bert_sst2_padding0model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
bert_sst2_padding0model

like

0

text-classification

generated_from_trainer

google-bert/bert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

bert_sst2_padding0model

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: 0.7626
Accuracy: 0.9160

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
No log	1.0	433	0.2204	0.9116
0.3073	2.0	866	0.2837	0.9105
0.1486	3.0	1299	0.3761	0.9165
0.0614	4.0	1732	0.4230	0.9259
0.0267	5.0	2165	0.7280	0.8962
0.0123	6.0	2598	0.5046	0.9215
0.0107	7.0	3031	0.6166	0.9182
0.0107	8.0	3464	0.6515	0.9149
0.0126	9.0	3897	0.5875	0.9182
0.0092	10.0	4330	0.7368	0.9110
0.009	11.0	4763	0.6714	0.9072
0.0104	12.0	5196	0.5756	0.9193
0.0076	13.0	5629	0.6955	0.9099
0.0034	14.0	6062	0.6715	0.9182
0.0034	15.0	6495	0.7194	0.9209
0.0005	16.0	6928	0.7723	0.9154
0.0031	17.0	7361	0.7843	0.9121
0.0016	18.0	7794	0.7563	0.9176
0.0	19.0	8227	0.7569	0.9198
0.0016	20.0	8660	0.7626	0.9160

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3