lora-out-math
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: 1.0946
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 |
|---|---|---|---|
| 1.1956 | 0.0 | 1 | 1.1464 |
| 1.1544 | 0.25 | 180 | 1.0905 |
| 1.1932 | 0.5 | 360 | 1.0890 |
| 1.1827 | 0.75 | 540 | 1.0873 |
| 1.0816 | 1.0 | 720 | 1.0861 |
| 1.0741 | 1.24 | 900 | 1.0887 |
| 1.0849 | 1.49 | 1080 | 1.0885 |
| 1.0629 | 1.74 | 1260 | 1.0878 |
| 1.0165 | 1.99 | 1440 | 1.0866 |
| 1.1012 | 2.22 | 1620 | 1.0938 |
| 1.0574 | 2.47 | 1800 | 1.0943 |
| 1.033 | 2.72 | 1980 | 1.0946 |
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