bert-base-uncased-rte
This model is a fine-tuned version of bert-base-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6972
- Accuracy: 0.6895
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 156 | 0.6537 | 0.6318 |
| No log | 2.0 | 312 | 0.6383 | 0.6534 |
| No log | 3.0 | 468 | 0.6972 | 0.6895 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 232
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for JeremiahZ/bert-base-uncased-rte
Base model
google-bert/bert-base-uncasedDataset used to train JeremiahZ/bert-base-uncased-rte
Evaluation results
- Accuracy on GLUE RTEself-reported0.690
- Accuracy on gluevalidation set verified0.682
- Precision on gluevalidation set verified0.705
- Recall on gluevalidation set verified0.565
- AUC on gluevalidation set verified0.739
- F1 on gluevalidation set verified0.627
- loss on gluevalidation set verified0.700