|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: edos-2023-baseline-roberta-base-label_sexist |
|
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. --> |
|
|
|
# edos-2023-baseline-roberta-base-label_sexist |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0182 |
|
- F1: 0.9951 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 5 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.5623 | 0.29 | 100 | 0.4459 | 0.6857 | |
|
| 0.4055 | 0.57 | 200 | 0.3119 | 0.8135 | |
|
| 0.3455 | 0.86 | 300 | 0.2704 | 0.8430 | |
|
| 0.3198 | 1.14 | 400 | 0.2431 | 0.8640 | |
|
| 0.2817 | 1.43 | 500 | 0.2579 | 0.8650 | |
|
| 0.2997 | 1.71 | 600 | 0.2089 | 0.8911 | |
|
| 0.2784 | 2.0 | 700 | 0.2069 | 0.8818 | |
|
| 0.2231 | 2.29 | 800 | 0.2233 | 0.8872 | |
|
| 0.2261 | 2.57 | 900 | 0.1598 | 0.9215 | |
|
| 0.238 | 2.86 | 1000 | 0.1524 | 0.9137 | |
|
| 0.2014 | 3.14 | 1100 | 0.1155 | 0.9441 | |
|
| 0.1669 | 3.43 | 1200 | 0.1203 | 0.9436 | |
|
| 0.1691 | 3.71 | 1300 | 0.0957 | 0.9566 | |
|
| 0.1787 | 4.0 | 1400 | 0.0763 | 0.9709 | |
|
| 0.1277 | 4.29 | 1500 | 0.0696 | 0.9717 | |
|
| 0.1359 | 4.57 | 1600 | 0.0654 | 0.9734 | |
|
| 0.1138 | 4.86 | 1700 | 0.0542 | 0.9788 | |
|
| 0.1057 | 5.14 | 1800 | 0.0587 | 0.9747 | |
|
| 0.1055 | 5.43 | 1900 | 0.0420 | 0.9843 | |
|
| 0.0908 | 5.71 | 2000 | 0.0386 | 0.9866 | |
|
| 0.1094 | 6.0 | 2100 | 0.0328 | 0.9890 | |
|
| 0.0845 | 6.29 | 2200 | 0.0320 | 0.9885 | |
|
| 0.0697 | 6.57 | 2300 | 0.0322 | 0.9893 | |
|
| 0.083 | 6.86 | 2400 | 0.0260 | 0.9912 | |
|
| 0.0659 | 7.14 | 2500 | 0.0259 | 0.9923 | |
|
| 0.0745 | 7.43 | 2600 | 0.0304 | 0.9900 | |
|
| 0.0623 | 7.71 | 2700 | 0.0284 | 0.9912 | |
|
| 0.0825 | 8.0 | 2800 | 0.0215 | 0.9933 | |
|
| 0.0414 | 8.29 | 2900 | 0.0222 | 0.9939 | |
|
| 0.0477 | 8.57 | 3000 | 0.0231 | 0.9940 | |
|
| 0.0606 | 8.86 | 3100 | 0.0211 | 0.9937 | |
|
| 0.0616 | 9.14 | 3200 | 0.0190 | 0.9947 | |
|
| 0.0413 | 9.43 | 3300 | 0.0182 | 0.9950 | |
|
| 0.0462 | 9.71 | 3400 | 0.0181 | 0.9949 | |
|
| 0.0473 | 10.0 | 3500 | 0.0182 | 0.9951 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.2 |
|
|
