bert-base-uncased-mnli
This model is a fine-tuned version of bert-base-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.4056
- Accuracy: 0.8501
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: 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 |
|---|---|---|---|---|
| 0.4526 | 1.0 | 12272 | 0.4244 | 0.8388 |
| 0.3344 | 2.0 | 24544 | 0.4252 | 0.8469 |
| 0.2307 | 3.0 | 36816 | 0.4974 | 0.8445 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 37
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-mnli
Base model
google-bert/bert-base-uncasedDataset used to train JeremiahZ/bert-base-uncased-mnli
Evaluation results
- Accuracy on GLUE MNLIself-reported0.850
- Accuracy on gluevalidation set verified0.847
- Precision Macro on gluevalidation set verified0.846
- Precision Micro on gluevalidation set verified0.847
- Precision Weighted on gluevalidation set verified0.848
- Recall Macro on gluevalidation set verified0.846
- Recall Micro on gluevalidation set verified0.847
- Recall Weighted on gluevalidation set verified0.847
- F1 Macro on gluevalidation set verified0.846
- F1 Micro on gluevalidation set verified0.847