roberta_sst2_padding90model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
roberta_sst2_padding90model

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

roberta_sst2_padding90model

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5344
Accuracy: 0.9445

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	0.2083	0.9171
0.3231	2.0	866	0.2668	0.9308
0.1721	3.0	1299	0.3085	0.9303
0.1148	4.0	1732	0.2910	0.9363
0.0679	5.0	2165	0.4164	0.9325
0.0424	6.0	2598	0.3419	0.9489
0.0292	7.0	3031	0.4437	0.9418
0.0292	8.0	3464	0.6145	0.9171
0.023	9.0	3897	0.4383	0.9456
0.0181	10.0	4330	0.4449	0.9462
0.0102	11.0	4763	0.6482	0.9270
0.0131	12.0	5196	0.4929	0.9418
0.0053	13.0	5629	0.4902	0.9473
0.0065	14.0	6062	0.4971	0.9434
0.0065	15.0	6495	0.5722	0.9385
0.0071	16.0	6928	0.5055	0.9445
0.0057	17.0	7361	0.5643	0.9418
0.0033	18.0	7794	0.5291	0.9412
0.0053	19.0	8227	0.5127	0.9473
0.0006	20.0	8660	0.5344	0.9445

Framework versions

Transformers 4.32.1
Pytorch 2.1.1
Datasets 2.12.0
Tokenizers 0.13.3