experiments-llama
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the pubmed-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.7158
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: 0.0001
- 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
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.799 | 0.4 | 36 | 1.7739 |
| 1.6351 | 0.8 | 72 | 1.7412 |
| 1.6894 | 1.2 | 108 | 1.7203 |
| 1.7854 | 1.6 | 144 | 1.7165 |
| 1.8052 | 2.0 | 180 | 1.7158 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
Model tree for aj30/experiments-llama
Base model
meta-llama/Llama-2-7b-hf