parsBERT_text_emotion_classification-finetuned-bmd-20250122_113034-LOSO-section-out4
This model is a fine-tuned version of Nhoseinnia/parsBERT_text_emotion_classification on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7465
- Accuracy: 0.4783
- F1: 0.4679
- Precision: 0.4645
- Recall: 0.4783
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 11
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 3 | 0.7009 | 0.6087 | 0.5750 | 0.6063 | 0.6087 |
| No log | 2.0 | 6 | 0.7005 | 0.5652 | 0.5399 | 0.5499 | 0.5652 |
| No log | 3.0 | 9 | 0.7175 | 0.5652 | 0.5399 | 0.5499 | 0.5652 |
| 0.604 | 4.0 | 12 | 0.7366 | 0.5652 | 0.5399 | 0.5499 | 0.5652 |
| 0.604 | 5.0 | 15 | 0.7350 | 0.5217 | 0.5043 | 0.5043 | 0.5217 |
| 0.604 | 6.0 | 18 | 0.7414 | 0.4783 | 0.4679 | 0.4645 | 0.4783 |
| 0.4604 | 7.0 | 21 | 0.7461 | 0.4783 | 0.4679 | 0.4645 | 0.4783 |
| 0.4604 | 7.3636 | 22 | 0.7465 | 0.4783 | 0.4679 | 0.4645 | 0.4783 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0