ILT37
/

distilbert-base-uncased-finetuned-cola

Text Classification

Generated from Trainer

Eval Results (legacy)

text-embeddings-inference

Model card Files Files and versions

Metrics Training metrics Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

distilbert-base-uncased-finetuned-cola

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

Loss: 0.7249
Matthews Correlation: 0.5419

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

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.526	1.0	535	0.4683	0.4681
0.3541	2.0	1070	0.5655	0.4614
0.2419	3.0	1605	0.6095	0.5215
0.1697	4.0	2140	0.7249	0.5419
0.123	5.0	2675	0.8144	0.5370

Framework versions

Transformers 4.31.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3

Downloads last month: -

Dataset used to train ILT37/distilbert-base-uncased-finetuned-cola

Evaluation results

Matthews Correlation on glue
validation set self-reported

0.542