bert-base-uncased-finetuned-cola-batch-2
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.3833
- Matthews Correlation: 0.5725
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: 2
- eval_batch_size: 2
- seed: 42
- 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 | Matthews Correlation |
---|---|---|---|---|
0.8292 | 1.0 | 4276 | 0.8945 | 0.5153 |
0.5519 | 2.0 | 8552 | 1.0523 | 0.5019 |
0.4064 | 3.0 | 12828 | 1.1277 | 0.5356 |
0.2463 | 4.0 | 17104 | 1.3046 | 0.5248 |
0.1523 | 5.0 | 21380 | 1.4914 | 0.5094 |
0.0697 | 6.0 | 25656 | 1.4854 | 0.5574 |
0.0894 | 7.0 | 29932 | 1.3833 | 0.5725 |
0.0375 | 8.0 | 34208 | 1.5318 | 0.5670 |
0.0297 | 9.0 | 38484 | 1.8043 | 0.5550 |
0.0105 | 10.0 | 42760 | 1.8241 | 0.5565 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 13
Dataset used to train cansurav/bert-base-uncased-finetuned-cola-batch-2
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.573