distilbert-go-emotions
This model is a fine-tuned version of distilbert-base-uncased on the go_emotions dataset. It achieves the following results on the evaluation set:
- Loss: 0.0907
- Accuracy: 0.4287
- Precision: 0.4504
- Recall: 0.5003
- F1: 0.4702
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 340 | 0.1102 | 0.4125 | 0.2946 | 0.2139 | 0.2014 |
| 0.1347 | 2.0 | 680 | 0.0890 | 0.3900 | 0.4252 | 0.4627 | 0.4262 |
| 0.1347 | 3.0 | 1020 | 0.0860 | 0.4097 | 0.4344 | 0.4992 | 0.4578 |
| 0.0771 | 4.0 | 1360 | 0.0864 | 0.4298 | 0.4561 | 0.4974 | 0.4701 |
| 0.0771 | 5.0 | 1700 | 0.0891 | 0.4266 | 0.4522 | 0.4992 | 0.4703 |
| 0.0617 | 6.0 | 2040 | 0.0907 | 0.4287 | 0.4504 | 0.5003 | 0.4702 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0
- Datasets 2.1.0
- Tokenizers 0.12.1