|
--- |
|
license: mit |
|
base_model: FacebookAI/roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: uniBERT.RoBERTa.2 |
|
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. --> |
|
|
|
# uniBERT.RoBERTa.2 |
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5630 |
|
- Accuracy: (0.5576407506702413,) |
|
- F1: (0.5567150966762268,) |
|
- Precision: (0.5821362469913879,) |
|
- Recall: 0.5576 |
|
|
|
## 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: 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 | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:----------------------:|:----------------------:|:------:| |
|
| 3.2109 | 1.0 | 187 | 2.8161 | (0.14075067024128687,) | (0.11441602156126289,) | (0.14931859559553662,) | 0.1408 | |
|
| 2.379 | 2.0 | 374 | 2.1989 | (0.29624664879356566,) | (0.29511135501125035,) | (0.46510470134694354,) | 0.2962 | |
|
| 1.8982 | 3.0 | 561 | 1.8944 | (0.39812332439678283,) | (0.3899880572417641,) | (0.5315801863934072,) | 0.3981 | |
|
| 1.5421 | 4.0 | 748 | 1.7216 | (0.435656836461126,) | (0.43699437984272427,) | (0.5225927530578255,) | 0.4357 | |
|
| 1.2096 | 5.0 | 935 | 1.6234 | (0.4906166219839142,) | (0.4898871795571693,) | (0.5614942106807528,) | 0.4906 | |
|
| 1.0077 | 6.0 | 1122 | 1.5807 | (0.5201072386058981,) | (0.5180183790949172,) | (0.5564502396694377,) | 0.5201 | |
|
| 0.9205 | 7.0 | 1309 | 1.5927 | (0.5308310991957105,) | (0.5275104307804458,) | (0.5702694562019299,) | 0.5308 | |
|
| 0.7537 | 8.0 | 1496 | 1.5717 | (0.532171581769437,) | (0.5297487624770745,) | (0.5623053308004577,) | 0.5322 | |
|
| 0.6635 | 9.0 | 1683 | 1.5720 | (0.5495978552278821,) | (0.5497874364324945,) | (0.579798743930685,) | 0.5496 | |
|
| 0.6479 | 10.0 | 1870 | 1.5630 | (0.5576407506702413,) | (0.5567150966762268,) | (0.5821362469913879,) | 0.5576 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|