metadata

language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: bert-base-cased-finetuned-mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8602941176470589
          - name: F1
            type: f1
            value: 0.9025641025641027

bert-base-cased-finetuned-mrpc

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

Loss: 0.7132
Accuracy: 0.8603
F1: 0.9026
Combined Score: 0.8814

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 \
  --model_name_or_path bert-base-cased \
  --task_name mrpc \
  --do_train \
  --do_eval \
  --max_seq_length 512 \
  --per_device_train_batch_size 16 \
  --learning_rate 2e-5 \
  --num_train_epochs 5 \
  --output_dir bert-base-cased-finetuned-mrpc \
  --push_to_hub \
  --hub_strategy all_checkpoints \
  --logging_strategy epoch \
  --save_strategy epoch \
  --evaluation_strategy epoch \

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	F1	Combined Score
0.5981	1.0	230	0.4580	0.7892	0.8562	0.8227
0.3739	2.0	460	0.3806	0.8480	0.8942	0.8711
0.1991	3.0	690	0.4879	0.8529	0.8958	0.8744
0.1286	4.0	920	0.6342	0.8529	0.8986	0.8758
0.0812	5.0	1150	0.7132	0.8603	0.9026	0.8814

Framework versions

Transformers 4.11.0.dev0
Pytorch 1.9.0
Datasets 1.12.1
Tokenizers 0.10.3