|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_pct_default |
|
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_default |
|
|
|
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: 2.0259 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.1169 | 0.0206 | 8 | 2.0201 | |
|
| 2.1264 | 0.0412 | 16 | 2.0886 | |
|
| 2.1468 | 0.0618 | 24 | 2.0745 | |
|
| 2.0954 | 0.0824 | 32 | 2.0725 | |
|
| 2.136 | 0.1031 | 40 | 2.0759 | |
|
| 2.1289 | 0.1237 | 48 | 2.1111 | |
|
| 2.131 | 0.1443 | 56 | 2.0744 | |
|
| 2.1168 | 0.1649 | 64 | 2.0766 | |
|
| 2.149 | 0.1855 | 72 | 2.1028 | |
|
| 2.1947 | 0.2061 | 80 | 2.0999 | |
|
| 2.1727 | 0.2267 | 88 | 2.0999 | |
|
| 2.1438 | 0.2473 | 96 | 2.0979 | |
|
| 2.1639 | 0.2680 | 104 | 2.0984 | |
|
| 2.0768 | 0.2886 | 112 | 2.0967 | |
|
| 2.1262 | 0.3092 | 120 | 2.0943 | |
|
| 2.1261 | 0.3298 | 128 | 2.0995 | |
|
| 2.1411 | 0.3504 | 136 | 2.1028 | |
|
| 2.1369 | 0.3710 | 144 | 2.1030 | |
|
| 2.1419 | 0.3916 | 152 | 2.0989 | |
|
| 2.165 | 0.4122 | 160 | 2.0972 | |
|
| 2.1948 | 0.4329 | 168 | 2.0925 | |
|
| 2.1076 | 0.4535 | 176 | 2.0968 | |
|
| 2.1183 | 0.4741 | 184 | 2.0916 | |
|
| 2.16 | 0.4947 | 192 | 2.0885 | |
|
| 2.0938 | 0.5153 | 200 | 2.0884 | |
|
| 2.1387 | 0.5359 | 208 | 2.0866 | |
|
| 2.1735 | 0.5565 | 216 | 2.0854 | |
|
| 2.0786 | 0.5771 | 224 | 2.0755 | |
|
| 2.0929 | 0.5977 | 232 | 2.0793 | |
|
| 2.0871 | 0.6184 | 240 | 2.0635 | |
|
| 2.0744 | 0.6390 | 248 | 2.0637 | |
|
| 2.1142 | 0.6596 | 256 | 2.0616 | |
|
| 2.0861 | 0.6802 | 264 | 2.0570 | |
|
| 2.1428 | 0.7008 | 272 | 2.0534 | |
|
| 2.0474 | 0.7214 | 280 | 2.0486 | |
|
| 2.1296 | 0.7420 | 288 | 2.0439 | |
|
| 2.062 | 0.7626 | 296 | 2.0425 | |
|
| 2.0758 | 0.7833 | 304 | 2.0405 | |
|
| 2.0604 | 0.8039 | 312 | 2.0370 | |
|
| 2.0963 | 0.8245 | 320 | 2.0361 | |
|
| 2.0926 | 0.8451 | 328 | 2.0342 | |
|
| 2.0571 | 0.8657 | 336 | 2.0307 | |
|
| 2.0858 | 0.8863 | 344 | 2.0297 | |
|
| 2.066 | 0.9069 | 352 | 2.0270 | |
|
| 2.1284 | 0.9275 | 360 | 2.0260 | |
|
| 2.0618 | 0.9481 | 368 | 2.0257 | |
|
| 2.1074 | 0.9688 | 376 | 2.0256 | |
|
| 2.0625 | 0.9894 | 384 | 2.0259 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
