xlm-roberta-base-pcm-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: 0.4237
- F1: 0.4302
- Roc Auc: 0.6457
- Accuracy: 0.3081
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 |
|---|---|---|---|---|---|---|
| 0.4949 | 1.0 | 159 | 0.4592 | 0.1074 | 0.5319 | 0.1726 |
| 0.428 | 2.0 | 318 | 0.4154 | 0.2990 | 0.5972 | 0.2952 |
| 0.3804 | 3.0 | 477 | 0.4116 | 0.3552 | 0.6247 | 0.3016 |
| 0.3329 | 4.0 | 636 | 0.4237 | 0.4302 | 0.6457 | 0.3081 |
| 0.3116 | 5.0 | 795 | 0.4302 | 0.4257 | 0.6417 | 0.3097 |
| 0.2684 | 6.0 | 954 | 0.4445 | 0.4270 | 0.6463 | 0.3145 |
| 0.2433 | 7.0 | 1113 | 0.4619 | 0.4250 | 0.6455 | 0.3194 |
| 0.2221 | 8.0 | 1272 | 0.4965 | 0.4185 | 0.6495 | 0.3194 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0