metadata
base_model: aubmindlab/bert-base-arabertv02-twitter
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: unfortified_arabert
results: []
unfortified_arabert
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02-twitter on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2946
- Accuracy: 0.92
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: 2e-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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 0.0546 | 50 | 0.4109 | 0.84 |
No log | 0.1092 | 100 | 0.3536 | 0.87 |
No log | 0.1638 | 150 | 0.3609 | 0.88 |
No log | 0.2183 | 200 | 0.3567 | 0.88 |
No log | 0.2729 | 250 | 0.2934 | 0.91 |
No log | 0.3275 | 300 | 0.2243 | 0.95 |
No log | 0.3821 | 350 | 0.2257 | 0.92 |
No log | 0.4367 | 400 | 0.2350 | 0.94 |
No log | 0.4913 | 450 | 0.2917 | 0.91 |
0.2619 | 0.5459 | 500 | 0.3450 | 0.9 |
0.2619 | 0.6004 | 550 | 0.2562 | 0.91 |
0.2619 | 0.6550 | 600 | 0.2258 | 0.93 |
0.2619 | 0.7096 | 650 | 0.2705 | 0.9 |
0.2619 | 0.7642 | 700 | 0.2250 | 0.92 |
0.2619 | 0.8188 | 750 | 0.2246 | 0.92 |
0.2619 | 0.8734 | 800 | 0.2566 | 0.92 |
0.2619 | 0.9279 | 850 | 0.1948 | 0.92 |
0.2619 | 0.9825 | 900 | 0.2673 | 0.91 |
0.2619 | 1.0371 | 950 | 0.3450 | 0.91 |
0.2108 | 1.0917 | 1000 | 0.2748 | 0.92 |
0.2108 | 1.1463 | 1050 | 0.2977 | 0.91 |
0.2108 | 1.2009 | 1100 | 0.3209 | 0.91 |
0.2108 | 1.2555 | 1150 | 0.2821 | 0.91 |
0.2108 | 1.3100 | 1200 | 0.3070 | 0.92 |
0.2108 | 1.3646 | 1250 | 0.2946 | 0.92 |
Framework versions
- Transformers 4.42.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1