bert-base-uncased-finetuned-glue_wnli
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: 0.7030
- Accuracy: 0.3521
- F1: 0.2934
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 40 | 0.6921 | 0.5070 | 0.3791 |
No log | 2.0 | 80 | 0.6956 | 0.4789 | 0.3649 |
No log | 3.0 | 120 | 0.7030 | 0.3521 | 0.2934 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 15
Finetuned from
Dataset used to train nickapch/bert-base-uncased-finetuned-glue_wnli
Evaluation results
- Accuracy on gluevalidation set self-reported0.352
- F1 on gluevalidation set self-reported0.293