opt-350m_adalora_lr5e-05_bs4_epoch20_wd0.01
This model is a fine-tuned version of facebook/opt-350m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4792
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.0628 | 1.0 | 157 | 4.7979 |
| 4.8511 | 2.0 | 314 | 4.5284 |
| 4.5758 | 3.0 | 471 | 3.9450 |
| 3.8268 | 4.0 | 628 | 3.6092 |
| 3.6672 | 5.0 | 785 | 3.5374 |
| 3.5446 | 6.0 | 942 | 3.5019 |
| 3.5009 | 7.0 | 1099 | 3.4825 |
| 3.4183 | 8.0 | 1256 | 3.4741 |
| 3.4299 | 9.0 | 1413 | 3.4689 |
| 3.3831 | 10.0 | 1570 | 3.4699 |
| 3.3121 | 11.0 | 1727 | 3.4698 |
| 3.2631 | 12.0 | 1884 | 3.4691 |
| 3.2326 | 13.0 | 2041 | 3.4717 |
| 3.2115 | 14.0 | 2198 | 3.4719 |
| 3.2042 | 15.0 | 2355 | 3.4753 |
| 3.1537 | 16.0 | 2512 | 3.4738 |
| 3.1587 | 17.0 | 2669 | 3.4764 |
| 3.1446 | 18.0 | 2826 | 3.4777 |
| 3.209 | 19.0 | 2983 | 3.4790 |
| 3.1281 | 20.0 | 3140 | 3.4792 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 4
Model tree for jysssacc/opt-350m_adalora_lr5e-05_bs4_epoch20_wd0.01
Base model
facebook/opt-350m