finetuned_bert-base-on-IEMOCAP_3
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0342
- Accuracy: 0.6490
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2553 | 1.0 | 110 | 1.2256 | 0.4636 |
| 0.8935 | 2.0 | 220 | 0.9211 | 0.6355 |
| 0.7189 | 3.0 | 330 | 0.7761 | 0.7107 |
| 0.5676 | 4.0 | 440 | 0.8031 | 0.7210 |
| 0.3598 | 5.0 | 550 | 0.8454 | 0.7301 |
| 0.2774 | 6.0 | 660 | 0.8871 | 0.7153 |
| 0.2699 | 7.0 | 770 | 0.9372 | 0.7175 |
| 0.1963 | 8.0 | 880 | 0.9686 | 0.7244 |
| 0.2565 | 9.0 | 990 | 1.0099 | 0.7016 |
| 0.1849 | 10.0 | 1100 | 1.0425 | 0.7175 |
| 0.1769 | 11.0 | 1210 | 1.1145 | 0.7118 |
| 0.1727 | 12.0 | 1320 | 1.1316 | 0.7187 |
| 0.1132 | 13.0 | 1430 | 1.0963 | 0.7244 |
| 0.1314 | 14.0 | 1540 | 1.1908 | 0.7118 |
| 0.0833 | 15.0 | 1650 | 1.2133 | 0.7164 |
| 0.1378 | 16.0 | 1760 | 1.1971 | 0.7210 |
| 0.1067 | 17.0 | 1870 | 1.2330 | 0.7118 |
| 0.0539 | 18.0 | 1980 | 1.2246 | 0.7198 |
| 0.0718 | 19.0 | 2090 | 1.2364 | 0.7164 |
| 0.1036 | 20.0 | 2200 | 1.2446 | 0.7164 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3