<!-- 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-training-cola
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2215
- Matthews Correlation: 0.8777
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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 | Matthews Correlation |
---|---|---|---|---|
No log | 1.0 | 113 | 0.2954 | 0.7090 |
No log | 2.0 | 226 | 0.2212 | 0.8232 |
No log | 3.0 | 339 | 0.1899 | 0.8671 |
No log | 4.0 | 452 | 0.2006 | 0.8672 |
0.19 | 5.0 | 565 | 0.2215 | 0.8777 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.8.0+cu111
- Datasets 2.1.0
- Tokenizers 0.11.6