tiny_bert_rand_100_v1_qnli

Hartunka/tiny_bert_rand_100_v1_qnli

tiny_bert_rand_100_v1_qnli is a machine learning model from Hartunka. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

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

Downloads · 30 days

47% of all-time downloads

All-time downloads

Public

Parameters

33M

791 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors132 MB · 99%

At a glance

Model type: distilbert
Access: Public
Created: Apr 16, 2025
Updated: Apr 16, 2025
SHA: 14047e9a

Base models

Hartunka/tiny_bert_rand_100_v1

Datasets

glue

Model card

From the Hugging Face model README

tiny_bert_rand_100_v1_qnli

This model is a fine-tuned version of Hartunka/tiny_bert_rand_100_v1 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.6503
Accuracy: 0.6193

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: 256
eval_batch_size: 256
seed: 10
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6657	1.0	410	0.6503	0.6193
0.6367	2.0	820	0.6539	0.6213
0.5927	3.0	1230	0.6680	0.6129
0.531	4.0	1640	0.7184	0.6116
0.4631	5.0	2050	0.8040	0.6059
0.3972	6.0	2460	0.9131	0.6070

Framework versions

Transformers 4.40.0
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.19.1

Type: distilbert
Languages: en
Created: Apr 16, 2025
Updated: Apr 16, 2025