Upload UNO Scorer (initial version)
Browse files- .gitattributes +1 -0
- README.md +100 -0
- added_tokens.json +28 -0
- all_results.json +12 -0
- config.json +30 -0
- eval_results.json +7 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +450 -0
- special_tokens_map.json +31 -0
- test_scorer_hf.py +194 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- train_results.json +8 -0
- trainer_log.jsonl +75 -0
- trainer_state.json +573 -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 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# UNO-Scorer: A Unified General Scoring Model for UNO-Bench
|
| 3 |
+
|
| 4 |
+
<div align="center">
|
| 5 |
+
|
| 6 |
+
[](https://arxiv.org/abs/2510.18915)
|
| 7 |
+
[](https://huggingface.co/Qwen/Qwen3-14B)
|
| 8 |
+
[]()
|
| 9 |
+
|
| 10 |
+
</div>
|
| 11 |
+
|
| 12 |
+
## 📖 Introduction
|
| 13 |
+
|
| 14 |
+
**UNO-Scorer** is a lightweight yet high-precision general scoring model developed as part of **UNO-Bench**. It is designed to efficiently automate the evaluation of Large Multimodal Models (LMMs) with minimal computational overhead.
|
| 15 |
+
|
| 16 |
+
Built upon the powerful **Qwen3-14B** backbone, UNO-Scorer is fine-tuned on 13K high-quality in-house data. It overcomes the limitations of traditional Overall Reward Models (ORMs) by supporting **6 distinct question types**, with particular excellence in **Multi-Step Open-Ended Questions (MO)**.
|
| 17 |
+
|
| 18 |
+
## 📊 Performance
|
| 19 |
+
|
| 20 |
+
UNO-Scorer demonstrates superior performance in automated evaluation, particularly in handling complex **Multi-Step Open-Ended Questions**. We compared the accuracy of our scorer against other advanced evaluators:
|
| 21 |
+
|
| 22 |
+
| Model | Accuracy |
|
| 23 |
+
| :--- | :--- |
|
| 24 |
+
| Seed-1.5-VL | 0.9118 |
|
| 25 |
+
| GPT-4.1 | 0.9457 |
|
| 26 |
+
| **UNO-Scorer (Ours)** | **0.9505** |
|
| 27 |
+
|
| 28 |
+
Experiments show that UNO-Scorer surpasses even proprietary frontier models like GPT-4.1 in this specific evaluation domain with lower cost.
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
## 💻 Usage
|
| 33 |
+
|
| 34 |
+
### 0. Quick Start
|
| 35 |
+
|
| 36 |
+
```bash
|
| 37 |
+
pip install -U transformers
|
| 38 |
+
python3 test_scorer_hf.py --model-name /path/to/your/model
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
We recommend using vLLM for inference as it offers significantly better efficiency compared to the standard HuggingFace approach. Please follow the steps below to set up the environment and run the inference script provided in our official repository.
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
### 1. Clone the Repository
|
| 45 |
+
First, clone the UNO-Bench repository:
|
| 46 |
+
|
| 47 |
+
```bash
|
| 48 |
+
git clone https://github.com/meituan-longcat/UNO-Bench.git
|
| 49 |
+
cd UNO-Bench/uno_eval
|
| 50 |
+
```
|
| 51 |
+
|
| 52 |
+
### 2. Install Dependencies
|
| 53 |
+
Install the necessary Python libraries:
|
| 54 |
+
|
| 55 |
+
```bash
|
| 56 |
+
pip install -r requirement.txt
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
### 3. Run Inference
|
| 60 |
+
We provide an example script based on **vLLM** for efficient model inference. You can run the following command to test the scorer:
|
| 61 |
+
|
| 62 |
+
```bash
|
| 63 |
+
bash examples/test_scorer.sh
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
### 4. Adapt Your Reference Answer
|
| 67 |
+
The most critical aspect of utilizing the UNO-Scorer lies in the proper formatting of the Reference Answer. Specifically, it is required to:
|
| 68 |
+
|
| 69 |
+
1. Assign point values to the answer components. The total points for the question should typically sum to 10 points.
|
| 70 |
+
2. You may customize detailed scoring criteria for each reference answer to suit your needs(e.g., clarifying how to judge cases where the final choice is correct but the reasoning is flawed).
|
| 71 |
+
|
| 72 |
+
Note: Since the model is primarily trained on Chinese corpora, it adheres more accurately to instructions when these specific descriptions are written in Chinese.
|
| 73 |
+
|
| 74 |
+
You can structure the Reference Answer as follows:
|
| 75 |
+
|
| 76 |
+
| Question Type | Scenario | **Reference Answer** | Example |
|
| 77 |
+
| :--- | :--- | :--- | :--- |
|
| 78 |
+
| **Single Question** | The model only needs to check if the final result matches. | Format as a single sub-question (Sub-question 1) worth exactly 10 points.<br><br>Template:<br>`小问1：{Answer}，总分10分，无需关注推理过程，最终答案正确即可` | **Raw Answer:** "C"<br>**Input Answer:** `小问1：C，总分10分，无需关注推理过程，最终答案正确即可` |
|
| 79 |
+
| **Multiple Question** | The model needs to grade specific checkpoints. | Break down the answer into numbered sub-steps with assigned points (summing to exactly 10).<br><br>Template:<br>`1. {Sub-Answer A} ({X} points); 2. {Sub-Answer B} ({Y} points).` | **Raw Answer:** "5 apples, 6 bananas"<br>**Input Answer:** `1. 5 apples (4 points); 2. 6 bananas (6 points).` |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
## 📜 Citation
|
| 83 |
+
|
| 84 |
+
If you find this model or the UNO-Bench useful for your research, please cite our paper:
|
| 85 |
+
|
| 86 |
+
```bibtex
|
| 87 |
+
@misc{chen2025unobench,
|
| 88 |
+
title={UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models},
|
| 89 |
+
author={Chen Chen and ZeYang Hu and Fengjiao Chen and Liya Ma and Jiaxing Liu and Xiaoyu Li and Ziwen Wang and Xuezhi Cao and Xunliang Cai},
|
| 90 |
+
year={2025},
|
| 91 |
+
eprint={2510.18915},
|
| 92 |
+
archivePrefix={arXiv},
|
| 93 |
+
primaryClass={cs.CL},
|
| 94 |
+
url={https://arxiv.org/abs/2510.18915},
|
| 95 |
+
}
|
| 96 |
+
```
|
| 97 |
+
|
| 98 |
+
---
|
| 99 |
+
|
| 100 |
+
**Disclaimer:** This model is based on Qwen3-14B. Please strictly follow the license and usage policy of the original Qwen model series.
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9891956782713085,
|
| 3 |
+
"eval_loss": 0.15651731193065643,
|
| 4 |
+
"eval_runtime": 8.6007,
|
| 5 |
+
"eval_samples_per_second": 15.696,
|
| 6 |
+
"eval_steps_per_second": 1.977,
|
| 7 |
+
"total_flos": 170865984536576.0,
|
| 8 |
+
"train_loss": 0.1184023514103431,
|
| 9 |
+
"train_runtime": 9824.5273,
|
| 10 |
+
"train_samples_per_second": 4.068,
|
| 11 |
+
"train_steps_per_second": 0.064
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 17408,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 40,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 40,
|
| 18 |
+
"num_hidden_layers": 40,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.51.0",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9891956782713085,
|
| 3 |
+
"eval_loss": 0.15651731193065643,
|
| 4 |
+
"eval_runtime": 8.6007,
|
| 5 |
+
"eval_samples_per_second": 15.696,
|
| 6 |
+
"eval_steps_per_second": 1.977
|
| 7 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdb25da8e44943b0d0c4ae36ef642823a85cd73e88d837d3741ef0ada03af74f
|
| 3 |
+
size 4984780784
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f10f2ce02ecbff623315b99527ee701752f22de57d8b17402b2ec7eec5e92bb
|
| 3 |
+
size 4980892048
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a82a8b6e9fd7bca4e5a160fed235c9d0c1a51e1b130e25144291d3fcc67971de
|
| 3 |
+
size 4928485104
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c3d62883a9ba5cae605192a27066ce27d6b1dca4f30a9aae1ba3ed02f9e8482
|
| 3 |
+
size 4980892112
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85fb9f1a718b34a7a08bd56e5862f27fc7e4956128a03ece1b04dd2e1bd82f2e
|
| 3 |
+
size 4928485104
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df79aad074fc95e9706491ababe75f872d20e8b0afff2d1d6a56bdf955a3f9f6
|
| 3 |
+
size 4733130504
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,450 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 29536614400
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 41 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 52 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 63 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 74 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 85 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 96 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 107 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 118 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 129 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 140 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 151 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 162 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 173 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 184 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 195 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 206 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 217 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 228 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 239 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 250 |
+
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 272 |
+
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 283 |
+
"model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 294 |
+
"model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 295 |
+
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 296 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 297 |
+
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 298 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 305 |
+
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 306 |
+
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 307 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 308 |
+
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 309 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 316 |
+
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 317 |
+
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 318 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 319 |
+
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 320 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 327 |
+
"model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 328 |
+
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 329 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 330 |
+
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 331 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 338 |
+
"model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 339 |
+
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 340 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 341 |
+
"model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 342 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 343 |
+
"model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 344 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 345 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 346 |
+
"model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 347 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 348 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 349 |
+
"model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 350 |
+
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 351 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 352 |
+
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 353 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 354 |
+
"model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 355 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 356 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 357 |
+
"model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 358 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 359 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 360 |
+
"model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 361 |
+
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 362 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 363 |
+
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 364 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 365 |
+
"model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 366 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 367 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 368 |
+
"model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 369 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 370 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 371 |
+
"model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 372 |
+
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 373 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 374 |
+
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 375 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 376 |
+
"model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 377 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 378 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 379 |
+
"model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 380 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 381 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 382 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 383 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 384 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 385 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 386 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 387 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
| 388 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 389 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 390 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
| 391 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 392 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 393 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 394 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 395 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 396 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 397 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 398 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
| 399 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 400 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 401 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
| 402 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 403 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 404 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 405 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 406 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 407 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 408 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 409 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 410 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 411 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 412 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 413 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 414 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 415 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 416 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 417 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 418 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 419 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 420 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 421 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 422 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 423 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 424 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 425 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 426 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 427 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 428 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 429 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 430 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 431 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 432 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 433 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 434 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 435 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 436 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 437 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 438 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 439 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 440 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 441 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 442 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
| 443 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 444 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 445 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
| 446 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 447 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 448 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
| 449 |
+
}
|
| 450 |
+
}
|
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 |
+
}
|
test_scorer_hf.py
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
import argparse
|
| 3 |
+
from tqdm import tqdm
|
| 4 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 5 |
+
|
| 6 |
+
def extract_last_boxed(text):
|
| 7 |
+
try:
|
| 8 |
+
pattern = r'<score>([\d.]+)</score>'
|
| 9 |
+
matches = re.findall(pattern, text)
|
| 10 |
+
if matches:
|
| 11 |
+
return float(matches[-1])
|
| 12 |
+
else:
|
| 13 |
+
return 0.0
|
| 14 |
+
except Exception as e:
|
| 15 |
+
print(f"Error extracting boxed content: {e}")
|
| 16 |
+
return 0.0
|
| 17 |
+
|
| 18 |
+
def parse_from_score_model(response: str, scale_factor=10) -> float:
|
| 19 |
+
score = extract_last_boxed(response)
|
| 20 |
+
score = score / scale_factor
|
| 21 |
+
return score
|
| 22 |
+
|
| 23 |
+
def load_model(model_name: str) -> AutoModelForCausalLM:
|
| 24 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 25 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 26 |
+
model_name,
|
| 27 |
+
torch_dtype="auto",
|
| 28 |
+
device_map="auto"
|
| 29 |
+
)
|
| 30 |
+
return tokenizer, model
|
| 31 |
+
|
| 32 |
+
def generate(model, tokenizer, prompt: str) -> str:
|
| 33 |
+
messages = [
|
| 34 |
+
{
|
| 35 |
+
"role": "system",
|
| 36 |
+
"content": "You are a helpful assistant."
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"role": "user",
|
| 40 |
+
"content": prompt
|
| 41 |
+
}
|
| 42 |
+
]
|
| 43 |
+
text = tokenizer.apply_chat_template(
|
| 44 |
+
messages,
|
| 45 |
+
tokenize=False,
|
| 46 |
+
add_generation_prompt=True,
|
| 47 |
+
)
|
| 48 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 49 |
+
|
| 50 |
+
# conduct text completion
|
| 51 |
+
generated_ids = model.generate(
|
| 52 |
+
**model_inputs,
|
| 53 |
+
max_new_tokens=16384,
|
| 54 |
+
do_sample=False
|
| 55 |
+
)
|
| 56 |
+
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
| 57 |
+
|
| 58 |
+
content = tokenizer.decode(output_ids, skip_special_tokens=True)
|
| 59 |
+
return content
|
| 60 |
+
|
| 61 |
+
def remove_thought_block(text: str) -> str:
|
| 62 |
+
pattern = r"^(<think>.*?</think>|.*?)"
|
| 63 |
+
match = re.match(pattern, text, flags=re.DOTALL)
|
| 64 |
+
if match:
|
| 65 |
+
end_of_match = match.end()
|
| 66 |
+
return text[end_of_match:].lstrip()
|
| 67 |
+
return text
|
| 68 |
+
|
| 69 |
+
def process_score_prompt(question, reference, response):
|
| 70 |
+
promt_template = """请先通读问题信息，然后基于参考答案对模型回复的结果进行正确性打分。每道题可能包含多个小问，每个小问都已给出了相应的参考答案和分值，请逐小问校验模型回复是否正确，正确得对应分值，错误或漏答得0分，累计计分，有如下要求。
|
| 71 |
+
|
| 72 |
+
---
|
| 73 |
+
|
| 74 |
+
### 要求1：信息梳理
|
| 75 |
+
|
| 76 |
+
- 梳理出如下信息
|
| 77 |
+
- 问题内容
|
| 78 |
+
- 参考答案（可适度完善表达，但不改变核心内容）
|
| 79 |
+
- 模型回复（需要将模型回复中的指代关系与参考答案对齐）
|
| 80 |
+
- 分值
|
| 81 |
+
|
| 82 |
+
### 要求2：判断题型
|
| 83 |
+
|
| 84 |
+
- 明确该小问属于以下哪种题型之一，并基于该类型的打分标准进行打分，需要给出详细的比对过程。
|
| 85 |
+
- **数值型**，要求模型回复与标准答案的数值完全相同，不允许有误差。例，`问题：北京奥运会是哪一年？参考答案：2008，模型回复：2004，打分结果：错误。`
|
| 86 |
+
- **枚举型**，要求模型回复列举出参考答案的全部对象，缺一不可、错一不可，允许同义词等语义相近的表达，题中有顺序要求则必须按顺序枚举。例，`图中出现了哪些动物？参考答案：大熊猫、河马、长颈鹿，模型回复：河马、小熊猫、长颈鹿，打分结果：错误。 `注：“/”表示“或”，如，XXA/XXB，表示回答出任意一项即可。
|
| 87 |
+
- **选择题**，要求模型回复与参考答案相同的选项或选项内容。例，`问题：李白是哪个朝代的诗人？A. 唐朝 B. 宋朝 C. 元朝，模型回复：李白是唐朝诗人，打分结果：正确。`
|
| 88 |
+
- **判断题**，要求模型回复与参考答案的判断一致。例，`问题：图中鼠标是否放在了笔记本电脑左侧？参考答案：是，模型回复：图中鼠标在笔记本电脑的左侧。打分结果：正确。`
|
| 89 |
+
- **简答题**，要求模型回复包括与参考答案语义一致的短语或表达，允许表达方式不同。例，`问题：视频中最后放入锅中的食材是什么？参考答案：洋葱，模型回复：胡萝卜。打分结果：错误。`
|
| 90 |
+
- **论述题**，要求模型回复包含参考答案的核心观点。例，`问题：请简要论述为什么要保护生物多样性。参考答案：维持生态平衡，模型回复：保护生物多样性能够让生态系统保持稳定，促进人类社会的可持续发展。打分结果：正确。`
|
| 91 |
+
|
| 92 |
+
### 要求3：打分标准
|
| 93 |
+
|
| 94 |
+
- **完全正确**：得满分。
|
| 95 |
+
- **错误或漏答**：得0分。
|
| 96 |
+
- 如模型回复与参考答案大意相同但细节略有差别，且非核心内容，视为正确，具体参考参考答案的详细要求。
|
| 97 |
+
- 若模型回复未直接给出答案，需主动归纳总结结论，只关注结论是否一致。
|
| 98 |
+
- 每小问独立打分，前序错误不影响后续小问的结果。
|
| 99 |
+
|
| 100 |
+
### 要求4：输出格式
|
| 101 |
+
|
| 102 |
+
- 逐小问列出得分说明。
|
| 103 |
+
- 所有小问得分相加，在<score></score>中给出总分，例如：<score>5</score>
|
| 104 |
+
|
| 105 |
+
---
|
| 106 |
+
|
| 107 |
+
## 问题���息
|
| 108 |
+
{{question}}
|
| 109 |
+
## 参考答案
|
| 110 |
+
{{reference}}
|
| 111 |
+
## 模型回复
|
| 112 |
+
{{response}}
|
| 113 |
+
## 逐小问打分"""
|
| 114 |
+
|
| 115 |
+
prompt = promt_template.replace("{{question}}", remove_thought_block(question.strip()))
|
| 116 |
+
prompt = prompt.replace("{{reference}}", reference)
|
| 117 |
+
prompt = prompt.replace("{{response}}", response)
|
| 118 |
+
return prompt
|
| 119 |
+
|
| 120 |
+
|
| 121 |
+
if __name__ == "__main__":
|
| 122 |
+
|
| 123 |
+
parser = argparse.ArgumentParser(description="Run evaluation on a given model and dataset.")
|
| 124 |
+
parser.add_argument("--model-name", type=str, default="", help="The model name or path.")
|
| 125 |
+
|
| 126 |
+
args = parser.parse_args()
|
| 127 |
+
tokenizer, model = load_model(args.model_name)
|
| 128 |
+
|
| 129 |
+
test_cases = [
|
| 130 |
+
# Multiple-choice question
|
| 131 |
+
{
|
| 132 |
+
"question_type": "multiple-choice",
|
| 133 |
+
"question": "Which one is the best depiction of this image?\nA. A beautiful woman wearing a hat is holding a rose in her right hand and is opening her mouth big to eat it.\nB. A young woman is wearing a hat and her right hand is pierced by a bouquet of pink roses, and she opens her mouth to express pain.\nC. A young girl wearing brown clothes is holding a blooming pink flower in her right hand, with her mouth slightly open.\nD. A young girl wearing brown clothes is holding a blooming magic wand in her right hand, with her mouth slightly open.",
|
| 134 |
+
"answer": "C",
|
| 135 |
+
"response": "Well, if we're talking about the best depiction of this image, I'd say it's C. The young girl in brown clothes holding a blooming pink flower in her right hand with her mouth slightly open seems to match the image the most. What do you think? Do you agree with that?",
|
| 136 |
+
"target_score": 1
|
| 137 |
+
},
|
| 138 |
+
# Yes/No question
|
| 139 |
+
{
|
| 140 |
+
"question_type": "yes/no",
|
| 141 |
+
"question": "The following images show two graphs. Each graph is represented in a separate image. Are these graphs isomorphic?Answer Yes or No.",
|
| 142 |
+
"answer": "Yes",
|
| 143 |
+
"response": "No. If you have any other questions about these graphs or anything else, feel free to ask!",
|
| 144 |
+
"target_score": 0
|
| 145 |
+
},
|
| 146 |
+
# Open-ended question
|
| 147 |
+
{
|
| 148 |
+
"question_type": "open-ended",
|
| 149 |
+
"question": "How many seasons did 90210 have?",
|
| 150 |
+
"answer": "Ten",
|
| 151 |
+
"response": "I'm not sure which \"90210\" you're referring to. There are different shows or things with that name. If it's the TV show \"90210\", it had 7 seasons. But if it's something else, you might need to give me a bit more context.",
|
| 152 |
+
"target_score": 0
|
| 153 |
+
},
|
| 154 |
+
# Multiple-question answer
|
| 155 |
+
{
|
| 156 |
+
# If the question type is multi-question, you must specify the answer in detail.
|
| 157 |
+
"question_type": "multiple-question",
|
| 158 |
+
"question": "David is playing an escape room game. In one of the levels, he needs to find the key to the room. The game rules state that he must locate the box containing the key among a row of identical-looking boxes, and correctly enter the box's password to obtain the key to escape. It is known that the box with the key meets the following conditions: it is not at either end; it is not in the very middle; the number of boxes on both its left and right sides is even. In addition, each box has a three-digit password, with each digit being one of the numbers from 0 to 9. The arrangement of the boxes and the password puzzle are hidden in image <image_1>. The image puzzle provides two decryption examples, and you need to use these examples to decode which digits the two question marks at the bottom of the image represent. Among all the numbers given in the provided examples and obtained after decoding, the smallest number is interference information and should be excluded. Partial clues about the box containing the key and its password are hidden in audio <audio_1>. Based on the above information, and combining the image and audio clues, answer:\n1. Which box (counting from left to right) contains the key?\n2. What is the correct password for the box containing the key?",
|
| 159 |
+
"answer": "1. The 5th box from the left (4 points);\n2. The password is 569 (6 points).",
|
| 160 |
+
"response": "Hmm… let me think. According to the hint in the audio, the key to decryption lies in the Roman numerals hidden in the words, and these numbers are all no greater than 10. From the image, there are six boxes. Based on the rules, the key is neither at the ends nor in the middle, so it should be in the 5th box from the left. As for the password, arranging in ascending order, it should be Victory = 2, give = 3. So the password for the box with the key is 23. If you have any other ideas or questions, feel free to let me know.",
|
| 161 |
+
"target_score": 0.4
|
| 162 |
+
}
|
| 163 |
+
]
|
| 164 |
+
|
| 165 |
+
prompts = []
|
| 166 |
+
for case in test_cases:
|
| 167 |
+
answer = case["answer"]
|
| 168 |
+
if case["question_type"] != "multiple-question":
|
| 169 |
+
# The Chinese rule will be better because the scorer model is trained in Chinese.
|
| 170 |
+
answer = f"小问1：{answer}，总分10分，无需关注推理过程，最终答案正确即可"
|
| 171 |
+
question = case["question"]
|
| 172 |
+
response = remove_thought_block(case["response"])
|
| 173 |
+
prompt = process_score_prompt(question=question, reference=answer, response=response)
|
| 174 |
+
prompts.append(prompt)
|
| 175 |
+
|
| 176 |
+
score_responses = []
|
| 177 |
+
for prompt in tqdm(prompts):
|
| 178 |
+
score_response = generate(model, tokenizer, prompt)
|
| 179 |
+
score_responses.append(score_response)
|
| 180 |
+
|
| 181 |
+
pass_cnt = 0
|
| 182 |
+
for score_response, case in zip(score_responses, test_cases):
|
| 183 |
+
print("="*32)
|
| 184 |
+
score = parse_from_score_model(score_response)
|
| 185 |
+
for key,value in case.items():
|
| 186 |
+
print(f"{key}: {value}")
|
| 187 |
+
print("Score response:\n", score_response)
|
| 188 |
+
print(f"Score: {score}, Target Score: {case['target_score']}")
|
| 189 |
+
|
| 190 |
+
if score == case["target_score"]:
|
| 191 |
+
pass_cnt += 1
|
| 192 |
+
print("*"*32)
|
| 193 |
+
print(f"Pass: {pass_cnt}/{len(test_cases)}")
|
| 194 |
+
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"padding_side": "right",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9891956782713085,
|
| 3 |
+
"total_flos": 170865984536576.0,
|
| 4 |
+
"train_loss": 0.1184023514103431,
|
| 5 |
+
"train_runtime": 9824.5273,
|
| 6 |
+
"train_samples_per_second": 4.068,
|
| 7 |
+
"train_steps_per_second": 0.064
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 624, "loss": 0.4239, "lr": 1.4285714285714286e-06, "epoch": 0.04801920768307323, "percentage": 1.6, "elapsed_time": "0:02:33", "remaining_time": "2:37:16"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 624, "loss": 0.3052, "lr": 3.015873015873016e-06, "epoch": 0.09603841536614646, "percentage": 3.21, "elapsed_time": "0:04:55", "remaining_time": "2:28:51"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 624, "loss": 0.2483, "lr": 4.603174603174604e-06, "epoch": 0.14405762304921968, "percentage": 4.81, "elapsed_time": "0:07:20", "remaining_time": "2:25:26"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 624, "loss": 0.2312, "lr": 6.1904761904761914e-06, "epoch": 0.19207683073229292, "percentage": 6.41, "elapsed_time": "0:09:58", "remaining_time": "2:25:35"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 624, "loss": 0.1988, "lr": 7.77777777777778e-06, "epoch": 0.24009603841536614, "percentage": 8.01, "elapsed_time": "0:12:33", "remaining_time": "2:24:11"}
|
| 6 |
+
{"current_steps": 50, "total_steps": 624, "eval_loss": 0.2022361308336258, "epoch": 0.24009603841536614, "percentage": 8.01, "elapsed_time": "0:12:42", "remaining_time": "2:25:51"}
|
| 7 |
+
{"current_steps": 60, "total_steps": 624, "loss": 0.1855, "lr": 9.365079365079366e-06, "epoch": 0.28811524609843936, "percentage": 9.62, "elapsed_time": "0:15:20", "remaining_time": "2:24:10"}
|
| 8 |
+
{"current_steps": 70, "total_steps": 624, "loss": 0.1874, "lr": 9.99717787871887e-06, "epoch": 0.33613445378151263, "percentage": 11.22, "elapsed_time": "0:17:42", "remaining_time": "2:20:12"}
|
| 9 |
+
{"current_steps": 80, "total_steps": 624, "loss": 0.1732, "lr": 9.979943117513265e-06, "epoch": 0.38415366146458585, "percentage": 12.82, "elapsed_time": "0:20:03", "remaining_time": "2:16:23"}
|
| 10 |
+
{"current_steps": 90, "total_steps": 624, "loss": 0.1798, "lr": 9.947095408534483e-06, "epoch": 0.43217286914765907, "percentage": 14.42, "elapsed_time": "0:22:31", "remaining_time": "2:13:38"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 624, "loss": 0.1671, "lr": 9.898737734799134e-06, "epoch": 0.4801920768307323, "percentage": 16.03, "elapsed_time": "0:24:57", "remaining_time": "2:10:49"}
|
| 12 |
+
{"current_steps": 100, "total_steps": 624, "eval_loss": 0.17217175662517548, "epoch": 0.4801920768307323, "percentage": 16.03, "elapsed_time": "0:25:06", "remaining_time": "2:11:35"}
|
| 13 |
+
{"current_steps": 110, "total_steps": 624, "loss": 0.1672, "lr": 9.835021705636201e-06, "epoch": 0.5282112845138055, "percentage": 17.63, "elapsed_time": "0:27:39", "remaining_time": "2:09:12"}
|
| 14 |
+
{"current_steps": 120, "total_steps": 624, "loss": 0.1661, "lr": 9.756147081366673e-06, "epoch": 0.5762304921968787, "percentage": 19.23, "elapsed_time": "0:30:05", "remaining_time": "2:06:23"}
|
| 15 |
+
{"current_steps": 130, "total_steps": 624, "loss": 0.1678, "lr": 9.66236114702178e-06, "epoch": 0.6242496998799519, "percentage": 20.83, "elapsed_time": "0:32:29", "remaining_time": "2:03:27"}
|
| 16 |
+
{"current_steps": 140, "total_steps": 624, "loss": 0.1604, "lr": 9.55395793706341e-06, "epoch": 0.6722689075630253, "percentage": 22.44, "elapsed_time": "0:34:53", "remaining_time": "2:00:36"}
|
| 17 |
+
{"current_steps": 150, "total_steps": 624, "loss": 0.1581, "lr": 9.43127731353729e-06, "epoch": 0.7202881152460985, "percentage": 24.04, "elapsed_time": "0:37:08", "remaining_time": "1:57:23"}
|
| 18 |
+
{"current_steps": 150, "total_steps": 624, "eval_loss": 0.15990422666072845, "epoch": 0.7202881152460985, "percentage": 24.04, "elapsed_time": "0:37:17", "remaining_time": "1:57:51"}
|
| 19 |
+
{"current_steps": 160, "total_steps": 624, "loss": 0.1608, "lr": 9.294703900549096e-06, "epoch": 0.7683073229291717, "percentage": 25.64, "elapsed_time": "0:39:45", "remaining_time": "1:55:18"}
|
| 20 |
+
{"current_steps": 170, "total_steps": 624, "loss": 0.162, "lr": 9.14466587840408e-06, "epoch": 0.8163265306122449, "percentage": 27.24, "elapsed_time": "0:42:05", "remaining_time": "1:52:24"}
|
| 21 |
+
{"current_steps": 180, "total_steps": 624, "loss": 0.1566, "lr": 8.981633641190779e-06, "epoch": 0.8643457382953181, "percentage": 28.85, "elapsed_time": "0:44:37", "remaining_time": "1:50:05"}
|
| 22 |
+
{"current_steps": 190, "total_steps": 624, "loss": 0.1486, "lr": 8.806118322017525e-06, "epoch": 0.9123649459783914, "percentage": 30.45, "elapsed_time": "0:47:01", "remaining_time": "1:47:25"}
|
| 23 |
+
{"current_steps": 200, "total_steps": 624, "loss": 0.1513, "lr": 8.61867019052535e-06, "epoch": 0.9603841536614646, "percentage": 32.05, "elapsed_time": "0:49:25", "remaining_time": "1:44:46"}
|
| 24 |
+
{"current_steps": 200, "total_steps": 624, "eval_loss": 0.1510133445262909, "epoch": 0.9603841536614646, "percentage": 32.05, "elapsed_time": "0:49:33", "remaining_time": "1:45:04"}
|
| 25 |
+
{"current_steps": 210, "total_steps": 624, "loss": 0.1452, "lr": 8.41987692770139e-06, "epoch": 1.0048019207683074, "percentage": 33.65, "elapsed_time": "0:54:20", "remaining_time": "1:47:08"}
|
| 26 |
+
{"current_steps": 220, "total_steps": 624, "loss": 0.1086, "lr": 8.210361783401491e-06, "epoch": 1.0528211284513807, "percentage": 35.26, "elapsed_time": "0:56:50", "remaining_time": "1:44:22"}
|
| 27 |
+
{"current_steps": 230, "total_steps": 624, "loss": 0.1098, "lr": 7.990781622358535e-06, "epoch": 1.1008403361344539, "percentage": 36.86, "elapsed_time": "0:59:14", "remaining_time": "1:41:29"}
|
| 28 |
+
{"current_steps": 240, "total_steps": 624, "loss": 0.1042, "lr": 7.76182486480253e-06, "epoch": 1.148859543817527, "percentage": 38.46, "elapsed_time": "1:01:38", "remaining_time": "1:38:36"}
|
| 29 |
+
{"current_steps": 250, "total_steps": 624, "loss": 0.1104, "lr": 7.524209328148995e-06, "epoch": 1.1968787515006003, "percentage": 40.06, "elapsed_time": "1:04:00", "remaining_time": "1:35:45"}
|
| 30 |
+
{"current_steps": 250, "total_steps": 624, "eval_loss": 0.15508781373500824, "epoch": 1.1968787515006003, "percentage": 40.06, "elapsed_time": "1:04:09", "remaining_time": "1:35:58"}
|
| 31 |
+
{"current_steps": 260, "total_steps": 624, "loss": 0.1024, "lr": 7.278679976522279e-06, "epoch": 1.2448979591836735, "percentage": 41.67, "elapsed_time": "1:06:31", "remaining_time": "1:33:08"}
|
| 32 |
+
{"current_steps": 270, "total_steps": 624, "loss": 0.1067, "lr": 7.026006585169467e-06, "epoch": 1.2929171668667467, "percentage": 43.27, "elapsed_time": "1:08:59", "remaining_time": "1:30:27"}
|
| 33 |
+
{"current_steps": 280, "total_steps": 624, "loss": 0.1106, "lr": 6.766981327087271e-06, "epoch": 1.34093637454982, "percentage": 44.87, "elapsed_time": "1:11:27", "remaining_time": "1:27:47"}
|
| 34 |
+
{"current_steps": 290, "total_steps": 624, "loss": 0.1027, "lr": 6.502416289428282e-06, "epoch": 1.3889555822328932, "percentage": 46.47, "elapsed_time": "1:13:54", "remaining_time": "1:25:07"}
|
| 35 |
+
{"current_steps": 300, "total_steps": 624, "loss": 0.1068, "lr": 6.233140927473033e-06, "epoch": 1.4369747899159664, "percentage": 48.08, "elapsed_time": "1:16:23", "remaining_time": "1:22:30"}
|
| 36 |
+
{"current_steps": 300, "total_steps": 624, "eval_loss": 0.14931099116802216, "epoch": 1.4369747899159664, "percentage": 48.08, "elapsed_time": "1:16:32", "remaining_time": "1:22:39"}
|
| 37 |
+
{"current_steps": 310, "total_steps": 624, "loss": 0.1043, "lr": 5.959999464150101e-06, "epoch": 1.4849939975990396, "percentage": 49.68, "elapsed_time": "1:18:56", "remaining_time": "1:19:57"}
|
| 38 |
+
{"current_steps": 320, "total_steps": 624, "loss": 0.1058, "lr": 5.683848243257181e-06, "epoch": 1.5330132052821128, "percentage": 51.28, "elapsed_time": "1:21:17", "remaining_time": "1:17:13"}
|
| 39 |
+
{"current_steps": 330, "total_steps": 624, "loss": 0.1035, "lr": 5.40555304468122e-06, "epoch": 1.581032412965186, "percentage": 52.88, "elapsed_time": "1:23:38", "remaining_time": "1:14:31"}
|
| 40 |
+
{"current_steps": 340, "total_steps": 624, "loss": 0.1032, "lr": 5.125986370034862e-06, "epoch": 1.6290516206482593, "percentage": 54.49, "elapsed_time": "1:26:02", "remaining_time": "1:11:51"}
|
| 41 |
+
{"current_steps": 350, "total_steps": 624, "loss": 0.1006, "lr": 4.846024707219149e-06, "epoch": 1.6770708283313325, "percentage": 56.09, "elapsed_time": "1:28:25", "remaining_time": "1:09:13"}
|
| 42 |
+
{"current_steps": 350, "total_steps": 624, "eval_loss": 0.14417614042758942, "epoch": 1.6770708283313325, "percentage": 56.09, "elapsed_time": "1:28:33", "remaining_time": "1:09:19"}
|
| 43 |
+
{"current_steps": 360, "total_steps": 624, "loss": 0.1019, "lr": 4.566545782488554e-06, "epoch": 1.725090036014406, "percentage": 57.69, "elapsed_time": "1:31:04", "remaining_time": "1:06:47"}
|
| 44 |
+
{"current_steps": 370, "total_steps": 624, "loss": 0.0976, "lr": 4.2884258086335755e-06, "epoch": 1.773109243697479, "percentage": 59.29, "elapsed_time": "1:33:32", "remaining_time": "1:04:13"}
|
| 45 |
+
{"current_steps": 380, "total_steps": 624, "loss": 0.1003, "lr": 4.012536737908288e-06, "epoch": 1.8211284513805523, "percentage": 60.9, "elapsed_time": "1:35:46", "remaining_time": "1:01:30"}
|
| 46 |
+
{"current_steps": 390, "total_steps": 624, "loss": 0.0991, "lr": 3.7397435283153795e-06, "epoch": 1.8691476590636253, "percentage": 62.5, "elapsed_time": "1:38:08", "remaining_time": "0:58:53"}
|
| 47 |
+
{"current_steps": 400, "total_steps": 624, "loss": 0.1029, "lr": 3.4709014318193298e-06, "epoch": 1.9171668667466988, "percentage": 64.1, "elapsed_time": "1:40:48", "remaining_time": "0:56:27"}
|
| 48 |
+
{"current_steps": 400, "total_steps": 624, "eval_loss": 0.14110355079174042, "epoch": 1.9171668667466988, "percentage": 64.1, "elapsed_time": "1:40:57", "remaining_time": "0:56:32"}
|
| 49 |
+
{"current_steps": 410, "total_steps": 624, "loss": 0.1035, "lr": 3.2068533129896273e-06, "epoch": 1.9651860744297718, "percentage": 65.71, "elapsed_time": "1:46:03", "remaining_time": "0:55:21"}
|
| 50 |
+
{"current_steps": 420, "total_steps": 624, "loss": 0.0912, "lr": 2.948427006480528e-06, "epoch": 2.009603841536615, "percentage": 67.31, "elapsed_time": "1:48:16", "remaining_time": "0:52:35"}
|
| 51 |
+
{"current_steps": 430, "total_steps": 624, "loss": 0.059, "lr": 2.696432721632082e-06, "epoch": 2.057623049219688, "percentage": 68.91, "elapsed_time": "1:50:42", "remaining_time": "0:49:56"}
|
| 52 |
+
{"current_steps": 440, "total_steps": 624, "loss": 0.0567, "lr": 2.4516605023294626e-06, "epoch": 2.1056422569027613, "percentage": 70.51, "elapsed_time": "1:53:10", "remaining_time": "0:47:19"}
|
| 53 |
+
{"current_steps": 450, "total_steps": 624, "loss": 0.0617, "lr": 2.2148777500843125e-06, "epoch": 2.1536614645858343, "percentage": 72.12, "elapsed_time": "1:55:34", "remaining_time": "0:44:41"}
|
| 54 |
+
{"current_steps": 450, "total_steps": 624, "eval_loss": 0.1581123322248459, "epoch": 2.1536614645858343, "percentage": 72.12, "elapsed_time": "1:55:43", "remaining_time": "0:44:44"}
|
| 55 |
+
{"current_steps": 460, "total_steps": 624, "loss": 0.0584, "lr": 1.9868268181037186e-06, "epoch": 2.2016806722689077, "percentage": 73.72, "elapsed_time": "1:58:09", "remaining_time": "0:42:07"}
|
| 56 |
+
{"current_steps": 470, "total_steps": 624, "loss": 0.058, "lr": 1.768222683889757e-06, "epoch": 2.2496998799519807, "percentage": 75.32, "elapsed_time": "2:00:29", "remaining_time": "0:39:28"}
|
| 57 |
+
{"current_steps": 480, "total_steps": 624, "loss": 0.0588, "lr": 1.5597507076664187e-06, "epoch": 2.297719087635054, "percentage": 76.92, "elapsed_time": "2:02:49", "remaining_time": "0:36:50"}
|
| 58 |
+
{"current_steps": 490, "total_steps": 624, "loss": 0.0555, "lr": 1.362064483661617e-06, "epoch": 2.345738295318127, "percentage": 78.53, "elapsed_time": "2:05:16", "remaining_time": "0:34:15"}
|
| 59 |
+
{"current_steps": 500, "total_steps": 624, "loss": 0.0584, "lr": 1.1757837909808628e-06, "epoch": 2.3937575030012006, "percentage": 80.13, "elapsed_time": "2:07:44", "remaining_time": "0:31:40"}
|
| 60 |
+
{"current_steps": 500, "total_steps": 624, "eval_loss": 0.1588136851787567, "epoch": 2.3937575030012006, "percentage": 80.13, "elapsed_time": "2:07:52", "remaining_time": "0:31:42"}
|
| 61 |
+
{"current_steps": 510, "total_steps": 624, "loss": 0.0568, "lr": 1.0014926504969535e-06, "epoch": 2.4417767106842736, "percentage": 81.73, "elapsed_time": "2:10:10", "remaining_time": "0:29:05"}
|
| 62 |
+
{"current_steps": 520, "total_steps": 624, "loss": 0.057, "lr": 8.397374938476594e-07, "epoch": 2.489795918367347, "percentage": 83.33, "elapsed_time": "2:12:39", "remaining_time": "0:26:31"}
|
| 63 |
+
{"current_steps": 530, "total_steps": 624, "loss": 0.0562, "lr": 6.910254502818914e-07, "epoch": 2.53781512605042, "percentage": 84.94, "elapsed_time": "2:15:02", "remaining_time": "0:23:57"}
|
| 64 |
+
{"current_steps": 540, "total_steps": 624, "loss": 0.0571, "lr": 5.558227567253832e-07, "epoch": 2.5858343337334935, "percentage": 86.54, "elapsed_time": "2:17:39", "remaining_time": "0:21:24"}
|
| 65 |
+
{"current_steps": 550, "total_steps": 624, "loss": 0.0585, "lr": 4.3455329605058436e-07, "epoch": 2.6338535414165665, "percentage": 88.14, "elapsed_time": "2:20:14", "remaining_time": "0:18:52"}
|
| 66 |
+
{"current_steps": 550, "total_steps": 624, "eval_loss": 0.1571720838546753, "epoch": 2.6338535414165665, "percentage": 88.14, "elapsed_time": "2:20:23", "remaining_time": "0:18:53"}
|
| 67 |
+
{"current_steps": 560, "total_steps": 624, "loss": 0.0557, "lr": 3.275972681335421e-07, "epoch": 2.68187274909964, "percentage": 89.74, "elapsed_time": "2:22:48", "remaining_time": "0:16:19"}
|
| 68 |
+
{"current_steps": 570, "total_steps": 624, "loss": 0.0551, "lr": 2.3528999786421758e-07, "epoch": 2.729891956782713, "percentage": 91.35, "elapsed_time": "2:25:13", "remaining_time": "0:13:45"}
|
| 69 |
+
{"current_steps": 580, "total_steps": 624, "loss": 0.0578, "lr": 1.5792088384733174e-07, "epoch": 2.7779111644657863, "percentage": 92.95, "elapsed_time": "2:27:44", "remaining_time": "0:11:12"}
|
| 70 |
+
{"current_steps": 590, "total_steps": 624, "loss": 0.0571, "lr": 9.573249108973281e-08, "epoch": 2.82593037214886, "percentage": 94.55, "elapsed_time": "2:30:00", "remaining_time": "0:08:38"}
|
| 71 |
+
{"current_steps": 600, "total_steps": 624, "loss": 0.0552, "lr": 4.891979051886153e-08, "epoch": 2.8739495798319328, "percentage": 96.15, "elapsed_time": "2:32:29", "remaining_time": "0:06:05"}
|
| 72 |
+
{"current_steps": 600, "total_steps": 624, "eval_loss": 0.15641489624977112, "epoch": 2.8739495798319328, "percentage": 96.15, "elapsed_time": "2:32:38", "remaining_time": "0:06:06"}
|
| 73 |
+
{"current_steps": 610, "total_steps": 624, "loss": 0.058, "lr": 1.762954771655001e-08, "epoch": 2.9219687875150058, "percentage": 97.76, "elapsed_time": "2:37:50", "remaining_time": "0:03:37"}
|
| 74 |
+
{"current_steps": 620, "total_steps": 624, "loss": 0.0548, "lr": 1.959862784577937e-09, "epoch": 2.969987995198079, "percentage": 99.36, "elapsed_time": "2:40:11", "remaining_time": "0:01:02"}
|
| 75 |
+
{"current_steps": 624, "total_steps": 624, "epoch": 2.9891956782713085, "percentage": 100.0, "elapsed_time": "2:43:44", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.9891956782713085,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 624,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04801920768307323,
|
| 14 |
+
"grad_norm": 3.922592356078373,
|
| 15 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 16 |
+
"loss": 0.4239,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09603841536614646,
|
| 21 |
+
"grad_norm": 1.048139141700484,
|
| 22 |
+
"learning_rate": 3.015873015873016e-06,
|
| 23 |
+
"loss": 0.3052,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.14405762304921968,
|
| 28 |
+
"grad_norm": 0.8538085575650297,
|
| 29 |
+
"learning_rate": 4.603174603174604e-06,
|
| 30 |
+
"loss": 0.2483,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.19207683073229292,
|
| 35 |
+
"grad_norm": 0.7208408522041903,
|
| 36 |
+
"learning_rate": 6.1904761904761914e-06,
|
| 37 |
+
"loss": 0.2312,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.24009603841536614,
|
| 42 |
+
"grad_norm": 0.6048748741273176,
|
| 43 |
+
"learning_rate": 7.77777777777778e-06,
|
| 44 |
+
"loss": 0.1988,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.24009603841536614,
|
| 49 |
+
"eval_loss": 0.2022361308336258,
|
| 50 |
+
"eval_runtime": 8.7258,
|
| 51 |
+
"eval_samples_per_second": 15.471,
|
| 52 |
+
"eval_steps_per_second": 1.948,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.28811524609843936,
|
| 57 |
+
"grad_norm": 0.6463317852210085,
|
| 58 |
+
"learning_rate": 9.365079365079366e-06,
|
| 59 |
+
"loss": 0.1855,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.33613445378151263,
|
| 64 |
+
"grad_norm": 0.7181148124716302,
|
| 65 |
+
"learning_rate": 9.99717787871887e-06,
|
| 66 |
+
"loss": 0.1874,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.38415366146458585,
|
| 71 |
+
"grad_norm": 0.6510412334843603,
|
| 72 |
+
"learning_rate": 9.979943117513265e-06,
|
| 73 |
+
"loss": 0.1732,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.43217286914765907,
|
| 78 |
+
"grad_norm": 0.6418219788086171,
|
| 79 |
+
"learning_rate": 9.947095408534483e-06,
|
| 80 |
+
"loss": 0.1798,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.4801920768307323,
|
| 85 |
+
"grad_norm": 0.5909891764283862,
|
| 86 |
+
"learning_rate": 9.898737734799134e-06,
|
| 87 |
+
"loss": 0.1671,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.4801920768307323,
|
| 92 |
+
"eval_loss": 0.17217175662517548,
|
| 93 |
+
"eval_runtime": 8.7329,
|
| 94 |
+
"eval_samples_per_second": 15.459,
|
| 95 |
+
"eval_steps_per_second": 1.947,
|
| 96 |
+
"step": 100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.5282112845138055,
|
| 100 |
+
"grad_norm": 0.5490095561563818,
|
| 101 |
+
"learning_rate": 9.835021705636201e-06,
|
| 102 |
+
"loss": 0.1672,
|
| 103 |
+
"step": 110
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.5762304921968787,
|
| 107 |
+
"grad_norm": 0.5919523660281423,
|
| 108 |
+
"learning_rate": 9.756147081366673e-06,
|
| 109 |
+
"loss": 0.1661,
|
| 110 |
+
"step": 120
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.6242496998799519,
|
| 114 |
+
"grad_norm": 0.5553308704075627,
|
| 115 |
+
"learning_rate": 9.66236114702178e-06,
|
| 116 |
+
"loss": 0.1678,
|
| 117 |
+
"step": 130
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.6722689075630253,
|
| 121 |
+
"grad_norm": 0.5921710123949474,
|
| 122 |
+
"learning_rate": 9.55395793706341e-06,
|
| 123 |
+
"loss": 0.1604,
|
| 124 |
+
"step": 140
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.7202881152460985,
|
| 128 |
+
"grad_norm": 0.6297463589804964,
|
| 129 |
+
"learning_rate": 9.43127731353729e-06,
|
| 130 |
+
"loss": 0.1581,
|
| 131 |
+
"step": 150
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.7202881152460985,
|
| 135 |
+
"eval_loss": 0.15990422666072845,
|
| 136 |
+
"eval_runtime": 8.7401,
|
| 137 |
+
"eval_samples_per_second": 15.446,
|
| 138 |
+
"eval_steps_per_second": 1.945,
|
| 139 |
+
"step": 150
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.7683073229291717,
|
| 143 |
+
"grad_norm": 0.5203866298970263,
|
| 144 |
+
"learning_rate": 9.294703900549096e-06,
|
| 145 |
+
"loss": 0.1608,
|
| 146 |
+
"step": 160
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.8163265306122449,
|
| 150 |
+
"grad_norm": 0.5100770394064513,
|
| 151 |
+
"learning_rate": 9.14466587840408e-06,
|
| 152 |
+
"loss": 0.162,
|
| 153 |
+
"step": 170
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.8643457382953181,
|
| 157 |
+
"grad_norm": 0.5455220998770557,
|
| 158 |
+
"learning_rate": 8.981633641190779e-06,
|
| 159 |
+
"loss": 0.1566,
|
| 160 |
+
"step": 180
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.9123649459783914,
|
| 164 |
+
"grad_norm": 0.48213355422073995,
|
| 165 |
+
"learning_rate": 8.806118322017525e-06,
|
| 166 |
+
"loss": 0.1486,
|
| 167 |
+
"step": 190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.9603841536614646,
|
| 171 |
+
"grad_norm": 0.49326253901345773,
|
| 172 |
+
"learning_rate": 8.61867019052535e-06,
|
| 173 |
+
"loss": 0.1513,
|
| 174 |
+
"step": 200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.9603841536614646,
|
| 178 |
+
"eval_loss": 0.1510133445262909,
|
| 179 |
+
"eval_runtime": 8.7214,
|
| 180 |
+
"eval_samples_per_second": 15.479,
|
| 181 |
+
"eval_steps_per_second": 1.949,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.0048019207683074,
|
| 186 |
+
"grad_norm": 1.2575485399779591,
|
| 187 |
+
"learning_rate": 8.41987692770139e-06,
|
| 188 |
+
"loss": 0.1452,
|
| 189 |
+
"step": 210
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.0528211284513807,
|
| 193 |
+
"grad_norm": 0.49974946529817293,
|
| 194 |
+
"learning_rate": 8.210361783401491e-06,
|
| 195 |
+
"loss": 0.1086,
|
| 196 |
+
"step": 220
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.1008403361344539,
|
| 200 |
+
"grad_norm": 0.5909720459940095,
|
| 201 |
+
"learning_rate": 7.990781622358535e-06,
|
| 202 |
+
"loss": 0.1098,
|
| 203 |
+
"step": 230
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.148859543817527,
|
| 207 |
+
"grad_norm": 0.5289140362803703,
|
| 208 |
+
"learning_rate": 7.76182486480253e-06,
|
| 209 |
+
"loss": 0.1042,
|
| 210 |
+
"step": 240
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.1968787515006003,
|
| 214 |
+
"grad_norm": 0.5570818538274178,
|
| 215 |
+
"learning_rate": 7.524209328148995e-06,
|
| 216 |
+
"loss": 0.1104,
|
| 217 |
+
"step": 250
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.1968787515006003,
|
| 221 |
+
"eval_loss": 0.15508781373500824,
|
| 222 |
+
"eval_runtime": 8.7041,
|
| 223 |
+
"eval_samples_per_second": 15.51,
|
| 224 |
+
"eval_steps_per_second": 1.953,
|
| 225 |
+
"step": 250
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.2448979591836735,
|
| 229 |
+
"grad_norm": 0.5285122850283916,
|
| 230 |
+
"learning_rate": 7.278679976522279e-06,
|
| 231 |
+
"loss": 0.1024,
|
| 232 |
+
"step": 260
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.2929171668667467,
|
| 236 |
+
"grad_norm": 0.5198193011546469,
|
| 237 |
+
"learning_rate": 7.026006585169467e-06,
|
| 238 |
+
"loss": 0.1067,
|
| 239 |
+
"step": 270
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.34093637454982,
|
| 243 |
+
"grad_norm": 0.5433402449341223,
|
| 244 |
+
"learning_rate": 6.766981327087271e-06,
|
| 245 |
+
"loss": 0.1106,
|
| 246 |
+
"step": 280
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.3889555822328932,
|
| 250 |
+
"grad_norm": 0.591675736467511,
|
| 251 |
+
"learning_rate": 6.502416289428282e-06,
|
| 252 |
+
"loss": 0.1027,
|
| 253 |
+
"step": 290
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.4369747899159664,
|
| 257 |
+
"grad_norm": 0.49602130865146205,
|
| 258 |
+
"learning_rate": 6.233140927473033e-06,
|
| 259 |
+
"loss": 0.1068,
|
| 260 |
+
"step": 300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.4369747899159664,
|
| 264 |
+
"eval_loss": 0.14931099116802216,
|
| 265 |
+
"eval_runtime": 8.7136,
|
| 266 |
+
"eval_samples_per_second": 15.493,
|
| 267 |
+
"eval_steps_per_second": 1.951,
|
| 268 |
+
"step": 300
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.4849939975990396,
|
| 272 |
+
"grad_norm": 0.5205229035157025,
|
| 273 |
+
"learning_rate": 5.959999464150101e-06,
|
| 274 |
+
"loss": 0.1043,
|
| 275 |
+
"step": 310
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.5330132052821128,
|
| 279 |
+
"grad_norm": 0.5213512259437505,
|
| 280 |
+
"learning_rate": 5.683848243257181e-06,
|
| 281 |
+
"loss": 0.1058,
|
| 282 |
+
"step": 320
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.581032412965186,
|
| 286 |
+
"grad_norm": 0.5252416105681743,
|
| 287 |
+
"learning_rate": 5.40555304468122e-06,
|
| 288 |
+
"loss": 0.1035,
|
| 289 |
+
"step": 330
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6290516206482593,
|
| 293 |
+
"grad_norm": 0.479035517749776,
|
| 294 |
+
"learning_rate": 5.125986370034862e-06,
|
| 295 |
+
"loss": 0.1032,
|
| 296 |
+
"step": 340
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6770708283313325,
|
| 300 |
+
"grad_norm": 0.47617986914412186,
|
| 301 |
+
"learning_rate": 4.846024707219149e-06,
|
| 302 |
+
"loss": 0.1006,
|
| 303 |
+
"step": 350
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6770708283313325,
|
| 307 |
+
"eval_loss": 0.14417614042758942,
|
| 308 |
+
"eval_runtime": 8.7246,
|
| 309 |
+
"eval_samples_per_second": 15.473,
|
| 310 |
+
"eval_steps_per_second": 1.949,
|
| 311 |
+
"step": 350
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.725090036014406,
|
| 315 |
+
"grad_norm": 0.5665748104077248,
|
| 316 |
+
"learning_rate": 4.566545782488554e-06,
|
| 317 |
+
"loss": 0.1019,
|
| 318 |
+
"step": 360
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.773109243697479,
|
| 322 |
+
"grad_norm": 0.5167955766147265,
|
| 323 |
+
"learning_rate": 4.2884258086335755e-06,
|
| 324 |
+
"loss": 0.0976,
|
| 325 |
+
"step": 370
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.8211284513805523,
|
| 329 |
+
"grad_norm": 0.5042866007823615,
|
| 330 |
+
"learning_rate": 4.012536737908288e-06,
|
| 331 |
+
"loss": 0.1003,
|
| 332 |
+
"step": 380
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.8691476590636253,
|
| 336 |
+
"grad_norm": 0.5495519515030309,
|
| 337 |
+
"learning_rate": 3.7397435283153795e-06,
|
| 338 |
+
"loss": 0.0991,
|
| 339 |
+
"step": 390
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.9171668667466988,
|
| 343 |
+
"grad_norm": 0.4815628493479367,
|
| 344 |
+
"learning_rate": 3.4709014318193298e-06,
|
| 345 |
+
"loss": 0.1029,
|
| 346 |
+
"step": 400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.9171668667466988,
|
| 350 |
+
"eval_loss": 0.14110355079174042,
|
| 351 |
+
"eval_runtime": 8.7254,
|
| 352 |
+
"eval_samples_per_second": 15.472,
|
| 353 |
+
"eval_steps_per_second": 1.948,
|
| 354 |
+
"step": 400
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.9651860744297718,
|
| 358 |
+
"grad_norm": 0.5378667536535642,
|
| 359 |
+
"learning_rate": 3.2068533129896273e-06,
|
| 360 |
+
"loss": 0.1035,
|
| 361 |
+
"step": 410
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.009603841536615,
|
| 365 |
+
"grad_norm": 0.4775497724990149,
|
| 366 |
+
"learning_rate": 2.948427006480528e-06,
|
| 367 |
+
"loss": 0.0912,
|
| 368 |
+
"step": 420
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.057623049219688,
|
| 372 |
+
"grad_norm": 0.6087554919185391,
|
| 373 |
+
"learning_rate": 2.696432721632082e-06,
|
| 374 |
+
"loss": 0.059,
|
| 375 |
+
"step": 430
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.1056422569027613,
|
| 379 |
+
"grad_norm": 0.466286415886031,
|
| 380 |
+
"learning_rate": 2.4516605023294626e-06,
|
| 381 |
+
"loss": 0.0567,
|
| 382 |
+
"step": 440
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.1536614645858343,
|
| 386 |
+
"grad_norm": 0.5402767853471913,
|
| 387 |
+
"learning_rate": 2.2148777500843125e-06,
|
| 388 |
+
"loss": 0.0617,
|
| 389 |
+
"step": 450
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.1536614645858343,
|
| 393 |
+
"eval_loss": 0.1581123322248459,
|
| 394 |
+
"eval_runtime": 8.7373,
|
| 395 |
+
"eval_samples_per_second": 15.451,
|
| 396 |
+
"eval_steps_per_second": 1.946,
|
| 397 |
+
"step": 450
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.2016806722689077,
|
| 401 |
+
"grad_norm": 0.5420430891075357,
|
| 402 |
+
"learning_rate": 1.9868268181037186e-06,
|
| 403 |
+
"loss": 0.0584,
|
| 404 |
+
"step": 460
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.2496998799519807,
|
| 408 |
+
"grad_norm": 0.4884067898678699,
|
| 409 |
+
"learning_rate": 1.768222683889757e-06,
|
| 410 |
+
"loss": 0.058,
|
| 411 |
+
"step": 470
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.297719087635054,
|
| 415 |
+
"grad_norm": 0.49574699167442754,
|
| 416 |
+
"learning_rate": 1.5597507076664187e-06,
|
| 417 |
+
"loss": 0.0588,
|
| 418 |
+
"step": 480
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.345738295318127,
|
| 422 |
+
"grad_norm": 0.484031285869081,
|
| 423 |
+
"learning_rate": 1.362064483661617e-06,
|
| 424 |
+
"loss": 0.0555,
|
| 425 |
+
"step": 490
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.3937575030012006,
|
| 429 |
+
"grad_norm": 0.49868843579846434,
|
| 430 |
+
"learning_rate": 1.1757837909808628e-06,
|
| 431 |
+
"loss": 0.0584,
|
| 432 |
+
"step": 500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.3937575030012006,
|
| 436 |
+
"eval_loss": 0.1588136851787567,
|
| 437 |
+
"eval_runtime": 8.722,
|
| 438 |
+
"eval_samples_per_second": 15.478,
|
| 439 |
+
"eval_steps_per_second": 1.949,
|
| 440 |
+
"step": 500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.4417767106842736,
|
| 444 |
+
"grad_norm": 0.505195377790213,
|
| 445 |
+
"learning_rate": 1.0014926504969535e-06,
|
| 446 |
+
"loss": 0.0568,
|
| 447 |
+
"step": 510
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.489795918367347,
|
| 451 |
+
"grad_norm": 0.48055085037067635,
|
| 452 |
+
"learning_rate": 8.397374938476594e-07,
|
| 453 |
+
"loss": 0.057,
|
| 454 |
+
"step": 520
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.53781512605042,
|
| 458 |
+
"grad_norm": 0.48774374180423785,
|
| 459 |
+
"learning_rate": 6.910254502818914e-07,
|
| 460 |
+
"loss": 0.0562,
|
| 461 |
+
"step": 530
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.5858343337334935,
|
| 465 |
+
"grad_norm": 0.506896175562434,
|
| 466 |
+
"learning_rate": 5.558227567253832e-07,
|
| 467 |
+
"loss": 0.0571,
|
| 468 |
+
"step": 540
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.6338535414165665,
|
| 472 |
+
"grad_norm": 0.4794928604324473,
|
| 473 |
+
"learning_rate": 4.3455329605058436e-07,
|
| 474 |
+
"loss": 0.0585,
|
| 475 |
+
"step": 550
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.6338535414165665,
|
| 479 |
+
"eval_loss": 0.1571720838546753,
|
| 480 |
+
"eval_runtime": 8.7061,
|
| 481 |
+
"eval_samples_per_second": 15.506,
|
| 482 |
+
"eval_steps_per_second": 1.953,
|
| 483 |
+
"step": 550
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.68187274909964,
|
| 487 |
+
"grad_norm": 0.4447078585594017,
|
| 488 |
+
"learning_rate": 3.275972681335421e-07,
|
| 489 |
+
"loss": 0.0557,
|
| 490 |
+
"step": 560
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.729891956782713,
|
| 494 |
+
"grad_norm": 0.5074668455489234,
|
| 495 |
+
"learning_rate": 2.3528999786421758e-07,
|
| 496 |
+
"loss": 0.0551,
|
| 497 |
+
"step": 570
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.7779111644657863,
|
| 501 |
+
"grad_norm": 0.4931479047936826,
|
| 502 |
+
"learning_rate": 1.5792088384733174e-07,
|
| 503 |
+
"loss": 0.0578,
|
| 504 |
+
"step": 580
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.82593037214886,
|
| 508 |
+
"grad_norm": 0.4945483234224741,
|
| 509 |
+
"learning_rate": 9.573249108973281e-08,
|
| 510 |
+
"loss": 0.0571,
|
| 511 |
+
"step": 590
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.8739495798319328,
|
| 515 |
+
"grad_norm": 0.49071499326291995,
|
| 516 |
+
"learning_rate": 4.891979051886153e-08,
|
| 517 |
+
"loss": 0.0552,
|
| 518 |
+
"step": 600
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.8739495798319328,
|
| 522 |
+
"eval_loss": 0.15641489624977112,
|
| 523 |
+
"eval_runtime": 8.7188,
|
| 524 |
+
"eval_samples_per_second": 15.484,
|
| 525 |
+
"eval_steps_per_second": 1.95,
|
| 526 |
+
"step": 600
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.9219687875150058,
|
| 530 |
+
"grad_norm": 0.4898132970657211,
|
| 531 |
+
"learning_rate": 1.762954771655001e-08,
|
| 532 |
+
"loss": 0.058,
|
| 533 |
+
"step": 610
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.969987995198079,
|
| 537 |
+
"grad_norm": 0.44485985772895487,
|
| 538 |
+
"learning_rate": 1.959862784577937e-09,
|
| 539 |
+
"loss": 0.0548,
|
| 540 |
+
"step": 620
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.9891956782713085,
|
| 544 |
+
"step": 624,
|
| 545 |
+
"total_flos": 170865984536576.0,
|
| 546 |
+
"train_loss": 0.1184023514103431,
|
| 547 |
+
"train_runtime": 9824.5273,
|
| 548 |
+
"train_samples_per_second": 4.068,
|
| 549 |
+
"train_steps_per_second": 0.064
|
| 550 |
+
}
|
| 551 |
+
],
|
| 552 |
+
"logging_steps": 10,
|
| 553 |
+
"max_steps": 624,
|
| 554 |
+
"num_input_tokens_seen": 0,
|
| 555 |
+
"num_train_epochs": 3,
|
| 556 |
+
"save_steps": 200,
|
| 557 |
+
"stateful_callbacks": {
|
| 558 |
+
"TrainerControl": {
|
| 559 |
+
"args": {
|
| 560 |
+
"should_epoch_stop": false,
|
| 561 |
+
"should_evaluate": false,
|
| 562 |
+
"should_log": false,
|
| 563 |
+
"should_save": true,
|
| 564 |
+
"should_training_stop": true
|
| 565 |
+
},
|
| 566 |
+
"attributes": {}
|
| 567 |
+
}
|
| 568 |
+
},
|
| 569 |
+
"total_flos": 170865984536576.0,
|
| 570 |
+
"train_batch_size": 2,
|
| 571 |
+
"trial_name": null,
|
| 572 |
+
"trial_params": null
|
| 573 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50a815ff58781d61b959ea17727b10ac4468438720e9aa6ed2816dcedcc5f19f
|
| 3 |
+
size 7672
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|