xlm-roberta-base-kin-finetuned
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3006
- F1: 0.3526
- Roc Auc: 0.6351
- Accuracy: 0.4226
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.3496 | 1.0 | 104 | 0.3465 | 0.0 | 0.5 | 0.2899 |
| 0.3139 | 2.0 | 208 | 0.3268 | 0.0 | 0.5 | 0.2899 |
| 0.3147 | 3.0 | 312 | 0.3091 | 0.1087 | 0.5574 | 0.3022 |
| 0.2992 | 4.0 | 416 | 0.3060 | 0.2137 | 0.5917 | 0.3661 |
| 0.2793 | 5.0 | 520 | 0.3020 | 0.2765 | 0.6080 | 0.3931 |
| 0.2663 | 6.0 | 624 | 0.3004 | 0.3518 | 0.6354 | 0.4201 |
| 0.2553 | 7.0 | 728 | 0.3132 | 0.3030 | 0.6193 | 0.4079 |
| 0.2301 | 8.0 | 832 | 0.3006 | 0.3526 | 0.6351 | 0.4226 |
| 0.2136 | 9.0 | 936 | 0.3033 | 0.3437 | 0.6304 | 0.4201 |
| 0.1941 | 10.0 | 1040 | 0.3257 | 0.3403 | 0.6379 | 0.4177 |
| 0.1662 | 11.0 | 1144 | 0.3268 | 0.3454 | 0.6349 | 0.4103 |
| 0.1648 | 12.0 | 1248 | 0.3398 | 0.3512 | 0.6378 | 0.4201 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0