generated_from_trainer fnet-bert-base-comparison

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

bert-base-cased-finetuned-sst2

This model is a fine-tuned version of bert-base-cased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

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 sst2 \\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-sst2 \\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 |
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
| 0.233         | 1.0   | 4210  | 0.9174   | 0.2841          |
| 0.1261        | 2.0   | 8420  | 0.9278   | 0.3310          |
| 0.0768        | 3.0   | 12630 | 0.9232   | 0.3649          |


### Framework versions

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