hBERTv2_new_pretrain_48_KD_wnli

gokuls/hBERTv2_new_pretrain_48_KD_wnli

hBERTv2_new_pretrain_48_KD_wnli 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.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

208

Public

Repo size

953 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin477 MB · 100%

At a glance

Task: Text Classification
Library: transformers
Model type: hybridbert
Access: Public
Created: Jun 15, 2023
Updated: Jun 15, 2023
SHA: daba4e29

Try a prompt

Datasets

glue

Model card

From the Hugging Face model README

hBERTv2_new_pretrain_48_KD_wnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48_KD on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.6863
Accuracy: 0.5634

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: 4e-05
train_batch_size: 128
eval_batch_size: 128
seed: 10
distributed_type: multi-GPU
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
0.9584	1.0	5	0.7296	0.5634
0.7454	2.0	10	0.6897	0.5352
0.7071	3.0	15	0.7028	0.4366
0.6975	4.0	20	0.6943	0.4366
0.6981	5.0	25	0.6863	0.5634
0.7028	6.0	30	0.7001	0.4366
0.699	7.0	35	0.6905	0.5634
0.7045	8.0	40	0.6892	0.5634
0.7113	9.0	45	0.6996	0.4366
0.6966	10.0	50	0.6924	0.5634

Framework versions

Transformers 4.30.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3

Task: Text Classification
Library: transformers
Type: hybridbert
Languages: en
Created: Jun 15, 2023
Updated: Jun 15, 2023