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: 0.5060
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.641 | 0.01 | 1 | 0.6417 |
| 0.5093 | 0.25 | 42 | 0.5260 |
| 0.4665 | 0.5 | 84 | 0.5118 |
| 0.4431 | 0.75 | 126 | 0.5043 |
| 0.4523 | 1.0 | 168 | 0.4985 |
| 0.4237 | 1.23 | 210 | 0.4985 |
| 0.4002 | 1.48 | 252 | 0.4976 |
| 0.3656 | 1.73 | 294 | 0.4955 |
| 0.3744 | 1.98 | 336 | 0.4942 |
| 0.3278 | 2.21 | 378 | 0.5012 |
| 0.344 | 2.46 | 420 | 0.5003 |
| 0.3216 | 2.71 | 462 | 0.4984 |
| 0.3371 | 2.96 | 504 | 0.4980 |
| 0.3243 | 3.19 | 546 | 0.5051 |
| 0.3184 | 3.44 | 588 | 0.5052 |
| 0.313 | 3.69 | 630 | 0.5060 |
| 0.3097 | 3.94 | 672 | 0.5060 |
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
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support