|
--- |
|
license: mit |
|
base_model: prajjwal1/bert-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert-small-finetuned |
|
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. --> |
|
|
|
# bert-small-finetuned |
|
|
|
This model is a fine-tuned version of [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9941 |
|
- Accuracy: 0.5903 |
|
- F1 Score: 0.5865 |
|
|
|
## 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: 2e-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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:| |
|
| No log | 1.0 | 24 | 1.2145 | 0.4933 | 0.4701 | |
|
| No log | 2.0 | 48 | 1.0960 | 0.5391 | 0.5365 | |
|
| No log | 3.0 | 72 | 1.0569 | 0.5768 | 0.5791 | |
|
| No log | 4.0 | 96 | 1.0052 | 0.5714 | 0.5698 | |
|
| No log | 5.0 | 120 | 0.9889 | 0.5714 | 0.5702 | |
|
| No log | 6.0 | 144 | 0.9932 | 0.5795 | 0.5772 | |
|
| No log | 7.0 | 168 | 0.9841 | 0.5714 | 0.5680 | |
|
| No log | 8.0 | 192 | 0.9941 | 0.5903 | 0.5865 | |
|
| No log | 9.0 | 216 | 0.9788 | 0.5903 | 0.5891 | |
|
| No log | 10.0 | 240 | 1.0105 | 0.5660 | 0.5617 | |
|
| No log | 11.0 | 264 | 1.0473 | 0.5526 | 0.5464 | |
|
| No log | 12.0 | 288 | 1.0272 | 0.5714 | 0.5685 | |
|
| No log | 13.0 | 312 | 1.0627 | 0.5499 | 0.5492 | |
|
| No log | 14.0 | 336 | 1.0428 | 0.5795 | 0.5782 | |
|
| No log | 15.0 | 360 | 1.0644 | 0.5633 | 0.5625 | |
|
| No log | 16.0 | 384 | 1.1463 | 0.5364 | 0.5261 | |
|
| No log | 17.0 | 408 | 1.1109 | 0.5714 | 0.5689 | |
|
| No log | 18.0 | 432 | 1.1260 | 0.5741 | 0.5739 | |
|
| No log | 19.0 | 456 | 1.1793 | 0.5580 | 0.5533 | |
|
| No log | 20.0 | 480 | 1.1968 | 0.5580 | 0.5535 | |
|
| 0.6103 | 21.0 | 504 | 1.1961 | 0.5741 | 0.5722 | |
|
| 0.6103 | 22.0 | 528 | 1.2399 | 0.5553 | 0.5504 | |
|
| 0.6103 | 23.0 | 552 | 1.2642 | 0.5526 | 0.5473 | |
|
| 0.6103 | 24.0 | 576 | 1.2530 | 0.5660 | 0.5625 | |
|
| 0.6103 | 25.0 | 600 | 1.2637 | 0.5714 | 0.5687 | |
|
| 0.6103 | 26.0 | 624 | 1.3012 | 0.5526 | 0.5468 | |
|
| 0.6103 | 27.0 | 648 | 1.2932 | 0.5606 | 0.5579 | |
|
| 0.6103 | 28.0 | 672 | 1.2888 | 0.5687 | 0.5664 | |
|
| 0.6103 | 29.0 | 696 | 1.3087 | 0.5660 | 0.5634 | |
|
| 0.6103 | 30.0 | 720 | 1.3073 | 0.5714 | 0.5687 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|