metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
base_model: xlm-roberta-base
model-index:
- name: DIPROMATS_subtask_1
results: []
DIPROMATS_subtask_1
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0338
- F1: 0.9893
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.2333 | 1.0 | 227 | 0.3143 | 0.8275 |
| 0.2264 | 2.0 | 454 | 0.2628 | 0.8729 |
| 0.2179 | 3.0 | 681 | 0.1320 | 0.9398 |
| 0.1609 | 4.0 | 908 | 0.1025 | 0.9508 |
| 0.1894 | 5.0 | 1135 | 0.0947 | 0.9640 |
| 0.0291 | 6.0 | 1362 | 0.0581 | 0.9793 |
| 0.0075 | 7.0 | 1589 | 0.0633 | 0.9785 |
| 0.1243 | 8.0 | 1816 | 0.0372 | 0.9874 |
| 0.0925 | 9.0 | 2043 | 0.0483 | 0.9851 |
| 0.1582 | 10.0 | 2270 | 0.0338 | 0.9893 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.13.1
- Datasets 2.12.0
- Tokenizers 0.13.3