hBERTv2_new_pretrain_w_init_48_qnli

gokuls/hBERTv2_new_pretrain_w_init_48_qnli

hBERTv2_new_pretrain_w_init_48_qnli 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

5% of all-time downloads

All-time downloads

214

Public

Repo size

3.8 GB

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 6, 2023
Updated: Jun 6, 2023
SHA: 55b7f624

Try a prompt

Datasets

glue

Model card

From the Hugging Face model README

hBERTv2_new_pretrain_w_init_48_qnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.4725
Accuracy: 0.7867

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
0.6735	1.0	819	0.6754	0.5689
0.6251	2.0	1638	0.5403	0.7346
0.4993	3.0	2457	0.4725	0.7867
0.4195	4.0	3276	0.5245	0.7681
0.3542	5.0	4095	0.5522	0.7569
0.2952	6.0	4914	0.5402	0.7785
0.2422	7.0	5733	0.6739	0.7578
0.2024	8.0	6552	0.5727	0.7851

Framework versions

Transformers 4.29.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3

Task: Text Classification
Library: transformers
Type: hybridbert
Languages: en
Created: Jun 6, 2023
Updated: Jun 6, 2023