|
--- |
|
base_model: meta-llama/Meta-Llama-3.1-8B |
|
library_name: peft |
|
license: llama3.1 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: LlaMa_3.1_8B |
|
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. --> |
|
|
|
# LlaMa_3.1_8B |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6314 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.0074 | 0.0440 | 100 | 0.8141 | |
|
| 0.7582 | 0.0879 | 200 | 0.7417 | |
|
| 0.7663 | 0.1319 | 300 | 0.7115 | |
|
| 0.6939 | 0.1758 | 400 | 0.6899 | |
|
| 0.6787 | 0.2198 | 500 | 0.6792 | |
|
| 0.6553 | 0.2637 | 600 | 0.6664 | |
|
| 0.6747 | 0.3077 | 700 | 0.6535 | |
|
| 0.6614 | 0.3516 | 800 | 0.6404 | |
|
| 0.6343 | 0.3956 | 900 | 0.6343 | |
|
| 0.6264 | 0.4396 | 1000 | 0.6314 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
