|
--- |
|
base_model: NousResearch/Meta-Llama-3.1-8B-Instruct |
|
datasets: |
|
- generator |
|
library_name: peft |
|
license: llama3.1 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: llama381binstruct_summarize |
|
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. --> |
|
|
|
# llama381binstruct_summarize |
|
|
|
This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7355 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 30 |
|
- training_steps: 500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 1.6918 | 1.3158 | 25 | 1.6215 | |
|
| 0.6871 | 2.6316 | 50 | 1.6851 | |
|
| 0.3017 | 3.9474 | 75 | 1.8694 | |
|
| 0.1642 | 5.2632 | 100 | 2.2410 | |
|
| 0.0667 | 6.5789 | 125 | 2.2806 | |
|
| 0.0352 | 7.8947 | 150 | 2.4889 | |
|
| 0.0292 | 9.2105 | 175 | 2.5073 | |
|
| 0.0117 | 10.5263 | 200 | 2.5430 | |
|
| 0.0111 | 11.8421 | 225 | 2.5160 | |
|
| 0.0101 | 13.1579 | 250 | 2.5102 | |
|
| 0.0083 | 14.4737 | 275 | 2.5176 | |
|
| 0.0033 | 15.7895 | 300 | 2.5635 | |
|
| 0.0028 | 17.1053 | 325 | 2.6311 | |
|
| 0.0022 | 18.4211 | 350 | 2.6684 | |
|
| 0.0016 | 19.7368 | 375 | 2.6933 | |
|
| 0.0021 | 21.0526 | 400 | 2.7102 | |
|
| 0.0019 | 22.3684 | 425 | 2.7220 | |
|
| 0.0016 | 23.6842 | 450 | 2.7295 | |
|
| 0.0018 | 25.0 | 475 | 2.7339 | |
|
| 0.0017 | 26.3158 | 500 | 2.7355 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
