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: 1.5741
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 |
|---|---|---|---|
| 2.3216 | 0.0 | 1 | 2.2561 |
| 1.7379 | 0.25 | 92 | 1.7855 |
| 1.6935 | 0.5 | 184 | 1.7075 |
| 1.7016 | 0.75 | 276 | 1.6663 |
| 1.5761 | 1.0 | 368 | 1.6371 |
| 1.4785 | 1.23 | 460 | 1.6220 |
| 1.4492 | 1.49 | 552 | 1.6023 |
| 1.6224 | 1.74 | 644 | 1.5887 |
| 1.5154 | 1.99 | 736 | 1.5789 |
| 1.4758 | 2.22 | 828 | 1.5787 |
| 1.4005 | 2.47 | 920 | 1.5758 |
| 1.458 | 2.72 | 1012 | 1.5741 |
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
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support