metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: edos-2023-baseline-xlm-roberta-base-label_category
results: []
edos-2023-baseline-xlm-roberta-base-label_category
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4469
- F1: 0.8470
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 |
|---|---|---|---|---|
| 1.1983 | 1.18 | 100 | 1.1133 | 0.1623 |
| 1.0984 | 2.35 | 200 | 0.9809 | 0.2407 |
| 0.9901 | 3.53 | 300 | 0.8533 | 0.5465 |
| 0.8389 | 4.71 | 400 | 0.7101 | 0.6863 |
| 0.7889 | 5.88 | 500 | 0.5927 | 0.7696 |
| 0.6865 | 7.06 | 600 | 0.5303 | 0.8061 |
| 0.6364 | 8.24 | 700 | 0.4778 | 0.8278 |
| 0.5907 | 9.41 | 800 | 0.4469 | 0.8470 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2