<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xlmroberta-2nd-finetune-epru
This model is a fine-tuned version of mmillet/xlm-roberta-base_single_finetuned_on_cedr_augmented on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3666
- Accuracy: 0.9325
- F1: 0.9329
- Precision: 0.9352
- Recall: 0.9325
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4757 | 1.0 | 12 | 0.2387 | 0.9264 | 0.9267 | 0.9333 | 0.9264 |
| 0.3086 | 2.0 | 24 | 0.3059 | 0.9141 | 0.9143 | 0.9270 | 0.9141 |
| 0.2151 | 3.0 | 36 | 0.2394 | 0.9202 | 0.9214 | 0.9266 | 0.9202 |
| 0.1629 | 4.0 | 48 | 0.3025 | 0.9325 | 0.9332 | 0.9385 | 0.9325 |
| 0.0911 | 5.0 | 60 | 0.2597 | 0.9387 | 0.9390 | 0.9434 | 0.9387 |
| 0.0455 | 6.0 | 72 | 0.3476 | 0.9387 | 0.9389 | 0.9400 | 0.9387 |
| 0.0521 | 7.0 | 84 | 0.3630 | 0.9325 | 0.9329 | 0.9356 | 0.9325 |
| 0.029 | 8.0 | 96 | 0.3100 | 0.9509 | 0.9513 | 0.9531 | 0.9509 |
| 0.0379 | 9.0 | 108 | 0.3044 | 0.9448 | 0.9450 | 0.9455 | 0.9448 |
| 0.0363 | 10.0 | 120 | 0.4181 | 0.9141 | 0.9147 | 0.9191 | 0.9141 |
| 0.0165 | 11.0 | 132 | 0.3666 | 0.9325 | 0.9329 | 0.9352 | 0.9325 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
