opt-350m_PrefixTuning_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: 7.3679
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 |
|---|---|---|---|
| 9.7195 | 1.0 | 157 | 9.7698 |
| 9.4441 | 2.0 | 314 | 9.3700 |
| 9.1944 | 3.0 | 471 | 8.7393 |
| 8.663 | 4.0 | 628 | 8.3164 |
| 8.4504 | 5.0 | 785 | 8.0815 |
| 8.201 | 6.0 | 942 | 7.9094 |
| 8.0965 | 7.0 | 1099 | 7.7845 |
| 7.9382 | 8.0 | 1256 | 7.6983 |
| 7.7828 | 9.0 | 1413 | 7.6242 |
| 7.7907 | 10.0 | 1570 | 7.5654 |
| 7.7221 | 11.0 | 1727 | 7.5225 |
| 7.5905 | 12.0 | 1884 | 7.4850 |
| 7.5802 | 13.0 | 2041 | 7.4554 |
| 7.5914 | 14.0 | 2198 | 7.4319 |
| 7.5632 | 15.0 | 2355 | 7.4102 |
| 7.4937 | 16.0 | 2512 | 7.3961 |
| 7.4921 | 17.0 | 2669 | 7.3838 |
| 7.457 | 18.0 | 2826 | 7.3748 |
| 7.5307 | 19.0 | 2983 | 7.3697 |
| 7.4599 | 20.0 | 3140 | 7.3679 |
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
- 2
Model tree for jysssacc/opt-350m_PrefixTuning_lr5e-05_bs4_epoch20_wd0.01
Base model
facebook/opt-350m