|
--- |
|
base_model: scb10x/typhoon-7b |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: local_model_directory |
|
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. --> |
|
|
|
# local_model_directory |
|
|
|
This model is a fine-tuned version of [scb10x/typhoon-7b](https://huggingface.co/scb10x/typhoon-7b) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4505 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- num_epochs: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 5.0407 | 0.9524 | 5 | 4.8168 | |
|
| 3.5268 | 1.9048 | 10 | 2.1234 | |
|
| 1.9397 | 2.8571 | 15 | 1.2800 | |
|
| 1.0223 | 4.0 | 21 | 0.7717 | |
|
| 0.8135 | 4.9524 | 26 | 0.5757 | |
|
| 0.6574 | 5.9048 | 31 | 0.5178 | |
|
| 0.5833 | 6.8571 | 36 | 0.4854 | |
|
| 0.4549 | 8.0 | 42 | 0.4494 | |
|
| 0.5012 | 8.9524 | 47 | 0.4294 | |
|
| 0.514 | 9.9048 | 52 | 0.4505 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
