<!-- 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. -->
baseline_nli_xlmr_zero_shot
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: 1.4063
- Accuracy: 0.4452
- Precision: 0.4452
- Recall: 0.4452
- F1 Score: 0.4102
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-06
- train_batch_size: 12
- eval_batch_size: 12
- seed: 101
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|---|---|---|---|---|---|---|---|
| 1.0598 | 1.0 | 861 | 1.0376 | 0.4356 | 0.4356 | 0.4356 | 0.4093 |
| 0.8459 | 2.0 | 1722 | 1.2189 | 0.4342 | 0.4342 | 0.4342 | 0.3792 |
| 0.7501 | 3.0 | 2583 | 1.3530 | 0.4224 | 0.4224 | 0.4224 | 0.3779 |
| 0.7097 | 4.0 | 3444 | 1.3412 | 0.4315 | 0.4315 | 0.4315 | 0.3887 |
| 0.6706 | 5.0 | 4305 | 1.3792 | 0.4497 | 0.4497 | 0.4497 | 0.4187 |
| 0.6534 | 6.0 | 5166 | 1.4063 | 0.4452 | 0.4452 | 0.4452 | 0.4102 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
