small-vanilla-target-glue-cola-linear-probe
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6097
- Matthews Correlation: 0.0
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: 3e-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: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6185 | 1.87 | 500 | 0.6137 | 0.0 |
| 0.6093 | 3.73 | 1000 | 0.6125 | 0.0 |
| 0.6073 | 5.6 | 1500 | 0.6100 | 0.0 |
| 0.6052 | 7.46 | 2000 | 0.6097 | 0.0 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2