kaporter
/

bert-base-uncased-finetuned-squad

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

bert-base-uncased-finetuned-squad

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

Loss: 1.0725

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.0749	1.0	5533	1.0167
0.7851	2.0	11066	1.0299
0.6067	3.0	16599	1.0725

Framework versions

Transformers 4.8.1
Pytorch 1.8.1
Datasets 1.16.1
Tokenizers 0.10.1

Downloads last month: 371

Inference Providers NEW

Question Answering

This model is not currently available via any of the supported Inference Providers.

Model tree for kaporter/bert-base-uncased-finetuned-squad

Finetunes

1 model

Dataset used to train kaporter/bert-base-uncased-finetuned-squad