bart_qa_model

smrynrz20/bart_qa_model

bart_qa_model is a question answering model from smrynrz20. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

3% of all-time downloads

All-time downloads

271

Public

Parameters

139M

3.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors558 MB · 99%

At a glance

Task: Question Answering
Library: transformers
License: apache-2.0
Model type: bart
Access: Public
Created: Jan 7, 2024
Updated: Jun 24, 2024
SHA: 905bce3f

Try a prompt

Base models

facebook/bart-base

Model card

From the Hugging Face model README

bart_qa_model

This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2074
F1: 0.7487
Exact Match: 0.612

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: 3.7185140364032e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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	F1	Exact Match
2.497	1.0	125	1.3235	0.6994	0.552
1.1709	2.0	250	1.1675	0.7374	0.601
0.8943	3.0	375	1.2074	0.7487	0.612

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Task: Question Answering
Library: transformers
Type: bart
License: apache-2.0
Created: Jan 7, 2024
Updated: Jun 24, 2024