Edit model card

bert-base-cased-finetuned-qnli

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

  • Loss: 0.3986
  • Accuracy: 0.9099

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 qnli \\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 3 \\n  --output_dir bert-base-cased-finetuned-qnli \\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: 3.0

### Training results

| Training Loss | Epoch | Step  | Accuracy | Validation Loss |
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
| 0.337         | 1.0   | 6547  | 0.9013   | 0.2448          |
| 0.1971        | 2.0   | 13094 | 0.9143   | 0.2839          |
| 0.1175        | 3.0   | 19641 | 0.9099   | 0.3986          |


### Framework versions

- Transformers 4.11.0.dev0
- Pytorch 1.9.0
- Datasets 1.12.1
- Tokenizers 0.10.3
Downloads last month
1,315
Inference Examples
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.

Dataset used to train gchhablani/bert-base-cased-finetuned-qnli

Evaluation results