sft-chatbot2
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8890
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 17 | 0.8223 |
| No log | 2.0 | 34 | 0.7790 |
| No log | 3.0 | 51 | 0.7755 |
| No log | 4.0 | 68 | 0.7868 |
| No log | 5.0 | 85 | 0.8287 |
| No log | 6.0 | 102 | 0.8845 |
| No log | 7.0 | 119 | 0.8892 |
| No log | 8.0 | 136 | 0.8890 |
Framework versions
- PEFT 0.13.1
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for JasonBounre/sft-chatbot2
Base model
meta-llama/Meta-Llama-3-8B