xlm_r_base-finetuned_after_mrp-v2-exalted-paper-1
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: 0.4290
- Precision 0: 0.8620
- Precision 1: 0.7980
- Recall 0: 0.8620
- Recall 1: 0.7980
- F1 0: 0.8620
- F1 1: 0.7980
- Precision Weighted: 0.836
- Recall Weighted: 0.836
- F1 Weighted: 0.836
- Accuracy: 0.836
- F1 Macro: 0.8300
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision 0 | Precision 1 | Recall 0 | Recall 1 | F1 0 | F1 1 | Precision Weighted | Recall Weighted | F1 Weighted | Accuracy | F1 Macro |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.494 | 1.0 | 469 | 0.5547 | 0.7104 | 0.8409 | 0.9434 | 0.4374 | 0.8105 | 0.5755 | 0.7634 | 0.738 | 0.7151 | 0.738 | 0.6930 |
0.3727 | 2.0 | 938 | 0.4339 | 0.8431 | 0.7784 | 0.8505 | 0.7685 | 0.8468 | 0.7734 | 0.8169 | 0.8172 | 0.8170 | 0.8172 | 0.8101 |
0.4121 | 3.0 | 1407 | 0.3944 | 0.8492 | 0.8099 | 0.8761 | 0.7724 | 0.8624 | 0.7907 | 0.8333 | 0.834 | 0.8333 | 0.834 | 0.8266 |
0.2712 | 4.0 | 1876 | 0.3985 | 0.8463 | 0.8121 | 0.8788 | 0.7665 | 0.8622 | 0.7886 | 0.8324 | 0.8332 | 0.8324 | 0.8332 | 0.8254 |
0.284 | 5.0 | 2345 | 0.4290 | 0.8620 | 0.7980 | 0.8620 | 0.7980 | 0.8620 | 0.7980 | 0.836 | 0.836 | 0.836 | 0.836 | 0.8300 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1