Upload without hidden files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+datasets: boot_osworld_vscode
+library_name: transformers
+tags:
+- generated_from_trainer
+- R1-V
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [None](https://huggingface.co/None) on the [boot_osworld_vscode](https://huggingface.co/datasets/boot_osworld_vscode) dataset.
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.17.0
+- Transformers: 4.51.3
+- Pytorch: 2.6.0
+- Datasets: 3.5.1
+- Tokenizers: 0.21.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

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
+}

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 %}"
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 64,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "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": "4.51.3",
+  "use_cache": true,
+  "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": 3456,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 5120,
+    "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
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "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": "4.51.3",
+  "use_cache": false
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3c5530a78787633441e70d9d823f203ae4dfbe24af1d8178376dbf55c0ec92
+size 4958700928

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4465fdc5a5864493dbc1d48b358710339041afb5120384e4700b18efb7d0923
+size 4928488272

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5eff31953a2988a2ea2fd2a585ac53db5dc9d66151f0dd59b8d1a846856836
+size 4876059368

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a83110daca67bf50de4fa12ea14c61b49110aa5769eb6d6c5f82583ab3da51a
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1819e41d0e4823525d961f4a83826711eec903df0921d43fc30d3db2876d66f0
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98931f3dc22162514662b32c54e3026fe4c576debf7996faf61396dbf8b1a125
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044f0bddf632aa6ffdb195e8a162d20b48018dd407e97a0ea65d29b5ff62783e
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699e722df8bf352ba125a975afbfc82a5c56f9c359df5b7c7118703c2e9a6f47
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b3e93677c40a89d7587ebcb9b307b20d953cccdd3e4ddce8fed0acc4e1e554
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3b37a098a1954a8c0a481baa789ecacc2fadf192994365f88b81fc6481c9ce
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d56f2cb516152302ae143ca91f278eb7001c50a47d46c037acd05c39e9260df
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e8a061d685574cc35f68a365512c283007944a23e72d0636b97d6571461aaf
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de3febd28d4a7ef8b370b4cfed8f2d924f4de308d69739ef9f2528dd3319bc0
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb43cc12853b36230573c5622fee7a448e9c8f9d0d0db4422bb52b11e51e283
+size 3381725320

model.safetensors.index.json

@@ -0,0 +1,1168 @@
+{
+  "metadata": {
+    "total_size": 66905436672
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00014.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00014.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00014.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00014.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00014.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0c439f7be467bf47d12a7e6f9adc6116201056fc60c67f431c679b7c16afc8
+size 11422064

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2113 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.602150537634408,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.043010752688172046,
+      "grad_norm": 11.91717546170225,
+      "learning_rate": 0.0,
+      "loss": 0.7999,
+      "mean_token_accuracy": 0.7625279724597931,
+      "num_tokens": 367812.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 9.023052509105142,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 0.8777,
+      "mean_token_accuracy": 0.7521283626556396,
+      "num_tokens": 746486.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 8.573471835574493,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.8113,
+      "mean_token_accuracy": 0.749506875872612,
+      "num_tokens": 1126566.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 5.577877324067109,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.7698,
+      "mean_token_accuracy": 0.7678339183330536,
+      "num_tokens": 1507062.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.21505376344086022,
+      "grad_norm": 4.129947299735385,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.7601,
+      "mean_token_accuracy": 0.7700327038764954,
+      "num_tokens": 1881779.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 3.4130681291525984,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.7044,
+      "mean_token_accuracy": 0.7722686380147934,
+      "num_tokens": 2265581.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.3010752688172043,
+      "grad_norm": 2.9935342196668655,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.66,
+      "mean_token_accuracy": 0.7871796786785126,
+      "num_tokens": 2646672.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 2.4639857428718863,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.6528,
+      "mean_token_accuracy": 0.7861378192901611,
+      "num_tokens": 3024415.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 2.1893799102976637,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.6118,
+      "mean_token_accuracy": 0.7930850088596344,
+      "num_tokens": 3400301.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 2.186514396506674,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.589,
+      "mean_token_accuracy": 0.798459991812706,
+      "num_tokens": 3782217.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.4731182795698925,
+      "grad_norm": 3.0465126347830602,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.6752,
+      "mean_token_accuracy": 0.7804096639156342,
+      "num_tokens": 4150420.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 2.6537477460552275,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.6027,
+      "mean_token_accuracy": 0.7908397912979126,
+      "num_tokens": 4524870.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.5591397849462365,
+      "grad_norm": 2.396118650881142,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.5859,
+      "mean_token_accuracy": 0.792891800403595,
+      "num_tokens": 4916036.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 2.2226168829192114,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.5514,
+      "mean_token_accuracy": 0.8134036660194397,
+      "num_tokens": 5284361.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 1.8673665641432782,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.5486,
+      "mean_token_accuracy": 0.8076689690351486,
+      "num_tokens": 5648932.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 1.8442596020009865,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.5263,
+      "mean_token_accuracy": 0.8252855390310287,
+      "num_tokens": 6013624.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.7311827956989247,
+      "grad_norm": 1.7829423593903526,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.5096,
+      "mean_token_accuracy": 0.8202553987503052,
+      "num_tokens": 6392059.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 1.8090352579295244,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.521,
+      "mean_token_accuracy": 0.8225749135017395,
+      "num_tokens": 6790097.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.8172043010752689,
+      "grad_norm": 1.75919933696252,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.4948,
+      "mean_token_accuracy": 0.828051283955574,
+      "num_tokens": 7160612.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 1.9385645040102704,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.5251,
+      "mean_token_accuracy": 0.8155874758958817,
+      "num_tokens": 7527524.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 1.8027184161622232,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.5057,
+      "mean_token_accuracy": 0.8297092467546463,
+      "num_tokens": 7888136.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 2.1820648482478187,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.5036,
+      "mean_token_accuracy": 0.8194401413202286,
+      "num_tokens": 8267314.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.989247311827957,
+      "grad_norm": 1.9518940278276342,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.4965,
+      "mean_token_accuracy": 0.8308457583189011,
+      "num_tokens": 8644626.0,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9518940278276342,
+      "learning_rate": 2e-05,
+      "loss": 0.0981,
+      "mean_token_accuracy": 0.8572691082954407,
+      "num_tokens": 8735951.0,
+      "step": 24
+    },
+    {
+      "epoch": 1.043010752688172,
+      "grad_norm": 1.658616504963653,
+      "learning_rate": 1.999884834944106e-05,
+      "loss": 0.3613,
+      "mean_token_accuracy": 0.8678812235593796,
+      "num_tokens": 9111064.0,
+      "step": 25
+    },
+    {
+      "epoch": 1.086021505376344,
+      "grad_norm": 1.6457610214496745,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.3551,
+      "mean_token_accuracy": 0.8692608177661896,
+      "num_tokens": 9496130.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 3.5904835403286754,
+      "learning_rate": 1.9989636736467278e-05,
+      "loss": 0.3695,
+      "mean_token_accuracy": 0.866924524307251,
+      "num_tokens": 9858972.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.1720430107526882,
+      "grad_norm": 1.7874385949477343,
+      "learning_rate": 1.9981578895764272e-05,
+      "loss": 0.3212,
+      "mean_token_accuracy": 0.890799954533577,
+      "num_tokens": 10231593.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.2150537634408602,
+      "grad_norm": 1.8049361403495439,
+      "learning_rate": 1.9971221996878395e-05,
+      "loss": 0.3554,
+      "mean_token_accuracy": 0.8701900094747543,
+      "num_tokens": 10601477.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 1.3711396350791194,
+      "learning_rate": 1.9958568425315316e-05,
+      "loss": 0.309,
+      "mean_token_accuracy": 0.8979966044425964,
+      "num_tokens": 10971400.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.3010752688172043,
+      "grad_norm": 1.5009618715368216,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.3301,
+      "mean_token_accuracy": 0.8754479885101318,
+      "num_tokens": 11338917.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.3440860215053765,
+      "grad_norm": 1.4417013210198348,
+      "learning_rate": 1.9926383450473344e-05,
+      "loss": 0.2909,
+      "mean_token_accuracy": 0.8934924155473709,
+      "num_tokens": 11708711.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 1.3285539132923128,
+      "learning_rate": 1.9906859460363307e-05,
+      "loss": 0.3018,
+      "mean_token_accuracy": 0.8906232416629791,
+      "num_tokens": 12088883.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.4301075268817205,
+      "grad_norm": 1.5218190255666082,
+      "learning_rate": 1.9885053622206305e-05,
+      "loss": 0.3363,
+      "mean_token_accuracy": 0.8796575218439102,
+      "num_tokens": 12468165.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.4731182795698925,
+      "grad_norm": 1.3816402287843272,
+      "learning_rate": 1.986097095854347e-05,
+      "loss": 0.3157,
+      "mean_token_accuracy": 0.8860495537519455,
+      "num_tokens": 12841352.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 1.442754299402919,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.3211,
+      "mean_token_accuracy": 0.8844448328018188,
+      "num_tokens": 13227719.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.5591397849462365,
+      "grad_norm": 1.4155340183010523,
+      "learning_rate": 1.9805997865694616e-05,
+      "loss": 0.3453,
+      "mean_token_accuracy": 0.8787361979484558,
+      "num_tokens": 13607472.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.6021505376344085,
+      "grad_norm": 1.1437615335312725,
+      "learning_rate": 1.9775120098467212e-05,
+      "loss": 0.2762,
+      "mean_token_accuracy": 0.9029232263565063,
+      "num_tokens": 13982708.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.6451612903225805,
+      "grad_norm": 1.3406964229739868,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 0.2998,
+      "mean_token_accuracy": 0.8943506330251694,
+      "num_tokens": 14364424.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.6881720430107527,
+      "grad_norm": 1.25822076002706,
+      "learning_rate": 1.970661768116622e-05,
+      "loss": 0.2537,
+      "mean_token_accuracy": 0.9153124392032623,
+      "num_tokens": 14755621.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.7311827956989247,
+      "grad_norm": 1.1260474975551218,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.2936,
+      "mean_token_accuracy": 0.8934088349342346,
+      "num_tokens": 15127506.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 1.1356922171937402,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.2639,
+      "mean_token_accuracy": 0.9112239480018616,
+      "num_tokens": 15503327.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.817204301075269,
+      "grad_norm": 1.1298046162246171,
+      "learning_rate": 1.9587119049229558e-05,
+      "loss": 0.29,
+      "mean_token_accuracy": 0.8936085551977158,
+      "num_tokens": 15880530.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.860215053763441,
+      "grad_norm": 1.1389639144335877,
+      "learning_rate": 1.954285702277879e-05,
+      "loss": 0.2934,
+      "mean_token_accuracy": 0.8923312425613403,
+      "num_tokens": 16263155.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.903225806451613,
+      "grad_norm": 1.0066342748134163,
+      "learning_rate": 1.9496396989003195e-05,
+      "loss": 0.2798,
+      "mean_token_accuracy": 0.8991601765155792,
+      "num_tokens": 16634276.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.946236559139785,
+      "grad_norm": 1.2385856620277536,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.3036,
+      "mean_token_accuracy": 0.8929028362035751,
+      "num_tokens": 17013425.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.989247311827957,
+      "grad_norm": 1.0574616204979852,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2916,
+      "mean_token_accuracy": 0.8939765691757202,
+      "num_tokens": 17380847.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0574616204979852,
+      "learning_rate": 1.9343938371606714e-05,
+      "loss": 0.0465,
+      "mean_token_accuracy": 0.9277108311653137,
+      "num_tokens": 17474187.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.043010752688172,
+      "grad_norm": 1.1539619815555024,
+      "learning_rate": 1.9288798344984673e-05,
+      "loss": 0.1697,
+      "mean_token_accuracy": 0.9405381679534912,
+      "num_tokens": 17848143.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.086021505376344,
+      "grad_norm": 0.9946315524935219,
+      "learning_rate": 1.9231518828401458e-05,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.946861207485199,
+      "num_tokens": 18231846.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": 1.0205876962667297,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.1631,
+      "mean_token_accuracy": 0.9437925517559052,
+      "num_tokens": 18629481.0,
+      "step": 51
+    },
+    {
+      "epoch": 2.172043010752688,
+      "grad_norm": 1.2180236071671326,
+      "learning_rate": 1.911059458789152e-05,
+      "loss": 0.1596,
+      "mean_token_accuracy": 0.9489908963441849,
+      "num_tokens": 19012798.0,
+      "step": 52
+    },
+    {
+      "epoch": 2.21505376344086,
+      "grad_norm": 1.1932774403236657,
+      "learning_rate": 1.9046977716458627e-05,
+      "loss": 0.1524,
+      "mean_token_accuracy": 0.9486334323883057,
+      "num_tokens": 19397188.0,
+      "step": 53
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 1.1190279919994257,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 0.1767,
+      "mean_token_accuracy": 0.9350408464670181,
+      "num_tokens": 19779411.0,
+      "step": 54
+    },
+    {
+      "epoch": 2.3010752688172045,
+      "grad_norm": 1.0935887572069407,
+      "learning_rate": 1.891350773226754e-05,
+      "loss": 0.1575,
+      "mean_token_accuracy": 0.9455375522375107,
+      "num_tokens": 20148217.0,
+      "step": 55
+    },
+    {
+      "epoch": 2.3440860215053765,
+      "grad_norm": 0.8268906453812284,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.1495,
+      "mean_token_accuracy": 0.9489219486713409,
+      "num_tokens": 20517539.0,
+      "step": 56
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 0.8463600848872256,
+      "learning_rate": 1.8771826024025944e-05,
+      "loss": 0.1625,
+      "mean_token_accuracy": 0.9414703994989395,
+      "num_tokens": 20886139.0,
+      "step": 57
+    },
+    {
+      "epoch": 2.4301075268817205,
+      "grad_norm": 0.8514202559815353,
+      "learning_rate": 1.8697946270717468e-05,
+      "loss": 0.1444,
+      "mean_token_accuracy": 0.9490186870098114,
+      "num_tokens": 21255999.0,
+      "step": 58
+    },
+    {
+      "epoch": 2.4731182795698925,
+      "grad_norm": 0.8543888251991751,
+      "learning_rate": 1.8622063118472135e-05,
+      "loss": 0.1714,
+      "mean_token_accuracy": 0.9381113350391388,
+      "num_tokens": 21626463.0,
+      "step": 59
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": 0.9035063674891346,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.1843,
+      "mean_token_accuracy": 0.9337188005447388,
+      "num_tokens": 21991893.0,
+      "step": 60
+    },
+    {
+      "epoch": 2.5591397849462365,
+      "grad_norm": 0.8418292533035925,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.1526,
+      "mean_token_accuracy": 0.9460138976573944,
+      "num_tokens": 22361724.0,
+      "step": 61
+    },
+    {
+      "epoch": 2.6021505376344085,
+      "grad_norm": 0.7418502959925466,
+      "learning_rate": 1.8382570332820045e-05,
+      "loss": 0.142,
+      "mean_token_accuracy": 0.9545767903327942,
+      "num_tokens": 22736647.0,
+      "step": 62
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": 0.9322325837904922,
+      "learning_rate": 1.8298852919990254e-05,
+      "loss": 0.1498,
+      "mean_token_accuracy": 0.9440304934978485,
+      "num_tokens": 23100836.0,
+      "step": 63
+    },
+    {
+      "epoch": 2.688172043010753,
+      "grad_norm": 0.7735956031556342,
+      "learning_rate": 1.821322403143969e-05,
+      "loss": 0.1392,
+      "mean_token_accuracy": 0.9508139789104462,
+      "num_tokens": 23482604.0,
+      "step": 64
+    },
+    {
+      "epoch": 2.731182795698925,
+      "grad_norm": 0.9120084675913216,
+      "learning_rate": 1.812570339007983e-05,
+      "loss": 0.1506,
+      "mean_token_accuracy": 0.9453353136777878,
+      "num_tokens": 23865993.0,
+      "step": 65
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 0.7503811468513143,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.1363,
+      "mean_token_accuracy": 0.9510210454463959,
+      "num_tokens": 24224549.0,
+      "step": 66
+    },
+    {
+      "epoch": 2.817204301075269,
+      "grad_norm": 1.1460712341286583,
+      "learning_rate": 1.7945067914573147e-05,
+      "loss": 0.1664,
+      "mean_token_accuracy": 0.9413717687129974,
+      "num_tokens": 24598626.0,
+      "step": 67
+    },
+    {
+      "epoch": 2.860215053763441,
+      "grad_norm": 0.8670992068464418,
+      "learning_rate": 1.7851994686215592e-05,
+      "loss": 0.1577,
+      "mean_token_accuracy": 0.9477098882198334,
+      "num_tokens": 24981628.0,
+      "step": 68
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.7836229996954126,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 0.1427,
+      "mean_token_accuracy": 0.9498772025108337,
+      "num_tokens": 25357328.0,
+      "step": 69
+    },
+    {
+      "epoch": 2.946236559139785,
+      "grad_norm": 0.9864794829369287,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.1548,
+      "mean_token_accuracy": 0.9467099010944366,
+      "num_tokens": 25736995.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.989247311827957,
+      "grad_norm": 0.8453374404480977,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.1328,
+      "mean_token_accuracy": 0.9533079415559769,
+      "num_tokens": 26119812.0,
+      "step": 71
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8453374404480977,
+      "learning_rate": 1.7461836858476858e-05,
+      "loss": 0.023,
+      "mean_token_accuracy": 0.9692671298980713,
+      "num_tokens": 26217050.0,
+      "step": 72
+    },
+    {
+      "epoch": 3.043010752688172,
+      "grad_norm": 0.7191008184533193,
+      "learning_rate": 1.7359943506922775e-05,
+      "loss": 0.085,
+      "mean_token_accuracy": 0.9692452400922775,
+      "num_tokens": 26579836.0,
+      "step": 73
+    },
+    {
+      "epoch": 3.086021505376344,
+      "grad_norm": 0.7033653480672031,
+      "learning_rate": 1.725635493875799e-05,
+      "loss": 0.084,
+      "mean_token_accuracy": 0.9705889225006104,
+      "num_tokens": 26954186.0,
+      "step": 74
+    },
+    {
+      "epoch": 3.129032258064516,
+      "grad_norm": 0.5815187767804908,
+      "learning_rate": 1.7151095013548996e-05,
+      "loss": 0.0795,
+      "mean_token_accuracy": 0.9710359871387482,
+      "num_tokens": 27331222.0,
+      "step": 75
+    },
+    {
+      "epoch": 3.172043010752688,
+      "grad_norm": 0.6837466146484604,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.0779,
+      "mean_token_accuracy": 0.9715389311313629,
+      "num_tokens": 27695626.0,
+      "step": 76
+    },
+    {
+      "epoch": 3.21505376344086,
+      "grad_norm": 0.7647564443576131,
+      "learning_rate": 1.693565844949933e-05,
+      "loss": 0.0592,
+      "mean_token_accuracy": 0.9778129011392593,
+      "num_tokens": 28074766.0,
+      "step": 77
+    },
+    {
+      "epoch": 3.258064516129032,
+      "grad_norm": 0.6960445168765227,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.0825,
+      "mean_token_accuracy": 0.9732242673635483,
+      "num_tokens": 28441758.0,
+      "step": 78
+    },
+    {
+      "epoch": 3.3010752688172045,
+      "grad_norm": 0.8162134588348661,
+      "learning_rate": 1.671383228945597e-05,
+      "loss": 0.0795,
+      "mean_token_accuracy": 0.9723010808229446,
+      "num_tokens": 28816556.0,
+      "step": 79
+    },
+    {
+      "epoch": 3.3440860215053765,
+      "grad_norm": 0.7752408104041487,
+      "learning_rate": 1.6600586748983642e-05,
+      "loss": 0.0791,
+      "mean_token_accuracy": 0.9741756767034531,
+      "num_tokens": 29190153.0,
+      "step": 80
+    },
+    {
+      "epoch": 3.3870967741935485,
+      "grad_norm": 0.6264771832821134,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.0885,
+      "mean_token_accuracy": 0.9700659811496735,
+      "num_tokens": 29556225.0,
+      "step": 81
+    },
+    {
+      "epoch": 3.4301075268817205,
+      "grad_norm": 0.7087453451133532,
+      "learning_rate": 1.6369561160419783e-05,
+      "loss": 0.0756,
+      "mean_token_accuracy": 0.9748696535825729,
+      "num_tokens": 29944628.0,
+      "step": 82
+    },
+    {
+      "epoch": 3.4731182795698925,
+      "grad_norm": 0.6666804960250854,
+      "learning_rate": 1.625183432447789e-05,
+      "loss": 0.0768,
+      "mean_token_accuracy": 0.9723282903432846,
+      "num_tokens": 30326403.0,
+      "step": 83
+    },
+    {
+      "epoch": 3.5161290322580645,
+      "grad_norm": 0.7492247001485264,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 0.0862,
+      "mean_token_accuracy": 0.9687108993530273,
+      "num_tokens": 30707604.0,
+      "step": 84
+    },
+    {
+      "epoch": 3.5591397849462365,
+      "grad_norm": 0.6413601535507213,
+      "learning_rate": 1.6012088143204953e-05,
+      "loss": 0.0771,
+      "mean_token_accuracy": 0.9721613973379135,
+      "num_tokens": 31094255.0,
+      "step": 85
+    },
+    {
+      "epoch": 3.6021505376344085,
+      "grad_norm": 0.7214880008358299,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.0902,
+      "mean_token_accuracy": 0.9686519354581833,
+      "num_tokens": 31465554.0,
+      "step": 86
+    },
+    {
+      "epoch": 3.6451612903225805,
+      "grad_norm": 0.6072340945600113,
+      "learning_rate": 1.5766803221148676e-05,
+      "loss": 0.0783,
+      "mean_token_accuracy": 0.97231625020504,
+      "num_tokens": 31841954.0,
+      "step": 87
+    },
+    {
+      "epoch": 3.688172043010753,
+      "grad_norm": 0.7141144509929378,
+      "learning_rate": 1.5642154155228124e-05,
+      "loss": 0.0784,
+      "mean_token_accuracy": 0.9737986773252487,
+      "num_tokens": 32231678.0,
+      "step": 88
+    },
+    {
+      "epoch": 3.731182795698925,
+      "grad_norm": 0.5930435846744901,
+      "learning_rate": 1.5516205531310272e-05,
+      "loss": 0.0773,
+      "mean_token_accuracy": 0.9729326516389847,
+      "num_tokens": 32611952.0,
+      "step": 89
+    },
+    {
+      "epoch": 3.774193548387097,
+      "grad_norm": 0.6873339835587674,
+      "learning_rate": 1.538898635915576e-05,
+      "loss": 0.0917,
+      "mean_token_accuracy": 0.9682262241840363,
+      "num_tokens": 32987305.0,
+      "step": 90
+    },
+    {
+      "epoch": 3.817204301075269,
+      "grad_norm": 0.628718128223866,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.0769,
+      "mean_token_accuracy": 0.9746036380529404,
+      "num_tokens": 33361173.0,
+      "step": 91
+    },
+    {
+      "epoch": 3.860215053763441,
+      "grad_norm": 0.7444168004427851,
+      "learning_rate": 1.513085386565758e-05,
+      "loss": 0.0766,
+      "mean_token_accuracy": 0.9750553965568542,
+      "num_tokens": 33744871.0,
+      "step": 92
+    },
+    {
+      "epoch": 3.903225806451613,
+      "grad_norm": 0.6080354599152884,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0881,
+      "mean_token_accuracy": 0.9682539403438568,
+      "num_tokens": 34122873.0,
+      "step": 93
+    },
+    {
+      "epoch": 3.946236559139785,
+      "grad_norm": 0.6254599667505842,
+      "learning_rate": 1.4867994483783485e-05,
+      "loss": 0.0674,
+      "mean_token_accuracy": 0.9770089983940125,
+      "num_tokens": 34492949.0,
+      "step": 94
+    },
+    {
+      "epoch": 3.989247311827957,
+      "grad_norm": 0.5928494398285244,
+      "learning_rate": 1.4734867721853341e-05,
+      "loss": 0.0723,
+      "mean_token_accuracy": 0.9745485931634903,
+      "num_tokens": 34864951.0,
+      "step": 95
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6180172580268953,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.0162,
+      "mean_token_accuracy": 0.9717925190925598,
+      "num_tokens": 34956848.0,
+      "step": 96
+    },
+    {
+      "epoch": 4.043010752688172,
+      "grad_norm": 0.4798007088122171,
+      "learning_rate": 1.4465373364454001e-05,
+      "loss": 0.0415,
+      "mean_token_accuracy": 0.9860930442810059,
+      "num_tokens": 35327401.0,
+      "step": 97
+    },
+    {
+      "epoch": 4.086021505376344,
+      "grad_norm": 0.5030678863912684,
+      "learning_rate": 1.4329067841650274e-05,
+      "loss": 0.0512,
+      "mean_token_accuracy": 0.9837829172611237,
+      "num_tokens": 35697068.0,
+      "step": 98
+    },
+    {
+      "epoch": 4.129032258064516,
+      "grad_norm": 0.4887047754497154,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 0.035,
+      "mean_token_accuracy": 0.9878916591405869,
+      "num_tokens": 36078911.0,
+      "step": 99
+    },
+    {
+      "epoch": 4.172043010752688,
+      "grad_norm": 0.556764696779543,
+      "learning_rate": 1.4053497076934948e-05,
+      "loss": 0.0388,
+      "mean_token_accuracy": 0.9873095601797104,
+      "num_tokens": 36457881.0,
+      "step": 100
+    },
+    {
+      "epoch": 4.21505376344086,
+      "grad_norm": 0.6105146685797401,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.0426,
+      "mean_token_accuracy": 0.9871442914009094,
+      "num_tokens": 36840608.0,
+      "step": 101
+    },
+    {
+      "epoch": 4.258064516129032,
+      "grad_norm": 0.5520281427427763,
+      "learning_rate": 1.3774191957526144e-05,
+      "loss": 0.0353,
+      "mean_token_accuracy": 0.9887934029102325,
+      "num_tokens": 37215456.0,
+      "step": 102
+    },
+    {
+      "epoch": 4.301075268817204,
+      "grad_norm": 0.5752554242126501,
+      "learning_rate": 1.3633219297728415e-05,
+      "loss": 0.049,
+      "mean_token_accuracy": 0.9847937226295471,
+      "num_tokens": 37600868.0,
+      "step": 103
+    },
+    {
+      "epoch": 4.344086021505376,
+      "grad_norm": 0.6228700798176202,
+      "learning_rate": 1.3491409798123687e-05,
+      "loss": 0.041,
+      "mean_token_accuracy": 0.9858721643686295,
+      "num_tokens": 37964996.0,
+      "step": 104
+    },
+    {
+      "epoch": 4.387096774193548,
+      "grad_norm": 0.545565814617341,
+      "learning_rate": 1.3348796121709862e-05,
+      "loss": 0.0432,
+      "mean_token_accuracy": 0.9834143966436386,
+      "num_tokens": 38331633.0,
+      "step": 105
+    },
+    {
+      "epoch": 4.43010752688172,
+      "grad_norm": 0.6431910601756529,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.044,
+      "mean_token_accuracy": 0.9857050627470016,
+      "num_tokens": 38703641.0,
+      "step": 106
+    },
+    {
+      "epoch": 4.473118279569892,
+      "grad_norm": 0.6183635335692609,
+      "learning_rate": 1.3061287809011243e-05,
+      "loss": 0.0486,
+      "mean_token_accuracy": 0.9833229929208755,
+      "num_tokens": 39075811.0,
+      "step": 107
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 0.5734112514278982,
+      "learning_rate": 1.291645939454825e-05,
+      "loss": 0.0466,
+      "mean_token_accuracy": 0.982891172170639,
+      "num_tokens": 39453732.0,
+      "step": 108
+    },
+    {
+      "epoch": 4.559139784946236,
+      "grad_norm": 0.5062927460342779,
+      "learning_rate": 1.277095923166689e-05,
+      "loss": 0.0407,
+      "mean_token_accuracy": 0.9859268963336945,
+      "num_tokens": 39846622.0,
+      "step": 109
+    },
+    {
+      "epoch": 4.602150537634409,
+      "grad_norm": 0.6337986686205553,
+      "learning_rate": 1.2624820833435939e-05,
+      "loss": 0.0433,
+      "mean_token_accuracy": 0.9856242388486862,
+      "num_tokens": 40230600.0,
+      "step": 110
+    },
+    {
+      "epoch": 4.645161290322581,
+      "grad_norm": 0.4815068983509369,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.042,
+      "mean_token_accuracy": 0.9860651940107346,
+      "num_tokens": 40608421.0,
+      "step": 111
+    },
+    {
+      "epoch": 4.688172043010753,
+      "grad_norm": 0.3922313992389828,
+      "learning_rate": 1.2330764110471567e-05,
+      "loss": 0.0297,
+      "mean_token_accuracy": 0.9892211109399796,
+      "num_tokens": 40988293.0,
+      "step": 112
+    },
+    {
+      "epoch": 4.731182795698925,
+      "grad_norm": 0.46224024107519485,
+      "learning_rate": 1.2182913515856016e-05,
+      "loss": 0.0449,
+      "mean_token_accuracy": 0.984123483300209,
+      "num_tokens": 41357882.0,
+      "step": 113
+    },
+    {
+      "epoch": 4.774193548387097,
+      "grad_norm": 0.5508908953527153,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.0467,
+      "mean_token_accuracy": 0.9867139011621475,
+      "num_tokens": 41725815.0,
+      "step": 114
+    },
+    {
+      "epoch": 4.817204301075269,
+      "grad_norm": 0.4834883935633812,
+      "learning_rate": 1.1885738124734359e-05,
+      "loss": 0.052,
+      "mean_token_accuracy": 0.9825968146324158,
+      "num_tokens": 42093847.0,
+      "step": 115
+    },
+    {
+      "epoch": 4.860215053763441,
+      "grad_norm": 0.5017978176670704,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.0373,
+      "mean_token_accuracy": 0.9864843785762787,
+      "num_tokens": 42470652.0,
+      "step": 116
+    },
+    {
+      "epoch": 4.903225806451613,
+      "grad_norm": 0.436532105510215,
+      "learning_rate": 1.1586825464562515e-05,
+      "loss": 0.0302,
+      "mean_token_accuracy": 0.989154502749443,
+      "num_tokens": 42844022.0,
+      "step": 117
+    },
+    {
+      "epoch": 4.946236559139785,
+      "grad_norm": 0.5594322206619027,
+      "learning_rate": 1.1436803658769082e-05,
+      "loss": 0.0336,
+      "mean_token_accuracy": 0.9877772778272629,
+      "num_tokens": 43217049.0,
+      "step": 118
+    },
+    {
+      "epoch": 4.989247311827957,
+      "grad_norm": 0.46803693804934354,
+      "learning_rate": 1.1286450913828313e-05,
+      "loss": 0.0441,
+      "mean_token_accuracy": 0.9841972589492798,
+      "num_tokens": 43601245.0,
+      "step": 119
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.46803693804934354,
+      "learning_rate": 1.113580186050475e-05,
+      "loss": 0.0072,
+      "mean_token_accuracy": 0.9910504221916199,
+      "num_tokens": 43691552.0,
+      "step": 120
+    },
+    {
+      "epoch": 5.043010752688172,
+      "grad_norm": 0.36589314652289223,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.0189,
+      "mean_token_accuracy": 0.9931964129209518,
+      "num_tokens": 44069981.0,
+      "step": 121
+    },
+    {
+      "epoch": 5.086021505376344,
+      "grad_norm": 0.3262477287689747,
+      "learning_rate": 1.0833753685018935e-05,
+      "loss": 0.0172,
+      "mean_token_accuracy": 0.9938466399908066,
+      "num_tokens": 44452961.0,
+      "step": 122
+    },
+    {
+      "epoch": 5.129032258064516,
+      "grad_norm": 0.37126458666561746,
+      "learning_rate": 1.0682424133646712e-05,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.9916689246892929,
+      "num_tokens": 44829261.0,
+      "step": 123
+    },
+    {
+      "epoch": 5.172043010752688,
+      "grad_norm": 0.39854735969327243,
+      "learning_rate": 1.0530937399447496e-05,
+      "loss": 0.0208,
+      "mean_token_accuracy": 0.9931624680757523,
+      "num_tokens": 45195677.0,
+      "step": 124
+    },
+    {
+      "epoch": 5.21505376344086,
+      "grad_norm": 0.4011633602771004,
+      "learning_rate": 1.0379328374377715e-05,
+      "loss": 0.0187,
+      "mean_token_accuracy": 0.9931042641401291,
+      "num_tokens": 45582399.0,
+      "step": 125
+    },
+    {
+      "epoch": 5.258064516129032,
+      "grad_norm": 0.4149531963831674,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.0201,
+      "mean_token_accuracy": 0.9933370649814606,
+      "num_tokens": 45957909.0,
+      "step": 126
+    },
+    {
+      "epoch": 5.301075268817204,
+      "grad_norm": 0.35580739164687514,
+      "learning_rate": 1.0075883152245334e-05,
+      "loss": 0.0182,
+      "mean_token_accuracy": 0.9931957274675369,
+      "num_tokens": 46331702.0,
+      "step": 127
+    },
+    {
+      "epoch": 5.344086021505376,
+      "grad_norm": 0.3659638692288794,
+      "learning_rate": 9.92411684775467e-06,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.992146834731102,
+      "num_tokens": 46699926.0,
+      "step": 128
+    },
+    {
+      "epoch": 5.387096774193548,
+      "grad_norm": 0.5124446313766259,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 0.0224,
+      "mean_token_accuracy": 0.9933983087539673,
+      "num_tokens": 47084802.0,
+      "step": 129
+    },
+    {
+      "epoch": 5.43010752688172,
+      "grad_norm": 0.3646431524853468,
+      "learning_rate": 9.620671625622287e-06,
+      "loss": 0.0213,
+      "mean_token_accuracy": 0.9931617379188538,
+      "num_tokens": 47454900.0,
+      "step": 130
+    },
+    {
+      "epoch": 5.473118279569892,
+      "grad_norm": 0.43644622149160334,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.0183,
+      "mean_token_accuracy": 0.9936078786849976,
+      "num_tokens": 47824110.0,
+      "step": 131
+    },
+    {
+      "epoch": 5.516129032258064,
+      "grad_norm": 0.40737855715835,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.0167,
+      "mean_token_accuracy": 0.9936787039041519,
+      "num_tokens": 48199410.0,
+      "step": 132
+    },
+    {
+      "epoch": 5.559139784946236,
+      "grad_norm": 0.3453003430092695,
+      "learning_rate": 9.166246314981066e-06,
+      "loss": 0.016,
+      "mean_token_accuracy": 0.9941088110208511,
+      "num_tokens": 48571600.0,
+      "step": 133
+    },
+    {
+      "epoch": 5.602150537634409,
+      "grad_norm": 0.4044531156287549,
+      "learning_rate": 9.015108802188314e-06,
+      "loss": 0.0203,
+      "mean_token_accuracy": 0.9922708123922348,
+      "num_tokens": 48944562.0,
+      "step": 134
+    },
+    {
+      "epoch": 5.645161290322581,
+      "grad_norm": 0.39933569411586073,
+      "learning_rate": 8.86419813949525e-06,
+      "loss": 0.026,
+      "mean_token_accuracy": 0.9936483949422836,
+      "num_tokens": 49329440.0,
+      "step": 135
+    },
+    {
+      "epoch": 5.688172043010753,
+      "grad_norm": 0.5189339190149178,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.0142,
+      "mean_token_accuracy": 0.9950688779354095,
+      "num_tokens": 49715705.0,
+      "step": 136
+    },
+    {
+      "epoch": 5.731182795698925,
+      "grad_norm": 0.4042026330549438,
+      "learning_rate": 8.56319634123092e-06,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9928712397813797,
+      "num_tokens": 50105592.0,
+      "step": 137
+    },
+    {
+      "epoch": 5.774193548387097,
+      "grad_norm": 0.4159641462800478,
+      "learning_rate": 8.413174535437486e-06,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.9930095821619034,
+      "num_tokens": 50473889.0,
+      "step": 138
+    },
+    {
+      "epoch": 5.817204301075269,
+      "grad_norm": 0.46704221505297566,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0264,
+      "mean_token_accuracy": 0.9904347956180573,
+      "num_tokens": 50848608.0,
+      "step": 139
+    },
+    {
+      "epoch": 5.860215053763441,
+      "grad_norm": 0.4423535789298909,
+      "learning_rate": 8.114261875265643e-06,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9932683557271957,
+      "num_tokens": 51213311.0,
+      "step": 140
+    },
+    {
+      "epoch": 5.903225806451613,
+      "grad_norm": 0.39628026138404,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.02,
+      "mean_token_accuracy": 0.9924024939537048,
+      "num_tokens": 51582321.0,
+      "step": 141
+    },
+    {
+      "epoch": 5.946236559139785,
+      "grad_norm": 0.40141553841310146,
+      "learning_rate": 7.817086484143987e-06,
+      "loss": 0.0251,
+      "mean_token_accuracy": 0.9912929236888885,
+      "num_tokens": 51957175.0,
+      "step": 142
+    },
+    {
+      "epoch": 5.989247311827957,
+      "grad_norm": 0.37692584612441205,
+      "learning_rate": 7.669235889528436e-06,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9928417950868607,
+      "num_tokens": 52337657.0,
+      "step": 143
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.37692584612441205,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9955406785011292,
+      "num_tokens": 52435404.0,
+      "step": 144
+    },
+    {
+      "epoch": 6.043010752688172,
+      "grad_norm": 0.2777527936559124,
+      "learning_rate": 7.375179166564062e-06,
+      "loss": 0.0096,
+      "mean_token_accuracy": 0.9978060573339462,
+      "num_tokens": 52801343.0,
+      "step": 145
+    },
+    {
+      "epoch": 6.086021505376344,
+      "grad_norm": 0.22061818508623526,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9961294829845428,
+      "num_tokens": 53170023.0,
+      "step": 146
+    },
+    {
+      "epoch": 6.129032258064516,
+      "grad_norm": 0.2450891259162475,
+      "learning_rate": 7.0835406054517505e-06,
+      "loss": 0.0098,
+      "mean_token_accuracy": 0.9963818788528442,
+      "num_tokens": 53540818.0,
+      "step": 147
+    },
+    {
+      "epoch": 6.172043010752688,
+      "grad_norm": 0.27354650244267165,
+      "learning_rate": 6.93871219098876e-06,
+      "loss": 0.0083,
+      "mean_token_accuracy": 0.9976299554109573,
+      "num_tokens": 53912206.0,
+      "step": 148
+    },
+    {
+      "epoch": 6.21505376344086,
+      "grad_norm": 0.24292132564074775,
+      "learning_rate": 6.79458888328903e-06,
+      "loss": 0.0091,
+      "mean_token_accuracy": 0.9975238144397736,
+      "num_tokens": 54290644.0,
+      "step": 149
+    },
+    {
+      "epoch": 6.258064516129032,
+      "grad_norm": 0.25903061511703607,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.0084,
+      "mean_token_accuracy": 0.9973570704460144,
+      "num_tokens": 54671572.0,
+      "step": 150
+    },
+    {
+      "epoch": 6.301075268817204,
+      "grad_norm": 0.27785773779575323,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.0068,
+      "mean_token_accuracy": 0.9980671256780624,
+      "num_tokens": 55043557.0,
+      "step": 151
+    },
+    {
+      "epoch": 6.344086021505376,
+      "grad_norm": 0.22495303178328654,
+      "learning_rate": 6.366780702271589e-06,
+      "loss": 0.0081,
+      "mean_token_accuracy": 0.9977790415287018,
+      "num_tokens": 55434084.0,
+      "step": 152
+    },
+    {
+      "epoch": 6.387096774193548,
+      "grad_norm": 0.21767145483330294,
+      "learning_rate": 6.225808042473857e-06,
+      "loss": 0.0073,
+      "mean_token_accuracy": 0.9982246607542038,
+      "num_tokens": 55816748.0,
+      "step": 153
+    },
+    {
+      "epoch": 6.43010752688172,
+      "grad_norm": 0.1720994423666938,
+      "learning_rate": 6.085704692731609e-06,
+      "loss": 0.0089,
+      "mean_token_accuracy": 0.9972024708986282,
+      "num_tokens": 56204052.0,
+      "step": 154
+    },
+    {
+      "epoch": 6.473118279569892,
+      "grad_norm": 0.4151871031911838,
+      "learning_rate": 5.946502923065054e-06,
+      "loss": 0.0064,
+      "mean_token_accuracy": 0.9978921562433243,
+      "num_tokens": 56584279.0,
+      "step": 155
+    },
+    {
+      "epoch": 6.516129032258064,
+      "grad_norm": 0.24009379583099646,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.0061,
+      "mean_token_accuracy": 0.9981395900249481,
+      "num_tokens": 56966123.0,
+      "step": 156
+    },
+    {
+      "epoch": 6.559139784946236,
+      "grad_norm": 0.24984505593518833,
+      "learning_rate": 5.670932158349732e-06,
+      "loss": 0.0079,
+      "mean_token_accuracy": 0.9977651834487915,
+      "num_tokens": 57340499.0,
+      "step": 157
+    },
+    {
+      "epoch": 6.602150537634409,
+      "grad_norm": 0.22800352911247235,
+      "learning_rate": 5.534626635546e-06,
+      "loss": 0.0066,
+      "mean_token_accuracy": 0.9973956197500229,
+      "num_tokens": 57722362.0,
+      "step": 158
+    },
+    {
+      "epoch": 6.645161290322581,
+      "grad_norm": 0.3972684492677971,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 0.0129,
+      "mean_token_accuracy": 0.9956333786249161,
+      "num_tokens": 58089687.0,
+      "step": 159
+    },
+    {
+      "epoch": 6.688172043010753,
+      "grad_norm": 0.2855037997818557,
+      "learning_rate": 5.2651322781466606e-06,
+      "loss": 0.0097,
+      "mean_token_accuracy": 0.9961634278297424,
+      "num_tokens": 58440751.0,
+      "step": 160
+    },
+    {
+      "epoch": 6.731182795698925,
+      "grad_norm": 0.2561924349864501,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.0095,
+      "mean_token_accuracy": 0.9967732727527618,
+      "num_tokens": 58816520.0,
+      "step": 161
+    },
+    {
+      "epoch": 6.774193548387097,
+      "grad_norm": 0.2550205734143902,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0096,
+      "mean_token_accuracy": 0.9970249980688095,
+      "num_tokens": 59199244.0,
+      "step": 162
+    },
+    {
+      "epoch": 6.817204301075269,
+      "grad_norm": 0.2895162694155573,
+      "learning_rate": 4.869146134342426e-06,
+      "loss": 0.0112,
+      "mean_token_accuracy": 0.995991975069046,
+      "num_tokens": 59564510.0,
+      "step": 163
+    },
+    {
+      "epoch": 6.860215053763441,
+      "grad_norm": 0.27109152841491596,
+      "learning_rate": 4.739474058829288e-06,
+      "loss": 0.0098,
+      "mean_token_accuracy": 0.9966453909873962,
+      "num_tokens": 59933755.0,
+      "step": 164
+    },
+    {
+      "epoch": 6.903225806451613,
+      "grad_norm": 0.20196018529315143,
+      "learning_rate": 4.611013640844245e-06,
+      "loss": 0.0072,
+      "mean_token_accuracy": 0.9972820430994034,
+      "num_tokens": 60318049.0,
+      "step": 165
+    },
+    {
+      "epoch": 6.946236559139785,
+      "grad_norm": 0.28770462101147276,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.0075,
+      "mean_token_accuracy": 0.9979050308465958,
+      "num_tokens": 60702707.0,
+      "step": 166
+    },
+    {
+      "epoch": 6.989247311827957,
+      "grad_norm": 0.2570986978659673,
+      "learning_rate": 4.357845844771881e-06,
+      "loss": 0.0072,
+      "mean_token_accuracy": 0.9979168772697449,
+      "num_tokens": 61080551.0,
+      "step": 167
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.2570986978659673,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.001,
+      "mean_token_accuracy": 0.9990871548652649,
+      "num_tokens": 61169909.0,
+      "step": 168
+    },
+    {
+      "epoch": 7.043010752688172,
+      "grad_norm": 0.18638689720743132,
+      "learning_rate": 4.109875981361363e-06,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9993208199739456,
+      "num_tokens": 61548169.0,
+      "step": 169
+    },
+    {
+      "epoch": 7.086021505376344,
+      "grad_norm": 0.09274868532077754,
+      "learning_rate": 3.987911856795047e-06,
+      "loss": 0.0024,
+      "mean_token_accuracy": 0.9993245899677277,
+      "num_tokens": 61927780.0,
+      "step": 170
+    },
+    {
+      "epoch": 7.129032258064516,
+      "grad_norm": 0.11314592234156305,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.0043,
+      "mean_token_accuracy": 0.9991153180599213,
+      "num_tokens": 62295765.0,
+      "step": 171
+    },
+    {
+      "epoch": 7.172043010752688,
+      "grad_norm": 0.125324034467096,
+      "learning_rate": 3.748165675522113e-06,
+      "loss": 0.0043,
+      "mean_token_accuracy": 0.998317152261734,
+      "num_tokens": 62680703.0,
+      "step": 172
+    },
+    {
+      "epoch": 7.21505376344086,
+      "grad_norm": 0.162207800509228,
+      "learning_rate": 3.630438839580217e-06,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9989175051450729,
+      "num_tokens": 63048051.0,
+      "step": 173
+    },
+    {
+      "epoch": 7.258064516129032,
+      "grad_norm": 0.14736979534555758,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9988811016082764,
+      "num_tokens": 63420296.0,
+      "step": 174
+    },
+    {
+      "epoch": 7.301075268817204,
+      "grad_norm": 0.24994209797043623,
+      "learning_rate": 3.399413251016359e-06,
+      "loss": 0.0045,
+      "mean_token_accuracy": 0.9984373897314072,
+      "num_tokens": 63802044.0,
+      "step": 175
+    },
+    {
+      "epoch": 7.344086021505376,
+      "grad_norm": 0.19480816289308553,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.004,
+      "mean_token_accuracy": 0.9981936365365982,
+      "num_tokens": 64179447.0,
+      "step": 176
+    },
+    {
+      "epoch": 7.387096774193548,
+      "grad_norm": 0.13577926396280693,
+      "learning_rate": 3.174468567813461e-06,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9986472874879837,
+      "num_tokens": 64553814.0,
+      "step": 177
+    },
+    {
+      "epoch": 7.43010752688172,
+      "grad_norm": 0.1558952871547043,
+      "learning_rate": 3.0643415505006733e-06,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991411715745926,
+      "num_tokens": 64937169.0,
+      "step": 178
+    },
+    {
+      "epoch": 7.473118279569892,
+      "grad_norm": 0.19500035034736574,
+      "learning_rate": 2.9558120241738786e-06,
+      "loss": 0.0047,
+      "mean_token_accuracy": 0.9986667931079865,
+      "num_tokens": 65304620.0,
+      "step": 179
+    },
+    {
+      "epoch": 7.516129032258064,
+      "grad_norm": 0.11403208704075335,
+      "learning_rate": 2.8489049864510053e-06,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9994394332170486,
+      "num_tokens": 65683792.0,
+      "step": 180
+    },
+    {
+      "epoch": 7.559139784946236,
+      "grad_norm": 0.09515486390531766,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9987542629241943,
+      "num_tokens": 66052076.0,
+      "step": 181
+    },
+    {
+      "epoch": 7.602150537634409,
+      "grad_norm": 0.11427433435445018,
+      "learning_rate": 2.640056493077231e-06,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.9984430074691772,
+      "num_tokens": 66429336.0,
+      "step": 182
+    },
+    {
+      "epoch": 7.645161290322581,
+      "grad_norm": 0.14803270246342048,
+      "learning_rate": 2.5381631415231455e-06,
+      "loss": 0.0024,
+      "mean_token_accuracy": 0.9995441436767578,
+      "num_tokens": 66808483.0,
+      "step": 183
+    },
+    {
+      "epoch": 7.688172043010753,
+      "grad_norm": 0.060271743291256424,
+      "learning_rate": 2.4379884756868167e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9994434714317322,
+      "num_tokens": 67196644.0,
+      "step": 184
+    },
+    {
+      "epoch": 7.731182795698925,
+      "grad_norm": 0.15449382158867014,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.998866930603981,
+      "num_tokens": 67576705.0,
+      "step": 185
+    },
+    {
+      "epoch": 7.774193548387097,
+      "grad_norm": 0.15970881151513372,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9994314312934875,
+      "num_tokens": 67955564.0,
+      "step": 186
+    },
+    {
+      "epoch": 7.817204301075269,
+      "grad_norm": 0.17023262969614245,
+      "learning_rate": 2.1480053137844115e-06,
+      "loss": 0.0023,
+      "mean_token_accuracy": 0.999400720000267,
+      "num_tokens": 68336162.0,
+      "step": 187
+    },
+    {
+      "epoch": 7.860215053763441,
+      "grad_norm": 0.12445830166048269,
+      "learning_rate": 2.054932085426856e-06,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9985401034355164,
+      "num_tokens": 68713903.0,
+      "step": 188
+    },
+    {
+      "epoch": 7.903225806451613,
+      "grad_norm": 0.10664444106034968,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 0.0042,
+      "mean_token_accuracy": 0.9983135461807251,
+      "num_tokens": 69083101.0,
+      "step": 189
+    },
+    {
+      "epoch": 7.946236559139785,
+      "grad_norm": 0.20267328769221749,
+      "learning_rate": 1.8742966099201699e-06,
+      "loss": 0.0025,
+      "mean_token_accuracy": 0.9991088360548019,
+      "num_tokens": 69450911.0,
+      "step": 190
+    },
+    {
+      "epoch": 7.989247311827957,
+      "grad_norm": 0.07966294331340328,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.0043,
+      "mean_token_accuracy": 0.9985426664352417,
+      "num_tokens": 69816019.0,
+      "step": 191
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.160752083075703,
+      "learning_rate": 1.7011470800097496e-06,
+      "loss": 0.0006,
+      "mean_token_accuracy": 0.9995448589324951,
+      "num_tokens": 69909418.0,
+      "step": 192
+    },
+    {
+      "epoch": 8.043010752688172,
+      "grad_norm": 0.12953983503212843,
+      "learning_rate": 1.6174296671799571e-06,
+      "loss": 0.0023,
+      "mean_token_accuracy": 0.9991968870162964,
+      "num_tokens": 70287063.0,
+      "step": 193
+    },
+    {
+      "epoch": 8.086021505376344,
+      "grad_norm": 0.11355014942214375,
+      "learning_rate": 1.5356430127119915e-06,
+      "loss": 0.0023,
+      "mean_token_accuracy": 0.9992813766002655,
+      "num_tokens": 70677976.0,
+      "step": 194
+    },
+    {
+      "epoch": 8.129032258064516,
+      "grad_norm": 0.09452954664073393,
+      "learning_rate": 1.4558059545351144e-06,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9995724707841873,
+      "num_tokens": 71039103.0,
+      "step": 195
+    },
+    {
+      "epoch": 8.172043010752688,
+      "grad_norm": 0.0611357247699829,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9998900592327118,
+      "num_tokens": 71408946.0,
+      "step": 196
+    },
+    {
+      "epoch": 8.21505376344086,
+      "grad_norm": 0.05878301201751446,
+      "learning_rate": 1.302053729282533e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9993925988674164,
+      "num_tokens": 71787495.0,
+      "step": 197
+    },
+    {
+      "epoch": 8.258064516129032,
+      "grad_norm": 0.05644673250508509,
+      "learning_rate": 1.2281739759740575e-06,
+      "loss": 0.0012,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 72167744.0,
+      "step": 198
+    },
+    {
+      "epoch": 8.301075268817204,
+      "grad_norm": 0.0678174975886251,
+      "learning_rate": 1.156314638334277e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995383620262146,
+      "num_tokens": 72535197.0,
+      "step": 199
+    },
+    {
+      "epoch": 8.344086021505376,
+      "grad_norm": 0.07187441226828475,
+      "learning_rate": 1.086492267732462e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9995486289262772,
+      "num_tokens": 72912819.0,
+      "step": 200
+    },
+    {
+      "epoch": 8.387096774193548,
+      "grad_norm": 0.07795205289710616,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9996720552444458,
+      "num_tokens": 73288384.0,
+      "step": 201
+    },
+    {
+      "epoch": 8.43010752688172,
+      "grad_norm": 0.07266542626737585,
+      "learning_rate": 9.530222835413739e-07,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9992012083530426,
+      "num_tokens": 73649231.0,
+      "step": 202
+    },
+    {
+      "epoch": 8.473118279569892,
+      "grad_norm": 0.05690867261143057,
+      "learning_rate": 8.894054121084839e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995424598455429,
+      "num_tokens": 74024940.0,
+      "step": 203
+    },
+    {
+      "epoch": 8.516129032258064,
+      "grad_norm": 0.07784424768246319,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9997651875019073,
+      "num_tokens": 74393707.0,
+      "step": 204
+    },
+    {
+      "epoch": 8.559139784946236,
+      "grad_norm": 0.08544567215406322,
+      "learning_rate": 7.684811715985429e-07,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9993268847465515,
+      "num_tokens": 74769770.0,
+      "step": 205
+    },
+    {
+      "epoch": 8.602150537634408,
+      "grad_norm": 0.04848205681346562,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.9996765702962875,
+      "num_tokens": 75144638.0,
+      "step": 206
+    },
+    {
+      "epoch": 8.64516129032258,
+      "grad_norm": 0.07153581712473589,
+      "learning_rate": 6.560616283932897e-07,
+      "loss": 0.0019,
+      "mean_token_accuracy": 0.9993336498737335,
+      "num_tokens": 75517948.0,
+      "step": 207
+    },
+    {
+      "epoch": 8.688172043010752,
+      "grad_norm": 0.03218818118067709,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.0005,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 75913411.0,
+      "step": 208
+    },
+    {
+      "epoch": 8.731182795698924,
+      "grad_norm": 0.043871722359634206,
+      "learning_rate": 5.522503509524591e-07,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.9997778683900833,
+      "num_tokens": 76292535.0,
+      "step": 209
+    },
+    {
+      "epoch": 8.774193548387096,
+      "grad_norm": 0.11523726962843446,
+      "learning_rate": 5.036030109968082e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9996742606163025,
+      "num_tokens": 76668845.0,
+      "step": 210
+    },
+    {
+      "epoch": 8.817204301075268,
+      "grad_norm": 0.0558278621305881,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.0012,
+      "mean_token_accuracy": 0.9997794181108475,
+      "num_tokens": 77057588.0,
+      "step": 211
+    },
+    {
+      "epoch": 8.86021505376344,
+      "grad_norm": 0.05082679865672205,
+      "learning_rate": 4.128809507704445e-07,
+      "loss": 0.0008,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 77440951.0,
+      "step": 212
+    },
+    {
+      "epoch": 8.903225806451612,
+      "grad_norm": 0.06077000745250929,
+      "learning_rate": 3.708271265220087e-07,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9994602203369141,
+      "num_tokens": 77816116.0,
+      "step": 213
+    },
+    {
+      "epoch": 8.946236559139784,
+      "grad_norm": 0.05162284627072263,
+      "learning_rate": 3.309911907379393e-07,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.9997801780700684,
+      "num_tokens": 78172575.0,
+      "step": 214
+    },
+    {
+      "epoch": 8.989247311827956,
+      "grad_norm": 0.05274284118745483,
+      "learning_rate": 2.9338231883378365e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.999669536948204,
+      "num_tokens": 78554073.0,
+      "step": 215
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.05274284118745483,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.0006,
+      "mean_token_accuracy": 0.9990884065628052,
+      "num_tokens": 78652031.0,
+      "step": 216
+    },
+    {
+      "epoch": 9.043010752688172,
+      "grad_norm": 0.057243512265435566,
+      "learning_rate": 2.248799015327907e-07,
+      "loss": 0.0008,
+      "mean_token_accuracy": 0.9998939335346222,
+      "num_tokens": 79037063.0,
+      "step": 217
+    },
+    {
+      "epoch": 9.086021505376344,
+      "grad_norm": 0.05131590701841364,
+      "learning_rate": 1.9400213430538773e-07,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9996659904718399,
+      "num_tokens": 79408170.0,
+      "step": 218
+    },
+    {
+      "epoch": 9.129032258064516,
+      "grad_norm": 0.06907734176650242,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9998951852321625,
+      "num_tokens": 79777017.0,
+      "step": 219
+    },
+    {
+      "epoch": 9.172043010752688,
+      "grad_norm": 0.040367078778572214,
+      "learning_rate": 1.3902904145653094e-07,
+      "loss": 0.0008,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 80135769.0,
+      "step": 220
+    },
+    {
+      "epoch": 9.21505376344086,
+      "grad_norm": 0.054348476268462176,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9996242523193359,
+      "num_tokens": 80517437.0,
+      "step": 221
+    },
+    {
+      "epoch": 9.258064516129032,
+      "grad_norm": 0.04194468920603892,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.0009,
+      "mean_token_accuracy": 0.9998854249715805,
+      "num_tokens": 80904669.0,
+      "step": 222
+    },
+    {
+      "epoch": 9.301075268817204,
+      "grad_norm": 0.050517226281810455,
+      "learning_rate": 7.361654952665608e-08,
+      "loss": 0.0009,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 81283528.0,
+      "step": 223
+    },
+    {
+      "epoch": 9.344086021505376,
+      "grad_norm": 0.04714202439779049,
+      "learning_rate": 5.637890442641403e-08,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.9998873323202133,
+      "num_tokens": 81655270.0,
+      "step": 224
+    },
+    {
+      "epoch": 9.387096774193548,
+      "grad_norm": 0.055175970745747455,
+      "learning_rate": 4.143157468468717e-08,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995371699333191,
+      "num_tokens": 82027314.0,
+      "step": 225
+    },
+    {
+      "epoch": 9.43010752688172,
+      "grad_norm": 0.044056512200001,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9993147253990173,
+      "num_tokens": 82402877.0,
+      "step": 226
+    },
+    {
+      "epoch": 9.473118279569892,
+      "grad_norm": 0.06449776282190266,
+      "learning_rate": 1.8421104235727406e-08,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9998880922794342,
+      "num_tokens": 82793640.0,
+      "step": 227
+    },
+    {
+      "epoch": 9.516129032258064,
+      "grad_norm": 0.04738484622052601,
+      "learning_rate": 1.0363263532724433e-08,
+      "loss": 0.001,
+      "mean_token_accuracy": 0.999885693192482,
+      "num_tokens": 83167856.0,
+      "step": 228
+    },
+    {
+      "epoch": 9.559139784946236,
+      "grad_norm": 0.05120616744078798,
+      "learning_rate": 4.606336975948589e-09,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9992931187152863,
+      "num_tokens": 83549841.0,
+      "step": 229
+    },
+    {
+      "epoch": 9.602150537634408,
+      "grad_norm": 0.06416283623906281,
+      "learning_rate": 1.1516505589381777e-09,
+      "loss": 0.0008,
+      "mean_token_accuracy": 0.9997781366109848,
+      "num_tokens": 83929557.0,
+      "step": 230
+    },
+    {
+      "epoch": 9.602150537634408,
+      "step": 230,
+      "total_flos": 824307871121408.0,
+      "train_loss": 0.1251811162315552,
+      "train_runtime": 58145.7461,
+      "train_samples_per_second": 0.507,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 824307871121408.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634cd4545b54a0ee557e2eacb54767aba282d12b0f39b7c5636c0cf0675f5fc4
+size 7928