hbertv1-mini-wt-frz-48-emotion-emb-comp
This model is a fine-tuned version of gokuls/model_v1_complete_training_wt_init_48_mini_emb_comp_frz on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3850
- Accuracy: 0.883
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 |
|---|---|---|---|---|
| 1.0654 | 1.0 | 250 | 0.5938 | 0.8075 |
| 0.4743 | 2.0 | 500 | 0.4150 | 0.8575 |
| 0.324 | 3.0 | 750 | 0.3850 | 0.883 |
| 0.2558 | 4.0 | 1000 | 0.3847 | 0.8755 |
| 0.2103 | 5.0 | 1250 | 0.3978 | 0.87 |
| 0.1763 | 6.0 | 1500 | 0.3857 | 0.874 |
| 0.1454 | 7.0 | 1750 | 0.3880 | 0.879 |
| 0.1205 | 8.0 | 2000 | 0.4153 | 0.88 |
| 0.0995 | 9.0 | 2250 | 0.4228 | 0.8765 |
| 0.0828 | 10.0 | 2500 | 0.4313 | 0.878 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.1
- Tokenizers 0.13.3