<!-- 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_L10_H256_A4_emotion
This model is a fine-tuned version of gokuls/HBERTv1_48_L10_H256_A4 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.4543
- Accuracy: 0.862
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 |
|---|---|---|---|---|
| 1.4516 | 1.0 | 250 | 1.2557 | 0.5385 |
| 1.1623 | 2.0 | 500 | 1.0736 | 0.586 |
| 0.8971 | 3.0 | 750 | 0.8424 | 0.715 |
| 0.6843 | 4.0 | 1000 | 0.7092 | 0.773 |
| 0.583 | 5.0 | 1250 | 0.6343 | 0.7985 |
| 0.5184 | 6.0 | 1500 | 0.6129 | 0.8 |
| 0.4467 | 7.0 | 1750 | 0.5106 | 0.8405 |
| 0.3534 | 8.0 | 2000 | 0.4543 | 0.862 |
| 0.3167 | 9.0 | 2250 | 0.4388 | 0.862 |
| 0.2938 | 10.0 | 2500 | 0.4424 | 0.8615 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.0
