|
|
--- |
|
|
base_model: meta-llama/Llama-3.2-3B-Instruct |
|
|
library_name: peft |
|
|
license: llama3.2 |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: model |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# model |
|
|
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.9184 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 100 |
|
|
- training_steps: 3000 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 3.1421 | 0.5330 | 500 | 2.8658 | |
|
|
| 2.8251 | 1.0661 | 1000 | 2.8294 | |
|
|
| 2.6508 | 1.5991 | 1500 | 2.8203 | |
|
|
| 2.5872 | 2.1322 | 2000 | 2.8783 | |
|
|
| 2.4264 | 2.6652 | 2500 | 2.8816 | |
|
|
| 2.3586 | 3.1983 | 3000 | 2.9184 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.13.1 |
|
|
- Transformers 4.44.2 |
|
|
- Pytorch 2.4.1+cu118 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.19.1 |
