Model save
Browse files- .gitattributes +1 -0
- README.md +58 -0
- added_tokens.json +24 -0
- all_results.json +8 -0
- chat_template.jinja +7 -0
- config.json +105 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +831 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +207 -0
- train_results.json +8 -0
- trainer_state.json +1375 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-VL-3B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-VL-3B-Instruct-Agentic-GUI
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-VL-3B-Instruct-Agentic-GUI
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="A-Mahla/Qwen2.5-VL-3B-Instruct-Agentic-GUI", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/smolagents/runs/7y8mgnns)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.18.0
|
| 38 |
+
- Transformers: 4.52.3
|
| 39 |
+
- Pytorch: 2.6.0
|
| 40 |
+
- Datasets: 4.0.0
|
| 41 |
+
- Tokenizers: 0.21.2
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1.2125984924893184e+16,
|
| 3 |
+
"train_loss": 0.645972225476395,
|
| 4 |
+
"train_runtime": 88419.8411,
|
| 5 |
+
"train_samples": 360252,
|
| 6 |
+
"train_samples_per_second": 4.074,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% 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
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% 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|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"image_token_id": 151655,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 128000,
|
| 14 |
+
"max_window_layers": 70,
|
| 15 |
+
"model_type": "qwen2_5_vl",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 36,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"text_config": {
|
| 32 |
+
"architectures": [
|
| 33 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 34 |
+
],
|
| 35 |
+
"attention_dropout": 0.0,
|
| 36 |
+
"bos_token_id": 151643,
|
| 37 |
+
"eos_token_id": 151645,
|
| 38 |
+
"hidden_act": "silu",
|
| 39 |
+
"hidden_size": 2048,
|
| 40 |
+
"image_token_id": null,
|
| 41 |
+
"initializer_range": 0.02,
|
| 42 |
+
"intermediate_size": 11008,
|
| 43 |
+
"max_position_embeddings": 128000,
|
| 44 |
+
"max_window_layers": 70,
|
| 45 |
+
"model_type": "qwen2_5_vl_text",
|
| 46 |
+
"num_attention_heads": 16,
|
| 47 |
+
"num_hidden_layers": 36,
|
| 48 |
+
"num_key_value_heads": 2,
|
| 49 |
+
"rms_norm_eps": 1e-06,
|
| 50 |
+
"rope_scaling": {
|
| 51 |
+
"mrope_section": [
|
| 52 |
+
16,
|
| 53 |
+
24,
|
| 54 |
+
24
|
| 55 |
+
],
|
| 56 |
+
"rope_type": "default",
|
| 57 |
+
"type": "default"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": 32768,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"video_token_id": null,
|
| 66 |
+
"vision_end_token_id": 151653,
|
| 67 |
+
"vision_start_token_id": 151652,
|
| 68 |
+
"vision_token_id": 151654,
|
| 69 |
+
"vocab_size": 151936
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "bfloat16",
|
| 72 |
+
"transformers_version": "4.52.3",
|
| 73 |
+
"use_cache": false,
|
| 74 |
+
"use_sliding_window": false,
|
| 75 |
+
"video_token_id": 151656,
|
| 76 |
+
"vision_config": {
|
| 77 |
+
"depth": 32,
|
| 78 |
+
"fullatt_block_indexes": [
|
| 79 |
+
7,
|
| 80 |
+
15,
|
| 81 |
+
23,
|
| 82 |
+
31
|
| 83 |
+
],
|
| 84 |
+
"hidden_act": "silu",
|
| 85 |
+
"hidden_size": 1280,
|
| 86 |
+
"in_channels": 3,
|
| 87 |
+
"in_chans": 3,
|
| 88 |
+
"initializer_range": 0.02,
|
| 89 |
+
"intermediate_size": 3420,
|
| 90 |
+
"model_type": "qwen2_5_vl",
|
| 91 |
+
"num_heads": 16,
|
| 92 |
+
"out_hidden_size": 2048,
|
| 93 |
+
"patch_size": 14,
|
| 94 |
+
"spatial_merge_size": 2,
|
| 95 |
+
"spatial_patch_size": 14,
|
| 96 |
+
"temporal_patch_size": 2,
|
| 97 |
+
"tokens_per_second": 2,
|
| 98 |
+
"torch_dtype": "bfloat16",
|
| 99 |
+
"window_size": 112
|
| 100 |
+
},
|
| 101 |
+
"vision_end_token_id": 151653,
|
| 102 |
+
"vision_start_token_id": 151652,
|
| 103 |
+
"vision_token_id": 151654,
|
| 104 |
+
"vocab_size": 151936
|
| 105 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 1e-06,
|
| 11 |
+
"transformers_version": "4.52.3"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0bd1bf2cdf09d2aba3c8913a60dffeae4c7e482ec4a7109b5283c72b75ba007
|
| 3 |
+
size 4997756664
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:464b852d99ffe18b4ab4fbf725c2b3d95ae58db3d6390d3a191ca55799407cbf
|
| 3 |
+
size 2511590128
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,831 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7509245952
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.language_model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.language_model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.language_model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"model.visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"model.visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"model.visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"model.visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"model.visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"model.visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"model.visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"model.visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"model.visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"model.visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"model.visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"model.visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"model.visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"model.visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"model.visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"model.visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"model.visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"model.visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"model.visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"model.visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"model.visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"model.visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"model.visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"model.visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"model.visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"model.visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"model.visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"model.visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"model.visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 763 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"model.visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"model.visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"model.visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 775 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"model.visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"model.visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"model.visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"model.visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"model.visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"model.visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 799 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"model.visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"model.visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 808 |
+
"model.visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 809 |
+
"model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 810 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 811 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 813 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 814 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 815 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 816 |
+
"model.visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 817 |
+
"model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 818 |
+
"model.visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 819 |
+
"model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 820 |
+
"model.visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 821 |
+
"model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 822 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 823 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"model.visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 825 |
+
"model.visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 826 |
+
"model.visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 827 |
+
"model.visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
| 828 |
+
"model.visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 829 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
| 830 |
+
}
|
| 831 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1.2125984924893184e+16,
|
| 3 |
+
"train_loss": 0.645972225476395,
|
| 4 |
+
"train_runtime": 88419.8411,
|
| 5 |
+
"train_samples": 360252,
|
| 6 |
+
"train_samples_per_second": 4.074,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 704,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007106057914372002,
|
| 14 |
+
"grad_norm": 66.55605725941018,
|
| 15 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 16 |
+
"loss": 2.4888,
|
| 17 |
+
"mean_token_accuracy": 0.6310219071805477,
|
| 18 |
+
"num_tokens": 5923034.0,
|
| 19 |
+
"step": 5
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.014212115828744005,
|
| 23 |
+
"grad_norm": 31.27595336039531,
|
| 24 |
+
"learning_rate": 8.181818181818183e-06,
|
| 25 |
+
"loss": 1.6522,
|
| 26 |
+
"mean_token_accuracy": 0.6847351841628552,
|
| 27 |
+
"num_tokens": 11832986.0,
|
| 28 |
+
"step": 10
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.021318173743116006,
|
| 32 |
+
"grad_norm": 6.505788538701925,
|
| 33 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 34 |
+
"loss": 1.0489,
|
| 35 |
+
"mean_token_accuracy": 0.7373726107180119,
|
| 36 |
+
"num_tokens": 17770055.0,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02842423165748801,
|
| 41 |
+
"grad_norm": 3.4652580364487653,
|
| 42 |
+
"learning_rate": 1.7272727272727274e-05,
|
| 43 |
+
"loss": 0.8759,
|
| 44 |
+
"mean_token_accuracy": 0.7604092583060265,
|
| 45 |
+
"num_tokens": 23710854.0,
|
| 46 |
+
"step": 20
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.03553028957186001,
|
| 50 |
+
"grad_norm": 3.073564258123934,
|
| 51 |
+
"learning_rate": 1.999961805535155e-05,
|
| 52 |
+
"loss": 0.8341,
|
| 53 |
+
"mean_token_accuracy": 0.7634279936552048,
|
| 54 |
+
"num_tokens": 29669291.0,
|
| 55 |
+
"step": 25
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.04263634748623201,
|
| 59 |
+
"grad_norm": 2.908944153808897,
|
| 60 |
+
"learning_rate": 1.9995321550350065e-05,
|
| 61 |
+
"loss": 0.7871,
|
| 62 |
+
"mean_token_accuracy": 0.7735667265951633,
|
| 63 |
+
"num_tokens": 35600851.0,
|
| 64 |
+
"step": 30
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.04974240540060401,
|
| 68 |
+
"grad_norm": 3.8874402850017673,
|
| 69 |
+
"learning_rate": 1.998625339625423e-05,
|
| 70 |
+
"loss": 0.7597,
|
| 71 |
+
"mean_token_accuracy": 0.7763237416744232,
|
| 72 |
+
"num_tokens": 41530042.0,
|
| 73 |
+
"step": 35
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.05684846331497602,
|
| 77 |
+
"grad_norm": 2.5449731597634697,
|
| 78 |
+
"learning_rate": 1.9972418403347817e-05,
|
| 79 |
+
"loss": 0.7219,
|
| 80 |
+
"mean_token_accuracy": 0.7790968000888825,
|
| 81 |
+
"num_tokens": 47452248.0,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.06395452122934801,
|
| 86 |
+
"grad_norm": 1.7369247244872457,
|
| 87 |
+
"learning_rate": 1.9953823910527057e-05,
|
| 88 |
+
"loss": 0.6924,
|
| 89 |
+
"mean_token_accuracy": 0.7809838131070137,
|
| 90 |
+
"num_tokens": 53373989.0,
|
| 91 |
+
"step": 45
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.07106057914372002,
|
| 95 |
+
"grad_norm": 1.619526678453925,
|
| 96 |
+
"learning_rate": 1.993047978140764e-05,
|
| 97 |
+
"loss": 0.6759,
|
| 98 |
+
"mean_token_accuracy": 0.7882510013878345,
|
| 99 |
+
"num_tokens": 59280737.0,
|
| 100 |
+
"step": 50
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07816663705809203,
|
| 104 |
+
"grad_norm": 1.4050312043738487,
|
| 105 |
+
"learning_rate": 1.9902398399092494e-05,
|
| 106 |
+
"loss": 0.6604,
|
| 107 |
+
"mean_token_accuracy": 0.7918689742684364,
|
| 108 |
+
"num_tokens": 65195627.0,
|
| 109 |
+
"step": 55
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.08527269497246402,
|
| 113 |
+
"grad_norm": 3.4085768530761555,
|
| 114 |
+
"learning_rate": 1.9869594659603032e-05,
|
| 115 |
+
"loss": 0.6644,
|
| 116 |
+
"mean_token_accuracy": 0.7887415766716004,
|
| 117 |
+
"num_tokens": 71142550.0,
|
| 118 |
+
"step": 60
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.09237875288683603,
|
| 122 |
+
"grad_norm": 2.1575833755380707,
|
| 123 |
+
"learning_rate": 1.9832085963977445e-05,
|
| 124 |
+
"loss": 0.6732,
|
| 125 |
+
"mean_token_accuracy": 0.786578668653965,
|
| 126 |
+
"num_tokens": 77081694.0,
|
| 127 |
+
"step": 65
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.09948481080120802,
|
| 131 |
+
"grad_norm": 2.1880249716642743,
|
| 132 |
+
"learning_rate": 1.978989220904016e-05,
|
| 133 |
+
"loss": 0.6647,
|
| 134 |
+
"mean_token_accuracy": 0.7869649574160575,
|
| 135 |
+
"num_tokens": 83044225.0,
|
| 136 |
+
"step": 70
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.10659086871558003,
|
| 140 |
+
"grad_norm": 3.500718658694026,
|
| 141 |
+
"learning_rate": 1.9743035776847377e-05,
|
| 142 |
+
"loss": 0.6618,
|
| 143 |
+
"mean_token_accuracy": 0.7884958483278751,
|
| 144 |
+
"num_tokens": 88988372.0,
|
| 145 |
+
"step": 75
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.11369692662995204,
|
| 149 |
+
"grad_norm": 3.5435216425879,
|
| 150 |
+
"learning_rate": 1.9691541522814327e-05,
|
| 151 |
+
"loss": 0.6538,
|
| 152 |
+
"mean_token_accuracy": 0.7917183473706245,
|
| 153 |
+
"num_tokens": 94931302.0,
|
| 154 |
+
"step": 80
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.12080298454432403,
|
| 158 |
+
"grad_norm": 3.3524381829737675,
|
| 159 |
+
"learning_rate": 1.963543676253048e-05,
|
| 160 |
+
"loss": 0.668,
|
| 161 |
+
"mean_token_accuracy": 0.7873365215957164,
|
| 162 |
+
"num_tokens": 100848612.0,
|
| 163 |
+
"step": 85
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12790904245869603,
|
| 167 |
+
"grad_norm": 2.5235394583310655,
|
| 168 |
+
"learning_rate": 1.9574751257269748e-05,
|
| 169 |
+
"loss": 0.6632,
|
| 170 |
+
"mean_token_accuracy": 0.7879712589085102,
|
| 171 |
+
"num_tokens": 106754467.0,
|
| 172 |
+
"step": 90
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.13501510037306805,
|
| 176 |
+
"grad_norm": 2.1804248444209673,
|
| 177 |
+
"learning_rate": 1.950951719820335e-05,
|
| 178 |
+
"loss": 0.6519,
|
| 179 |
+
"mean_token_accuracy": 0.7906477533280849,
|
| 180 |
+
"num_tokens": 112664258.0,
|
| 181 |
+
"step": 95
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.14212115828744004,
|
| 185 |
+
"grad_norm": 2.1726552942080497,
|
| 186 |
+
"learning_rate": 1.9439769189323727e-05,
|
| 187 |
+
"loss": 0.654,
|
| 188 |
+
"mean_token_accuracy": 0.7900555059313774,
|
| 189 |
+
"num_tokens": 118606688.0,
|
| 190 |
+
"step": 100
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.14212115828744004,
|
| 194 |
+
"eval_loss": 0.6459761261940002,
|
| 195 |
+
"eval_mean_token_accuracy": 0.7921642295101232,
|
| 196 |
+
"eval_num_tokens": 118606688.0,
|
| 197 |
+
"eval_runtime": 295.44,
|
| 198 |
+
"eval_samples_per_second": 12.317,
|
| 199 |
+
"eval_steps_per_second": 0.386,
|
| 200 |
+
"step": 100
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.14922721620181204,
|
| 204 |
+
"grad_norm": 2.0323675408135484,
|
| 205 |
+
"learning_rate": 1.9365544229088517e-05,
|
| 206 |
+
"loss": 0.6521,
|
| 207 |
+
"mean_token_accuracy": 0.7909861005842685,
|
| 208 |
+
"num_tokens": 124512961.0,
|
| 209 |
+
"step": 105
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.15633327411618406,
|
| 213 |
+
"grad_norm": 5.430519736360723,
|
| 214 |
+
"learning_rate": 1.9286881690794425e-05,
|
| 215 |
+
"loss": 0.6453,
|
| 216 |
+
"mean_token_accuracy": 0.7935434632003308,
|
| 217 |
+
"num_tokens": 130441640.0,
|
| 218 |
+
"step": 110
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.16343933203055605,
|
| 222 |
+
"grad_norm": 2.6425373488919943,
|
| 223 |
+
"learning_rate": 1.9203823301691272e-05,
|
| 224 |
+
"loss": 0.6683,
|
| 225 |
+
"mean_token_accuracy": 0.7861981622874736,
|
| 226 |
+
"num_tokens": 136394287.0,
|
| 227 |
+
"step": 115
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.17054538994492804,
|
| 231 |
+
"grad_norm": 3.2273755870117724,
|
| 232 |
+
"learning_rate": 1.9116413120847425e-05,
|
| 233 |
+
"loss": 0.6649,
|
| 234 |
+
"mean_token_accuracy": 0.7885523498058319,
|
| 235 |
+
"num_tokens": 142309319.0,
|
| 236 |
+
"step": 120
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.17765144785930007,
|
| 240 |
+
"grad_norm": 4.163268789121899,
|
| 241 |
+
"learning_rate": 1.902469751577826e-05,
|
| 242 |
+
"loss": 0.6679,
|
| 243 |
+
"mean_token_accuracy": 0.7868955120444298,
|
| 244 |
+
"num_tokens": 148247490.0,
|
| 245 |
+
"step": 125
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.18475750577367206,
|
| 249 |
+
"grad_norm": 1.6661402706531616,
|
| 250 |
+
"learning_rate": 1.892872513785008e-05,
|
| 251 |
+
"loss": 0.6394,
|
| 252 |
+
"mean_token_accuracy": 0.7936947368085384,
|
| 253 |
+
"num_tokens": 154195595.0,
|
| 254 |
+
"step": 130
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.19186356368804405,
|
| 258 |
+
"grad_norm": 1.5794423300632663,
|
| 259 |
+
"learning_rate": 1.88285468964726e-05,
|
| 260 |
+
"loss": 0.6373,
|
| 261 |
+
"mean_token_accuracy": 0.7937119543552399,
|
| 262 |
+
"num_tokens": 160139401.0,
|
| 263 |
+
"step": 135
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.19896962160241605,
|
| 267 |
+
"grad_norm": 1.9146265900976953,
|
| 268 |
+
"learning_rate": 1.872421593209355e-05,
|
| 269 |
+
"loss": 0.6367,
|
| 270 |
+
"mean_token_accuracy": 0.7936570249497891,
|
| 271 |
+
"num_tokens": 166057697.0,
|
| 272 |
+
"step": 140
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.20607567951678807,
|
| 276 |
+
"grad_norm": 1.8920022402043013,
|
| 277 |
+
"learning_rate": 1.861578758800989e-05,
|
| 278 |
+
"loss": 0.6448,
|
| 279 |
+
"mean_token_accuracy": 0.7935090765357018,
|
| 280 |
+
"num_tokens": 171980981.0,
|
| 281 |
+
"step": 145
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.21318173743116006,
|
| 285 |
+
"grad_norm": 1.8829721816030007,
|
| 286 |
+
"learning_rate": 1.8503319381010414e-05,
|
| 287 |
+
"loss": 0.6394,
|
| 288 |
+
"mean_token_accuracy": 0.7929822854697705,
|
| 289 |
+
"num_tokens": 177920811.0,
|
| 290 |
+
"step": 150
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.22028779534553206,
|
| 294 |
+
"grad_norm": 2.710625896660201,
|
| 295 |
+
"learning_rate": 1.8386870970865488e-05,
|
| 296 |
+
"loss": 0.6297,
|
| 297 |
+
"mean_token_accuracy": 0.795507474988699,
|
| 298 |
+
"num_tokens": 183857404.0,
|
| 299 |
+
"step": 155
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.22739385325990408,
|
| 303 |
+
"grad_norm": 1.7692011271897554,
|
| 304 |
+
"learning_rate": 1.8266504128679988e-05,
|
| 305 |
+
"loss": 0.6374,
|
| 306 |
+
"mean_token_accuracy": 0.7952376157045364,
|
| 307 |
+
"num_tokens": 189793021.0,
|
| 308 |
+
"step": 160
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.23449991117427607,
|
| 312 |
+
"grad_norm": 1.226150395650258,
|
| 313 |
+
"learning_rate": 1.814228270412624e-05,
|
| 314 |
+
"loss": 0.6525,
|
| 315 |
+
"mean_token_accuracy": 0.7921756438910961,
|
| 316 |
+
"num_tokens": 195715230.0,
|
| 317 |
+
"step": 165
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.24160596908864806,
|
| 321 |
+
"grad_norm": 2.1730739897367206,
|
| 322 |
+
"learning_rate": 1.8014272591574405e-05,
|
| 323 |
+
"loss": 0.6452,
|
| 324 |
+
"mean_token_accuracy": 0.7933229982852936,
|
| 325 |
+
"num_tokens": 201644724.0,
|
| 326 |
+
"step": 170
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.2487120270030201,
|
| 330 |
+
"grad_norm": 1.1273239605881678,
|
| 331 |
+
"learning_rate": 1.7882541695138224e-05,
|
| 332 |
+
"loss": 0.6328,
|
| 333 |
+
"mean_token_accuracy": 0.795696322619915,
|
| 334 |
+
"num_tokens": 207585561.0,
|
| 335 |
+
"step": 175
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.25581808491739205,
|
| 339 |
+
"grad_norm": 1.094910349166684,
|
| 340 |
+
"learning_rate": 1.7747159892654646e-05,
|
| 341 |
+
"loss": 0.6294,
|
| 342 |
+
"mean_token_accuracy": 0.7952122300863266,
|
| 343 |
+
"num_tokens": 213540458.0,
|
| 344 |
+
"step": 180
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.2629241428317641,
|
| 348 |
+
"grad_norm": 1.4265158165299685,
|
| 349 |
+
"learning_rate": 1.7608198998616533e-05,
|
| 350 |
+
"loss": 0.6401,
|
| 351 |
+
"mean_token_accuracy": 0.7934339419007301,
|
| 352 |
+
"num_tokens": 219456523.0,
|
| 353 |
+
"step": 185
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2700302007461361,
|
| 357 |
+
"grad_norm": 1.1866353031490813,
|
| 358 |
+
"learning_rate": 1.7465732726077993e-05,
|
| 359 |
+
"loss": 0.6376,
|
| 360 |
+
"mean_token_accuracy": 0.7937880590558052,
|
| 361 |
+
"num_tokens": 225385658.0,
|
| 362 |
+
"step": 190
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.27713625866050806,
|
| 366 |
+
"grad_norm": 1.1122272717695676,
|
| 367 |
+
"learning_rate": 1.731983664755264e-05,
|
| 368 |
+
"loss": 0.6434,
|
| 369 |
+
"mean_token_accuracy": 0.793655838817358,
|
| 370 |
+
"num_tokens": 231315244.0,
|
| 371 |
+
"step": 195
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.2842423165748801,
|
| 375 |
+
"grad_norm": 0.9655859557982183,
|
| 376 |
+
"learning_rate": 1.717058815492548e-05,
|
| 377 |
+
"loss": 0.641,
|
| 378 |
+
"mean_token_accuracy": 0.792879494279623,
|
| 379 |
+
"num_tokens": 237275441.0,
|
| 380 |
+
"step": 200
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2842423165748801,
|
| 384 |
+
"eval_loss": 0.6347336769104004,
|
| 385 |
+
"eval_mean_token_accuracy": 0.7943492432435354,
|
| 386 |
+
"eval_num_tokens": 237275441.0,
|
| 387 |
+
"eval_runtime": 296.27,
|
| 388 |
+
"eval_samples_per_second": 12.283,
|
| 389 |
+
"eval_steps_per_second": 0.385,
|
| 390 |
+
"step": 200
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.2913483744892521,
|
| 394 |
+
"grad_norm": 0.9237497775331585,
|
| 395 |
+
"learning_rate": 1.701806641839967e-05,
|
| 396 |
+
"loss": 0.6373,
|
| 397 |
+
"mean_token_accuracy": 0.7951489560306072,
|
| 398 |
+
"num_tokens": 243189498.0,
|
| 399 |
+
"step": 205
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.29845443240362407,
|
| 403 |
+
"grad_norm": 0.953221738403784,
|
| 404 |
+
"learning_rate": 1.6862352344500004e-05,
|
| 405 |
+
"loss": 0.6402,
|
| 406 |
+
"mean_token_accuracy": 0.7936429545283318,
|
| 407 |
+
"num_tokens": 249109887.0,
|
| 408 |
+
"step": 210
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3055604903179961,
|
| 412 |
+
"grad_norm": 0.9703848636195304,
|
| 413 |
+
"learning_rate": 1.6703528533155283e-05,
|
| 414 |
+
"loss": 0.6414,
|
| 415 |
+
"mean_token_accuracy": 0.7941999517381191,
|
| 416 |
+
"num_tokens": 255049150.0,
|
| 417 |
+
"step": 215
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.3126665482323681,
|
| 421 |
+
"grad_norm": 0.96915858246581,
|
| 422 |
+
"learning_rate": 1.6541679233882477e-05,
|
| 423 |
+
"loss": 0.6298,
|
| 424 |
+
"mean_token_accuracy": 0.7961237229406833,
|
| 425 |
+
"num_tokens": 260976846.0,
|
| 426 |
+
"step": 220
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.3197726061467401,
|
| 430 |
+
"grad_norm": 0.9933766730385373,
|
| 431 |
+
"learning_rate": 1.63768903010958e-05,
|
| 432 |
+
"loss": 0.6356,
|
| 433 |
+
"mean_token_accuracy": 0.795130829513073,
|
| 434 |
+
"num_tokens": 266905427.0,
|
| 435 |
+
"step": 225
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.3268786640611121,
|
| 439 |
+
"grad_norm": 1.0546956761351753,
|
| 440 |
+
"learning_rate": 1.6209249148564437e-05,
|
| 441 |
+
"loss": 0.6304,
|
| 442 |
+
"mean_token_accuracy": 0.7961406633257866,
|
| 443 |
+
"num_tokens": 272824016.0,
|
| 444 |
+
"step": 230
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3339847219754841,
|
| 448 |
+
"grad_norm": 0.9224242489597514,
|
| 449 |
+
"learning_rate": 1.603884470304318e-05,
|
| 450 |
+
"loss": 0.6414,
|
| 451 |
+
"mean_token_accuracy": 0.7928595051169396,
|
| 452 |
+
"num_tokens": 278772935.0,
|
| 453 |
+
"step": 235
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.3410907798898561,
|
| 457 |
+
"grad_norm": 1.775037599109117,
|
| 458 |
+
"learning_rate": 1.5865767357100383e-05,
|
| 459 |
+
"loss": 0.6247,
|
| 460 |
+
"mean_token_accuracy": 0.7980937138199806,
|
| 461 |
+
"num_tokens": 284699860.0,
|
| 462 |
+
"step": 240
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.3481968378042281,
|
| 466 |
+
"grad_norm": 3.6986968651179866,
|
| 467 |
+
"learning_rate": 1.5690108921168428e-05,
|
| 468 |
+
"loss": 0.6282,
|
| 469 |
+
"mean_token_accuracy": 0.7979529812932015,
|
| 470 |
+
"num_tokens": 290642638.0,
|
| 471 |
+
"step": 245
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35530289571860013,
|
| 475 |
+
"grad_norm": 1.1970583265540296,
|
| 476 |
+
"learning_rate": 1.5511962574842073e-05,
|
| 477 |
+
"loss": 0.6265,
|
| 478 |
+
"mean_token_accuracy": 0.7972055464982987,
|
| 479 |
+
"num_tokens": 296584355.0,
|
| 480 |
+
"step": 250
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.3624089536329721,
|
| 484 |
+
"grad_norm": 1.3725931963002411,
|
| 485 |
+
"learning_rate": 1.5331422817450485e-05,
|
| 486 |
+
"loss": 0.6316,
|
| 487 |
+
"mean_token_accuracy": 0.7962015710771084,
|
| 488 |
+
"num_tokens": 302514276.0,
|
| 489 |
+
"step": 255
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3695150115473441,
|
| 493 |
+
"grad_norm": 1.052505642053235,
|
| 494 |
+
"learning_rate": 1.5148585417929212e-05,
|
| 495 |
+
"loss": 0.6265,
|
| 496 |
+
"mean_token_accuracy": 0.797739926725626,
|
| 497 |
+
"num_tokens": 308442058.0,
|
| 498 |
+
"step": 260
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.37662106946171614,
|
| 502 |
+
"grad_norm": 1.2266076226995661,
|
| 503 |
+
"learning_rate": 1.4963547364018711e-05,
|
| 504 |
+
"loss": 0.6228,
|
| 505 |
+
"mean_token_accuracy": 0.7978610590100288,
|
| 506 |
+
"num_tokens": 314358386.0,
|
| 507 |
+
"step": 265
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3837271273760881,
|
| 511 |
+
"grad_norm": 0.9779433419910959,
|
| 512 |
+
"learning_rate": 1.477640681081632e-05,
|
| 513 |
+
"loss": 0.6274,
|
| 514 |
+
"mean_token_accuracy": 0.797017228603363,
|
| 515 |
+
"num_tokens": 320330186.0,
|
| 516 |
+
"step": 270
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.39083318529046013,
|
| 520 |
+
"grad_norm": 1.386190197186753,
|
| 521 |
+
"learning_rate": 1.4587263028709013e-05,
|
| 522 |
+
"loss": 0.6243,
|
| 523 |
+
"mean_token_accuracy": 0.7981224037706852,
|
| 524 |
+
"num_tokens": 326254997.0,
|
| 525 |
+
"step": 275
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.3979392432048321,
|
| 529 |
+
"grad_norm": 2.614420120110884,
|
| 530 |
+
"learning_rate": 1.4396216350714512e-05,
|
| 531 |
+
"loss": 0.6262,
|
| 532 |
+
"mean_token_accuracy": 0.7971527561545372,
|
| 533 |
+
"num_tokens": 332131183.0,
|
| 534 |
+
"step": 280
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4050453011192041,
|
| 538 |
+
"grad_norm": 1.042309981896861,
|
| 539 |
+
"learning_rate": 1.4203368119258759e-05,
|
| 540 |
+
"loss": 0.6239,
|
| 541 |
+
"mean_token_accuracy": 0.7973503857851029,
|
| 542 |
+
"num_tokens": 338051217.0,
|
| 543 |
+
"step": 285
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.41215135903357614,
|
| 547 |
+
"grad_norm": 1.3072882069993246,
|
| 548 |
+
"learning_rate": 1.4008820632417906e-05,
|
| 549 |
+
"loss": 0.6153,
|
| 550 |
+
"mean_token_accuracy": 0.8006650306284427,
|
| 551 |
+
"num_tokens": 343962755.0,
|
| 552 |
+
"step": 290
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.4192574169479481,
|
| 556 |
+
"grad_norm": 0.9860476843101288,
|
| 557 |
+
"learning_rate": 1.381267708965339e-05,
|
| 558 |
+
"loss": 0.6203,
|
| 559 |
+
"mean_token_accuracy": 0.7994598127901554,
|
| 560 |
+
"num_tokens": 349868870.0,
|
| 561 |
+
"step": 295
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.4263634748623201,
|
| 565 |
+
"grad_norm": 1.4036170847387148,
|
| 566 |
+
"learning_rate": 1.3615041537068831e-05,
|
| 567 |
+
"loss": 0.6295,
|
| 568 |
+
"mean_token_accuracy": 0.7960586912930012,
|
| 569 |
+
"num_tokens": 355805962.0,
|
| 570 |
+
"step": 300
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4263634748623201,
|
| 574 |
+
"eval_loss": 0.6163658499717712,
|
| 575 |
+
"eval_mean_token_accuracy": 0.7995022409840634,
|
| 576 |
+
"eval_num_tokens": 355805962.0,
|
| 577 |
+
"eval_runtime": 296.606,
|
| 578 |
+
"eval_samples_per_second": 12.269,
|
| 579 |
+
"eval_steps_per_second": 0.384,
|
| 580 |
+
"step": 300
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.43346953277669215,
|
| 584 |
+
"grad_norm": 1.4151324155929559,
|
| 585 |
+
"learning_rate": 1.3416018812217866e-05,
|
| 586 |
+
"loss": 0.6254,
|
| 587 |
+
"mean_token_accuracy": 0.7966083332896232,
|
| 588 |
+
"num_tokens": 361723150.0,
|
| 589 |
+
"step": 305
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.4405755906910641,
|
| 593 |
+
"grad_norm": 1.2868115337774566,
|
| 594 |
+
"learning_rate": 1.3215714488492121e-05,
|
| 595 |
+
"loss": 0.6078,
|
| 596 |
+
"mean_token_accuracy": 0.8015532568097115,
|
| 597 |
+
"num_tokens": 367658526.0,
|
| 598 |
+
"step": 310
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.44768164860543613,
|
| 602 |
+
"grad_norm": 1.928461708072047,
|
| 603 |
+
"learning_rate": 1.3014234819118846e-05,
|
| 604 |
+
"loss": 0.606,
|
| 605 |
+
"mean_token_accuracy": 0.8015141606330871,
|
| 606 |
+
"num_tokens": 373569982.0,
|
| 607 |
+
"step": 315
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.45478770651980815,
|
| 611 |
+
"grad_norm": 1.899128993970621,
|
| 612 |
+
"learning_rate": 1.2811686680797942e-05,
|
| 613 |
+
"loss": 0.6182,
|
| 614 |
+
"mean_token_accuracy": 0.7982937648892403,
|
| 615 |
+
"num_tokens": 379503775.0,
|
| 616 |
+
"step": 320
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.4618937644341801,
|
| 620 |
+
"grad_norm": 1.4589431652822673,
|
| 621 |
+
"learning_rate": 1.2608177517008268e-05,
|
| 622 |
+
"loss": 0.606,
|
| 623 |
+
"mean_token_accuracy": 0.8024964012205601,
|
| 624 |
+
"num_tokens": 385421798.0,
|
| 625 |
+
"step": 325
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.46899982234855214,
|
| 629 |
+
"grad_norm": 2.312165029030224,
|
| 630 |
+
"learning_rate": 1.240381528101327e-05,
|
| 631 |
+
"loss": 0.6036,
|
| 632 |
+
"mean_token_accuracy": 0.8019742712378501,
|
| 633 |
+
"num_tokens": 391368024.0,
|
| 634 |
+
"step": 330
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.47610588026292416,
|
| 638 |
+
"grad_norm": 1.538144906292264,
|
| 639 |
+
"learning_rate": 1.2198708378596198e-05,
|
| 640 |
+
"loss": 0.5993,
|
| 641 |
+
"mean_token_accuracy": 0.804237449914217,
|
| 642 |
+
"num_tokens": 397292736.0,
|
| 643 |
+
"step": 335
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.48321193817729613,
|
| 647 |
+
"grad_norm": 1.307446043015124,
|
| 648 |
+
"learning_rate": 1.19929656105553e-05,
|
| 649 |
+
"loss": 0.6046,
|
| 650 |
+
"mean_token_accuracy": 0.8020064242184162,
|
| 651 |
+
"num_tokens": 403217739.0,
|
| 652 |
+
"step": 340
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.49031799609166815,
|
| 656 |
+
"grad_norm": 1.4958823006704178,
|
| 657 |
+
"learning_rate": 1.1786696114989455e-05,
|
| 658 |
+
"loss": 0.6049,
|
| 659 |
+
"mean_token_accuracy": 0.8029085315763951,
|
| 660 |
+
"num_tokens": 409134483.0,
|
| 661 |
+
"step": 345
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4974240540060402,
|
| 665 |
+
"grad_norm": 1.3590504704358832,
|
| 666 |
+
"learning_rate": 1.1580009309404887e-05,
|
| 667 |
+
"loss": 0.6068,
|
| 668 |
+
"mean_token_accuracy": 0.8020060114562512,
|
| 669 |
+
"num_tokens": 415063752.0,
|
| 670 |
+
"step": 350
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.5045301119204122,
|
| 674 |
+
"grad_norm": 1.5361640914741626,
|
| 675 |
+
"learning_rate": 1.1373014832673661e-05,
|
| 676 |
+
"loss": 0.6058,
|
| 677 |
+
"mean_token_accuracy": 0.8034303903579711,
|
| 678 |
+
"num_tokens": 420986440.0,
|
| 679 |
+
"step": 355
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.5116361698347841,
|
| 683 |
+
"grad_norm": 1.7406253504574596,
|
| 684 |
+
"learning_rate": 1.1165822486874773e-05,
|
| 685 |
+
"loss": 0.6013,
|
| 686 |
+
"mean_token_accuracy": 0.8025040835142135,
|
| 687 |
+
"num_tokens": 426919043.0,
|
| 688 |
+
"step": 360
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5187422277491561,
|
| 692 |
+
"grad_norm": 1.4252805000356146,
|
| 693 |
+
"learning_rate": 1.0958542179048637e-05,
|
| 694 |
+
"loss": 0.5975,
|
| 695 |
+
"mean_token_accuracy": 0.8049191392958164,
|
| 696 |
+
"num_tokens": 432835321.0,
|
| 697 |
+
"step": 365
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.5258482856635281,
|
| 701 |
+
"grad_norm": 1.6635488719233447,
|
| 702 |
+
"learning_rate": 1.0751283862895914e-05,
|
| 703 |
+
"loss": 0.6198,
|
| 704 |
+
"mean_token_accuracy": 0.7999552808701992,
|
| 705 |
+
"num_tokens": 438731328.0,
|
| 706 |
+
"step": 370
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.5329543435779002,
|
| 710 |
+
"grad_norm": 1.3128810337611407,
|
| 711 |
+
"learning_rate": 1.0544157480451586e-05,
|
| 712 |
+
"loss": 0.6091,
|
| 713 |
+
"mean_token_accuracy": 0.800326906144619,
|
| 714 |
+
"num_tokens": 444678429.0,
|
| 715 |
+
"step": 375
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.5400604014922722,
|
| 719 |
+
"grad_norm": 1.4889952603189804,
|
| 720 |
+
"learning_rate": 1.033727290376522e-05,
|
| 721 |
+
"loss": 0.6138,
|
| 722 |
+
"mean_token_accuracy": 0.8001590967178345,
|
| 723 |
+
"num_tokens": 450570676.0,
|
| 724 |
+
"step": 380
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.5471664594066442,
|
| 728 |
+
"grad_norm": 1.466863294864097,
|
| 729 |
+
"learning_rate": 1.013073987661834e-05,
|
| 730 |
+
"loss": 0.6135,
|
| 731 |
+
"mean_token_accuracy": 0.7993282429873944,
|
| 732 |
+
"num_tokens": 456505695.0,
|
| 733 |
+
"step": 385
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.5542725173210161,
|
| 737 |
+
"grad_norm": 2.0382279212397996,
|
| 738 |
+
"learning_rate": 9.924667956309862e-06,
|
| 739 |
+
"loss": 0.5994,
|
| 740 |
+
"mean_token_accuracy": 0.8032713256776333,
|
| 741 |
+
"num_tokens": 462436441.0,
|
| 742 |
+
"step": 390
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.5613785752353881,
|
| 746 |
+
"grad_norm": 2.5944556078034373,
|
| 747 |
+
"learning_rate": 9.719166455540437e-06,
|
| 748 |
+
"loss": 0.6081,
|
| 749 |
+
"mean_token_accuracy": 0.801172049343586,
|
| 750 |
+
"num_tokens": 468376688.0,
|
| 751 |
+
"step": 395
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5684846331497602,
|
| 755 |
+
"grad_norm": 2.3431282794499113,
|
| 756 |
+
"learning_rate": 9.51434438442655e-06,
|
| 757 |
+
"loss": 0.6024,
|
| 758 |
+
"mean_token_accuracy": 0.8036491274833679,
|
| 759 |
+
"num_tokens": 474296296.0,
|
| 760 |
+
"step": 400
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.5684846331497602,
|
| 764 |
+
"eval_loss": 0.6026122570037842,
|
| 765 |
+
"eval_mean_token_accuracy": 0.8030629869092974,
|
| 766 |
+
"eval_num_tokens": 474296296.0,
|
| 767 |
+
"eval_runtime": 295.7635,
|
| 768 |
+
"eval_samples_per_second": 12.304,
|
| 769 |
+
"eval_steps_per_second": 0.385,
|
| 770 |
+
"step": 400
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.5755906910641322,
|
| 774 |
+
"grad_norm": 2.004552904299561,
|
| 775 |
+
"learning_rate": 9.310310392675132e-06,
|
| 776 |
+
"loss": 0.5946,
|
| 777 |
+
"mean_token_accuracy": 0.8059669084846973,
|
| 778 |
+
"num_tokens": 480221232.0,
|
| 779 |
+
"step": 405
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5826967489785042,
|
| 783 |
+
"grad_norm": 2.182094919737894,
|
| 784 |
+
"learning_rate": 9.107172711949324e-06,
|
| 785 |
+
"loss": 0.6098,
|
| 786 |
+
"mean_token_accuracy": 0.8020808771252632,
|
| 787 |
+
"num_tokens": 486176414.0,
|
| 788 |
+
"step": 410
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.5898028068928762,
|
| 792 |
+
"grad_norm": 2.181381325740844,
|
| 793 |
+
"learning_rate": 8.905039098456049e-06,
|
| 794 |
+
"loss": 0.6011,
|
| 795 |
+
"mean_token_accuracy": 0.8030769810080528,
|
| 796 |
+
"num_tokens": 492102670.0,
|
| 797 |
+
"step": 415
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.5969088648072481,
|
| 801 |
+
"grad_norm": 1.8310617565549334,
|
| 802 |
+
"learning_rate": 8.704016775785742e-06,
|
| 803 |
+
"loss": 0.6047,
|
| 804 |
+
"mean_token_accuracy": 0.8027667418122292,
|
| 805 |
+
"num_tokens": 498034157.0,
|
| 806 |
+
"step": 420
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.6040149227216202,
|
| 810 |
+
"grad_norm": 1.8408277960821589,
|
| 811 |
+
"learning_rate": 8.50421237803464e-06,
|
| 812 |
+
"loss": 0.6,
|
| 813 |
+
"mean_token_accuracy": 0.8030680187046528,
|
| 814 |
+
"num_tokens": 503966085.0,
|
| 815 |
+
"step": 425
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6111209806359922,
|
| 819 |
+
"grad_norm": 1.58781331586126,
|
| 820 |
+
"learning_rate": 8.30573189323978e-06,
|
| 821 |
+
"loss": 0.5923,
|
| 822 |
+
"mean_token_accuracy": 0.8065764397382736,
|
| 823 |
+
"num_tokens": 509912387.0,
|
| 824 |
+
"step": 430
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.6182270385503642,
|
| 828 |
+
"grad_norm": 2.4917867524381085,
|
| 829 |
+
"learning_rate": 8.108680607156669e-06,
|
| 830 |
+
"loss": 0.6057,
|
| 831 |
+
"mean_token_accuracy": 0.8019099831581116,
|
| 832 |
+
"num_tokens": 515846667.0,
|
| 833 |
+
"step": 435
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.6253330964647362,
|
| 837 |
+
"grad_norm": 1.4683997587556166,
|
| 838 |
+
"learning_rate": 7.913163047409533e-06,
|
| 839 |
+
"loss": 0.6007,
|
| 840 |
+
"mean_token_accuracy": 0.8031819522380829,
|
| 841 |
+
"num_tokens": 521759712.0,
|
| 842 |
+
"step": 440
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6324391543791081,
|
| 846 |
+
"grad_norm": 2.0497193131572993,
|
| 847 |
+
"learning_rate": 7.719282928043688e-06,
|
| 848 |
+
"loss": 0.6026,
|
| 849 |
+
"mean_token_accuracy": 0.8027250319719315,
|
| 850 |
+
"num_tokens": 527693723.0,
|
| 851 |
+
"step": 445
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.6395452122934802,
|
| 855 |
+
"grad_norm": 1.9866627694997772,
|
| 856 |
+
"learning_rate": 7.527143094509492e-06,
|
| 857 |
+
"loss": 0.5962,
|
| 858 |
+
"mean_token_accuracy": 0.8050611786544323,
|
| 859 |
+
"num_tokens": 533641375.0,
|
| 860 |
+
"step": 450
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.6466512702078522,
|
| 864 |
+
"grad_norm": 2.0671724220740284,
|
| 865 |
+
"learning_rate": 7.336845469107061e-06,
|
| 866 |
+
"loss": 0.6012,
|
| 867 |
+
"mean_token_accuracy": 0.8034082941710949,
|
| 868 |
+
"num_tokens": 539566506.0,
|
| 869 |
+
"step": 455
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.6537573281222242,
|
| 873 |
+
"grad_norm": 1.1733461701395618,
|
| 874 |
+
"learning_rate": 7.148490996920661e-06,
|
| 875 |
+
"loss": 0.6005,
|
| 876 |
+
"mean_token_accuracy": 0.8036525435745716,
|
| 877 |
+
"num_tokens": 545484724.0,
|
| 878 |
+
"step": 460
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.6608633860365962,
|
| 882 |
+
"grad_norm": 1.3593627896085958,
|
| 883 |
+
"learning_rate": 6.9621795922714805e-06,
|
| 884 |
+
"loss": 0.5938,
|
| 885 |
+
"mean_token_accuracy": 0.8044769234955311,
|
| 886 |
+
"num_tokens": 551415017.0,
|
| 887 |
+
"step": 465
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.6679694439509682,
|
| 891 |
+
"grad_norm": 1.3812452385551917,
|
| 892 |
+
"learning_rate": 6.778010085717202e-06,
|
| 893 |
+
"loss": 0.5998,
|
| 894 |
+
"mean_token_accuracy": 0.8046882562339306,
|
| 895 |
+
"num_tokens": 557320461.0,
|
| 896 |
+
"step": 470
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.6750755018653402,
|
| 900 |
+
"grad_norm": 1.8099599749434352,
|
| 901 |
+
"learning_rate": 6.596080171626409e-06,
|
| 902 |
+
"loss": 0.6023,
|
| 903 |
+
"mean_token_accuracy": 0.8030730128288269,
|
| 904 |
+
"num_tokens": 563258287.0,
|
| 905 |
+
"step": 475
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6821815597797122,
|
| 909 |
+
"grad_norm": 1.4003389577047656,
|
| 910 |
+
"learning_rate": 6.416486356355769e-06,
|
| 911 |
+
"loss": 0.6083,
|
| 912 |
+
"mean_token_accuracy": 0.8014967061579228,
|
| 913 |
+
"num_tokens": 569180910.0,
|
| 914 |
+
"step": 480
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.6892876176940842,
|
| 918 |
+
"grad_norm": 1.064555140921138,
|
| 919 |
+
"learning_rate": 6.239323907057342e-06,
|
| 920 |
+
"loss": 0.6031,
|
| 921 |
+
"mean_token_accuracy": 0.8031500183045864,
|
| 922 |
+
"num_tokens": 575092087.0,
|
| 923 |
+
"step": 485
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.6963936756084562,
|
| 927 |
+
"grad_norm": 1.42689507484952,
|
| 928 |
+
"learning_rate": 6.064686801143271e-06,
|
| 929 |
+
"loss": 0.5872,
|
| 930 |
+
"mean_token_accuracy": 0.8078797787427903,
|
| 931 |
+
"num_tokens": 581002946.0,
|
| 932 |
+
"step": 490
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.7034997335228282,
|
| 936 |
+
"grad_norm": 1.4988954301366828,
|
| 937 |
+
"learning_rate": 5.892667676434633e-06,
|
| 938 |
+
"loss": 0.5969,
|
| 939 |
+
"mean_token_accuracy": 0.805253654718399,
|
| 940 |
+
"num_tokens": 586913668.0,
|
| 941 |
+
"step": 495
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.7106057914372003,
|
| 945 |
+
"grad_norm": 1.812281786151278,
|
| 946 |
+
"learning_rate": 5.723357782020867e-06,
|
| 947 |
+
"loss": 0.5895,
|
| 948 |
+
"mean_token_accuracy": 0.8048664882779122,
|
| 949 |
+
"num_tokens": 592832114.0,
|
| 950 |
+
"step": 500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.7106057914372003,
|
| 954 |
+
"eval_loss": 0.5955030918121338,
|
| 955 |
+
"eval_mean_token_accuracy": 0.804359252515592,
|
| 956 |
+
"eval_num_tokens": 592832114.0,
|
| 957 |
+
"eval_runtime": 295.6444,
|
| 958 |
+
"eval_samples_per_second": 12.309,
|
| 959 |
+
"eval_steps_per_second": 0.386,
|
| 960 |
+
"step": 500
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.7177118493515722,
|
| 964 |
+
"grad_norm": 1.9139670158434299,
|
| 965 |
+
"learning_rate": 5.556846929855857e-06,
|
| 966 |
+
"loss": 0.5887,
|
| 967 |
+
"mean_token_accuracy": 0.8057731881737709,
|
| 968 |
+
"num_tokens": 598754045.0,
|
| 969 |
+
"step": 505
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7248179072659442,
|
| 973 |
+
"grad_norm": 1.5674173121754666,
|
| 974 |
+
"learning_rate": 5.393223447116409e-06,
|
| 975 |
+
"loss": 0.6035,
|
| 976 |
+
"mean_token_accuracy": 0.803417231887579,
|
| 977 |
+
"num_tokens": 604714198.0,
|
| 978 |
+
"step": 510
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.7319239651803162,
|
| 982 |
+
"grad_norm": 1.4540694573929962,
|
| 983 |
+
"learning_rate": 5.232574129348278e-06,
|
| 984 |
+
"loss": 0.5945,
|
| 985 |
+
"mean_token_accuracy": 0.804961483925581,
|
| 986 |
+
"num_tokens": 610643984.0,
|
| 987 |
+
"step": 515
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.7390300230946882,
|
| 991 |
+
"grad_norm": 1.5167979309975335,
|
| 992 |
+
"learning_rate": 5.0749841944247e-06,
|
| 993 |
+
"loss": 0.6049,
|
| 994 |
+
"mean_token_accuracy": 0.8024425834417344,
|
| 995 |
+
"num_tokens": 616589217.0,
|
| 996 |
+
"step": 520
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7461360810090603,
|
| 1000 |
+
"grad_norm": 1.4872845521101352,
|
| 1001 |
+
"learning_rate": 4.92053723734182e-06,
|
| 1002 |
+
"loss": 0.6022,
|
| 1003 |
+
"mean_token_accuracy": 0.8034923203289509,
|
| 1004 |
+
"num_tokens": 622495105.0,
|
| 1005 |
+
"step": 525
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.7532421389234323,
|
| 1009 |
+
"grad_norm": 2.4122501400628993,
|
| 1010 |
+
"learning_rate": 4.769315185874951e-06,
|
| 1011 |
+
"loss": 0.5961,
|
| 1012 |
+
"mean_token_accuracy": 0.8057848632335662,
|
| 1013 |
+
"num_tokens": 628430302.0,
|
| 1014 |
+
"step": 530
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.7603481968378042,
|
| 1018 |
+
"grad_norm": 3.0932302891179235,
|
| 1019 |
+
"learning_rate": 4.621398257119266e-06,
|
| 1020 |
+
"loss": 0.5966,
|
| 1021 |
+
"mean_token_accuracy": 0.8043950840830802,
|
| 1022 |
+
"num_tokens": 634369704.0,
|
| 1023 |
+
"step": 535
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.7674542547521762,
|
| 1027 |
+
"grad_norm": 2.761826923400515,
|
| 1028 |
+
"learning_rate": 4.476864914937923e-06,
|
| 1029 |
+
"loss": 0.5879,
|
| 1030 |
+
"mean_token_accuracy": 0.8060916163027286,
|
| 1031 |
+
"num_tokens": 640316507.0,
|
| 1032 |
+
"step": 540
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.7745603126665482,
|
| 1036 |
+
"grad_norm": 1.810383003438599,
|
| 1037 |
+
"learning_rate": 4.335791828340183e-06,
|
| 1038 |
+
"loss": 0.6014,
|
| 1039 |
+
"mean_token_accuracy": 0.8044339507818222,
|
| 1040 |
+
"num_tokens": 646273380.0,
|
| 1041 |
+
"step": 545
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.7816663705809203,
|
| 1045 |
+
"grad_norm": 1.57106874125145,
|
| 1046 |
+
"learning_rate": 4.1982538308116775e-06,
|
| 1047 |
+
"loss": 0.5933,
|
| 1048 |
+
"mean_token_accuracy": 0.8038996756076813,
|
| 1049 |
+
"num_tokens": 652201532.0,
|
| 1050 |
+
"step": 550
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.7887724284952923,
|
| 1054 |
+
"grad_norm": 1.65882515510847,
|
| 1055 |
+
"learning_rate": 4.064323880618279e-06,
|
| 1056 |
+
"loss": 0.5979,
|
| 1057 |
+
"mean_token_accuracy": 0.8053264081478119,
|
| 1058 |
+
"num_tokens": 658135558.0,
|
| 1059 |
+
"step": 555
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7958784864096642,
|
| 1063 |
+
"grad_norm": 1.7520635112367258,
|
| 1064 |
+
"learning_rate": 3.934073022104759e-06,
|
| 1065 |
+
"loss": 0.5942,
|
| 1066 |
+
"mean_token_accuracy": 0.8051018618047238,
|
| 1067 |
+
"num_tokens": 664053021.0,
|
| 1068 |
+
"step": 560
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.8029845443240362,
|
| 1072 |
+
"grad_norm": 2.747926156722073,
|
| 1073 |
+
"learning_rate": 3.807570348008672e-06,
|
| 1074 |
+
"loss": 0.5958,
|
| 1075 |
+
"mean_token_accuracy": 0.805073781311512,
|
| 1076 |
+
"num_tokens": 669989223.0,
|
| 1077 |
+
"step": 565
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.8100906022384082,
|
| 1081 |
+
"grad_norm": 1.2910340620000669,
|
| 1082 |
+
"learning_rate": 3.684882962809484e-06,
|
| 1083 |
+
"loss": 0.6003,
|
| 1084 |
+
"mean_token_accuracy": 0.804193302989006,
|
| 1085 |
+
"num_tokens": 675921465.0,
|
| 1086 |
+
"step": 570
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.8171966601527803,
|
| 1090 |
+
"grad_norm": 2.2556806715561817,
|
| 1091 |
+
"learning_rate": 3.5660759471324037e-06,
|
| 1092 |
+
"loss": 0.5971,
|
| 1093 |
+
"mean_token_accuracy": 0.8039252124726772,
|
| 1094 |
+
"num_tokens": 681852307.0,
|
| 1095 |
+
"step": 575
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.8243027180671523,
|
| 1099 |
+
"grad_norm": 1.7373756069231372,
|
| 1100 |
+
"learning_rate": 3.451212323225786e-06,
|
| 1101 |
+
"loss": 0.5925,
|
| 1102 |
+
"mean_token_accuracy": 0.8057592801749707,
|
| 1103 |
+
"num_tokens": 687769737.0,
|
| 1104 |
+
"step": 580
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.8314087759815243,
|
| 1108 |
+
"grad_norm": 3.192756357062325,
|
| 1109 |
+
"learning_rate": 3.340353021530409e-06,
|
| 1110 |
+
"loss": 0.5902,
|
| 1111 |
+
"mean_token_accuracy": 0.8047820582985878,
|
| 1112 |
+
"num_tokens": 693702256.0,
|
| 1113 |
+
"step": 585
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.8385148338958962,
|
| 1117 |
+
"grad_norm": 2.3339162718389854,
|
| 1118 |
+
"learning_rate": 3.2335568483583708e-06,
|
| 1119 |
+
"loss": 0.5867,
|
| 1120 |
+
"mean_token_accuracy": 0.8085503794252873,
|
| 1121 |
+
"num_tokens": 699642883.0,
|
| 1122 |
+
"step": 590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8456208918102682,
|
| 1126 |
+
"grad_norm": 1.7159764847482752,
|
| 1127 |
+
"learning_rate": 3.1308804546987615e-06,
|
| 1128 |
+
"loss": 0.5988,
|
| 1129 |
+
"mean_token_accuracy": 0.8035182796418667,
|
| 1130 |
+
"num_tokens": 705606507.0,
|
| 1131 |
+
"step": 595
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.8527269497246402,
|
| 1135 |
+
"grad_norm": 2.8135588347439984,
|
| 1136 |
+
"learning_rate": 3.0323783061666307e-06,
|
| 1137 |
+
"loss": 0.5943,
|
| 1138 |
+
"mean_token_accuracy": 0.805966579914093,
|
| 1139 |
+
"num_tokens": 711533271.0,
|
| 1140 |
+
"step": 600
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.8527269497246402,
|
| 1144 |
+
"eval_loss": 0.5903548002243042,
|
| 1145 |
+
"eval_mean_token_accuracy": 0.8059158665046358,
|
| 1146 |
+
"eval_num_tokens": 711533271.0,
|
| 1147 |
+
"eval_runtime": 296.5539,
|
| 1148 |
+
"eval_samples_per_second": 12.271,
|
| 1149 |
+
"eval_steps_per_second": 0.384,
|
| 1150 |
+
"step": 600
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.8598330076390123,
|
| 1154 |
+
"grad_norm": 1.620026356285568,
|
| 1155 |
+
"learning_rate": 2.9381026541112145e-06,
|
| 1156 |
+
"loss": 0.5934,
|
| 1157 |
+
"mean_token_accuracy": 0.8051214568316937,
|
| 1158 |
+
"num_tokens": 717498751.0,
|
| 1159 |
+
"step": 605
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 0.8669390655533843,
|
| 1163 |
+
"grad_norm": 1.346134723264547,
|
| 1164 |
+
"learning_rate": 2.848103507898745e-06,
|
| 1165 |
+
"loss": 0.5995,
|
| 1166 |
+
"mean_token_accuracy": 0.8026661708950996,
|
| 1167 |
+
"num_tokens": 723421175.0,
|
| 1168 |
+
"step": 610
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.8740451234677563,
|
| 1172 |
+
"grad_norm": 1.3133061113418305,
|
| 1173 |
+
"learning_rate": 2.7624286083845187e-06,
|
| 1174 |
+
"loss": 0.5905,
|
| 1175 |
+
"mean_token_accuracy": 0.8046399556100369,
|
| 1176 |
+
"num_tokens": 729353013.0,
|
| 1177 |
+
"step": 615
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.8811511813821282,
|
| 1181 |
+
"grad_norm": 1.7379818179026807,
|
| 1182 |
+
"learning_rate": 2.6811234025883457e-06,
|
| 1183 |
+
"loss": 0.5876,
|
| 1184 |
+
"mean_token_accuracy": 0.8071587301790715,
|
| 1185 |
+
"num_tokens": 735289319.0,
|
| 1186 |
+
"step": 620
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8882572392965002,
|
| 1190 |
+
"grad_norm": 4.0244229329833,
|
| 1191 |
+
"learning_rate": 2.604231019586761e-06,
|
| 1192 |
+
"loss": 0.5908,
|
| 1193 |
+
"mean_token_accuracy": 0.8060196414589882,
|
| 1194 |
+
"num_tokens": 741217107.0,
|
| 1195 |
+
"step": 625
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.8953632972108723,
|
| 1199 |
+
"grad_norm": 1.7622879809387222,
|
| 1200 |
+
"learning_rate": 2.5317922476348194e-06,
|
| 1201 |
+
"loss": 0.5952,
|
| 1202 |
+
"mean_token_accuracy": 0.8054036945104599,
|
| 1203 |
+
"num_tokens": 747147403.0,
|
| 1204 |
+
"step": 630
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.9024693551252443,
|
| 1208 |
+
"grad_norm": 2.2585412448119007,
|
| 1209 |
+
"learning_rate": 2.4638455125296043e-06,
|
| 1210 |
+
"loss": 0.5925,
|
| 1211 |
+
"mean_token_accuracy": 0.8054537117481232,
|
| 1212 |
+
"num_tokens": 753044605.0,
|
| 1213 |
+
"step": 635
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9095754130396163,
|
| 1217 |
+
"grad_norm": 1.5262303547489815,
|
| 1218 |
+
"learning_rate": 2.400426857226914e-06,
|
| 1219 |
+
"loss": 0.5879,
|
| 1220 |
+
"mean_token_accuracy": 0.8063779830932617,
|
| 1221 |
+
"num_tokens": 758944457.0,
|
| 1222 |
+
"step": 640
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.9166814709539882,
|
| 1226 |
+
"grad_norm": 2.545493717270523,
|
| 1227 |
+
"learning_rate": 2.3415699227219517e-06,
|
| 1228 |
+
"loss": 0.5992,
|
| 1229 |
+
"mean_token_accuracy": 0.8029563590884209,
|
| 1230 |
+
"num_tokens": 764871608.0,
|
| 1231 |
+
"step": 645
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.9237875288683602,
|
| 1235 |
+
"grad_norm": 1.7376685867634216,
|
| 1236 |
+
"learning_rate": 2.2873059302041627e-06,
|
| 1237 |
+
"loss": 0.5896,
|
| 1238 |
+
"mean_token_accuracy": 0.8063512444496155,
|
| 1239 |
+
"num_tokens": 770802003.0,
|
| 1240 |
+
"step": 650
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.9308935867827323,
|
| 1244 |
+
"grad_norm": 1.7377001386795896,
|
| 1245 |
+
"learning_rate": 2.2376636644956656e-06,
|
| 1246 |
+
"loss": 0.5874,
|
| 1247 |
+
"mean_token_accuracy": 0.8068042829632759,
|
| 1248 |
+
"num_tokens": 776734106.0,
|
| 1249 |
+
"step": 655
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.9379996446971043,
|
| 1253 |
+
"grad_norm": 3.942139353532877,
|
| 1254 |
+
"learning_rate": 2.192669458782096e-06,
|
| 1255 |
+
"loss": 0.5952,
|
| 1256 |
+
"mean_token_accuracy": 0.8051416061818599,
|
| 1257 |
+
"num_tokens": 782648208.0,
|
| 1258 |
+
"step": 660
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.9451057026114763,
|
| 1262 |
+
"grad_norm": 2.1646964014669794,
|
| 1263 |
+
"learning_rate": 2.1523471806439205e-06,
|
| 1264 |
+
"loss": 0.6057,
|
| 1265 |
+
"mean_token_accuracy": 0.8031233668327331,
|
| 1266 |
+
"num_tokens": 788582279.0,
|
| 1267 |
+
"step": 665
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.9522117605258483,
|
| 1271 |
+
"grad_norm": 2.4342297711554393,
|
| 1272 |
+
"learning_rate": 2.1167182193956738e-06,
|
| 1273 |
+
"loss": 0.5833,
|
| 1274 |
+
"mean_token_accuracy": 0.8084848992526531,
|
| 1275 |
+
"num_tokens": 794490250.0,
|
| 1276 |
+
"step": 670
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.9593178184402202,
|
| 1280 |
+
"grad_norm": 1.3849504055994097,
|
| 1281 |
+
"learning_rate": 2.0858014747397952e-06,
|
| 1282 |
+
"loss": 0.5927,
|
| 1283 |
+
"mean_token_accuracy": 0.8059051290154458,
|
| 1284 |
+
"num_tokens": 800406765.0,
|
| 1285 |
+
"step": 675
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.9664238763545923,
|
| 1289 |
+
"grad_norm": 1.8233541738404475,
|
| 1290 |
+
"learning_rate": 2.0596133467411213e-06,
|
| 1291 |
+
"loss": 0.5866,
|
| 1292 |
+
"mean_token_accuracy": 0.8072662524878979,
|
| 1293 |
+
"num_tokens": 806349672.0,
|
| 1294 |
+
"step": 680
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.9735299342689643,
|
| 1298 |
+
"grad_norm": 1.3071754875862744,
|
| 1299 |
+
"learning_rate": 2.0381677271273177e-06,
|
| 1300 |
+
"loss": 0.589,
|
| 1301 |
+
"mean_token_accuracy": 0.8057045452296734,
|
| 1302 |
+
"num_tokens": 812264222.0,
|
| 1303 |
+
"step": 685
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.9806359921833363,
|
| 1307 |
+
"grad_norm": 1.5289098269363515,
|
| 1308 |
+
"learning_rate": 2.0214759919198904e-06,
|
| 1309 |
+
"loss": 0.5831,
|
| 1310 |
+
"mean_token_accuracy": 0.8068839557468891,
|
| 1311 |
+
"num_tokens": 818190520.0,
|
| 1312 |
+
"step": 690
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.9877420500977083,
|
| 1316 |
+
"grad_norm": 2.015373930862521,
|
| 1317 |
+
"learning_rate": 2.0095469953996724e-06,
|
| 1318 |
+
"loss": 0.5994,
|
| 1319 |
+
"mean_token_accuracy": 0.8041414134204388,
|
| 1320 |
+
"num_tokens": 824098000.0,
|
| 1321 |
+
"step": 695
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.9948481080120803,
|
| 1325 |
+
"grad_norm": 2.2460839306695104,
|
| 1326 |
+
"learning_rate": 2.002387065409989e-06,
|
| 1327 |
+
"loss": 0.5962,
|
| 1328 |
+
"mean_token_accuracy": 0.8041631534695626,
|
| 1329 |
+
"num_tokens": 830080703.0,
|
| 1330 |
+
"step": 700
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.9948481080120803,
|
| 1334 |
+
"eval_loss": 0.5880739688873291,
|
| 1335 |
+
"eval_mean_token_accuracy": 0.8062155152622023,
|
| 1336 |
+
"eval_num_tokens": 830080703.0,
|
| 1337 |
+
"eval_runtime": 296.6258,
|
| 1338 |
+
"eval_samples_per_second": 12.268,
|
| 1339 |
+
"eval_steps_per_second": 0.384,
|
| 1340 |
+
"step": 700
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.0,
|
| 1344 |
+
"mean_token_accuracy": 0.8058657122069391,
|
| 1345 |
+
"num_tokens": 834374055.0,
|
| 1346 |
+
"step": 704,
|
| 1347 |
+
"total_flos": 1.2125984924893184e+16,
|
| 1348 |
+
"train_loss": 0.645972225476395,
|
| 1349 |
+
"train_runtime": 88419.8411,
|
| 1350 |
+
"train_samples_per_second": 4.074,
|
| 1351 |
+
"train_steps_per_second": 0.008
|
| 1352 |
+
}
|
| 1353 |
+
],
|
| 1354 |
+
"logging_steps": 5,
|
| 1355 |
+
"max_steps": 704,
|
| 1356 |
+
"num_input_tokens_seen": 0,
|
| 1357 |
+
"num_train_epochs": 1,
|
| 1358 |
+
"save_steps": 1,
|
| 1359 |
+
"stateful_callbacks": {
|
| 1360 |
+
"TrainerControl": {
|
| 1361 |
+
"args": {
|
| 1362 |
+
"should_epoch_stop": false,
|
| 1363 |
+
"should_evaluate": false,
|
| 1364 |
+
"should_log": false,
|
| 1365 |
+
"should_save": true,
|
| 1366 |
+
"should_training_stop": true
|
| 1367 |
+
},
|
| 1368 |
+
"attributes": {}
|
| 1369 |
+
}
|
| 1370 |
+
},
|
| 1371 |
+
"total_flos": 1.2125984924893184e+16,
|
| 1372 |
+
"train_batch_size": 4,
|
| 1373 |
+
"trial_name": null,
|
| 1374 |
+
"trial_params": null
|
| 1375 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75510d220562276768a262cdef788e60d531dcda3cc93519d59555c01f5d8f88
|
| 3 |
+
size 7416
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|