<!-- 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_H512_A8_emotion
This model is a fine-tuned version of gokuls/HBERTv1_48_L2_H512_A8 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3286
- Accuracy: 0.892
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 |
|---|---|---|---|---|
| 0.7772 | 1.0 | 250 | 0.3597 | 0.879 |
| 0.3236 | 2.0 | 500 | 0.3267 | 0.883 |
| 0.2453 | 3.0 | 750 | 0.3155 | 0.886 |
| 0.201 | 4.0 | 1000 | 0.3350 | 0.889 |
| 0.1635 | 5.0 | 1250 | 0.3286 | 0.892 |
| 0.135 | 6.0 | 1500 | 0.3490 | 0.883 |
| 0.1065 | 7.0 | 1750 | 0.3686 | 0.89 |
| 0.0887 | 8.0 | 2000 | 0.4164 | 0.8805 |
| 0.0719 | 9.0 | 2250 | 0.4409 | 0.8805 |
| 0.0626 | 10.0 | 2500 | 0.4464 | 0.8825 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.0
