metadata-cls_15_10 – AI Model by gechim | AlphaNeural AI

You can deploy this model and start earning money today!

gechim/
metadata-cls_15_10

like

0

text-classification

generated_from_trainer

vinai/phobert-base-v2

autotrain_compatible

endpoints_compatible

Views

No views yet

metadata-cls_15_10

This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0128
Accuracy: 0.9967
F1: 0.9932

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: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5273	1.0067	150	0.2313	0.9384	0.8468
0.2312	2.0134	300	0.1456	0.9581	0.9182
0.1542	3.0201	450	0.0944	0.9747	0.9471
0.1199	4.0268	600	0.0747	0.9810	0.9600
0.0943	5.0336	750	0.0640	0.9827	0.9608
0.0837	6.0403	900	0.0458	0.9894	0.9748
0.0645	7.0470	1050	0.0435	0.9894	0.9767
0.0509	8.0537	1200	0.0313	0.9925	0.9819
0.043	9.0604	1350	0.0242	0.9944	0.9859
0.0345	10.0671	1500	0.0196	0.9954	0.9904
0.03	11.0738	1650	0.0179	0.9956	0.9913
0.0231	12.0805	1800	0.0162	0.9958	0.9914
0.0227	13.0872	1950	0.0137	0.9966	0.9930
0.0181	14.0940	2100	0.0128	0.9967	0.9932

Framework versions

Transformers 4.45.2
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.20.1