N_bert_sst5_padding90model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
N_bert_sst5_padding90model

like

0

text-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

N_bert_sst5_padding90model

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 4.0980
Accuracy: 0.5281

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2963	1.0	534	1.1852	0.4683
0.9784	2.0	1068	1.0766	0.5353
0.752	3.0	1602	1.2790	0.5122
0.5814	4.0	2136	1.3846	0.5303
0.3912	5.0	2670	1.7390	0.5190
0.2841	6.0	3204	1.9218	0.5262
0.2248	7.0	3738	2.2241	0.5367
0.1707	8.0	4272	2.4928	0.5213
0.145	9.0	4806	2.8856	0.5244
0.1225	10.0	5340	3.1488	0.5172
0.0936	11.0	5874	3.2905	0.5326
0.0813	12.0	6408	3.4763	0.5231
0.0595	13.0	6942	3.6704	0.5344
0.0508	14.0	7476	3.8187	0.5281
0.0352	15.0	8010	3.8860	0.5303
0.0226	16.0	8544	4.0547	0.5222
0.0189	17.0	9078	3.9931	0.5312
0.0164	18.0	9612	4.0533	0.5330
0.0133	19.0	10146	4.0536	0.5353
0.0126	20.0	10680	4.0980	0.5281

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3