README.md

metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
model-index:
  - name: roberta-base-finetuned-cola-hps
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0.4499152516617143

roberta-base-finetuned-cola-hps

This model is a fine-tuned version of roberta-base on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 1.4407
• Matthews Correlation: 0.4499

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: 3.1634762591825634e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 35
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
No log	1.0	107	0.5371	0.4037
No log	2.0	214	0.8207	0.3212
No log	3.0	321	1.1269	0.4613
No log	4.0	428	1.2901	0.4852
0.341	5.0	535	1.4407	0.4499

Framework versions

• Transformers 4.16.2
• Pytorch 2.2.1+cu121
• Datasets 1.16.1
• Tokenizers 0.19.1