N_bert_sst5_padding70model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
N_bert_sst5_padding70model

like

0

text-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

N_bert_sst5_padding70model

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: 4.0548
Accuracy: 0.5240

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
1.3824	1.0	534	1.2185	0.4285
1.0502	2.0	1068	1.0713	0.5290
0.8207	3.0	1602	1.1478	0.5362
0.6396	4.0	2136	1.3321	0.5330
0.4658	5.0	2670	1.5674	0.5253
0.3315	6.0	3204	1.8728	0.5213
0.2523	7.0	3738	2.1015	0.5258
0.1802	8.0	4272	2.4265	0.5258
0.138	9.0	4806	2.6894	0.5158
0.1264	10.0	5340	3.0058	0.5140
0.1016	11.0	5874	3.2348	0.5186
0.0715	12.0	6408	3.4892	0.5122
0.0589	13.0	6942	3.5974	0.5244
0.0538	14.0	7476	3.7534	0.5240
0.029	15.0	8010	3.8630	0.5154
0.0231	16.0	8544	3.8886	0.5290
0.0215	17.0	9078	4.0295	0.5131
0.0181	18.0	9612	4.0194	0.5226
0.0128	19.0	10146	4.0560	0.5204
0.0102	20.0	10680	4.0548	0.5240

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3