<!-- 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. -->
lang_adapter_fa_twitter_xlm_roberta_base_pfeiffer
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: 1.6701
- Accuracy: 0.6447
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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.0195 | 0.48 | 500 | 1.7864 | 0.6289 |
| 2.3543 | 0.95 | 1000 | 1.7252 | 0.6366 |
| 2.2612 | 1.43 | 1500 | 1.7230 | 0.6363 |
| 2.2055 | 1.9 | 2000 | 1.6968 | 0.6415 |
| 2.1811 | 2.38 | 2500 | 1.6875 | 0.6413 |
| 2.1813 | 2.85 | 3000 | 1.6890 | 0.6419 |
| 2.1657 | 3.33 | 3500 | 1.6684 | 0.6453 |
| 2.1375 | 3.81 | 4000 | 1.6591 | 0.6486 |
| 2.1516 | 4.28 | 4500 | 1.6674 | 0.6452 |
| 2.1363 | 4.76 | 5000 | 1.6691 | 0.6423 |
| 2.1235 | 5.23 | 5500 | 1.6573 | 0.6465 |
| 2.132 | 5.71 | 6000 | 1.6597 | 0.6433 |
| 2.1043 | 6.18 | 6500 | 1.6370 | 0.6521 |
| 2.127 | 6.66 | 7000 | 1.6723 | 0.6446 |
| 2.1116 | 7.14 | 7500 | 1.6521 | 0.6450 |
| 2.0916 | 7.61 | 8000 | 1.6538 | 0.6492 |
| 2.105 | 8.09 | 8500 | 1.6380 | 0.6492 |
| 2.0921 | 8.56 | 9000 | 1.6747 | 0.6429 |
| 2.0929 | 9.04 | 9500 | 1.6496 | 0.6449 |
| 2.0915 | 9.51 | 10000 | 1.6552 | 0.6460 |
| 2.0715 | 9.99 | 10500 | 1.6649 | 0.6444 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
