<!-- 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. -->
ABSA-OTE-domainAdapt-SemEval-Adapter-pfeiffer_madx-run1
This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-msa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1191
- Precision: 0.7498
- Recall: 0.7778
- F1: 0.7635
- Accuracy: 0.9547
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: 32
- eval_batch_size: 8
- seed: 25
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.275 | 1.0 | 121 | 0.1425 | 0.7125 | 0.6791 | 0.6954 | 0.9472 |
| 0.1317 | 2.0 | 242 | 0.1232 | 0.7679 | 0.7170 | 0.7416 | 0.9521 |
| 0.1194 | 3.0 | 363 | 0.1197 | 0.7629 | 0.7359 | 0.7492 | 0.9529 |
| 0.114 | 4.0 | 484 | 0.1178 | 0.7651 | 0.7434 | 0.7541 | 0.9538 |
| 0.1104 | 5.0 | 605 | 0.1168 | 0.7790 | 0.7270 | 0.7521 | 0.9545 |
| 0.1045 | 6.0 | 726 | 0.1163 | 0.7499 | 0.7529 | 0.7514 | 0.9533 |
| 0.1024 | 7.0 | 847 | 0.1171 | 0.7369 | 0.7688 | 0.7525 | 0.9528 |
| 0.0996 | 8.0 | 968 | 0.1151 | 0.7585 | 0.7544 | 0.7564 | 0.9545 |
| 0.0978 | 9.0 | 1089 | 0.1179 | 0.7262 | 0.7902 | 0.7569 | 0.9522 |
| 0.0952 | 10.0 | 1210 | 0.1161 | 0.7782 | 0.7519 | 0.7648 | 0.9562 |
| 0.095 | 11.0 | 1331 | 0.1153 | 0.7752 | 0.7524 | 0.7636 | 0.9570 |
| 0.0902 | 12.0 | 1452 | 0.1194 | 0.7499 | 0.7678 | 0.7587 | 0.9541 |
| 0.0918 | 13.0 | 1573 | 0.1170 | 0.7600 | 0.7683 | 0.7641 | 0.9555 |
| 0.0884 | 14.0 | 1694 | 0.1183 | 0.7344 | 0.7922 | 0.7622 | 0.9539 |
| 0.0866 | 15.0 | 1815 | 0.1178 | 0.7819 | 0.7519 | 0.7666 | 0.9566 |
| 0.0852 | 16.0 | 1936 | 0.1188 | 0.7486 | 0.7788 | 0.7634 | 0.9548 |
| 0.0856 | 17.0 | 2057 | 0.1185 | 0.7586 | 0.7703 | 0.7644 | 0.9554 |
| 0.084 | 18.0 | 2178 | 0.1193 | 0.7462 | 0.7793 | 0.7624 | 0.9543 |
| 0.0837 | 19.0 | 2299 | 0.1193 | 0.7533 | 0.7728 | 0.7629 | 0.9545 |
| 0.0833 | 20.0 | 2420 | 0.1191 | 0.7498 | 0.7778 | 0.7635 | 0.9547 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
