metadata
license: llama3
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
- name: Genpro_Llama3-8b
results: []
Genpro_Llama3-8b
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6683
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3225 | 0.0634 | 100 | 1.3185 |
| 1.1249 | 0.1267 | 200 | 1.1062 |
| 1.0249 | 0.1901 | 300 | 1.0177 |
| 1.025 | 0.2535 | 400 | 0.9535 |
| 0.9842 | 0.3169 | 500 | 0.9055 |
| 0.9721 | 0.3802 | 600 | 0.8475 |
| 0.9047 | 0.4436 | 700 | 0.8295 |
| 0.8861 | 0.5070 | 800 | 0.7987 |
| 0.7792 | 0.5703 | 900 | 0.7721 |
| 0.8329 | 0.6337 | 1000 | 0.7541 |
| 0.7882 | 0.6971 | 1100 | 0.7305 |
| 0.8286 | 0.7605 | 1200 | 0.7095 |
| 0.7418 | 0.8238 | 1300 | 0.6927 |
| 0.7594 | 0.8872 | 1400 | 0.6725 |
| 0.7717 | 0.9506 | 1500 | 0.6683 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1