|
--- |
|
base_model: unsloth/qwen2-7b-bnb-4bit |
|
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-bnb-4bit](https://huggingface.co/unsloth/qwen2-7b-bnb-4bit) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1027 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.1596 | 0.0206 | 8 | 2.0832 | |
|
| 2.095 | 0.0412 | 16 | 2.0465 | |
|
| 2.1302 | 0.0618 | 24 | 2.0538 | |
|
| 2.0886 | 0.0824 | 32 | 2.0696 | |
|
| 2.1386 | 0.1031 | 40 | 2.0840 | |
|
| 2.141 | 0.1237 | 48 | 2.0979 | |
|
| 2.1451 | 0.1443 | 56 | 2.0972 | |
|
| 2.1323 | 0.1649 | 64 | 2.1059 | |
|
| 2.152 | 0.1855 | 72 | 2.1132 | |
|
| 2.2215 | 0.2061 | 80 | 2.1120 | |
|
| 2.187 | 0.2267 | 88 | 2.1149 | |
|
| 2.1712 | 0.2473 | 96 | 2.1171 | |
|
| 2.2009 | 0.2680 | 104 | 2.1281 | |
|
| 2.1177 | 0.2886 | 112 | 2.1351 | |
|
| 2.1735 | 0.3092 | 120 | 2.1326 | |
|
| 2.1785 | 0.3298 | 128 | 2.1293 | |
|
| 2.1826 | 0.3504 | 136 | 2.1398 | |
|
| 2.1799 | 0.3710 | 144 | 2.1419 | |
|
| 2.1817 | 0.3916 | 152 | 2.1564 | |
|
| 2.2199 | 0.4122 | 160 | 2.1452 | |
|
| 2.2533 | 0.4329 | 168 | 2.1420 | |
|
| 2.1606 | 0.4535 | 176 | 2.1434 | |
|
| 2.1773 | 0.4741 | 184 | 2.1394 | |
|
| 2.2177 | 0.4947 | 192 | 2.1369 | |
|
| 2.1614 | 0.5153 | 200 | 2.1360 | |
|
| 2.2003 | 0.5359 | 208 | 2.1389 | |
|
| 2.2389 | 0.5565 | 216 | 2.1424 | |
|
| 2.1515 | 0.5771 | 224 | 2.1329 | |
|
| 2.16 | 0.5977 | 232 | 2.1388 | |
|
| 2.1584 | 0.6184 | 240 | 2.1229 | |
|
| 2.1446 | 0.6390 | 248 | 2.1275 | |
|
| 2.19 | 0.6596 | 256 | 2.1256 | |
|
| 2.1612 | 0.6802 | 264 | 2.1182 | |
|
| 2.2218 | 0.7008 | 272 | 2.1202 | |
|
| 2.1112 | 0.7214 | 280 | 2.1163 | |
|
| 2.2125 | 0.7420 | 288 | 2.1118 | |
|
| 2.1432 | 0.7626 | 296 | 2.1115 | |
|
| 2.1537 | 0.7833 | 304 | 2.1066 | |
|
| 2.1391 | 0.8039 | 312 | 2.1069 | |
|
| 2.1831 | 0.8245 | 320 | 2.1115 | |
|
| 2.1835 | 0.8451 | 328 | 2.1099 | |
|
| 2.1461 | 0.8657 | 336 | 2.1126 | |
|
| 2.183 | 0.8863 | 344 | 2.1060 | |
|
| 2.1507 | 0.9069 | 352 | 2.1017 | |
|
| 2.216 | 0.9275 | 360 | 2.1033 | |
|
| 2.1464 | 0.9481 | 368 | 2.1032 | |
|
| 2.1925 | 0.9688 | 376 | 2.1028 | |
|
| 2.1514 | 0.9894 | 384 | 2.1027 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
