finetuned_llama3.1_modelv1
This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5369
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 140 | 0.7694 |
| No log | 2.0 | 280 | 0.7267 |
| No log | 3.0 | 420 | 0.6674 |
| 0.8529 | 4.0 | 560 | 0.5697 |
| 0.8529 | 5.0 | 700 | 0.5502 |
| 0.8529 | 6.0 | 840 | 0.5446 |
| 0.8529 | 7.0 | 980 | 0.5411 |
| 0.5332 | 8.0 | 1120 | 0.5392 |
| 0.5332 | 9.0 | 1260 | 0.5357 |
| 0.5332 | 10.0 | 1400 | 0.5369 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for smshr/finetuned_llama3.1_modelv1
Base model
meta-llama/Llama-3.1-8B