parsBERT_text_emotion_classification-finetuned-BMD-20241201_105236
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: 1.4538
- Accuracy: 0.5
- F1: 0.5058
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: 42
- optimizer: Use 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.1168 | 1.0 | 4 | 1.1421 | 0.2941 | 0.1677 |
| 1.0814 | 2.0 | 8 | 1.1399 | 0.3235 | 0.2160 |
| 1.0225 | 3.0 | 12 | 1.1935 | 0.3235 | 0.3116 |
| 0.9318 | 4.0 | 16 | 1.1264 | 0.3824 | 0.3781 |
| 0.9139 | 5.0 | 20 | 1.1417 | 0.3824 | 0.3369 |
| 0.7 | 6.0 | 24 | 1.1091 | 0.4706 | 0.4543 |
| 0.6879 | 7.0 | 28 | 1.0725 | 0.4118 | 0.4101 |
| 0.5547 | 8.0 | 32 | 1.1509 | 0.4706 | 0.4732 |
| 0.4669 | 9.0 | 36 | 1.1405 | 0.5 | 0.5041 |
| 0.401 | 10.0 | 40 | 1.1481 | 0.4706 | 0.4721 |
| 0.4147 | 11.0 | 44 | 1.2442 | 0.4412 | 0.4480 |
| 0.3014 | 12.0 | 48 | 1.2822 | 0.4118 | 0.4155 |
| 0.2392 | 13.0 | 52 | 1.3319 | 0.4118 | 0.4155 |
| 0.2147 | 14.0 | 56 | 1.3837 | 0.4118 | 0.4155 |
| 0.1618 | 15.0 | 60 | 1.4191 | 0.4118 | 0.4155 |
| 0.1509 | 16.0 | 64 | 1.4041 | 0.5 | 0.5058 |
| 0.1373 | 17.0 | 68 | 1.4388 | 0.4412 | 0.4480 |
| 0.1212 | 18.0 | 72 | 1.4829 | 0.4412 | 0.4480 |
| 0.111 | 19.0 | 76 | 1.4692 | 0.5 | 0.5058 |
| 0.1147 | 20.0 | 80 | 1.4538 | 0.5 | 0.5058 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3