roberta_sst5_padding10model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
roberta_sst5_padding10model

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

roberta_sst5_padding10model

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

Loss: 3.7178
Accuracy: 0.5575

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
1.2481	1.0	534	1.2717	0.4719
0.9994	2.0	1068	0.9912	0.5629
0.829	3.0	1602	1.1247	0.5457
0.6975	4.0	2136	1.1001	0.5692
0.5603	5.0	2670	1.3026	0.5561
0.4561	6.0	3204	1.4568	0.5620
0.3672	7.0	3738	1.7943	0.5439
0.2788	8.0	4272	1.8506	0.5430
0.2456	9.0	4806	1.9547	0.5516
0.2136	10.0	5340	2.5049	0.5403
0.1865	11.0	5874	2.6391	0.5575
0.1575	12.0	6408	3.0275	0.5421
0.1384	13.0	6942	3.1505	0.5520
0.1218	14.0	7476	3.2313	0.5566
0.0923	15.0	8010	3.4303	0.5457
0.0734	16.0	8544	3.4973	0.5493
0.0646	17.0	9078	3.5374	0.5597
0.0533	18.0	9612	3.6683	0.5597
0.0373	19.0	10146	3.7188	0.5575
0.0356	20.0	10680	3.7178	0.5575

Framework versions

Transformers 4.32.1
Pytorch 2.1.1
Datasets 2.12.0
Tokenizers 0.13.3