|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: unsupervised-fine-tune-bert-exist-5 |
|
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. --> |
|
|
|
# unsupervised-fine-tune-bert-exist-5 |
|
|
|
This model is a fine-tuned version of [nouman-10/unsupervised-exist](https://huggingface.co/nouman-10/unsupervised-exist) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8920 |
|
- Accuracy: 0.6337 |
|
- F1: 0.6337 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 1.0 | 194 | 0.9582 | 0.6337 | 0.6337 | |
|
| No log | 2.0 | 388 | 0.9158 | 0.6657 | 0.6657 | |
|
| 0.9283 | 3.0 | 582 | 1.0225 | 0.6453 | 0.6453 | |
|
| 0.9283 | 4.0 | 776 | 1.1757 | 0.6453 | 0.6453 | |
|
| 0.9283 | 5.0 | 970 | 1.4833 | 0.6541 | 0.6541 | |
|
| 0.3 | 6.0 | 1164 | 1.5788 | 0.6424 | 0.6424 | |
|
| 0.3 | 7.0 | 1358 | 1.7086 | 0.6424 | 0.6424 | |
|
| 0.0837 | 8.0 | 1552 | 1.7899 | 0.625 | 0.625 | |
|
| 0.0837 | 9.0 | 1746 | 1.8782 | 0.6366 | 0.6366 | |
|
| 0.0837 | 10.0 | 1940 | 1.8920 | 0.6337 | 0.6337 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
