metadata
base_model: meta-llama/Meta-Llama-3-8B-Instruct
library_name: peft
license: llama3
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: results_1
results: []
results_1
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5411
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: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7711 | 1.1844 | 53 | 0.6969 |
| 0.614 | 2.3687 | 106 | 0.6113 |
| 0.5994 | 3.5531 | 159 | 0.5945 |
| 0.5602 | 4.7374 | 212 | 0.5745 |
| 0.5807 | 5.9218 | 265 | 0.5630 |
| 0.5484 | 7.1061 | 318 | 0.5532 |
| 0.543 | 8.2905 | 371 | 0.5472 |
| 0.4977 | 9.4749 | 424 | 0.5436 |
| 0.5072 | 10.6592 | 477 | 0.5411 |
Framework versions
- PEFT 0.10.0
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1