bloomz-560m_PrefixTuning_lr5e-05_bs4_epoch20_wd0.01
This model is a fine-tuned version of bigscience/bloomz-560m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.2261
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 |
|---|---|---|---|
| 9.1516 | 1.0 | 157 | 9.3203 |
| 8.4578 | 2.0 | 314 | 8.7313 |
| 8.0583 | 3.0 | 471 | 8.0509 |
| 7.3164 | 4.0 | 628 | 7.5281 |
| 6.8518 | 5.0 | 785 | 7.1995 |
| 6.5703 | 6.0 | 942 | 6.9608 |
| 6.2196 | 7.0 | 1099 | 6.5931 |
| 5.6929 | 8.0 | 1256 | 6.3728 |
| 5.4456 | 9.0 | 1413 | 5.9738 |
| 5.2858 | 10.0 | 1570 | 5.8020 |
| 5.1488 | 11.0 | 1727 | 5.7370 |
| 5.0381 | 12.0 | 1884 | 5.6419 |
| 5.0491 | 13.0 | 2041 | 5.4965 |
| 4.929 | 14.0 | 2198 | 5.4047 |
| 4.94 | 15.0 | 2355 | 5.3458 |
| 4.8588 | 16.0 | 2512 | 5.3153 |
| 4.908 | 17.0 | 2669 | 5.2950 |
| 4.9253 | 18.0 | 2826 | 5.2741 |
| 4.9618 | 19.0 | 2983 | 5.2320 |
| 4.7994 | 20.0 | 3140 | 5.2261 |
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
- 0
Model tree for jysssacc/bloomz-560m_PrefixTuning_lr5e-05_bs4_epoch20_wd0.01
Base model
bigscience/bloomz-560m