Upload folder using huggingface_hub

.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 +1,68 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: bal_imb_cap_full_lr2e-4_epoch10.0_freezevisTrue_fps8
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bal_imb_cap_full_lr2e-4_epoch10.0_freezevisTrue_fps8
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the cam_motion_balanced_vqa, the cam_motion_imbalanced_vqa and the cam_motion_caption datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0054        | 2.7191 | 1000 | 0.0100          |
+| 0.0005        | 5.4358 | 2000 | 0.0036          |
+| 0.0           | 8.1525 | 3000 | 0.0000          |
+
+
+### Framework versions
+
+- Transformers 4.51.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

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
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 9.975144705481783,
+    "eval_loss": 1.0644954272720497e-05,
+    "eval_runtime": 145.1585,
+    "eval_samples_per_second": 1.378,
+    "eval_steps_per_second": 0.172,
+    "total_flos": 3659279013773312.0,
+    "train_loss": 0.050615286758120444,
+    "train_runtime": 386241.8476,
+    "train_samples_per_second": 2.433,
+    "train_steps_per_second": 0.01
+}

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,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.975144705481783,
+    "eval_loss": 1.0644954272720497e-05,
+    "eval_runtime": 145.1585,
+    "eval_samples_per_second": 1.378,
+    "eval_steps_per_second": 0.172
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf50bf2a7f4c903172836838c97739848d1958ce32d5801b24c1e3af450f828
+size 4968243304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be2c951d72cb1925262ff824269462505b2cdbf12e128e9babd7a71e7b4f7ebe
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6ad05ec94944d3e2c0b4eba2eaffd84864730c3b13bbf04fde5241404a0415
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0360e91c5934b0a6f4e923720deafd9e5c4164a463c5dbb094a9cb5a93d39f
+size 1691924384

model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.975144705481783,
+    "total_flos": 3659279013773312.0,
+    "train_loss": 0.050615286758120444,
+    "train_runtime": 386241.8476,
+    "train_samples_per_second": 2.433,
+    "train_steps_per_second": 0.01
+}

trainer_state.json

@@ -0,0 +1,2636 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.975144705481783,
+  "eval_steps": 1000,
+  "global_step": 3670,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027238678924072182,
+      "grad_norm": 94.36308714522585,
+      "learning_rate": 2.4523160762942784e-07,
+      "loss": 3.2941,
+      "step": 10
+    },
+    {
+      "epoch": 0.054477357848144364,
+      "grad_norm": 72.09113030659383,
+      "learning_rate": 5.177111716621253e-07,
+      "loss": 2.9481,
+      "step": 20
+    },
+    {
+      "epoch": 0.08171603677221655,
+      "grad_norm": 18.50935923305202,
+      "learning_rate": 7.90190735694823e-07,
+      "loss": 1.921,
+      "step": 30
+    },
+    {
+      "epoch": 0.10895471569628873,
+      "grad_norm": 8.59280831709028,
+      "learning_rate": 1.0626702997275206e-06,
+      "loss": 1.5096,
+      "step": 40
+    },
+    {
+      "epoch": 0.13619339462036092,
+      "grad_norm": 5.941916510585534,
+      "learning_rate": 1.335149863760218e-06,
+      "loss": 1.1101,
+      "step": 50
+    },
+    {
+      "epoch": 0.1634320735444331,
+      "grad_norm": 4.39962525080334,
+      "learning_rate": 1.6076294277929156e-06,
+      "loss": 0.9091,
+      "step": 60
+    },
+    {
+      "epoch": 0.1906707524685053,
+      "grad_norm": 4.489642566752767,
+      "learning_rate": 1.8801089918256133e-06,
+      "loss": 0.7886,
+      "step": 70
+    },
+    {
+      "epoch": 0.21790943139257746,
+      "grad_norm": 3.8997170693605914,
+      "learning_rate": 2.152588555858311e-06,
+      "loss": 0.7292,
+      "step": 80
+    },
+    {
+      "epoch": 0.24514811031664965,
+      "grad_norm": 4.2337949046127115,
+      "learning_rate": 2.4250681198910083e-06,
+      "loss": 0.6295,
+      "step": 90
+    },
+    {
+      "epoch": 0.27238678924072185,
+      "grad_norm": 3.887748571626415,
+      "learning_rate": 2.697547683923706e-06,
+      "loss": 0.5892,
+      "step": 100
+    },
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 4.071563747798551,
+      "learning_rate": 2.9700272479564033e-06,
+      "loss": 0.4879,
+      "step": 110
+    },
+    {
+      "epoch": 0.3268641470888662,
+      "grad_norm": 4.396940499759756,
+      "learning_rate": 3.2425068119891012e-06,
+      "loss": 0.4542,
+      "step": 120
+    },
+    {
+      "epoch": 0.35410282601293835,
+      "grad_norm": 3.784810689454143,
+      "learning_rate": 3.5149863760217988e-06,
+      "loss": 0.3211,
+      "step": 130
+    },
+    {
+      "epoch": 0.3813415049370106,
+      "grad_norm": 3.7737741184600595,
+      "learning_rate": 3.7874659400544963e-06,
+      "loss": 0.2891,
+      "step": 140
+    },
+    {
+      "epoch": 0.40858018386108275,
+      "grad_norm": 3.361771664086218,
+      "learning_rate": 4.059945504087194e-06,
+      "loss": 0.1996,
+      "step": 150
+    },
+    {
+      "epoch": 0.4358188627851549,
+      "grad_norm": 3.2907408057054237,
+      "learning_rate": 4.332425068119892e-06,
+      "loss": 0.133,
+      "step": 160
+    },
+    {
+      "epoch": 0.4630575417092271,
+      "grad_norm": 3.040778638316543,
+      "learning_rate": 4.604904632152589e-06,
+      "loss": 0.1101,
+      "step": 170
+    },
+    {
+      "epoch": 0.4902962206332993,
+      "grad_norm": 3.5750949211792156,
+      "learning_rate": 4.877384196185287e-06,
+      "loss": 0.0936,
+      "step": 180
+    },
+    {
+      "epoch": 0.5175348995573714,
+      "grad_norm": 3.857830728644118,
+      "learning_rate": 5.149863760217984e-06,
+      "loss": 0.0757,
+      "step": 190
+    },
+    {
+      "epoch": 0.5447735784814437,
+      "grad_norm": 4.5053152903816915,
+      "learning_rate": 5.422343324250682e-06,
+      "loss": 0.0677,
+      "step": 200
+    },
+    {
+      "epoch": 0.5720122574055159,
+      "grad_norm": 2.0169258478044423,
+      "learning_rate": 5.694822888283379e-06,
+      "loss": 0.0607,
+      "step": 210
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 2.7354337720763566,
+      "learning_rate": 5.9673024523160776e-06,
+      "loss": 0.057,
+      "step": 220
+    },
+    {
+      "epoch": 0.6264896152536602,
+      "grad_norm": 2.41187775653569,
+      "learning_rate": 6.239782016348774e-06,
+      "loss": 0.056,
+      "step": 230
+    },
+    {
+      "epoch": 0.6537282941777324,
+      "grad_norm": 2.7992598675350258,
+      "learning_rate": 6.512261580381472e-06,
+      "loss": 0.0515,
+      "step": 240
+    },
+    {
+      "epoch": 0.6809669731018045,
+      "grad_norm": 3.885137671280064,
+      "learning_rate": 6.78474114441417e-06,
+      "loss": 0.0517,
+      "step": 250
+    },
+    {
+      "epoch": 0.7082056520258767,
+      "grad_norm": 2.47654168655763,
+      "learning_rate": 7.057220708446867e-06,
+      "loss": 0.0462,
+      "step": 260
+    },
+    {
+      "epoch": 0.7354443309499489,
+      "grad_norm": 2.5720242451467454,
+      "learning_rate": 7.329700272479565e-06,
+      "loss": 0.0454,
+      "step": 270
+    },
+    {
+      "epoch": 0.7626830098740212,
+      "grad_norm": 4.695199938458052,
+      "learning_rate": 7.602179836512263e-06,
+      "loss": 0.0464,
+      "step": 280
+    },
+    {
+      "epoch": 0.7899216887980933,
+      "grad_norm": 2.080104008186552,
+      "learning_rate": 7.87465940054496e-06,
+      "loss": 0.0416,
+      "step": 290
+    },
+    {
+      "epoch": 0.8171603677221655,
+      "grad_norm": 2.1981255385062517,
+      "learning_rate": 8.147138964577658e-06,
+      "loss": 0.0446,
+      "step": 300
+    },
+    {
+      "epoch": 0.8443990466462377,
+      "grad_norm": 1.7239470049599528,
+      "learning_rate": 8.419618528610354e-06,
+      "loss": 0.0452,
+      "step": 310
+    },
+    {
+      "epoch": 0.8716377255703098,
+      "grad_norm": 1.8811480620279255,
+      "learning_rate": 8.692098092643052e-06,
+      "loss": 0.033,
+      "step": 320
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 2.4779574516049556,
+      "learning_rate": 8.964577656675751e-06,
+      "loss": 0.0438,
+      "step": 330
+    },
+    {
+      "epoch": 0.9261150834184542,
+      "grad_norm": 2.42289553821888,
+      "learning_rate": 9.237057220708447e-06,
+      "loss": 0.0392,
+      "step": 340
+    },
+    {
+      "epoch": 0.9533537623425263,
+      "grad_norm": 2.3174600464823256,
+      "learning_rate": 9.509536784741146e-06,
+      "loss": 0.0394,
+      "step": 350
+    },
+    {
+      "epoch": 0.9805924412665986,
+      "grad_norm": 2.076316899586314,
+      "learning_rate": 9.782016348773843e-06,
+      "loss": 0.0387,
+      "step": 360
+    },
+    {
+      "epoch": 1.0054477357848144,
+      "grad_norm": 1.7952293400096322,
+      "learning_rate": 9.99999095346085e-06,
+      "loss": 0.0332,
+      "step": 370
+    },
+    {
+      "epoch": 1.0326864147088866,
+      "grad_norm": 2.3966331090661925,
+      "learning_rate": 9.999674328027824e-06,
+      "loss": 0.0349,
+      "step": 380
+    },
+    {
+      "epoch": 1.0599250936329587,
+      "grad_norm": 1.8578054931433101,
+      "learning_rate": 9.998905408372662e-06,
+      "loss": 0.0332,
+      "step": 390
+    },
+    {
+      "epoch": 1.087163772557031,
+      "grad_norm": 2.067301033604286,
+      "learning_rate": 9.997684264055478e-06,
+      "loss": 0.036,
+      "step": 400
+    },
+    {
+      "epoch": 1.1144024514811033,
+      "grad_norm": 1.656723292655721,
+      "learning_rate": 9.99601100554677e-06,
+      "loss": 0.0315,
+      "step": 410
+    },
+    {
+      "epoch": 1.1416411304051755,
+      "grad_norm": 1.4305496511087652,
+      "learning_rate": 9.99388578421743e-06,
+      "loss": 0.0307,
+      "step": 420
+    },
+    {
+      "epoch": 1.1688798093292476,
+      "grad_norm": 1.4756680048744966,
+      "learning_rate": 9.991308792325045e-06,
+      "loss": 0.0279,
+      "step": 430
+    },
+    {
+      "epoch": 1.1961184882533198,
+      "grad_norm": 2.488649223393654,
+      "learning_rate": 9.988280262996507e-06,
+      "loss": 0.0263,
+      "step": 440
+    },
+    {
+      "epoch": 1.223357167177392,
+      "grad_norm": 1.4666750141420732,
+      "learning_rate": 9.98480047020693e-06,
+      "loss": 0.0268,
+      "step": 450
+    },
+    {
+      "epoch": 1.2505958461014641,
+      "grad_norm": 1.320119597330066,
+      "learning_rate": 9.980869728754847e-06,
+      "loss": 0.0298,
+      "step": 460
+    },
+    {
+      "epoch": 1.2778345250255363,
+      "grad_norm": 1.390841137051498,
+      "learning_rate": 9.976488394233752e-06,
+      "loss": 0.021,
+      "step": 470
+    },
+    {
+      "epoch": 1.3050732039496085,
+      "grad_norm": 1.4228820783227014,
+      "learning_rate": 9.971656862999917e-06,
+      "loss": 0.0276,
+      "step": 480
+    },
+    {
+      "epoch": 1.3323118828736806,
+      "grad_norm": 1.1183882912895564,
+      "learning_rate": 9.966375572136546e-06,
+      "loss": 0.0282,
+      "step": 490
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 1.1616366909466755,
+      "learning_rate": 9.960644999414226e-06,
+      "loss": 0.0214,
+      "step": 500
+    },
+    {
+      "epoch": 1.386789240721825,
+      "grad_norm": 1.409120984041759,
+      "learning_rate": 9.954465663247708e-06,
+      "loss": 0.0178,
+      "step": 510
+    },
+    {
+      "epoch": 1.4140279196458971,
+      "grad_norm": 0.9803319101168316,
+      "learning_rate": 9.947838122649014e-06,
+      "loss": 0.0202,
+      "step": 520
+    },
+    {
+      "epoch": 1.4412665985699693,
+      "grad_norm": 1.8131277665703773,
+      "learning_rate": 9.94076297717686e-06,
+      "loss": 0.0208,
+      "step": 530
+    },
+    {
+      "epoch": 1.4685052774940415,
+      "grad_norm": 1.1662863071032854,
+      "learning_rate": 9.933240866882418e-06,
+      "loss": 0.0169,
+      "step": 540
+    },
+    {
+      "epoch": 1.4957439564181136,
+      "grad_norm": 1.1465063039077388,
+      "learning_rate": 9.925272472251415e-06,
+      "loss": 0.0211,
+      "step": 550
+    },
+    {
+      "epoch": 1.5229826353421858,
+      "grad_norm": 1.193468165618273,
+      "learning_rate": 9.916858514142575e-06,
+      "loss": 0.0198,
+      "step": 560
+    },
+    {
+      "epoch": 1.550221314266258,
+      "grad_norm": 1.109324425932322,
+      "learning_rate": 9.907999753722407e-06,
+      "loss": 0.021,
+      "step": 570
+    },
+    {
+      "epoch": 1.5774599931903301,
+      "grad_norm": 1.290613695650256,
+      "learning_rate": 9.898696992396333e-06,
+      "loss": 0.0171,
+      "step": 580
+    },
+    {
+      "epoch": 1.6046986721144023,
+      "grad_norm": 1.6974083987042456,
+      "learning_rate": 9.888951071736215e-06,
+      "loss": 0.0192,
+      "step": 590
+    },
+    {
+      "epoch": 1.6319373510384745,
+      "grad_norm": 1.2163159155887682,
+      "learning_rate": 9.878762873404197e-06,
+      "loss": 0.013,
+      "step": 600
+    },
+    {
+      "epoch": 1.6591760299625467,
+      "grad_norm": 1.0193875076300951,
+      "learning_rate": 9.86813331907296e-06,
+      "loss": 0.0163,
+      "step": 610
+    },
+    {
+      "epoch": 1.686414708886619,
+      "grad_norm": 1.1034023564810655,
+      "learning_rate": 9.857063370342338e-06,
+      "loss": 0.0174,
+      "step": 620
+    },
+    {
+      "epoch": 1.7136533878106912,
+      "grad_norm": 1.5309168123244021,
+      "learning_rate": 9.845554028652331e-06,
+      "loss": 0.0158,
+      "step": 630
+    },
+    {
+      "epoch": 1.7408920667347634,
+      "grad_norm": 0.5532697619897224,
+      "learning_rate": 9.833606335192506e-06,
+      "loss": 0.0108,
+      "step": 640
+    },
+    {
+      "epoch": 1.7681307456588355,
+      "grad_norm": 1.0576521653821709,
+      "learning_rate": 9.821221370807805e-06,
+      "loss": 0.0154,
+      "step": 650
+    },
+    {
+      "epoch": 1.7953694245829077,
+      "grad_norm": 1.0783675700881836,
+      "learning_rate": 9.808400255900772e-06,
+      "loss": 0.0114,
+      "step": 660
+    },
+    {
+      "epoch": 1.8226081035069799,
+      "grad_norm": 0.599102289097004,
+      "learning_rate": 9.795144150330194e-06,
+      "loss": 0.0126,
+      "step": 670
+    },
+    {
+      "epoch": 1.849846782431052,
+      "grad_norm": 1.1075249779167584,
+      "learning_rate": 9.781454253306169e-06,
+      "loss": 0.0141,
+      "step": 680
+    },
+    {
+      "epoch": 1.8770854613551244,
+      "grad_norm": 0.69017494598675,
+      "learning_rate": 9.76733180328163e-06,
+      "loss": 0.0146,
+      "step": 690
+    },
+    {
+      "epoch": 1.9043241402791966,
+      "grad_norm": 0.9541591518502084,
+      "learning_rate": 9.752778077840302e-06,
+      "loss": 0.0097,
+      "step": 700
+    },
+    {
+      "epoch": 1.9315628192032688,
+      "grad_norm": 1.515252524842471,
+      "learning_rate": 9.737794393581125e-06,
+      "loss": 0.0102,
+      "step": 710
+    },
+    {
+      "epoch": 1.958801498127341,
+      "grad_norm": 0.6520067186874438,
+      "learning_rate": 9.722382105999156e-06,
+      "loss": 0.0121,
+      "step": 720
+    },
+    {
+      "epoch": 1.9860401770514131,
+      "grad_norm": 1.111673947257393,
+      "learning_rate": 9.706542609362928e-06,
+      "loss": 0.0101,
+      "step": 730
+    },
+    {
+      "epoch": 2.010895471569629,
+      "grad_norm": 1.2740352672206354,
+      "learning_rate": 9.690277336588338e-06,
+      "loss": 0.0093,
+      "step": 740
+    },
+    {
+      "epoch": 2.038134150493701,
+      "grad_norm": 1.2314399048766502,
+      "learning_rate": 9.673587759109007e-06,
+      "loss": 0.0082,
+      "step": 750
+    },
+    {
+      "epoch": 2.065372829417773,
+      "grad_norm": 0.6515664977184386,
+      "learning_rate": 9.656475386743166e-06,
+      "loss": 0.0078,
+      "step": 760
+    },
+    {
+      "epoch": 2.0926115083418453,
+      "grad_norm": 0.6076512914812847,
+      "learning_rate": 9.638941767557085e-06,
+      "loss": 0.0086,
+      "step": 770
+    },
+    {
+      "epoch": 2.1198501872659175,
+      "grad_norm": 0.49805773777686746,
+      "learning_rate": 9.620988487724999e-06,
+      "loss": 0.0094,
+      "step": 780
+    },
+    {
+      "epoch": 2.1470888661899896,
+      "grad_norm": 1.1149194861607004,
+      "learning_rate": 9.602617171385646e-06,
+      "loss": 0.0075,
+      "step": 790
+    },
+    {
+      "epoch": 2.174327545114062,
+      "grad_norm": 0.33357565062562405,
+      "learning_rate": 9.583829480495325e-06,
+      "loss": 0.0062,
+      "step": 800
+    },
+    {
+      "epoch": 2.201566224038134,
+      "grad_norm": 1.2725673141069516,
+      "learning_rate": 9.564627114677546e-06,
+      "loss": 0.0074,
+      "step": 810
+    },
+    {
+      "epoch": 2.2288049029622066,
+      "grad_norm": 0.8173124298927218,
+      "learning_rate": 9.54501181106928e-06,
+      "loss": 0.0102,
+      "step": 820
+    },
+    {
+      "epoch": 2.2560435818862787,
+      "grad_norm": 0.6950238807140082,
+      "learning_rate": 9.524985344163801e-06,
+      "loss": 0.0065,
+      "step": 830
+    },
+    {
+      "epoch": 2.283282260810351,
+      "grad_norm": 0.9944262630317349,
+      "learning_rate": 9.504549525650173e-06,
+      "loss": 0.0067,
+      "step": 840
+    },
+    {
+      "epoch": 2.310520939734423,
+      "grad_norm": 0.7645573101281118,
+      "learning_rate": 9.483706204249332e-06,
+      "loss": 0.0072,
+      "step": 850
+    },
+    {
+      "epoch": 2.3377596186584952,
+      "grad_norm": 0.5284367702467161,
+      "learning_rate": 9.462457265546867e-06,
+      "loss": 0.007,
+      "step": 860
+    },
+    {
+      "epoch": 2.3649982975825674,
+      "grad_norm": 0.5487759594771856,
+      "learning_rate": 9.440804631822421e-06,
+      "loss": 0.0073,
+      "step": 870
+    },
+    {
+      "epoch": 2.3922369765066396,
+      "grad_norm": 0.6876376014240485,
+      "learning_rate": 9.418750261875811e-06,
+      "loss": 0.006,
+      "step": 880
+    },
+    {
+      "epoch": 2.4194756554307117,
+      "grad_norm": 0.5930505890719068,
+      "learning_rate": 9.396296150849804e-06,
+      "loss": 0.0034,
+      "step": 890
+    },
+    {
+      "epoch": 2.446714334354784,
+      "grad_norm": 0.2924797737902157,
+      "learning_rate": 9.373444330049645e-06,
+      "loss": 0.0048,
+      "step": 900
+    },
+    {
+      "epoch": 2.473953013278856,
+      "grad_norm": 0.818504316665287,
+      "learning_rate": 9.350196866759289e-06,
+      "loss": 0.0065,
+      "step": 910
+    },
+    {
+      "epoch": 2.5011916922029283,
+      "grad_norm": 0.6173390676022147,
+      "learning_rate": 9.326555864054383e-06,
+      "loss": 0.0063,
+      "step": 920
+    },
+    {
+      "epoch": 2.5284303711270004,
+      "grad_norm": 0.42627927587804193,
+      "learning_rate": 9.302523460612015e-06,
+      "loss": 0.0055,
+      "step": 930
+    },
+    {
+      "epoch": 2.5556690500510726,
+      "grad_norm": 0.5539596964886677,
+      "learning_rate": 9.278101830517234e-06,
+      "loss": 0.0047,
+      "step": 940
+    },
+    {
+      "epoch": 2.5829077289751448,
+      "grad_norm": 0.3896212375163213,
+      "learning_rate": 9.253293183066382e-06,
+      "loss": 0.0056,
+      "step": 950
+    },
+    {
+      "epoch": 2.610146407899217,
+      "grad_norm": 0.658832029703366,
+      "learning_rate": 9.228099762567221e-06,
+      "loss": 0.0053,
+      "step": 960
+    },
+    {
+      "epoch": 2.637385086823289,
+      "grad_norm": 0.2940172656833637,
+      "learning_rate": 9.202523848135903e-06,
+      "loss": 0.005,
+      "step": 970
+    },
+    {
+      "epoch": 2.6646237657473613,
+      "grad_norm": 0.8264261097315277,
+      "learning_rate": 9.176567753490795e-06,
+      "loss": 0.0088,
+      "step": 980
+    },
+    {
+      "epoch": 2.6918624446714334,
+      "grad_norm": 0.47332662322314495,
+      "learning_rate": 9.15023382674317e-06,
+      "loss": 0.0049,
+      "step": 990
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "grad_norm": 0.6043816603050725,
+      "learning_rate": 9.12352445018478e-06,
+      "loss": 0.0054,
+      "step": 1000
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "eval_loss": 0.009971115738153458,
+      "eval_runtime": 149.6934,
+      "eval_samples_per_second": 1.336,
+      "eval_steps_per_second": 0.167,
+      "step": 1000
+    },
+    {
+      "epoch": 2.7463398025195778,
+      "grad_norm": 0.18838425652727245,
+      "learning_rate": 9.096442040072342e-06,
+      "loss": 0.0036,
+      "step": 1010
+    },
+    {
+      "epoch": 2.77357848144365,
+      "grad_norm": 0.33857822247434793,
+      "learning_rate": 9.06898904640896e-06,
+      "loss": 0.0038,
+      "step": 1020
+    },
+    {
+      "epoch": 2.800817160367722,
+      "grad_norm": 0.56645910713706,
+      "learning_rate": 9.04116795272248e-06,
+      "loss": 0.0055,
+      "step": 1030
+    },
+    {
+      "epoch": 2.8280558392917943,
+      "grad_norm": 0.28109810510949723,
+      "learning_rate": 9.01298127584082e-06,
+      "loss": 0.0036,
+      "step": 1040
+    },
+    {
+      "epoch": 2.8552945182158664,
+      "grad_norm": 0.542296858675033,
+      "learning_rate": 8.984431565664287e-06,
+      "loss": 0.0048,
+      "step": 1050
+    },
+    {
+      "epoch": 2.8825331971399386,
+      "grad_norm": 0.5373500607763515,
+      "learning_rate": 8.955521404934895e-06,
+      "loss": 0.0043,
+      "step": 1060
+    },
+    {
+      "epoch": 2.9097718760640108,
+      "grad_norm": 0.5880158628582186,
+      "learning_rate": 8.926253409002724e-06,
+      "loss": 0.0045,
+      "step": 1070
+    },
+    {
+      "epoch": 2.937010554988083,
+      "grad_norm": 1.0360372633008765,
+      "learning_rate": 8.896630225589325e-06,
+      "loss": 0.003,
+      "step": 1080
+    },
+    {
+      "epoch": 2.964249233912155,
+      "grad_norm": 0.6664430992854442,
+      "learning_rate": 8.866654534548188e-06,
+      "loss": 0.0035,
+      "step": 1090
+    },
+    {
+      "epoch": 2.9914879128362273,
+      "grad_norm": 0.3828974814299205,
+      "learning_rate": 8.836329047622315e-06,
+      "loss": 0.0051,
+      "step": 1100
+    },
+    {
+      "epoch": 3.0163432073544434,
+      "grad_norm": 0.5237696754640224,
+      "learning_rate": 8.805656508198893e-06,
+      "loss": 0.0025,
+      "step": 1110
+    },
+    {
+      "epoch": 3.0435818862785156,
+      "grad_norm": 0.31976718993311765,
+      "learning_rate": 8.774639691061133e-06,
+      "loss": 0.0027,
+      "step": 1120
+    },
+    {
+      "epoch": 3.0708205652025877,
+      "grad_norm": 0.8311789315891146,
+      "learning_rate": 8.743281402137234e-06,
+      "loss": 0.0043,
+      "step": 1130
+    },
+    {
+      "epoch": 3.09805924412666,
+      "grad_norm": 0.5395564063408896,
+      "learning_rate": 8.711584478246545e-06,
+      "loss": 0.0037,
+      "step": 1140
+    },
+    {
+      "epoch": 3.125297923050732,
+      "grad_norm": 0.4868560419941669,
+      "learning_rate": 8.679551786842947e-06,
+      "loss": 0.003,
+      "step": 1150
+    },
+    {
+      "epoch": 3.1525366019748042,
+      "grad_norm": 0.09982986237608656,
+      "learning_rate": 8.647186225755435e-06,
+      "loss": 0.004,
+      "step": 1160
+    },
+    {
+      "epoch": 3.1797752808988764,
+      "grad_norm": 0.2992508205991956,
+      "learning_rate": 8.614490722925976e-06,
+      "loss": 0.0025,
+      "step": 1170
+    },
+    {
+      "epoch": 3.2070139598229486,
+      "grad_norm": 0.7674760077175568,
+      "learning_rate": 8.581468236144624e-06,
+      "loss": 0.0029,
+      "step": 1180
+    },
+    {
+      "epoch": 3.2342526387470207,
+      "grad_norm": 0.688415374822658,
+      "learning_rate": 8.548121752781958e-06,
+      "loss": 0.0024,
+      "step": 1190
+    },
+    {
+      "epoch": 3.261491317671093,
+      "grad_norm": 0.9052988126796538,
+      "learning_rate": 8.514454289518815e-06,
+      "loss": 0.0034,
+      "step": 1200
+    },
+    {
+      "epoch": 3.288729996595165,
+      "grad_norm": 0.40120185903679884,
+      "learning_rate": 8.480468892073396e-06,
+      "loss": 0.002,
+      "step": 1210
+    },
+    {
+      "epoch": 3.3159686755192372,
+      "grad_norm": 0.5944020494018145,
+      "learning_rate": 8.446168634925744e-06,
+      "loss": 0.0027,
+      "step": 1220
+    },
+    {
+      "epoch": 3.3432073544433094,
+      "grad_norm": 0.4472237168192407,
+      "learning_rate": 8.411556621039587e-06,
+      "loss": 0.0076,
+      "step": 1230
+    },
+    {
+      "epoch": 3.3704460333673816,
+      "grad_norm": 0.28045654193358444,
+      "learning_rate": 8.376635981581652e-06,
+      "loss": 0.0035,
+      "step": 1240
+    },
+    {
+      "epoch": 3.3976847122914537,
+      "grad_norm": 0.17536506030522428,
+      "learning_rate": 8.341409875638396e-06,
+      "loss": 0.0038,
+      "step": 1250
+    },
+    {
+      "epoch": 3.424923391215526,
+      "grad_norm": 5.902141227200851,
+      "learning_rate": 8.305881489930224e-06,
+      "loss": 0.0075,
+      "step": 1260
+    },
+    {
+      "epoch": 3.452162070139598,
+      "grad_norm": 1.1226970845212438,
+      "learning_rate": 8.270054038523194e-06,
+      "loss": 0.0039,
+      "step": 1270
+    },
+    {
+      "epoch": 3.4794007490636703,
+      "grad_norm": 0.2305609441856671,
+      "learning_rate": 8.233930762538271e-06,
+      "loss": 0.0038,
+      "step": 1280
+    },
+    {
+      "epoch": 3.506639427987743,
+      "grad_norm": 0.17972249159415393,
+      "learning_rate": 8.197514929858108e-06,
+      "loss": 0.0033,
+      "step": 1290
+    },
+    {
+      "epoch": 3.533878106911815,
+      "grad_norm": 0.22572705207090887,
+      "learning_rate": 8.160809834831422e-06,
+      "loss": 0.0018,
+      "step": 1300
+    },
+    {
+      "epoch": 3.561116785835887,
+      "grad_norm": 0.48294663787369996,
+      "learning_rate": 8.123818797974973e-06,
+      "loss": 0.001,
+      "step": 1310
+    },
+    {
+      "epoch": 3.5883554647599594,
+      "grad_norm": 0.0324163008144768,
+      "learning_rate": 8.08654516567318e-06,
+      "loss": 0.0017,
+      "step": 1320
+    },
+    {
+      "epoch": 3.6155941436840315,
+      "grad_norm": 0.2702928606649647,
+      "learning_rate": 8.04899230987537e-06,
+      "loss": 0.0007,
+      "step": 1330
+    },
+    {
+      "epoch": 3.6428328226081037,
+      "grad_norm": 0.02733106163122347,
+      "learning_rate": 8.011163627790765e-06,
+      "loss": 0.0015,
+      "step": 1340
+    },
+    {
+      "epoch": 3.670071501532176,
+      "grad_norm": 0.17653493830017525,
+      "learning_rate": 7.97306254158113e-06,
+      "loss": 0.0033,
+      "step": 1350
+    },
+    {
+      "epoch": 3.697310180456248,
+      "grad_norm": 0.06779788652309977,
+      "learning_rate": 7.934692498051202e-06,
+      "loss": 0.0015,
+      "step": 1360
+    },
+    {
+      "epoch": 3.72454885938032,
+      "grad_norm": 0.04283617369672373,
+      "learning_rate": 7.896056968336868e-06,
+      "loss": 0.0016,
+      "step": 1370
+    },
+    {
+      "epoch": 3.7517875383043924,
+      "grad_norm": 0.4528535210316289,
+      "learning_rate": 7.857159447591153e-06,
+      "loss": 0.0015,
+      "step": 1380
+    },
+    {
+      "epoch": 3.7790262172284645,
+      "grad_norm": 0.03703542904667366,
+      "learning_rate": 7.81800345466804e-06,
+      "loss": 0.0007,
+      "step": 1390
+    },
+    {
+      "epoch": 3.8062648961525367,
+      "grad_norm": 0.22254648728704393,
+      "learning_rate": 7.778592531804115e-06,
+      "loss": 0.0018,
+      "step": 1400
+    },
+    {
+      "epoch": 3.833503575076609,
+      "grad_norm": 0.1551875795468263,
+      "learning_rate": 7.738930244298146e-06,
+      "loss": 0.003,
+      "step": 1410
+    },
+    {
+      "epoch": 3.860742254000681,
+      "grad_norm": 0.4498866311661179,
+      "learning_rate": 7.699020180188533e-06,
+      "loss": 0.0017,
+      "step": 1420
+    },
+    {
+      "epoch": 3.887980932924753,
+      "grad_norm": 1.4505936210625598,
+      "learning_rate": 7.658865949928717e-06,
+      "loss": 0.0021,
+      "step": 1430
+    },
+    {
+      "epoch": 3.9152196118488254,
+      "grad_norm": 0.2597247781008665,
+      "learning_rate": 7.618471186060574e-06,
+      "loss": 0.0009,
+      "step": 1440
+    },
+    {
+      "epoch": 3.9424582907728976,
+      "grad_norm": 0.05461306630022223,
+      "learning_rate": 7.577839542885783e-06,
+      "loss": 0.0012,
+      "step": 1450
+    },
+    {
+      "epoch": 3.9696969696969697,
+      "grad_norm": 0.2510446146562708,
+      "learning_rate": 7.5369746961352505e-06,
+      "loss": 0.0012,
+      "step": 1460
+    },
+    {
+      "epoch": 3.996935648621042,
+      "grad_norm": 0.027247865962538042,
+      "learning_rate": 7.495880342636581e-06,
+      "loss": 0.0016,
+      "step": 1470
+    },
+    {
+      "epoch": 4.021790943139258,
+      "grad_norm": 0.3181735974801834,
+      "learning_rate": 7.454560199979647e-06,
+      "loss": 0.0005,
+      "step": 1480
+    },
+    {
+      "epoch": 4.04902962206333,
+      "grad_norm": 0.03550322906594092,
+      "learning_rate": 7.413018006180278e-06,
+      "loss": 0.0006,
+      "step": 1490
+    },
+    {
+      "epoch": 4.076268300987402,
+      "grad_norm": 0.7839865968633526,
+      "learning_rate": 7.371257519342103e-06,
+      "loss": 0.0023,
+      "step": 1500
+    },
+    {
+      "epoch": 4.103506979911474,
+      "grad_norm": 0.27056209178067114,
+      "learning_rate": 7.329282517316574e-06,
+      "loss": 0.0013,
+      "step": 1510
+    },
+    {
+      "epoch": 4.130745658835546,
+      "grad_norm": 0.025007951464925165,
+      "learning_rate": 7.287096797361197e-06,
+      "loss": 0.0014,
+      "step": 1520
+    },
+    {
+      "epoch": 4.157984337759618,
+      "grad_norm": 0.1639293410219479,
+      "learning_rate": 7.244704175796028e-06,
+      "loss": 0.002,
+      "step": 1530
+    },
+    {
+      "epoch": 4.185223016683691,
+      "grad_norm": 0.09539274967398963,
+      "learning_rate": 7.202108487658416e-06,
+      "loss": 0.0017,
+      "step": 1540
+    },
+    {
+      "epoch": 4.212461695607763,
+      "grad_norm": 0.18901065014774657,
+      "learning_rate": 7.159313586356077e-06,
+      "loss": 0.002,
+      "step": 1550
+    },
+    {
+      "epoch": 4.239700374531835,
+      "grad_norm": 0.027388119425054664,
+      "learning_rate": 7.116323343318495e-06,
+      "loss": 0.0017,
+      "step": 1560
+    },
+    {
+      "epoch": 4.266939053455907,
+      "grad_norm": 0.13933358678308516,
+      "learning_rate": 7.073141647646691e-06,
+      "loss": 0.0009,
+      "step": 1570
+    },
+    {
+      "epoch": 4.294177732379979,
+      "grad_norm": 0.011964487372353175,
+      "learning_rate": 7.029772405761397e-06,
+      "loss": 0.0005,
+      "step": 1580
+    },
+    {
+      "epoch": 4.321416411304051,
+      "grad_norm": 0.044579473352322464,
+      "learning_rate": 6.9862195410496655e-06,
+      "loss": 0.0007,
+      "step": 1590
+    },
+    {
+      "epoch": 4.348655090228124,
+      "grad_norm": 0.9421209582985217,
+      "learning_rate": 6.942486993509941e-06,
+      "loss": 0.0011,
+      "step": 1600
+    },
+    {
+      "epoch": 4.375893769152196,
+      "grad_norm": 0.165168485428461,
+      "learning_rate": 6.898578719395622e-06,
+      "loss": 0.0007,
+      "step": 1610
+    },
+    {
+      "epoch": 4.403132448076268,
+      "grad_norm": 0.012552169908338339,
+      "learning_rate": 6.854498690857173e-06,
+      "loss": 0.0024,
+      "step": 1620
+    },
+    {
+      "epoch": 4.43037112700034,
+      "grad_norm": 0.33669756307886667,
+      "learning_rate": 6.810250895582773e-06,
+      "loss": 0.0013,
+      "step": 1630
+    },
+    {
+      "epoch": 4.457609805924413,
+      "grad_norm": 0.03430019485251983,
+      "learning_rate": 6.765839336437574e-06,
+      "loss": 0.001,
+      "step": 1640
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 0.7568315535654873,
+      "learning_rate": 6.721268031101586e-06,
+      "loss": 0.0018,
+      "step": 1650
+    },
+    {
+      "epoch": 4.5120871637725575,
+      "grad_norm": 0.36926846488952053,
+      "learning_rate": 6.676541011706212e-06,
+      "loss": 0.0032,
+      "step": 1660
+    },
+    {
+      "epoch": 4.539325842696629,
+      "grad_norm": 0.30700403135022064,
+      "learning_rate": 6.631662324469492e-06,
+      "loss": 0.0021,
+      "step": 1670
+    },
+    {
+      "epoch": 4.566564521620702,
+      "grad_norm": 0.07283695365864443,
+      "learning_rate": 6.586636029330054e-06,
+      "loss": 0.0015,
+      "step": 1680
+    },
+    {
+      "epoch": 4.593803200544773,
+      "grad_norm": 0.5098936742183463,
+      "learning_rate": 6.5414661995798346e-06,
+      "loss": 0.0026,
+      "step": 1690
+    },
+    {
+      "epoch": 4.621041879468846,
+      "grad_norm": 0.15016221369549917,
+      "learning_rate": 6.496156921495594e-06,
+      "loss": 0.0023,
+      "step": 1700
+    },
+    {
+      "epoch": 4.648280558392918,
+      "grad_norm": 0.7027337621531187,
+      "learning_rate": 6.450712293969251e-06,
+      "loss": 0.0036,
+      "step": 1710
+    },
+    {
+      "epoch": 4.6755192373169905,
+      "grad_norm": 0.48920213901161386,
+      "learning_rate": 6.405136428137072e-06,
+      "loss": 0.0024,
+      "step": 1720
+    },
+    {
+      "epoch": 4.702757916241063,
+      "grad_norm": 0.526663059492545,
+      "learning_rate": 6.359433447007761e-06,
+      "loss": 0.0037,
+      "step": 1730
+    },
+    {
+      "epoch": 4.729996595165135,
+      "grad_norm": 0.43485515633750277,
+      "learning_rate": 6.313607485089479e-06,
+      "loss": 0.002,
+      "step": 1740
+    },
+    {
+      "epoch": 4.757235274089207,
+      "grad_norm": 0.1608557350260687,
+      "learning_rate": 6.267662688015811e-06,
+      "loss": 0.0011,
+      "step": 1750
+    },
+    {
+      "epoch": 4.784473953013279,
+      "grad_norm": 0.016233665978459856,
+      "learning_rate": 6.221603212170727e-06,
+      "loss": 0.0016,
+      "step": 1760
+    },
+    {
+      "epoch": 4.811712631937351,
+      "grad_norm": 0.3060301856403388,
+      "learning_rate": 6.175433224312588e-06,
+      "loss": 0.0008,
+      "step": 1770
+    },
+    {
+      "epoch": 4.8389513108614235,
+      "grad_norm": 0.0535023008279656,
+      "learning_rate": 6.129156901197195e-06,
+      "loss": 0.0007,
+      "step": 1780
+    },
+    {
+      "epoch": 4.866189989785496,
+      "grad_norm": 0.22805192659166784,
+      "learning_rate": 6.082778429199937e-06,
+      "loss": 0.0011,
+      "step": 1790
+    },
+    {
+      "epoch": 4.893428668709568,
+      "grad_norm": 0.06801175552041476,
+      "learning_rate": 6.036302003937076e-06,
+      "loss": 0.0004,
+      "step": 1800
+    },
+    {
+      "epoch": 4.92066734763364,
+      "grad_norm": 0.3046742023784698,
+      "learning_rate": 5.9897318298861885e-06,
+      "loss": 0.0007,
+      "step": 1810
+    },
+    {
+      "epoch": 4.947906026557712,
+      "grad_norm": 0.033986290353038136,
+      "learning_rate": 5.943072120005816e-06,
+      "loss": 0.0007,
+      "step": 1820
+    },
+    {
+      "epoch": 4.975144705481784,
+      "grad_norm": 0.09040671159275827,
+      "learning_rate": 5.89632709535433e-06,
+      "loss": 0.0019,
+      "step": 1830
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2530736784412786,
+      "learning_rate": 5.849500984708082e-06,
+      "loss": 0.0016,
+      "step": 1840
+    },
+    {
+      "epoch": 5.027238678924072,
+      "grad_norm": 0.08687153636471827,
+      "learning_rate": 5.802598024178848e-06,
+      "loss": 0.0004,
+      "step": 1850
+    },
+    {
+      "epoch": 5.054477357848144,
+      "grad_norm": 0.45420511928877233,
+      "learning_rate": 5.755622456830605e-06,
+      "loss": 0.0008,
+      "step": 1860
+    },
+    {
+      "epoch": 5.0817160367722165,
+      "grad_norm": 0.1542430485091151,
+      "learning_rate": 5.708578532295691e-06,
+      "loss": 0.0016,
+      "step": 1870
+    },
+    {
+      "epoch": 5.108954715696289,
+      "grad_norm": 1.3515082865895989,
+      "learning_rate": 5.661470506390354e-06,
+      "loss": 0.0011,
+      "step": 1880
+    },
+    {
+      "epoch": 5.136193394620361,
+      "grad_norm": 0.1596903735504535,
+      "learning_rate": 5.61430264072976e-06,
+      "loss": 0.0014,
+      "step": 1890
+    },
+    {
+      "epoch": 5.163432073544433,
+      "grad_norm": 0.19923117752022435,
+      "learning_rate": 5.5670792023424615e-06,
+      "loss": 0.0015,
+      "step": 1900
+    },
+    {
+      "epoch": 5.190670752468505,
+      "grad_norm": 0.302828135997675,
+      "learning_rate": 5.519804463284382e-06,
+      "loss": 0.0009,
+      "step": 1910
+    },
+    {
+      "epoch": 5.217909431392577,
+      "grad_norm": 0.04653233725601432,
+      "learning_rate": 5.472482700252347e-06,
+      "loss": 0.0012,
+      "step": 1920
+    },
+    {
+      "epoch": 5.2451481103166495,
+      "grad_norm": 0.5190292480319276,
+      "learning_rate": 5.425118194197196e-06,
+      "loss": 0.0023,
+      "step": 1930
+    },
+    {
+      "epoch": 5.272386789240722,
+      "grad_norm": 0.007225303260017864,
+      "learning_rate": 5.3777152299365e-06,
+      "loss": 0.0005,
+      "step": 1940
+    },
+    {
+      "epoch": 5.299625468164794,
+      "grad_norm": 0.08842755160666287,
+      "learning_rate": 5.3302780957669454e-06,
+      "loss": 0.0006,
+      "step": 1950
+    },
+    {
+      "epoch": 5.326864147088866,
+      "grad_norm": 0.024822557291839333,
+      "learning_rate": 5.282811083076388e-06,
+      "loss": 0.0004,
+      "step": 1960
+    },
+    {
+      "epoch": 5.354102826012938,
+      "grad_norm": 1.2627706166913806,
+      "learning_rate": 5.235318485955638e-06,
+      "loss": 0.0007,
+      "step": 1970
+    },
+    {
+      "epoch": 5.38134150493701,
+      "grad_norm": 0.03392392848083845,
+      "learning_rate": 5.187804600809995e-06,
+      "loss": 0.0014,
+      "step": 1980
+    },
+    {
+      "epoch": 5.4085801838610825,
+      "grad_norm": 0.009487721281030682,
+      "learning_rate": 5.140273725970569e-06,
+      "loss": 0.0019,
+      "step": 1990
+    },
+    {
+      "epoch": 5.435818862785155,
+      "grad_norm": 0.03169860186889457,
+      "learning_rate": 5.092730161305444e-06,
+      "loss": 0.0005,
+      "step": 2000
+    },
+    {
+      "epoch": 5.435818862785155,
+      "eval_loss": 0.003610835410654545,
+      "eval_runtime": 149.9472,
+      "eval_samples_per_second": 1.334,
+      "eval_steps_per_second": 0.167,
+      "step": 2000
+    },
+    {
+      "epoch": 5.463057541709227,
+      "grad_norm": 0.26681987017023606,
+      "learning_rate": 5.045178207830687e-06,
+      "loss": 0.0005,
+      "step": 2010
+    },
+    {
+      "epoch": 5.490296220633299,
+      "grad_norm": 0.020589913051757485,
+      "learning_rate": 4.997622167321246e-06,
+      "loss": 0.0004,
+      "step": 2020
+    },
+    {
+      "epoch": 5.517534899557371,
+      "grad_norm": 0.005508716128027595,
+      "learning_rate": 4.950066341921813e-06,
+      "loss": 0.0002,
+      "step": 2030
+    },
+    {
+      "epoch": 5.544773578481443,
+      "grad_norm": 0.12421491718000478,
+      "learning_rate": 4.902515033757617e-06,
+      "loss": 0.0002,
+      "step": 2040
+    },
+    {
+      "epoch": 5.5720122574055155,
+      "grad_norm": 0.6904314051957775,
+      "learning_rate": 4.854972544545231e-06,
+      "loss": 0.0011,
+      "step": 2050
+    },
+    {
+      "epoch": 5.599250936329588,
+      "grad_norm": 0.020582980767102473,
+      "learning_rate": 4.807443175203432e-06,
+      "loss": 0.0008,
+      "step": 2060
+    },
+    {
+      "epoch": 5.62648961525366,
+      "grad_norm": 0.26044403454004866,
+      "learning_rate": 4.759931225464107e-06,
+      "loss": 0.0011,
+      "step": 2070
+    },
+    {
+      "epoch": 5.653728294177732,
+      "grad_norm": 0.13198469815528743,
+      "learning_rate": 4.712440993483281e-06,
+      "loss": 0.0005,
+      "step": 2080
+    },
+    {
+      "epoch": 5.680966973101804,
+      "grad_norm": 0.24787019272348249,
+      "learning_rate": 4.664976775452293e-06,
+      "loss": 0.0016,
+      "step": 2090
+    },
+    {
+      "epoch": 5.708205652025876,
+      "grad_norm": 0.06673597677280482,
+      "learning_rate": 4.617542865209133e-06,
+      "loss": 0.0001,
+      "step": 2100
+    },
+    {
+      "epoch": 5.7354443309499485,
+      "grad_norm": 0.01989819994546987,
+      "learning_rate": 4.5701435538500065e-06,
+      "loss": 0.0002,
+      "step": 2110
+    },
+    {
+      "epoch": 5.762683009874021,
+      "grad_norm": 0.06711337766264915,
+      "learning_rate": 4.522783129341141e-06,
+      "loss": 0.0011,
+      "step": 2120
+    },
+    {
+      "epoch": 5.789921688798094,
+      "grad_norm": 0.0258406372816757,
+      "learning_rate": 4.475465876130872e-06,
+      "loss": 0.0002,
+      "step": 2130
+    },
+    {
+      "epoch": 5.817160367722165,
+      "grad_norm": 0.0069848118261474626,
+      "learning_rate": 4.428196074762057e-06,
+      "loss": 0.0001,
+      "step": 2140
+    },
+    {
+      "epoch": 5.844399046646238,
+      "grad_norm": 0.00465294693967376,
+      "learning_rate": 4.380978001484836e-06,
+      "loss": 0.0008,
+      "step": 2150
+    },
+    {
+      "epoch": 5.871637725570309,
+      "grad_norm": 0.062291913740785465,
+      "learning_rate": 4.33381592786978e-06,
+      "loss": 0.0001,
+      "step": 2160
+    },
+    {
+      "epoch": 5.898876404494382,
+      "grad_norm": 0.00324106094253182,
+      "learning_rate": 4.286714120421465e-06,
+      "loss": 0.0001,
+      "step": 2170
+    },
+    {
+      "epoch": 5.926115083418454,
+      "grad_norm": 0.010405479601857403,
+      "learning_rate": 4.2396768401925044e-06,
+      "loss": 0.0001,
+      "step": 2180
+    },
+    {
+      "epoch": 5.953353762342527,
+      "grad_norm": 0.003621476287705226,
+      "learning_rate": 4.1927083423980755e-06,
+      "loss": 0.0001,
+      "step": 2190
+    },
+    {
+      "epoch": 5.980592441266599,
+      "grad_norm": 0.15175481500791388,
+      "learning_rate": 4.145812876030965e-06,
+      "loss": 0.0001,
+      "step": 2200
+    },
+    {
+      "epoch": 6.005447735784815,
+      "grad_norm": 0.009474114226140813,
+      "learning_rate": 4.098994683477197e-06,
+      "loss": 0.0,
+      "step": 2210
+    },
+    {
+      "epoch": 6.032686414708887,
+      "grad_norm": 0.010773928421478833,
+      "learning_rate": 4.0522580001322365e-06,
+      "loss": 0.0,
+      "step": 2220
+    },
+    {
+      "epoch": 6.059925093632959,
+      "grad_norm": 0.002749306413145174,
+      "learning_rate": 4.0056070540178425e-06,
+      "loss": 0.0,
+      "step": 2230
+    },
+    {
+      "epoch": 6.087163772557031,
+      "grad_norm": 0.001948904462067843,
+      "learning_rate": 3.959046065399575e-06,
+      "loss": 0.0,
+      "step": 2240
+    },
+    {
+      "epoch": 6.114402451481103,
+      "grad_norm": 0.001621993315411648,
+      "learning_rate": 3.912579246405016e-06,
+      "loss": 0.0,
+      "step": 2250
+    },
+    {
+      "epoch": 6.1416411304051755,
+      "grad_norm": 0.001255150538557096,
+      "learning_rate": 3.8662108006427165e-06,
+      "loss": 0.0,
+      "step": 2260
+    },
+    {
+      "epoch": 6.168879809329248,
+      "grad_norm": 0.004272455750195676,
+      "learning_rate": 3.819944922821914e-06,
+      "loss": 0.0,
+      "step": 2270
+    },
+    {
+      "epoch": 6.19611848825332,
+      "grad_norm": 0.00187243023068361,
+      "learning_rate": 3.773785798373069e-06,
+      "loss": 0.0,
+      "step": 2280
+    },
+    {
+      "epoch": 6.223357167177392,
+      "grad_norm": 0.0009374589516518995,
+      "learning_rate": 3.7277376030692263e-06,
+      "loss": 0.0,
+      "step": 2290
+    },
+    {
+      "epoch": 6.250595846101464,
+      "grad_norm": 0.001253252761018019,
+      "learning_rate": 3.681804502648254e-06,
+      "loss": 0.0,
+      "step": 2300
+    },
+    {
+      "epoch": 6.277834525025536,
+      "grad_norm": 0.002173317313832616,
+      "learning_rate": 3.6359906524359932e-06,
+      "loss": 0.0,
+      "step": 2310
+    },
+    {
+      "epoch": 6.3050732039496085,
+      "grad_norm": 0.00122096897637743,
+      "learning_rate": 3.590300196970341e-06,
+      "loss": 0.0,
+      "step": 2320
+    },
+    {
+      "epoch": 6.332311882873681,
+      "grad_norm": 0.0008158321760346172,
+      "learning_rate": 3.544737269626328e-06,
+      "loss": 0.0,
+      "step": 2330
+    },
+    {
+      "epoch": 6.359550561797753,
+      "grad_norm": 0.0011021236484427205,
+      "learning_rate": 3.4993059922421835e-06,
+      "loss": 0.0,
+      "step": 2340
+    },
+    {
+      "epoch": 6.386789240721825,
+      "grad_norm": 0.0007113597066715369,
+      "learning_rate": 3.4540104747464575e-06,
+      "loss": 0.0,
+      "step": 2350
+    },
+    {
+      "epoch": 6.414027919645897,
+      "grad_norm": 0.0007186713752736677,
+      "learning_rate": 3.408854814786219e-06,
+      "loss": 0.0,
+      "step": 2360
+    },
+    {
+      "epoch": 6.441266598569969,
+      "grad_norm": 0.0005956363546399899,
+      "learning_rate": 3.3638430973563597e-06,
+      "loss": 0.0,
+      "step": 2370
+    },
+    {
+      "epoch": 6.4685052774940415,
+      "grad_norm": 0.0013985565483587347,
+      "learning_rate": 3.318979394430051e-06,
+      "loss": 0.0,
+      "step": 2380
+    },
+    {
+      "epoch": 6.495743956418114,
+      "grad_norm": 0.0008815209213564751,
+      "learning_rate": 3.27426776459037e-06,
+      "loss": 0.0003,
+      "step": 2390
+    },
+    {
+      "epoch": 6.522982635342186,
+      "grad_norm": 0.0024178562381092818,
+      "learning_rate": 3.22971225266314e-06,
+      "loss": 0.0,
+      "step": 2400
+    },
+    {
+      "epoch": 6.550221314266258,
+      "grad_norm": 0.0010728069443376714,
+      "learning_rate": 3.1853168893510223e-06,
+      "loss": 0.0,
+      "step": 2410
+    },
+    {
+      "epoch": 6.57745999319033,
+      "grad_norm": 0.0010548514445552371,
+      "learning_rate": 3.141085690868871e-06,
+      "loss": 0.0,
+      "step": 2420
+    },
+    {
+      "epoch": 6.604698672114402,
+      "grad_norm": 0.0021998928664552233,
+      "learning_rate": 3.0970226585804175e-06,
+      "loss": 0.0001,
+      "step": 2430
+    },
+    {
+      "epoch": 6.6319373510384745,
+      "grad_norm": 0.0011062246966726207,
+      "learning_rate": 3.053131778636278e-06,
+      "loss": 0.0,
+      "step": 2440
+    },
+    {
+      "epoch": 6.659176029962547,
+      "grad_norm": 0.0011797120379395778,
+      "learning_rate": 3.0094170216133545e-06,
+      "loss": 0.0,
+      "step": 2450
+    },
+    {
+      "epoch": 6.686414708886619,
+      "grad_norm": 0.007225871987921568,
+      "learning_rate": 2.965882342155637e-06,
+      "loss": 0.0,
+      "step": 2460
+    },
+    {
+      "epoch": 6.713653387810691,
+      "grad_norm": 0.0010544539477212198,
+      "learning_rate": 2.9225316786164417e-06,
+      "loss": 0.0,
+      "step": 2470
+    },
+    {
+      "epoch": 6.740892066734763,
+      "grad_norm": 0.0006976448579587069,
+      "learning_rate": 2.8793689527021377e-06,
+      "loss": 0.0,
+      "step": 2480
+    },
+    {
+      "epoch": 6.768130745658835,
+      "grad_norm": 0.0027697202568828954,
+      "learning_rate": 2.836398069117362e-06,
+      "loss": 0.0,
+      "step": 2490
+    },
+    {
+      "epoch": 6.7953694245829075,
+      "grad_norm": 0.0005279000452700497,
+      "learning_rate": 2.7936229152117896e-06,
+      "loss": 0.0,
+      "step": 2500
+    },
+    {
+      "epoch": 6.82260810350698,
+      "grad_norm": 0.000826146277516193,
+      "learning_rate": 2.751047360628458e-06,
+      "loss": 0.0,
+      "step": 2510
+    },
+    {
+      "epoch": 6.849846782431052,
+      "grad_norm": 0.0007622689637331964,
+      "learning_rate": 2.708675256953708e-06,
+      "loss": 0.0,
+      "step": 2520
+    },
+    {
+      "epoch": 6.877085461355124,
+      "grad_norm": 0.0011470272220122446,
+      "learning_rate": 2.6665104373687455e-06,
+      "loss": 0.0006,
+      "step": 2530
+    },
+    {
+      "epoch": 6.904324140279196,
+      "grad_norm": 0.0009952201118956113,
+      "learning_rate": 2.624556716302876e-06,
+      "loss": 0.0,
+      "step": 2540
+    },
+    {
+      "epoch": 6.931562819203268,
+      "grad_norm": 0.0011435928941426047,
+      "learning_rate": 2.582817889088435e-06,
+      "loss": 0.0,
+      "step": 2550
+    },
+    {
+      "epoch": 6.9588014981273405,
+      "grad_norm": 0.01166505316182784,
+      "learning_rate": 2.541297731617437e-06,
+      "loss": 0.0,
+      "step": 2560
+    },
+    {
+      "epoch": 6.986040177051413,
+      "grad_norm": 0.0012091660156564501,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.0,
+      "step": 2570
+    },
+    {
+      "epoch": 7.010895471569629,
+      "grad_norm": 0.0015980505913388763,
+      "learning_rate": 2.458928430224548e-06,
+      "loss": 0.0,
+      "step": 2580
+    },
+    {
+      "epoch": 7.038134150493701,
+      "grad_norm": 0.0009393729565236982,
+      "learning_rate": 2.4180867378198274e-06,
+      "loss": 0.0,
+      "step": 2590
+    },
+    {
+      "epoch": 7.065372829417774,
+      "grad_norm": 0.0008257129118958041,
+      "learning_rate": 2.3774786175187932e-06,
+      "loss": 0.0,
+      "step": 2600
+    },
+    {
+      "epoch": 7.092611508341846,
+      "grad_norm": 0.0018052707906574057,
+      "learning_rate": 2.337107742924359e-06,
+      "loss": 0.0,
+      "step": 2610
+    },
+    {
+      "epoch": 7.119850187265918,
+      "grad_norm": 0.1645764072539005,
+      "learning_rate": 2.29697776617707e-06,
+      "loss": 0.0,
+      "step": 2620
+    },
+    {
+      "epoch": 7.14708886618999,
+      "grad_norm": 0.0007519843719597862,
+      "learning_rate": 2.25709231762471e-06,
+      "loss": 0.0,
+      "step": 2630
+    },
+    {
+      "epoch": 7.174327545114062,
+      "grad_norm": 0.0008477596842611903,
+      "learning_rate": 2.217455005493884e-06,
+      "loss": 0.0,
+      "step": 2640
+    },
+    {
+      "epoch": 7.201566224038134,
+      "grad_norm": 0.004509417330392989,
+      "learning_rate": 2.1780694155636014e-06,
+      "loss": 0.0,
+      "step": 2650
+    },
+    {
+      "epoch": 7.228804902962207,
+      "grad_norm": 0.0005766378225871001,
+      "learning_rate": 2.138939110840888e-06,
+      "loss": 0.0,
+      "step": 2660
+    },
+    {
+      "epoch": 7.256043581886279,
+      "grad_norm": 0.004100067804604992,
+      "learning_rate": 2.100067631238464e-06,
+      "loss": 0.0,
+      "step": 2670
+    },
+    {
+      "epoch": 7.283282260810351,
+      "grad_norm": 0.003930226882351156,
+      "learning_rate": 2.0614584932544955e-06,
+      "loss": 0.0,
+      "step": 2680
+    },
+    {
+      "epoch": 7.310520939734423,
+      "grad_norm": 0.0004427737628504764,
+      "learning_rate": 2.023115189654491e-06,
+      "loss": 0.0,
+      "step": 2690
+    },
+    {
+      "epoch": 7.337759618658495,
+      "grad_norm": 0.0008888326172641632,
+      "learning_rate": 1.9850411891553186e-06,
+      "loss": 0.0,
+      "step": 2700
+    },
+    {
+      "epoch": 7.364998297582567,
+      "grad_norm": 0.0006039128437105985,
+      "learning_rate": 1.9472399361114126e-06,
+      "loss": 0.0,
+      "step": 2710
+    },
+    {
+      "epoch": 7.39223697650664,
+      "grad_norm": 0.0004893946381054215,
+      "learning_rate": 1.909714850203177e-06,
+      "loss": 0.0,
+      "step": 2720
+    },
+    {
+      "epoch": 7.419475655430712,
+      "grad_norm": 0.0004317709133183237,
+      "learning_rate": 1.8724693261276345e-06,
+      "loss": 0.0,
+      "step": 2730
+    },
+    {
+      "epoch": 7.446714334354784,
+      "grad_norm": 0.0006212197750363989,
+      "learning_rate": 1.8355067332913156e-06,
+      "loss": 0.0,
+      "step": 2740
+    },
+    {
+      "epoch": 7.473953013278856,
+      "grad_norm": 0.0007456921468394779,
+      "learning_rate": 1.7988304155054541e-06,
+      "loss": 0.0,
+      "step": 2750
+    },
+    {
+      "epoch": 7.501191692202928,
+      "grad_norm": 0.0008149478511071161,
+      "learning_rate": 1.7624436906834842e-06,
+      "loss": 0.0,
+      "step": 2760
+    },
+    {
+      "epoch": 7.528430371127,
+      "grad_norm": 0.0007225352461383864,
+      "learning_rate": 1.7263498505408893e-06,
+      "loss": 0.0,
+      "step": 2770
+    },
+    {
+      "epoch": 7.555669050051073,
+      "grad_norm": 0.0005959357394697677,
+      "learning_rate": 1.6905521602974183e-06,
+      "loss": 0.0,
+      "step": 2780
+    },
+    {
+      "epoch": 7.582907728975145,
+      "grad_norm": 0.000635015561952419,
+      "learning_rate": 1.6550538583816967e-06,
+      "loss": 0.0,
+      "step": 2790
+    },
+    {
+      "epoch": 7.610146407899217,
+      "grad_norm": 0.0005433753417863713,
+      "learning_rate": 1.6198581561382643e-06,
+      "loss": 0.0,
+      "step": 2800
+    },
+    {
+      "epoch": 7.637385086823289,
+      "grad_norm": 0.00046276580358275586,
+      "learning_rate": 1.5849682375370601e-06,
+      "loss": 0.0,
+      "step": 2810
+    },
+    {
+      "epoch": 7.664623765747361,
+      "grad_norm": 0.0008516896607091807,
+      "learning_rate": 1.550387258885388e-06,
+      "loss": 0.0,
+      "step": 2820
+    },
+    {
+      "epoch": 7.691862444671433,
+      "grad_norm": 0.0005163692295676414,
+      "learning_rate": 1.5161183485423785e-06,
+      "loss": 0.0,
+      "step": 2830
+    },
+    {
+      "epoch": 7.719101123595506,
+      "grad_norm": 0.0011709181420231178,
+      "learning_rate": 1.482164606635989e-06,
+      "loss": 0.0,
+      "step": 2840
+    },
+    {
+      "epoch": 7.746339802519578,
+      "grad_norm": 0.0013056291673384528,
+      "learning_rate": 1.44852910478254e-06,
+      "loss": 0.0,
+      "step": 2850
+    },
+    {
+      "epoch": 7.77357848144365,
+      "grad_norm": 0.0004465783868552864,
+      "learning_rate": 1.4152148858088554e-06,
+      "loss": 0.0,
+      "step": 2860
+    },
+    {
+      "epoch": 7.800817160367722,
+      "grad_norm": 0.0005635784726540899,
+      "learning_rate": 1.3822249634769864e-06,
+      "loss": 0.0,
+      "step": 2870
+    },
+    {
+      "epoch": 7.828055839291794,
+      "grad_norm": 0.0003537589230160337,
+      "learning_rate": 1.3495623222115735e-06,
+      "loss": 0.0,
+      "step": 2880
+    },
+    {
+      "epoch": 7.855294518215866,
+      "grad_norm": 0.0004597321862407293,
+      "learning_rate": 1.3172299168298614e-06,
+      "loss": 0.0,
+      "step": 2890
+    },
+    {
+      "epoch": 7.882533197139939,
+      "grad_norm": 0.00040170519106549137,
+      "learning_rate": 1.2852306722743934e-06,
+      "loss": 0.0,
+      "step": 2900
+    },
+    {
+      "epoch": 7.909771876064011,
+      "grad_norm": 0.0016780869556999771,
+      "learning_rate": 1.253567483348407e-06,
+      "loss": 0.0,
+      "step": 2910
+    },
+    {
+      "epoch": 7.937010554988083,
+      "grad_norm": 0.000593202963073429,
+      "learning_rate": 1.222243214453951e-06,
+      "loss": 0.0,
+      "step": 2920
+    },
+    {
+      "epoch": 7.964249233912155,
+      "grad_norm": 0.0003643083864401578,
+      "learning_rate": 1.1912606993327685e-06,
+      "loss": 0.0,
+      "step": 2930
+    },
+    {
+      "epoch": 7.991487912836227,
+      "grad_norm": 0.0007434796810202931,
+      "learning_rate": 1.1606227408099347e-06,
+      "loss": 0.0,
+      "step": 2940
+    },
+    {
+      "epoch": 8.016343207354444,
+      "grad_norm": 0.00047702794678360533,
+      "learning_rate": 1.1303321105403026e-06,
+      "loss": 0.0,
+      "step": 2950
+    },
+    {
+      "epoch": 8.043581886278515,
+      "grad_norm": 0.0005298663692543725,
+      "learning_rate": 1.1003915487577683e-06,
+      "loss": 0.0,
+      "step": 2960
+    },
+    {
+      "epoch": 8.070820565202588,
+      "grad_norm": 0.004074165794804811,
+      "learning_rate": 1.0708037640273715e-06,
+      "loss": 0.0,
+      "step": 2970
+    },
+    {
+      "epoch": 8.09805924412666,
+      "grad_norm": 0.00040511964399428683,
+      "learning_rate": 1.0415714330002729e-06,
+      "loss": 0.0,
+      "step": 2980
+    },
+    {
+      "epoch": 8.125297923050733,
+      "grad_norm": 0.0012113673680468461,
+      "learning_rate": 1.0126972001716007e-06,
+      "loss": 0.0,
+      "step": 2990
+    },
+    {
+      "epoch": 8.152536601974804,
+      "grad_norm": 0.00041889827396330973,
+      "learning_rate": 9.841836776412294e-07,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "epoch": 8.152536601974804,
+      "eval_loss": 1.2345339200692251e-05,
+      "eval_runtime": 149.4558,
+      "eval_samples_per_second": 1.338,
+      "eval_steps_per_second": 0.167,
+      "step": 3000
+    },
+    {
+      "epoch": 8.179775280898877,
+      "grad_norm": 0.00048789814951889245,
+      "learning_rate": 9.560334448774705e-07,
+      "loss": 0.0,
+      "step": 3010
+    },
+    {
+      "epoch": 8.207013959822948,
+      "grad_norm": 0.00047638289528187925,
+      "learning_rate": 9.282490484837215e-07,
+      "loss": 0.0,
+      "step": 3020
+    },
+    {
+      "epoch": 8.234252638747021,
+      "grad_norm": 0.000455674971676968,
+      "learning_rate": 9.008330019680883e-07,
+      "loss": 0.0,
+      "step": 3030
+    },
+    {
+      "epoch": 8.261491317671092,
+      "grad_norm": 0.00041234844635284676,
+      "learning_rate": 8.737877855160032e-07,
+      "loss": 0.0,
+      "step": 3040
+    },
+    {
+      "epoch": 8.288729996595166,
+      "grad_norm": 0.0004512145872248025,
+      "learning_rate": 8.471158457658546e-07,
+      "loss": 0.0,
+      "step": 3050
+    },
+    {
+      "epoch": 8.315968675519237,
+      "grad_norm": 0.0003955500503942679,
+      "learning_rate": 8.208195955876513e-07,
+      "loss": 0.0,
+      "step": 3060
+    },
+    {
+      "epoch": 8.34320735444331,
+      "grad_norm": 0.00037757417965770856,
+      "learning_rate": 7.949014138647442e-07,
+      "loss": 0.0,
+      "step": 3070
+    },
+    {
+      "epoch": 8.370446033367381,
+      "grad_norm": 0.0005928754851042547,
+      "learning_rate": 7.693636452786213e-07,
+      "loss": 0.0,
+      "step": 3080
+    },
+    {
+      "epoch": 8.397684712291454,
+      "grad_norm": 0.0011757489143008526,
+      "learning_rate": 7.442086000967962e-07,
+      "loss": 0.0,
+      "step": 3090
+    },
+    {
+      "epoch": 8.424923391215525,
+      "grad_norm": 0.001091795641988052,
+      "learning_rate": 7.194385539638099e-07,
+      "loss": 0.0,
+      "step": 3100
+    },
+    {
+      "epoch": 8.452162070139599,
+      "grad_norm": 0.0004490144524655851,
+      "learning_rate": 6.950557476953674e-07,
+      "loss": 0.0,
+      "step": 3110
+    },
+    {
+      "epoch": 8.47940074906367,
+      "grad_norm": 0.0005170136229882478,
+      "learning_rate": 6.710623870756178e-07,
+      "loss": 0.0,
+      "step": 3120
+    },
+    {
+      "epoch": 8.506639427987743,
+      "grad_norm": 0.0005606121390368469,
+      "learning_rate": 6.474606426576157e-07,
+      "loss": 0.0,
+      "step": 3130
+    },
+    {
+      "epoch": 8.533878106911814,
+      "grad_norm": 0.0006494691276362171,
+      "learning_rate": 6.242526495669587e-07,
+      "loss": 0.0,
+      "step": 3140
+    },
+    {
+      "epoch": 8.561116785835887,
+      "grad_norm": 0.000705761138730125,
+      "learning_rate": 6.01440507308631e-07,
+      "loss": 0.0,
+      "step": 3150
+    },
+    {
+      "epoch": 8.588355464759958,
+      "grad_norm": 0.00037580712390274833,
+      "learning_rate": 5.790262795770785e-07,
+      "loss": 0.0,
+      "step": 3160
+    },
+    {
+      "epoch": 8.615594143684032,
+      "grad_norm": 0.00037712299260292257,
+      "learning_rate": 5.570119940695135e-07,
+      "loss": 0.0,
+      "step": 3170
+    },
+    {
+      "epoch": 8.642832822608103,
+      "grad_norm": 0.00038488025576517655,
+      "learning_rate": 5.353996423024804e-07,
+      "loss": 0.0,
+      "step": 3180
+    },
+    {
+      "epoch": 8.670071501532176,
+      "grad_norm": 0.0004034621134836744,
+      "learning_rate": 5.141911794316934e-07,
+      "loss": 0.0,
+      "step": 3190
+    },
+    {
+      "epoch": 8.697310180456247,
+      "grad_norm": 0.00038266845732824815,
+      "learning_rate": 4.93388524075164e-07,
+      "loss": 0.0,
+      "step": 3200
+    },
+    {
+      "epoch": 8.72454885938032,
+      "grad_norm": 0.00038362011868780437,
+      "learning_rate": 4.729935581396328e-07,
+      "loss": 0.0,
+      "step": 3210
+    },
+    {
+      "epoch": 8.751787538304391,
+      "grad_norm": 0.00035607543651581207,
+      "learning_rate": 4.5300812665032557e-07,
+      "loss": 0.0,
+      "step": 3220
+    },
+    {
+      "epoch": 8.779026217228465,
+      "grad_norm": 0.0006068778689349405,
+      "learning_rate": 4.334340375840418e-07,
+      "loss": 0.0,
+      "step": 3230
+    },
+    {
+      "epoch": 8.806264896152536,
+      "grad_norm": 0.00033490740677774155,
+      "learning_rate": 4.1427306170559624e-07,
+      "loss": 0.0,
+      "step": 3240
+    },
+    {
+      "epoch": 8.833503575076609,
+      "grad_norm": 0.00046859576305887497,
+      "learning_rate": 3.955269324076294e-07,
+      "loss": 0.0,
+      "step": 3250
+    },
+    {
+      "epoch": 8.86074225400068,
+      "grad_norm": 0.0008093853787619229,
+      "learning_rate": 3.771973455537936e-07,
+      "loss": 0.0,
+      "step": 3260
+    },
+    {
+      "epoch": 8.887980932924753,
+      "grad_norm": 0.0010513228996015518,
+      "learning_rate": 3.5928595932534005e-07,
+      "loss": 0.0,
+      "step": 3270
+    },
+    {
+      "epoch": 8.915219611848826,
+      "grad_norm": 0.0003623450487854711,
+      "learning_rate": 3.4179439407110714e-07,
+      "loss": 0.0,
+      "step": 3280
+    },
+    {
+      "epoch": 8.942458290772898,
+      "grad_norm": 0.000339362832377934,
+      "learning_rate": 3.247242321609434e-07,
+      "loss": 0.0,
+      "step": 3290
+    },
+    {
+      "epoch": 8.969696969696969,
+      "grad_norm": 0.0005334885527562191,
+      "learning_rate": 3.0807701784255296e-07,
+      "loss": 0.0,
+      "step": 3300
+    },
+    {
+      "epoch": 8.996935648621042,
+      "grad_norm": 0.00044685136023717045,
+      "learning_rate": 2.9185425710179737e-07,
+      "loss": 0.0,
+      "step": 3310
+    },
+    {
+      "epoch": 9.021790943139258,
+      "grad_norm": 0.0008018093014633273,
+      "learning_rate": 2.7605741752645686e-07,
+      "loss": 0.0,
+      "step": 3320
+    },
+    {
+      "epoch": 9.04902962206333,
+      "grad_norm": 0.0003794485076320959,
+      "learning_rate": 2.606879281734659e-07,
+      "loss": 0.0,
+      "step": 3330
+    },
+    {
+      "epoch": 9.076268300987403,
+      "grad_norm": 0.000514433360537291,
+      "learning_rate": 2.457471794396338e-07,
+      "loss": 0.0,
+      "step": 3340
+    },
+    {
+      "epoch": 9.103506979911474,
+      "grad_norm": 0.0006110392205499266,
+      "learning_rate": 2.3123652293586207e-07,
+      "loss": 0.0,
+      "step": 3350
+    },
+    {
+      "epoch": 9.130745658835547,
+      "grad_norm": 0.0004051883420581768,
+      "learning_rate": 2.1715727136487174e-07,
+      "loss": 0.0,
+      "step": 3360
+    },
+    {
+      "epoch": 9.157984337759618,
+      "grad_norm": 0.0017022735873803575,
+      "learning_rate": 2.0351069840244986e-07,
+      "loss": 0.0,
+      "step": 3370
+    },
+    {
+      "epoch": 9.185223016683691,
+      "grad_norm": 0.000833252754224706,
+      "learning_rate": 1.9029803858222896e-07,
+      "loss": 0.0,
+      "step": 3380
+    },
+    {
+      "epoch": 9.212461695607763,
+      "grad_norm": 0.0038641354937789443,
+      "learning_rate": 1.775204871840014e-07,
+      "loss": 0.0,
+      "step": 3390
+    },
+    {
+      "epoch": 9.239700374531836,
+      "grad_norm": 0.0003339132774971038,
+      "learning_rate": 1.6517920012559086e-07,
+      "loss": 0.0,
+      "step": 3400
+    },
+    {
+      "epoch": 9.266939053455907,
+      "grad_norm": 0.0003633204131676538,
+      "learning_rate": 1.5327529385828377e-07,
+      "loss": 0.0,
+      "step": 3410
+    },
+    {
+      "epoch": 9.29417773237998,
+      "grad_norm": 0.000322045602551698,
+      "learning_rate": 1.4180984526582675e-07,
+      "loss": 0.0,
+      "step": 3420
+    },
+    {
+      "epoch": 9.321416411304051,
+      "grad_norm": 0.0010744986200642887,
+      "learning_rate": 1.3078389156700842e-07,
+      "loss": 0.0,
+      "step": 3430
+    },
+    {
+      "epoch": 9.348655090228124,
+      "grad_norm": 0.0005973674276566756,
+      "learning_rate": 1.2019843022182898e-07,
+      "loss": 0.0,
+      "step": 3440
+    },
+    {
+      "epoch": 9.375893769152196,
+      "grad_norm": 0.00035574829244011577,
+      "learning_rate": 1.1005441884126278e-07,
+      "loss": 0.0,
+      "step": 3450
+    },
+    {
+      "epoch": 9.403132448076269,
+      "grad_norm": 0.0005334084677271788,
+      "learning_rate": 1.0035277510062835e-07,
+      "loss": 0.0,
+      "step": 3460
+    },
+    {
+      "epoch": 9.43037112700034,
+      "grad_norm": 0.00032947386696114886,
+      "learning_rate": 9.109437665657473e-08,
+      "loss": 0.0,
+      "step": 3470
+    },
+    {
+      "epoch": 9.457609805924413,
+      "grad_norm": 0.0003827344363811748,
+      "learning_rate": 8.228006106767883e-08,
+      "loss": 0.0,
+      "step": 3480
+    },
+    {
+      "epoch": 9.484848484848484,
+      "grad_norm": 0.00030067997503277467,
+      "learning_rate": 7.391062571868113e-08,
+      "loss": 0.0,
+      "step": 3490
+    },
+    {
+      "epoch": 9.512087163772557,
+      "grad_norm": 0.0003243561088926095,
+      "learning_rate": 6.598682774834775e-08,
+      "loss": 0.0,
+      "step": 3500
+    },
+    {
+      "epoch": 9.539325842696629,
+      "grad_norm": 0.0003467443287273098,
+      "learning_rate": 5.850938398097583e-08,
+      "loss": 0.0,
+      "step": 3510
+    },
+    {
+      "epoch": 9.566564521620702,
+      "grad_norm": 0.00035286356515664503,
+      "learning_rate": 5.1478970861548185e-08,
+      "loss": 0.0,
+      "step": 3520
+    },
+    {
+      "epoch": 9.593803200544773,
+      "grad_norm": 0.0009776284074226168,
+      "learning_rate": 4.4896224394537226e-08,
+      "loss": 0.0,
+      "step": 3530
+    },
+    {
+      "epoch": 9.621041879468846,
+      "grad_norm": 0.00039195791750442195,
+      "learning_rate": 3.8761740086369345e-08,
+      "loss": 0.0,
+      "step": 3540
+    },
+    {
+      "epoch": 9.648280558392917,
+      "grad_norm": 0.0005306094646929393,
+      "learning_rate": 3.307607289155301e-08,
+      "loss": 0.0,
+      "step": 3550
+    },
+    {
+      "epoch": 9.67551923731699,
+      "grad_norm": 0.0004368446632988839,
+      "learning_rate": 2.78397371624739e-08,
+      "loss": 0.0,
+      "step": 3560
+    },
+    {
+      "epoch": 9.702757916241062,
+      "grad_norm": 0.0006477180396400463,
+      "learning_rate": 2.305320660286603e-08,
+      "loss": 0.0,
+      "step": 3570
+    },
+    {
+      "epoch": 9.729996595165135,
+      "grad_norm": 0.0005051573397374285,
+      "learning_rate": 1.8716914224957138e-08,
+      "loss": 0.0,
+      "step": 3580
+    },
+    {
+      "epoch": 9.757235274089206,
+      "grad_norm": 0.00035959712658455894,
+      "learning_rate": 1.4831252310294474e-08,
+      "loss": 0.0,
+      "step": 3590
+    },
+    {
+      "epoch": 9.78447395301328,
+      "grad_norm": 0.00047611287827840345,
+      "learning_rate": 1.1396572374261505e-08,
+      "loss": 0.0,
+      "step": 3600
+    },
+    {
+      "epoch": 9.81171263193735,
+      "grad_norm": 0.0009275444049437501,
+      "learning_rate": 8.413185134273916e-09,
+      "loss": 0.0,
+      "step": 3610
+    },
+    {
+      "epoch": 9.838951310861423,
+      "grad_norm": 0.0010032462120567445,
+      "learning_rate": 5.881360481673759e-09,
+      "loss": 0.0,
+      "step": 3620
+    },
+    {
+      "epoch": 9.866189989785495,
+      "grad_norm": 0.0008774671042869975,
+      "learning_rate": 3.801327457311765e-09,
+      "loss": 0.0,
+      "step": 3630
+    },
+    {
+      "epoch": 9.893428668709568,
+      "grad_norm": 0.0007470443454518441,
+      "learning_rate": 2.173274230827249e-09,
+      "loss": 0.0,
+      "step": 3640
+    },
+    {
+      "epoch": 9.920667347633639,
+      "grad_norm": 0.0006590459160652287,
+      "learning_rate": 9.97348083627836e-10,
+      "loss": 0.0,
+      "step": 3650
+    },
+    {
+      "epoch": 9.947906026557712,
+      "grad_norm": 0.0008391834531967672,
+      "learning_rate": 2.7365539556234444e-10,
+      "loss": 0.0,
+      "step": 3660
+    },
+    {
+      "epoch": 9.975144705481783,
+      "grad_norm": 0.00034623849620746836,
+      "learning_rate": 2.261635299039e-12,
+      "loss": 0.0,
+      "step": 3670
+    },
+    {
+      "epoch": 9.975144705481783,
+      "step": 3670,
+      "total_flos": 3659279013773312.0,
+      "train_loss": 0.050615286758120444,
+      "train_runtime": 386241.8476,
+      "train_samples_per_second": 2.433,
+      "train_steps_per_second": 0.01
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3659279013773312.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d06e46526674d604a1767421a25b76b7f183e90882238b0fc978400064260a0
+size 7544