<!-- 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. -->
AraGPT2-finetuned-crossVal-fnd
This model is a fine-tuned version of aubmindlab/aragpt2-mega-detector-long on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2251
- Macro F1: 0.9002
- Accuracy: 0.9041
- Precision: 0.9040
- Recall: 0.8972
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: 32
- eval_batch_size: 64
- seed: 123
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
---|---|---|---|---|---|---|---|
No log | 1.0 | 399 | 0.2251 | 0.9002 | 0.9041 | 0.9040 | 0.8972 |
0.3416 | 2.0 | 798 | 0.2335 | 0.8962 | 0.9008 | 0.9030 | 0.8916 |
Framework versions
- Transformers 4.12.2
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.10.3