results
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0163
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: 3e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.2
- lr_scheduler_warmup_steps: 10
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.3627 | 0.9412 | 12 | 2.2633 |
2.2361 | 1.9608 | 25 | 2.1775 |
2.182 | 2.9804 | 38 | 2.1138 |
2.0893 | 4.0 | 51 | 2.0490 |
2.0489 | 4.9412 | 63 | 2.0275 |
2.0322 | 5.9608 | 76 | 2.0167 |
2.0752 | 6.9804 | 89 | 2.0126 |
2.0351 | 8.0 | 102 | 2.0130 |
2.0301 | 8.9412 | 114 | 2.0163 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.3
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2