opt-iml-max-1.3b-lora-s-t3000-v300-v2
This model is a fine-tuned version of facebook/opt-iml-max-1.3b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0578
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3525 | 0.43 | 20 | 2.1918 |
| 2.1991 | 0.85 | 40 | 2.0734 |
| 2.1575 | 1.28 | 60 | 2.0636 |
| 2.1974 | 1.71 | 80 | 2.0578 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2