<!-- 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. -->
HBERTv1_48_L2_H768_A12_emotion
This model is a fine-tuned version of gokuls/HBERTv1_48_L2_H768_A12 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.5001
- Accuracy: 0.902
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 33
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.652 | 1.0 | 250 | 0.3361 | 0.886 |
| 0.286 | 2.0 | 500 | 0.2842 | 0.8985 |
| 0.2136 | 3.0 | 750 | 0.3013 | 0.8895 |
| 0.1606 | 4.0 | 1000 | 0.3200 | 0.895 |
| 0.1234 | 5.0 | 1250 | 0.3292 | 0.8945 |
| 0.0937 | 6.0 | 1500 | 0.3903 | 0.8955 |
| 0.0682 | 7.0 | 1750 | 0.4032 | 0.8985 |
| 0.0471 | 8.0 | 2000 | 0.4627 | 0.9 |
| 0.0337 | 9.0 | 2250 | 0.4851 | 0.899 |
| 0.0269 | 10.0 | 2500 | 0.5001 | 0.902 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.0
