metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: baseline-ft-mrpc-IRoberta-b-unquantized
    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: 0.8995098039215687
          - name: F1
            type: f1
            value: 0.9266547406082289

baseline-ft-mrpc-IRoberta-b-unquantized

This model is a fine-tuned version of kssteven/ibert-roberta-base on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

Loss: 0.5354
Accuracy: 0.8995
F1: 0.9267
Combined Score: 0.9131

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
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
0.1212	1.0	230	0.3401	0.8799	0.9136	0.8967
0.0347	2.0	460	0.3085	0.8676	0.9059	0.8868
0.0495	3.0	690	0.3552	0.8848	0.9174	0.9011
0.0024	4.0	920	0.4960	0.8824	0.9158	0.8991
0.0046	5.0	1150	0.5354	0.8995	0.9267	0.9131

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.11.0
Tokenizers 0.13.3