<!-- 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. -->
hbertv2-emotion_48_KD
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48_KD on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 1.1141
- Accuracy: 0.581
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 |
|---|---|---|---|---|
| 1.5998 | 1.0 | 250 | 1.5899 | 0.352 |
| 1.5872 | 2.0 | 500 | 1.5967 | 0.275 |
| 1.6045 | 3.0 | 750 | 1.6220 | 0.275 |
| 1.5911 | 4.0 | 1000 | 1.4863 | 0.502 |
| 1.3919 | 5.0 | 1250 | 1.3375 | 0.5325 |
| 1.2936 | 6.0 | 1500 | 1.3029 | 0.546 |
| 1.2151 | 7.0 | 1750 | 1.2297 | 0.559 |
| 1.1985 | 8.0 | 2000 | 1.2658 | 0.551 |
| 1.1637 | 9.0 | 2250 | 1.1574 | 0.577 |
| 1.0928 | 10.0 | 2500 | 1.1141 | 0.581 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
