.8043562173843384,
+      "learning_rate": 2.0485367855684932e-06,
+      "loss": 0.2218,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.7840522527694702,
+      "learning_rate": 2.0173189818521442e-06,
+      "loss": 0.2212,
+      "step": 3300
+    },
+    {
+      "epoch": 0.7355555555555555,
+      "grad_norm": 0.679488480091095,
+      "learning_rate": 1.9862806491560315e-06,
+      "loss": 0.2597,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 1.9832565784454346,
+      "learning_rate": 1.955423655088928e-06,
+      "loss": 0.2315,
+      "step": 3320
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.7567440271377563,
+      "learning_rate": 1.9247498563482724e-06,
+      "loss": 0.2135,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7422222222222222,
+      "grad_norm": 0.6107955574989319,
+      "learning_rate": 1.8942610986084487e-06,
+      "loss": 0.2125,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7444444444444445,
+      "grad_norm": 0.9295490980148315,
+      "learning_rate": 1.8639592164097348e-06,
+      "loss": 0.216,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.6072530746459961,
+      "learning_rate": 1.8338460330479102e-06,
+      "loss": 0.2177,
+      "step": 3360
+    },
+    {
+      "epoch": 0.7488888888888889,
+      "grad_norm": 0.6220813393592834,
+      "learning_rate": 1.8039233604645468e-06,
+      "loss": 0.2192,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7511111111111111,
+      "grad_norm": 1.2467488050460815,
+      "learning_rate": 1.7741929991379914e-06,
+      "loss": 0.217,
+      "step": 3380
+    },
+    {
+      "epoch": 0.7533333333333333,
+      "grad_norm": 0.45881083607673645,
+      "learning_rate": 1.7446567379750167e-06,
+      "loss": 0.2528,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.4624572992324829,
+      "learning_rate": 1.7153163542031881e-06,
+      "loss": 0.2287,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7577777777777778,
+      "grad_norm": 0.6549725532531738,
+      "learning_rate": 1.686173613263925e-06,
+      "loss": 0.2085,
+      "step": 3410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.2874345779418945,
+      "learning_rate": 1.6572302687062718e-06,
+      "loss": 0.2186,
+      "step": 3420
+    },
+    {
+      "epoch": 0.7622222222222222,
+      "grad_norm": 0.5766834616661072,
+      "learning_rate": 1.6284880620813847e-06,
+      "loss": 0.2193,
+      "step": 3430
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.8272707462310791,
+      "learning_rate": 1.5999487228377398e-06,
+      "loss": 0.2367,
+      "step": 3440
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.8264459371566772,
+      "learning_rate": 1.5716139682170778e-06,
+      "loss": 0.2349,
+      "step": 3450
+    },
+    {
+      "epoch": 0.7688888888888888,
+      "grad_norm": 0.7468411922454834,
+      "learning_rate": 1.5434855031510626e-06,
+      "loss": 0.2352,
+      "step": 3460
+    },
+    {
+      "epoch": 0.7711111111111111,
+      "grad_norm": 0.8860440254211426,
+      "learning_rate": 1.515565020158703e-06,
+      "loss": 0.2152,
+      "step": 3470
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.9292101860046387,
+      "learning_rate": 1.4878541992445144e-06,
+      "loss": 0.2208,
+      "step": 3480
+    },
+    {
+      "epoch": 0.7755555555555556,
+      "grad_norm": 0.6765230298042297,
+      "learning_rate": 1.4603547077974217e-06,
+      "loss": 0.2259,
+      "step": 3490
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.6336573362350464,
+      "learning_rate": 1.4330682004904367e-06,
+      "loss": 0.2117,
+      "step": 3500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.6666709184646606,
+      "learning_rate": 1.4059963191810955e-06,
+      "loss": 0.2341,
+      "step": 3510
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.6277806162834167,
+      "learning_rate": 1.3791406928126638e-06,
+      "loss": 0.2307,
+      "step": 3520
+    },
+    {
+      "epoch": 0.7844444444444445,
+      "grad_norm": 0.8261449933052063,
+      "learning_rate": 1.352502937316122e-06,
+      "loss": 0.207,
+      "step": 3530
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 0.808182418346405,
+      "learning_rate": 1.3260846555129325e-06,
+      "loss": 0.2428,
+      "step": 3540
+    },
+    {
+      "epoch": 0.7888888888888889,
+      "grad_norm": 0.6502374410629272,
+      "learning_rate": 1.2998874370186026e-06,
+      "loss": 0.2203,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 0.6424347758293152,
+      "learning_rate": 1.273912858147024e-06,
+      "loss": 0.2308,
+      "step": 3560
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.8087573051452637,
+      "learning_rate": 1.2481624818156319e-06,
+      "loss": 0.2193,
+      "step": 3570
+    },
+    {
+      "epoch": 0.7955555555555556,
+      "grad_norm": 1.0368999242782593,
+      "learning_rate": 1.2226378574513654e-06,
+      "loss": 0.2269,
+      "step": 3580
+    },
+    {
+      "epoch": 0.7977777777777778,
+      "grad_norm": 0.6648699045181274,
+      "learning_rate": 1.1973405208974282e-06,
+      "loss": 0.1956,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8443555235862732,
+      "learning_rate": 1.1722719943208822e-06,
+      "loss": 0.2116,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8022222222222222,
+      "grad_norm": 0.6978488564491272,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 0.222,
+      "step": 3610
+    },
+    {
+      "epoch": 0.8044444444444444,
+      "grad_norm": 0.6660436391830444,
+      "learning_rate": 1.1228273908387756e-06,
+      "loss": 0.2435,
+      "step": 3620
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 0.7070465087890625,
+      "learning_rate": 1.0984542890664513e-06,
+      "loss": 0.2608,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 1.1687719821929932,
+      "learning_rate": 1.0743159473589738e-06,
+      "loss": 0.2203,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8111111111111111,
+      "grad_norm": 0.6448286175727844,
+      "learning_rate": 1.050413818145481e-06,
+      "loss": 0.2103,
+      "step": 3650
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 0.8359683156013489,
+      "learning_rate": 1.0267493396419559e-06,
+      "loss": 0.2171,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8155555555555556,
+      "grad_norm": 0.9623379111289978,
+      "learning_rate": 1.0033239357646913e-06,
+      "loss": 0.2368,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.1580039262771606,
+      "learning_rate": 9.801390160446135e-07,
+      "loss": 0.2174,
+      "step": 3680
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.7610867023468018,
+      "learning_rate": 9.571959755424643e-07,
+      "loss": 0.2394,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.9653570652008057,
+      "learning_rate": 9.344961947648624e-07,
+      "loss": 0.215,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8244444444444444,
+      "grad_norm": 0.7693958282470703,
+      "learning_rate": 9.120410395812346e-07,
+      "loss": 0.2295,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 1.1095337867736816,
+      "learning_rate": 8.898318611416329e-07,
+      "loss": 0.2306,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8288888888888889,
+      "grad_norm": 0.956220805644989,
+      "learning_rate": 8.678699957954323e-07,
+      "loss": 0.2167,
+      "step": 3730
+    },
+    {
+      "epoch": 0.8311111111111111,
+      "grad_norm": 0.5566705465316772,
+      "learning_rate": 8.461567650109187e-07,
+      "loss": 0.224,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.8079343438148499,
+      "learning_rate": 8.246934752957835e-07,
+      "loss": 0.2318,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.6054255366325378,
+      "learning_rate": 8.034814181184996e-07,
+      "loss": 0.1978,
+      "step": 3760
+    },
+    {
+      "epoch": 0.8377777777777777,
+      "grad_norm": 0.8135355114936829,
+      "learning_rate": 7.825218698306164e-07,
+      "loss": 0.2306,
+      "step": 3770
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.7578747272491455,
+      "learning_rate": 7.618160915899641e-07,
+      "loss": 0.222,
+      "step": 3780
+    },
+    {
+      "epoch": 0.8422222222222222,
+      "grad_norm": 1.038500189781189,
+      "learning_rate": 7.413653292847617e-07,
+      "loss": 0.2112,
+      "step": 3790
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.9095117449760437,
+      "learning_rate": 7.211708134586565e-07,
+      "loss": 0.2598,
+      "step": 3800
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 0.7200757265090942,
+      "learning_rate": 7.012337592366764e-07,
+      "loss": 0.2399,
+      "step": 3810
+    },
+    {
+      "epoch": 0.8488888888888889,
+      "grad_norm": 0.8625208735466003,
+      "learning_rate": 6.815553662521185e-07,
+      "loss": 0.2323,
+      "step": 3820
+    },
+    {
+      "epoch": 0.8511111111111112,
+      "grad_norm": 0.47625356912612915,
+      "learning_rate": 6.621368185743626e-07,
+      "loss": 0.2349,
+      "step": 3830
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.0169074535369873,
+      "learning_rate": 6.429792846376259e-07,
+      "loss": 0.2107,
+      "step": 3840
+    },
+    {
+      "epoch": 0.8555555555555555,
+      "grad_norm": 1.0716207027435303,
+      "learning_rate": 6.240839171706608e-07,
+      "loss": 0.2402,
+      "step": 3850
+    },
+    {
+      "epoch": 0.8577777777777778,
+      "grad_norm": 0.856113851070404,
+      "learning_rate": 6.054518531273861e-07,
+      "loss": 0.213,
+      "step": 3860
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.8451377749443054,
+      "learning_rate": 5.870842136184807e-07,
+      "loss": 0.2042,
+      "step": 3870
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 0.897478461265564,
+      "learning_rate": 5.689821038439264e-07,
+      "loss": 0.2422,
+      "step": 3880
+    },
+    {
+      "epoch": 0.8644444444444445,
+      "grad_norm": 0.956400454044342,
+      "learning_rate": 5.51146613026502e-07,
+      "loss": 0.1987,
+      "step": 3890
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 1.6359968185424805,
+      "learning_rate": 5.335788143462472e-07,
+      "loss": 0.2343,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8688888888888889,
+      "grad_norm": 0.6755963563919067,
+      "learning_rate": 5.162797648758877e-07,
+      "loss": 0.2159,
+      "step": 3910
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.2626124620437622,
+      "learning_rate": 4.992505055172287e-07,
+      "loss": 0.1967,
+      "step": 3920
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 0.9154727458953857,
+      "learning_rate": 4.824920609385242e-07,
+      "loss": 0.2158,
+      "step": 3930
+    },
+    {
+      "epoch": 0.8755555555555555,
+      "grad_norm": 0.5624186396598816,
+      "learning_rate": 4.6600543951281995e-07,
+      "loss": 0.2359,
+      "step": 3940
+    },
+    {
+      "epoch": 0.8777777777777778,
+      "grad_norm": 0.7864906191825867,
+      "learning_rate": 4.4979163325728324e-07,
+      "loss": 0.2361,
+      "step": 3950
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.7543439269065857,
+      "learning_rate": 4.3385161777350527e-07,
+      "loss": 0.2337,
+      "step": 3960
+    },
+    {
+      "epoch": 0.8822222222222222,
+      "grad_norm": 0.686770498752594,
+      "learning_rate": 4.1818635218880186e-07,
+      "loss": 0.2451,
+      "step": 3970
+    },
+    {
+      "epoch": 0.8844444444444445,
+      "grad_norm": 0.6183385848999023,
+      "learning_rate": 4.027967790985038e-07,
+      "loss": 0.2168,
+      "step": 3980
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.7445261478424072,
+      "learning_rate": 3.876838245092357e-07,
+      "loss": 0.25,
+      "step": 3990
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.6854656934738159,
+      "learning_rate": 3.728483977831998e-07,
+      "loss": 0.221,
+      "step": 4000
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.064013055405274e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

mixed_all_v5_300k_noreach/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac95c64d87e1e02e6baaf13a84a2f385efbf3a6ddc757c482437a4f9df7fa99c
+size 7416