metadata

language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: sa_BERT_24_mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          config: mrpc
          split: validation
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7083333333333334
          - name: F1
            type: f1
            value: 0.8199697428139183

sa_BERT_24_mrpc

This model is a fine-tuned version of gokuls/bert_base_24 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

Loss: 0.6042
Accuracy: 0.7083
F1: 0.8200
Combined Score: 0.7642

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: 4e-05
train_batch_size: 96
eval_batch_size: 96
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
0.6437	1.0	39	0.6042	0.7083	0.8200	0.7642
0.5784	2.0	78	0.6224	0.6544	0.7403	0.6974
0.4657	3.0	117	0.7196	0.6740	0.7816	0.7278
0.3555	4.0	156	0.8929	0.6348	0.7418	0.6883
0.2516	5.0	195	1.0482	0.6078	0.6992	0.6535
0.1654	6.0	234	1.3865	0.5515	0.6131	0.5823

Framework versions

Transformers 4.30.2
Pytorch 1.14.0a0+410ce96
Datasets 2.13.0
Tokenizers 0.13.3