<!-- 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. -->
xlm-roberta-base-ukraine-war-official-v2
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: 0.4596
- Accuracy: 0.7875
- F1: 0.7842
- Precision: 0.8062
- Recall: 0.7875
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 2402
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.447 | 1.0 | 1875 | 0.3923 | 0.833 | 0.8329 | 0.8339 | 0.833 |
| 0.3818 | 2.0 | 3750 | 0.3735 | 0.835 | 0.8350 | 0.8352 | 0.835 |
| 0.3548 | 3.0 | 5625 | 0.3966 | 0.841 | 0.8404 | 0.8465 | 0.841 |
| 0.3182 | 4.0 | 7500 | 0.4211 | 0.8375 | 0.8374 | 0.8385 | 0.8375 |
| 0.2907 | 5.0 | 9375 | 0.4874 | 0.8245 | 0.8236 | 0.8315 | 0.8245 |
| 0.2732 | 6.0 | 11250 | 0.5486 | 0.837 | 0.8364 | 0.8424 | 0.837 |
| 0.2318 | 7.0 | 13125 | 0.5750 | 0.8345 | 0.8339 | 0.8398 | 0.8345 |
| 0.2012 | 8.0 | 15000 | 0.6026 | 0.841 | 0.8408 | 0.8430 | 0.841 |
| 0.1769 | 9.0 | 16875 | 0.6859 | 0.8405 | 0.8401 | 0.8436 | 0.8405 |
| 0.1379 | 10.0 | 18750 | 0.7072 | 0.84 | 0.8398 | 0.8420 | 0.8400 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Tokenizers 0.13.3
