metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: FULL-12epoch-XLMRoBERTa-finetuned-CEFR_ner-60000news
results: []
FULL-12epoch-XLMRoBERTa-finetuned-CEFR_ner-60000news
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: 0.0687
- Accuracy: 0.3222
- Precision: 0.6358
- Recall: 0.8475
- F1: 0.6074
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
- lr_scheduler_warmup_steps: 100
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.087 | 1.0 | 1563 | 0.0917 | 0.3188 | 0.7203 | 0.8273 | 0.6562 |
| 0.08 | 2.0 | 3126 | 0.0747 | 0.3204 | 0.7147 | 0.8331 | 0.6569 |
| 0.0666 | 3.0 | 4689 | 0.0691 | 0.3211 | 0.7195 | 0.8376 | 0.6624 |
| 0.0583 | 4.0 | 6252 | 0.0667 | 0.3213 | 0.6889 | 0.8419 | 0.6433 |
| 0.0514 | 5.0 | 7815 | 0.0650 | 0.3216 | 0.7043 | 0.8433 | 0.6543 |
| 0.0463 | 6.0 | 9378 | 0.0642 | 0.3219 | 0.6780 | 0.8444 | 0.6362 |
| 0.0421 | 7.0 | 10941 | 0.0635 | 0.3220 | 0.6759 | 0.8458 | 0.6354 |
| 0.0385 | 8.0 | 12504 | 0.0644 | 0.3220 | 0.6330 | 0.8470 | 0.6066 |
| 0.0358 | 9.0 | 14067 | 0.0670 | 0.3221 | 0.6368 | 0.8467 | 0.6068 |
| 0.0331 | 10.0 | 15630 | 0.0676 | 0.3222 | 0.6442 | 0.8468 | 0.6130 |
| 0.0309 | 11.0 | 17193 | 0.0680 | 0.3222 | 0.6377 | 0.8472 | 0.6092 |
| 0.0298 | 12.0 | 18756 | 0.0687 | 0.3222 | 0.6358 | 0.8475 | 0.6074 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.1
- Datasets 2.19.2
- Tokenizers 0.19.1