opt-1.3b_adalora_627_lr5e-05_bs4_epoch5_wd0.01
This model is a fine-tuned version of facebook/opt-1.3b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0160
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: 4
- 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.5943 | 1.0 | 157 | 4.2292 |
4.1943 | 2.0 | 314 | 3.8077 |
3.8866 | 3.0 | 471 | 3.2970 |
3.2933 | 4.0 | 628 | 3.0521 |
3.1627 | 5.0 | 785 | 3.0160 |
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-1.3b_adalora_627_lr5e-05_bs4_epoch5_wd0.01
Base model
facebook/opt-1.3b
Adapter
this model