bert_uncased_L-10_H-128_A-2_emotion
This model is a fine-tuned version of google/bert_uncased_L-10_H-128_A-2 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2359
- Accuracy: 0.925
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 |
|---|---|---|---|---|
| 1.3594 | 1.0 | 250 | 1.0308 | 0.6695 |
| 0.8225 | 2.0 | 500 | 0.5984 | 0.865 |
| 0.5265 | 3.0 | 750 | 0.4195 | 0.9035 |
| 0.3839 | 4.0 | 1000 | 0.3446 | 0.9155 |
| 0.3104 | 5.0 | 1250 | 0.2972 | 0.9185 |
| 0.2594 | 6.0 | 1500 | 0.2710 | 0.9145 |
| 0.2267 | 7.0 | 1750 | 0.2511 | 0.9215 |
| 0.2099 | 8.0 | 2000 | 0.2459 | 0.9215 |
| 0.1942 | 9.0 | 2250 | 0.2359 | 0.925 |
| 0.1849 | 10.0 | 2500 | 0.2338 | 0.9235 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1