<!-- 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. -->
bert_uncased_L-8_H-128_A-2_emotion
This model is a fine-tuned version of google/bert_uncased_L-8_H-128_A-2 on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.2616
- Accuracy: 0.92
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 |
|---|---|---|---|---|
| 1.3829 | 1.0 | 250 | 1.0766 | 0.7075 |
| 0.9024 | 2.0 | 500 | 0.6960 | 0.802 |
| 0.6215 | 3.0 | 750 | 0.4793 | 0.8815 |
| 0.4581 | 4.0 | 1000 | 0.3860 | 0.897 |
| 0.3724 | 5.0 | 1250 | 0.3324 | 0.917 |
| 0.3179 | 6.0 | 1500 | 0.3069 | 0.9175 |
| 0.2772 | 7.0 | 1750 | 0.2867 | 0.9155 |
| 0.2549 | 8.0 | 2000 | 0.2756 | 0.9175 |
| 0.238 | 9.0 | 2250 | 0.2667 | 0.9195 |
| 0.2305 | 10.0 | 2500 | 0.2616 | 0.92 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
