bert_sst5_padding40model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
bert_sst5_padding40model

like

0

text-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

bert_sst5_padding40model

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: 4.1036
Accuracy: 0.5290

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
1.3762	1.0	534	1.2877	0.4308
1.0166	2.0	1068	1.0554	0.5434
0.7789	3.0	1602	1.1840	0.5285
0.5955	4.0	2136	1.3969	0.5226
0.4112	5.0	2670	1.7375	0.5059
0.298	6.0	3204	2.0244	0.5113
0.2306	7.0	3738	2.3077	0.5122
0.171	8.0	4272	2.4897	0.5127
0.1473	9.0	4806	2.8175	0.5240
0.1223	10.0	5340	3.0553	0.5348
0.102	11.0	5874	3.3033	0.5262
0.0812	12.0	6408	3.5173	0.5199
0.0647	13.0	6942	3.7110	0.5330
0.0468	14.0	7476	3.7872	0.5299
0.0324	15.0	8010	3.9852	0.5195
0.0206	16.0	8544	4.0106	0.5285
0.0172	17.0	9078	4.0319	0.5276
0.0151	18.0	9612	4.0855	0.5308
0.0089	19.0	10146	4.0883	0.5294
0.01	20.0	10680	4.1036	0.5290

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3