metadata
license: llama3
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
metrics:
- accuracy
model-index:
- name: fine_w
results: []
fine_w
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: 3.3694
- Accuracy: 0.345
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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6991 | 1.0 | 800 | 1.8686 | 0.284 |
| 1.8425 | 2.0 | 1600 | 1.9077 | 0.322 |
| 1.5979 | 3.0 | 2400 | 1.9907 | 0.361 |
| 0.9781 | 4.0 | 3200 | 2.4959 | 0.351 |
| 0.4766 | 5.0 | 4000 | 3.3694 | 0.345 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1