|
--- |
|
license: llama3.1 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
model-index: |
|
- name: llama3.1_8b_bwgenerator |
|
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. --> |
|
|
|
# llama3.1_8b_bwgenerator |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1856 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.8017 | 0.2585 | 10 | 0.8807 | |
|
| 0.5653 | 0.5170 | 20 | 0.3488 | |
|
| 0.3026 | 0.7754 | 30 | 0.2705 | |
|
| 0.255 | 1.0339 | 40 | 0.2418 | |
|
| 0.2307 | 1.2924 | 50 | 0.2223 | |
|
| 0.2157 | 1.5509 | 60 | 0.2099 | |
|
| 0.206 | 1.8094 | 70 | 0.2021 | |
|
| 0.1978 | 2.0679 | 80 | 0.1962 | |
|
| 0.1913 | 2.3263 | 90 | 0.1910 | |
|
| 0.1882 | 2.5848 | 100 | 0.1877 | |
|
| 0.1861 | 2.8433 | 110 | 0.1856 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.14.7 |
|
- Tokenizers 0.19.1 |
