<!-- 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_multilingual_base_cased2
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7034
- Accuracy: 0.6413
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 2.5064 | 0.59 | 500 | 2.0007 | 0.5923 |
| 2.3261 | 1.19 | 1000 | 1.9370 | 0.6004 |
| 2.2689 | 1.78 | 1500 | 1.9199 | 0.6049 |
| 2.2101 | 2.38 | 2000 | 1.8503 | 0.6167 |
| 2.2015 | 2.97 | 2500 | 1.8582 | 0.6148 |
| 2.1468 | 3.56 | 3000 | 1.8364 | 0.6186 |
| 2.1213 | 4.16 | 3500 | 1.8128 | 0.6203 |
| 2.0938 | 4.75 | 4000 | 1.7888 | 0.6254 |
| 2.0888 | 5.34 | 4500 | 1.7835 | 0.6285 |
| 2.0619 | 5.94 | 5000 | 1.7469 | 0.6320 |
| 2.045 | 6.53 | 5500 | 1.7322 | 0.6350 |
| 2.032 | 7.13 | 6000 | 1.7279 | 0.6363 |
| 2.012 | 7.72 | 6500 | 1.7045 | 0.6403 |
| 1.9992 | 8.31 | 7000 | 1.7063 | 0.6398 |
| 1.993 | 8.91 | 7500 | 1.7071 | 0.6405 |
| 1.9774 | 9.5 | 8000 | 1.6911 | 0.6419 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.12.1
