metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- generator
model-index:
- name: Llama-3-8B-sft-lora-food-nutrition-10-epoch
results: []
Llama-3-8B-sft-lora-food-nutrition-10-epoch
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.3265
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3207 | 1.0 | 2207 | 0.3432 |
| 0.3222 | 2.0 | 4414 | 0.3339 |
| 0.3442 | 3.0 | 6621 | 0.3298 |
| 0.3389 | 4.0 | 8828 | 0.3282 |
| 0.3293 | 5.0 | 11035 | 0.3271 |
| 0.3376 | 6.0 | 13242 | 0.3267 |
| 0.3543 | 7.0 | 15449 | 0.3266 |
| 0.3077 | 8.0 | 17656 | 0.3265 |
| 0.2973 | 9.0 | 19863 | 0.3266 |
| 0.3028 | 10.0 | 22070 | 0.3265 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1