sft-chatbot
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: 0.8663
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: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9836 | 30 | 0.7847 |
| No log | 2.0 | 61 | 0.7587 |
| No log | 2.9836 | 91 | 0.7729 |
| No log | 4.0 | 122 | 0.8109 |
| No log | 4.9836 | 152 | 0.8601 |
| No log | 5.9016 | 180 | 0.8663 |
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
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for JasonBounre/sft-chatbot
Base model
meta-llama/Meta-Llama-3-8B