metadata
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: clef1ar
results: []
clef1ar
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4347
- F1: 0.6539
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.5791 | 0.4843 | 200 | 0.5243 | 0.0 |
| 0.5199 | 0.9685 | 400 | 0.4892 | 0.5056 |
| 0.4637 | 1.4528 | 600 | 0.4469 | 0.5788 |
| 0.4391 | 1.9370 | 800 | 0.4363 | 0.5637 |
| 0.4206 | 2.4213 | 1000 | 0.4347 | 0.6539 |
| 0.4189 | 2.9056 | 1200 | 0.4250 | 0.6359 |
| 0.4049 | 3.3898 | 1400 | 0.4270 | 0.6217 |
| 0.3796 | 3.8741 | 1600 | 0.4386 | 0.6212 |
| 0.4007 | 4.3584 | 1800 | 0.4310 | 0.6301 |
| 0.3785 | 4.8426 | 2000 | 0.4315 | 0.6205 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1