N_bert_sst5_padding50model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
N_bert_sst5_padding50model

like

0

text-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

N_bert_sst5_padding50model

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: 4.1996
Accuracy: 0.5235

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
1.2757	1.0	534	1.2110	0.4475
0.9639	2.0	1068	1.0763	0.5271
0.7328	3.0	1602	1.1846	0.5394
0.5616	4.0	2136	1.4174	0.5199
0.3928	5.0	2670	1.7241	0.5217
0.2749	6.0	3204	2.0680	0.5086
0.2026	7.0	3738	2.3354	0.5
0.1556	8.0	4272	2.6114	0.5172
0.136	9.0	4806	2.8987	0.5172
0.1098	10.0	5340	3.1150	0.5271
0.0908	11.0	5874	3.3866	0.5339
0.0759	12.0	6408	3.5879	0.5262
0.0461	13.0	6942	3.7997	0.5376
0.043	14.0	7476	3.9415	0.5208
0.0313	15.0	8010	3.9936	0.5249
0.0206	16.0	8544	4.0512	0.5240
0.0202	17.0	9078	4.1304	0.5267
0.0131	18.0	9612	4.1558	0.5281
0.0114	19.0	10146	4.1741	0.5249
0.0092	20.0	10680	4.1996	0.5235

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3