|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: bert-base-uncased |
|
datasets: |
|
- swag |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: fine-tuned-bert-base-uncased-swag-peft |
|
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. --> |
|
|
|
# fine-tuned-bert-base-uncased-swag-peft |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co./bert-base-uncased) on the swag dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6557 |
|
- Accuracy: 0.7483 |
|
|
|
## 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: 1.5e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 1.0316 | 1.0 | 1150 | 0.8202 | 0.6860 | |
|
| 0.9261 | 2.0 | 2300 | 0.7423 | 0.7144 | |
|
| 0.8862 | 3.0 | 3450 | 0.7114 | 0.7268 | |
|
| 0.8612 | 4.0 | 4600 | 0.6924 | 0.7347 | |
|
| 0.8637 | 5.0 | 5750 | 0.6819 | 0.7393 | |
|
| 0.8541 | 6.0 | 6900 | 0.6691 | 0.7441 | |
|
| 0.8369 | 7.0 | 8050 | 0.6635 | 0.7464 | |
|
| 0.8349 | 8.0 | 9200 | 0.6591 | 0.7475 | |
|
| 0.8302 | 9.0 | 10350 | 0.6572 | 0.7483 | |
|
| 0.8333 | 10.0 | 11500 | 0.6557 | 0.7483 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
