JazibEijaz
/

bert-base-uncased-finetuned-swag-e1-b16-l5e5

Multiple Choice

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

bert-base-uncased-finetuned-swag-e1-b16-l5e5

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

Loss: 0.5202
Accuracy: 0.7997

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-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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.701	1.0	4597	0.5202	0.7997

Framework versions

Transformers 4.12.2
Pytorch 1.9.1
Datasets 1.12.1
Tokenizers 0.10.3

Downloads last month: 18

Inference Providers NEW

Multiple Choice

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train JazibEijaz/bert-base-uncased-finetuned-swag-e1-b16-l5e5