<!-- 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. -->
distilbert-base-uncased-finetuned-moral-action
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4632
- Accuracy: 0.7912
- F1: 0.7912
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: 9.716387809233253e-05
- train_batch_size: 2000
- eval_batch_size: 2000
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 10 | 0.5406 | 0.742 | 0.7399 |
| No log | 2.0 | 20 | 0.4810 | 0.7628 | 0.7616 |
| No log | 3.0 | 30 | 0.4649 | 0.786 | 0.7856 |
| No log | 4.0 | 40 | 0.4600 | 0.7916 | 0.7916 |
| No log | 5.0 | 50 | 0.4632 | 0.7912 | 0.7912 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.1
- Datasets 2.0.0
- Tokenizers 0.11.0
