bloomz-560m_adalora_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: 3.2939
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 |
|---|---|---|---|
| 5.0192 | 1.0 | 157 | 4.6374 |
| 4.7212 | 2.0 | 314 | 4.3532 |
| 4.4794 | 3.0 | 471 | 3.7274 |
| 3.6826 | 4.0 | 628 | 3.4142 |
| 3.5713 | 5.0 | 785 | 3.3583 |
| 3.4892 | 6.0 | 942 | 3.3334 |
| 3.4485 | 7.0 | 1099 | 3.3175 |
| 3.3712 | 8.0 | 1256 | 3.3086 |
| 3.4196 | 9.0 | 1413 | 3.3030 |
| 3.3404 | 10.0 | 1570 | 3.2977 |
| 3.2865 | 11.0 | 1727 | 3.2944 |
| 3.2568 | 12.0 | 1884 | 3.2936 |
| 3.2502 | 13.0 | 2041 | 3.2924 |
| 3.2052 | 14.0 | 2198 | 3.2918 |
| 3.2404 | 15.0 | 2355 | 3.2934 |
| 3.1706 | 16.0 | 2512 | 3.2934 |
| 3.2111 | 17.0 | 2669 | 3.2934 |
| 3.2227 | 18.0 | 2826 | 3.2937 |
| 3.2601 | 19.0 | 2983 | 3.2941 |
| 3.1703 | 20.0 | 3140 | 3.2939 |
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_adalora_lr5e-05_bs4_epoch20_wd0.01
Base model
bigscience/bloomz-560m