N_bert_sst5_padding30model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
N_bert_sst5_padding30model

like

0

text-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

N_bert_sst5_padding30model

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: 4.0345
Accuracy: 0.5403

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
1.3041	1.0	534	1.1828	0.4647
0.9728	2.0	1068	1.0656	0.5439
0.7353	3.0	1602	1.2170	0.5308
0.55	4.0	2136	1.3968	0.5385
0.3809	5.0	2670	1.7587	0.5095
0.2839	6.0	3204	2.0145	0.5258
0.2109	7.0	3738	2.3047	0.5281
0.1487	8.0	4272	2.5442	0.5421
0.1456	9.0	4806	2.9466	0.5317
0.107	10.0	5340	3.1653	0.5281
0.0964	11.0	5874	3.3776	0.5276
0.0757	12.0	6408	3.4191	0.5416
0.0649	13.0	6942	3.6545	0.5308
0.0568	14.0	7476	3.6844	0.5398
0.026	15.0	8010	3.8540	0.5353
0.0258	16.0	8544	3.8938	0.5362
0.0216	17.0	9078	3.9251	0.5303
0.0122	18.0	9612	3.9695	0.5376
0.0107	19.0	10146	4.0084	0.5348
0.0108	20.0	10680	4.0345	0.5403

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3