roberta_sst5_padding70model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
roberta_sst5_padding70model

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

roberta_sst5_padding70model

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

Loss: 3.5077
Accuracy: 0.5462

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
1.3088	1.0	534	1.2556	0.4167
1.0332	2.0	1068	1.0037	0.5593
0.8699	3.0	1602	1.0976	0.5466
0.7538	4.0	2136	1.1056	0.5602
0.6132	5.0	2670	1.2243	0.5561
0.5149	6.0	3204	1.4017	0.5475
0.4092	7.0	3738	1.6807	0.5439
0.3229	8.0	4272	1.6478	0.5525
0.296	9.0	4806	1.9343	0.5516
0.2412	10.0	5340	1.9477	0.5389
0.231	11.0	5874	2.4445	0.5561
0.2151	12.0	6408	2.6489	0.5566
0.1803	13.0	6942	2.9230	0.5507
0.1543	14.0	7476	3.0641	0.5502
0.1257	15.0	8010	3.1964	0.5516
0.1008	16.0	8544	3.2186	0.5548
0.0865	17.0	9078	3.3259	0.5475
0.065	18.0	9612	3.4088	0.5525
0.067	19.0	10146	3.4669	0.5443
0.0549	20.0	10680	3.5077	0.5462

Framework versions

Transformers 4.32.1
Pytorch 2.1.1
Datasets 2.12.0
Tokenizers 0.13.3