sft
This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the identity and the eightwords-20241112-alapaca datasets. It achieves the following results on the evaluation set:
- Loss: 1.6951
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 32.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7669 | 14.0474 | 2000 | 1.4163 |
| 0.4249 | 28.0948 | 4000 | 1.6929 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1