metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: baseline-ft-mrpc-IRoberta-b-8bit
    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: 0.8970588235294118
          - name: F1
            type: f1
            value: 0.9257950530035336

baseline-ft-mrpc-IRoberta-b-8bit

This model is a fine-tuned version of vuiseng9/baseline-ft-mrpc-IRoberta-b-unquantized on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

Loss: 0.3871
Accuracy: 0.8971
F1: 0.9258
Combined Score: 0.9114

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: 5e-07
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: 12.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
0.0021	1.0	230	0.4017	0.8848	0.9147	0.8998
0.0026	2.0	460	0.4105	0.8873	0.9173	0.9023
0.0026	3.0	690	0.3707	0.8946	0.9236	0.9091
0.0037	4.0	920	0.3893	0.8946	0.9228	0.9087
1.324	5.0	1150	0.3871	0.8897	0.9204	0.9050
0.0227	6.0	1380	0.3951	0.8897	0.9201	0.9049
0.0081	7.0	1610	0.3818	0.8824	0.9155	0.8989
0.0054	8.0	1840	0.3902	0.8873	0.9181	0.9027
0.0383	9.0	2070	0.3659	0.8922	0.9225	0.9073
0.3861	10.0	2300	0.4260	0.8652	0.9030	0.8841
0.0028	11.0	2530	0.3619	0.8946	0.9234	0.9090
0.0957	12.0	2760	0.3871	0.8971	0.9258	0.9114

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.11.0
Tokenizers 0.13.3