|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_pct_ortho |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Qwen2-7B_pct_ortho |
|
|
|
This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0729 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.0844 | 0.0206 | 8 | 1.9994 | |
|
| 2.0447 | 0.0412 | 16 | 1.9901 | |
|
| 2.0874 | 0.0618 | 24 | 2.0098 | |
|
| 2.0412 | 0.0824 | 32 | 2.0256 | |
|
| 2.0961 | 0.1031 | 40 | 2.0402 | |
|
| 2.1029 | 0.1237 | 48 | 2.0545 | |
|
| 2.1077 | 0.1443 | 56 | 2.0568 | |
|
| 2.0953 | 0.1649 | 64 | 2.0666 | |
|
| 2.1231 | 0.1855 | 72 | 2.0795 | |
|
| 2.187 | 0.2061 | 80 | 2.0806 | |
|
| 2.1587 | 0.2267 | 88 | 2.0897 | |
|
| 2.1437 | 0.2473 | 96 | 2.0826 | |
|
| 2.1689 | 0.2680 | 104 | 2.0951 | |
|
| 2.0886 | 0.2886 | 112 | 2.1059 | |
|
| 2.1436 | 0.3092 | 120 | 2.1058 | |
|
| 2.1525 | 0.3298 | 128 | 2.1013 | |
|
| 2.1577 | 0.3504 | 136 | 2.1073 | |
|
| 2.1438 | 0.3710 | 144 | 2.1086 | |
|
| 2.1596 | 0.3916 | 152 | 2.1189 | |
|
| 2.1911 | 0.4122 | 160 | 2.1118 | |
|
| 2.225 | 0.4329 | 168 | 2.1125 | |
|
| 2.1364 | 0.4535 | 176 | 2.1086 | |
|
| 2.1469 | 0.4741 | 184 | 2.1079 | |
|
| 2.19 | 0.4947 | 192 | 2.1081 | |
|
| 2.1236 | 0.5153 | 200 | 2.1063 | |
|
| 2.1678 | 0.5359 | 208 | 2.1112 | |
|
| 2.2087 | 0.5565 | 216 | 2.1102 | |
|
| 2.1172 | 0.5771 | 224 | 2.0990 | |
|
| 2.1274 | 0.5977 | 232 | 2.1043 | |
|
| 2.1229 | 0.6184 | 240 | 2.0957 | |
|
| 2.1097 | 0.6390 | 248 | 2.0978 | |
|
| 2.1596 | 0.6596 | 256 | 2.0958 | |
|
| 2.1294 | 0.6802 | 264 | 2.0876 | |
|
| 2.1938 | 0.7008 | 272 | 2.0930 | |
|
| 2.0728 | 0.7214 | 280 | 2.0849 | |
|
| 2.1827 | 0.7420 | 288 | 2.0802 | |
|
| 2.1082 | 0.7626 | 296 | 2.0804 | |
|
| 2.1212 | 0.7833 | 304 | 2.0782 | |
|
| 2.1074 | 0.8039 | 312 | 2.0761 | |
|
| 2.1474 | 0.8245 | 320 | 2.0791 | |
|
| 2.1557 | 0.8451 | 328 | 2.0802 | |
|
| 2.1122 | 0.8657 | 336 | 2.0803 | |
|
| 2.1462 | 0.8863 | 344 | 2.0764 | |
|
| 2.119 | 0.9069 | 352 | 2.0713 | |
|
| 2.1888 | 0.9275 | 360 | 2.0730 | |
|
| 2.1138 | 0.9481 | 368 | 2.0733 | |
|
| 2.1631 | 0.9688 | 376 | 2.0732 | |
|
| 2.1142 | 0.9894 | 384 | 2.0729 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
