bert-tiny-sst2-KD-BERT

gokuls/bert-tiny-sst2-KD-BERT

bert-tiny-sst2-KD-BERT is a text classification model from gokuls. Use it when you need a label for a piece of text. 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

2% of all-time downloads

All-time downloads

444

Public

Repo size

123 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin17.6 MB · 95%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Sep 24, 2022
Updated: Sep 24, 2022
SHA: 654f25db

Try a prompt

Datasets

glue

Model card

From the Hugging Face model README

bert-tiny-sst2-KD-BERT

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set:

Loss: 0.8257
Accuracy: 0.8349

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: 33
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7521	1.0	4210	0.7345	0.8234
0.4301	2.0	8420	0.7748	0.8303
0.3335	3.0	12630	0.8257	0.8349
0.2831	4.0	16840	0.9145	0.8188
0.2419	5.0	21050	0.9096	0.8177
0.2149	6.0	25260	0.8410	0.8234

Framework versions

Transformers 4.22.1
Pytorch 1.12.1+cu113
Datasets 2.5.1
Tokenizers 0.12.1

Task: Text Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Sep 24, 2022
Updated: Sep 24, 2022