HBERTv1_48_L6_H512_A8_emotion

gokuls/HBERTv1_48_L6_H512_A8_emotion

HBERTv1_48_L6_H512_A8_emotion 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

20% of all-time downloads

All-time downloads

Public

Repo size

600 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin150 MB · 99%

At a glance

Task: Text Classification
Library: transformers
Model type: hybridbert
Access: Public
Created: Oct 4, 2023
Updated: Oct 4, 2023
SHA: 019d6fd1

Try a prompt

Base models

gokuls/HBERTv1_48_L6_H512_A8

Datasets

emotion

Model card

From the Hugging Face model README

HBERTv1_48_L6_H512_A8_emotion

This model is a fine-tuned version of gokuls/HBERTv1_48_L6_H512_A8 on the emotion dataset. It achieves the following results on the evaluation set:

Loss: 0.4151
Accuracy: 0.894

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: 64
eval_batch_size: 64
seed: 33
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8919	1.0	250	0.4536	0.859
0.3635	2.0	500	0.3559	0.874
0.2506	3.0	750	0.3147	0.891
0.1866	4.0	1000	0.3472	0.885
0.1458	5.0	1250	0.3454	0.8905
0.1173	6.0	1500	0.3782	0.8855
0.0851	7.0	1750	0.4151	0.894
0.063	8.0	2000	0.4729	0.8895
0.0469	9.0	2250	0.5102	0.891
0.0368	10.0	2500	0.5250	0.89

Framework versions

Transformers 4.34.0
Pytorch 1.14.0a0+410ce96
Datasets 2.14.5
Tokenizers 0.14.0

Task: Text Classification
Library: transformers
Type: hybridbert
Created: Oct 4, 2023
Updated: Oct 4, 2023