my_awesome_qa_model

rugvedabodke/my_awesome_qa_model

my_awesome_qa_model is a question answering model from rugvedabodke. Use it when the input is a question plus a passage. It is set up for transformers.

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

Downloads · 30 days

1% of all-time downloads

All-time downloads

372

Public

Parameters

66.4M

1.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin265 MB · 50%

At a glance

Task: Question Answering
Library: transformers
Model type: distilbert
Access: Public
Created: Aug 8, 2023
Updated: Nov 29, 2023
SHA: b61a49ec

Try a prompt

Model card

From the Hugging Face model README

my_awesome_qa_model

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.0561

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	2.6419
No log	2.0	4	2.4093
No log	3.0	6	2.3048
No log	4.0	8	2.2732
No log	5.0	10	2.3026
No log	6.0	12	2.3105
No log	7.0	14	2.2481
No log	8.0	16	2.1339
No log	9.0	18	2.0817
No log	10.0	20	2.0949
No log	11.0	22	2.1169
No log	12.0	24	2.1656
No log	13.0	26	2.1781
No log	14.0	28	2.1759
No log	15.0	30	2.1443
No log	16.0	32	2.1105
No log	17.0	34	2.0871
No log	18.0	36	2.0660
No log	19.0	38	2.0585
No log	20.0	40	2.0561

Framework versions

Transformers 4.35.2
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0

Task: Question Answering
Library: transformers
Type: distilbert
Created: Aug 8, 2023
Updated: Nov 29, 2023