|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
base_model: xlm-roberta-base |
|
model-index: |
|
- name: SEMEVAL23_TASK3_SUBTASK1_MULTI |
|
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. --> |
|
|
|
# SEMEVAL23_TASK3_SUBTASK1_MULTI |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7683 |
|
- F1: 0.6317 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.9869 | 1.0 | 40 | 0.9517 | 0.4244 | |
|
| 0.5569 | 2.0 | 80 | 0.7365 | 0.5514 | |
|
| 0.4559 | 3.0 | 120 | 0.7829 | 0.5348 | |
|
| 0.2018 | 4.0 | 160 | 0.6281 | 0.6241 | |
|
| 0.1125 | 5.0 | 200 | 0.9291 | 0.5614 | |
|
| 0.2594 | 6.0 | 240 | 1.0367 | 0.5884 | |
|
| 0.1883 | 7.0 | 280 | 0.7683 | 0.6317 | |
|
| 0.1083 | 8.0 | 320 | 0.8660 | 0.6106 | |
|
| 0.0659 | 9.0 | 360 | 0.8695 | 0.6189 | |
|
| 0.2554 | 10.0 | 400 | 1.0094 | 0.5839 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.1 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.13.2 |
|
|
