|
|
--- |
|
|
license: other |
|
|
library_name: peft |
|
|
tags: |
|
|
- llama-factory |
|
|
- lora |
|
|
- generated_from_trainer |
|
|
base_model: meta-llama/Meta-Llama-3-8B-Instruct |
|
|
model-index: |
|
|
- name: sft |
|
|
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. --> |
|
|
|
|
|
# sft |
|
|
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the duie dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0501 |
|
|
|
|
|
## 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: 24 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 2 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 96 |
|
|
- total_eval_batch_size: 2 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 0.1 |
|
|
- num_epochs: 3.0 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.074 | 0.16 | 500 | 0.0621 | |
|
|
| 0.0625 | 0.31 | 1000 | 0.0562 | |
|
|
| 0.0581 | 0.47 | 1500 | 0.0543 | |
|
|
| 0.0626 | 0.62 | 2000 | 0.0530 | |
|
|
| 0.0597 | 0.78 | 2500 | 0.0524 | |
|
|
| 0.0619 | 0.93 | 3000 | 0.0500 | |
|
|
| 0.0445 | 1.09 | 3500 | 0.0499 | |
|
|
| 0.0501 | 1.25 | 4000 | 0.0492 | |
|
|
| 0.0487 | 1.4 | 4500 | 0.0490 | |
|
|
| 0.0501 | 1.56 | 5000 | 0.0485 | |
|
|
| 0.0516 | 1.71 | 5500 | 0.0472 | |
|
|
| 0.0458 | 1.87 | 6000 | 0.0468 | |
|
|
| 0.0381 | 2.03 | 6500 | 0.0482 | |
|
|
| 0.037 | 2.18 | 7000 | 0.0506 | |
|
|
| 0.0387 | 2.34 | 7500 | 0.0501 | |
|
|
| 0.0363 | 2.49 | 8000 | 0.0498 | |
|
|
| 0.0321 | 2.65 | 8500 | 0.0500 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.10.0 |
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
