llama-3-86-lora-pretrain
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the sm_artile dataset.
It achieves the following results on the evaluation set:
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
| 2.2949 |
0.6369 |
500 |
2.3349 |
| 2.2907 |
1.2739 |
1000 |
2.2571 |
| 2.0957 |
1.9108 |
1500 |
2.2253 |
| 2.2352 |
2.5478 |
2000 |
2.2145 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
