lora-out
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7317
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.795 | 0.0 | 1 | 1.8088 |
| 1.7519 | 0.25 | 137 | 1.7284 |
| 1.7442 | 0.5 | 274 | 1.7260 |
| 1.7182 | 0.75 | 411 | 1.7249 |
| 1.743 | 1.0 | 548 | 1.7237 |
| 1.7075 | 1.24 | 685 | 1.7265 |
| 1.7264 | 1.49 | 822 | 1.7267 |
| 1.6604 | 1.74 | 959 | 1.7260 |
| 1.6562 | 1.99 | 1096 | 1.7255 |
| 1.6455 | 2.22 | 1233 | 1.7308 |
| 1.6258 | 2.47 | 1370 | 1.7315 |
| 1.6792 | 2.72 | 1507 | 1.7317 |
| 1.6364 | 2.97 | 1644 | 1.7317 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support