<!-- 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. -->
monday2
This model is a fine-tuned version of aubmindlab/bert-base-arabert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Accuracy: 1.0
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.297 | 0.09 | 50 | 0.1440 | 0.96 |
| 0.1293 | 0.17 | 100 | 0.0765 | 0.98 |
| 0.0698 | 0.26 | 150 | 0.0453 | 0.98 |
| 0.0579 | 0.34 | 200 | 0.0689 | 0.98 |
| 0.0361 | 0.43 | 250 | 0.0776 | 0.98 |
| 0.0596 | 0.52 | 300 | 0.0472 | 0.98 |
| 0.0281 | 0.6 | 350 | 0.0373 | 0.99 |
| 0.0297 | 0.69 | 400 | 0.0010 | 1.0 |
| 0.0307 | 0.78 | 450 | 0.0004 | 1.0 |
| 0.0569 | 0.86 | 500 | 0.0214 | 0.99 |
| 0.0216 | 0.95 | 550 | 0.0008 | 1.0 |
| 0.0095 | 1.03 | 600 | 0.0034 | 1.0 |
| 0.0076 | 1.12 | 650 | 0.0002 | 1.0 |
| 0.0144 | 1.21 | 700 | 0.0002 | 1.0 |
| 0.0142 | 1.29 | 750 | 0.0002 | 1.0 |
| 0.0002 | 1.38 | 800 | 0.0001 | 1.0 |
| 0.0117 | 1.47 | 850 | 0.0081 | 0.99 |
| 0.0119 | 1.55 | 900 | 0.0003 | 1.0 |
| 0.0002 | 1.64 | 950 | 0.0014 | 1.0 |
| 0.034 | 1.72 | 1000 | 0.0164 | 0.99 |
| 0.014 | 1.81 | 1050 | 0.0025 | 1.0 |
| 0.0031 | 1.9 | 1100 | 0.0096 | 0.99 |
| 0.0001 | 1.98 | 1150 | 0.0085 | 0.99 |
| 0.0093 | 2.07 | 1200 | 0.0122 | 0.99 |
| 0.0054 | 2.16 | 1250 | 0.0006 | 1.0 |
| 0.0032 | 2.24 | 1300 | 0.0062 | 1.0 |
| 0.0003 | 2.33 | 1350 | 0.0001 | 1.0 |
| 0.0001 | 2.41 | 1400 | 0.0001 | 1.0 |
| 0.0104 | 2.5 | 1450 | 0.0001 | 1.0 |
| 0.0074 | 2.59 | 1500 | 0.0001 | 1.0 |
| 0.0001 | 2.67 | 1550 | 0.0001 | 1.0 |
| 0.0002 | 2.76 | 1600 | 0.0001 | 1.0 |
| 0.0002 | 2.84 | 1650 | 0.0000 | 1.0 |
| 0.0001 | 2.93 | 1700 | 0.0000 | 1.0 |
| 0.0004 | 3.02 | 1750 | 0.0000 | 1.0 |
| 0.0049 | 3.1 | 1800 | 0.0000 | 1.0 |
| 0.0003 | 3.19 | 1850 | 0.0000 | 1.0 |
| 0.0019 | 3.28 | 1900 | 0.0000 | 1.0 |
| 0.0092 | 3.36 | 1950 | 0.0000 | 1.0 |
| 0.0002 | 3.45 | 2000 | 0.0001 | 1.0 |
| 0.0001 | 3.53 | 2050 | 0.0001 | 1.0 |
| 0.0 | 3.62 | 2100 | 0.0001 | 1.0 |
| 0.004 | 3.71 | 2150 | 0.0000 | 1.0 |
| 0.0001 | 3.79 | 2200 | 0.0000 | 1.0 |
| 0.0001 | 3.88 | 2250 | 0.0000 | 1.0 |
| 0.0 | 3.97 | 2300 | 0.0000 | 1.0 |
| 0.0023 | 4.05 | 2350 | 0.0000 | 1.0 |
| 0.0045 | 4.14 | 2400 | 0.0000 | 1.0 |
| 0.0 | 4.22 | 2450 | 0.0000 | 1.0 |
| 0.0 | 4.31 | 2500 | 0.0000 | 1.0 |
| 0.0001 | 4.4 | 2550 | 0.0000 | 1.0 |
| 0.0001 | 4.48 | 2600 | 0.0000 | 1.0 |
| 0.0009 | 4.57 | 2650 | 0.0000 | 1.0 |
| 0.0002 | 4.66 | 2700 | 0.0000 | 1.0 |
| 0.0 | 4.74 | 2750 | 0.0000 | 1.0 |
| 0.0003 | 4.83 | 2800 | 0.0000 | 1.0 |
| 0.0001 | 4.91 | 2850 | 0.0000 | 1.0 |
| 0.0001 | 5.0 | 2900 | 0.0000 | 1.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
