bert-base-cased-finetuned-wnli

This model is a fine-tuned version of bert-base-cased on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6996
• Accuracy: 0.4648

The model was fine-tuned to compare google/fnet-base as introduced in this paper against bert-base-cased.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

This model is trained using the run_glue script. The following command was used:

#!/usr/bin/bash

python ../run_glue.py \\n  --model_name_or_path bert-base-cased \\n  --task_name wnli \\n  --do_train \\n  --do_eval \\n  --max_seq_length 512 \\n  --per_device_train_batch_size 16 \\n  --learning_rate 2e-5 \\n  --num_train_epochs 5 \\n  --output_dir bert-base-cased-finetuned-wnli \\n  --push_to_hub \\n  --hub_strategy all_checkpoints \\n  --logging_strategy epoch \\n  --save_strategy epoch \\n  --evaluation_strategy epoch \\n```

### 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: 5.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7299        | 1.0   | 40   | 0.6923          | 0.5634   |
| 0.6982        | 2.0   | 80   | 0.7027          | 0.3803   |
| 0.6972        | 3.0   | 120  | 0.7005          | 0.4507   |
| 0.6992        | 4.0   | 160  | 0.6977          | 0.5352   |
| 0.699         | 5.0   | 200  | 0.6996          | 0.4648   |


### Framework versions

- Transformers 4.11.0.dev0
- Pytorch 1.9.0
- Datasets 1.12.1
- Tokenizers 0.10.3