<!-- 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_L8_H768_A12_emotion
This model is a fine-tuned version of gokuls/HBERTv1_48_L8_H768_A12 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.5893
- Accuracy: 0.899
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 |
---|---|---|---|---|
0.853 | 1.0 | 250 | 0.4208 | 0.8595 |
0.3414 | 2.0 | 500 | 0.3500 | 0.879 |
0.2329 | 3.0 | 750 | 0.2792 | 0.897 |
0.1756 | 4.0 | 1000 | 0.3439 | 0.8925 |
0.1291 | 5.0 | 1250 | 0.3990 | 0.8905 |
0.1009 | 6.0 | 1500 | 0.3953 | 0.891 |
0.0665 | 7.0 | 1750 | 0.4638 | 0.892 |
0.0421 | 8.0 | 2000 | 0.5708 | 0.8905 |
0.0301 | 9.0 | 2250 | 0.5893 | 0.899 |
0.0196 | 10.0 | 2500 | 0.6249 | 0.8985 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.0