bert_uncased_L-4_H-512_A-8_emotion
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2079
- Accuracy: 0.9365
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 |
|---|---|---|---|---|
| 0.7234 | 1.0 | 250 | 0.2573 | 0.9145 |
| 0.2068 | 2.0 | 500 | 0.1762 | 0.924 |
| 0.1373 | 3.0 | 750 | 0.1689 | 0.9285 |
| 0.1018 | 4.0 | 1000 | 0.1626 | 0.9335 |
| 0.0857 | 5.0 | 1250 | 0.1740 | 0.932 |
| 0.0688 | 6.0 | 1500 | 0.1763 | 0.93 |
| 0.0543 | 7.0 | 1750 | 0.1850 | 0.9315 |
| 0.0434 | 8.0 | 2000 | 0.2079 | 0.9365 |
| 0.0352 | 9.0 | 2250 | 0.2148 | 0.9345 |
| 0.0334 | 10.0 | 2500 | 0.2220 | 0.9365 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1