opt-350m_IA3_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: 3.6239
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 |
|---|---|---|---|
| 4.0388 | 1.0 | 157 | 3.8362 |
| 4.0368 | 2.0 | 314 | 3.8185 |
| 3.9798 | 3.0 | 471 | 3.7923 |
| 3.9598 | 4.0 | 628 | 3.7634 |
| 3.941 | 5.0 | 785 | 3.7394 |
| 3.917 | 6.0 | 942 | 3.7193 |
| 3.8952 | 7.0 | 1099 | 3.7022 |
| 3.8515 | 8.0 | 1256 | 3.6878 |
| 3.8998 | 9.0 | 1413 | 3.6758 |
| 3.8849 | 10.0 | 1570 | 3.6655 |
| 3.829 | 11.0 | 1727 | 3.6568 |
| 3.8017 | 12.0 | 1884 | 3.6492 |
| 3.7914 | 13.0 | 2041 | 3.6428 |
| 3.808 | 14.0 | 2198 | 3.6374 |
| 3.7894 | 15.0 | 2355 | 3.6332 |
| 3.7412 | 16.0 | 2512 | 3.6298 |
| 3.7674 | 17.0 | 2669 | 3.6271 |
| 3.7697 | 18.0 | 2826 | 3.6253 |
| 3.8222 | 19.0 | 2983 | 3.6243 |
| 3.7506 | 20.0 | 3140 | 3.6239 |
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
- 1
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for jysssacc/opt-350m_IA3_lr5e-05_bs4_epoch20_wd0.01
Base model
facebook/opt-350m