<!-- 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-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: 0.5249
- Macro F1: 0.7536
- Accuracy: 0.7626
- Precision: 0.7563
- Recall: 0.7517
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: 32
- seed: 25
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.588 | 1.0 | 798 | 0.5131 | 0.7235 | 0.7384 | 0.7341 | 0.7197 |
| 0.462 | 2.0 | 1596 | 0.5112 | 0.7408 | 0.7574 | 0.7587 | 0.7357 |
| 0.4034 | 3.0 | 2394 | 0.5249 | 0.7536 | 0.7626 | 0.7563 | 0.7517 |
| 0.3234 | 4.0 | 3192 | 0.5967 | 0.7524 | 0.7585 | 0.7516 | 0.7534 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
