roberta_sst5_padding100model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
roberta_sst5_padding100model

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

roberta_sst5_padding100model

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

Loss: 3.8534
Accuracy: 0.5548

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
1.3058	1.0	534	1.2845	0.4588
1.0163	2.0	1068	1.0163	0.5629
0.8465	3.0	1602	1.0217	0.5688
0.7225	4.0	2136	1.1287	0.5738
0.5728	5.0	2670	1.2625	0.5538
0.4591	6.0	3204	1.5232	0.5534
0.3448	7.0	3738	1.6822	0.5534
0.2719	8.0	4272	1.9461	0.5561
0.2199	9.0	4806	2.2640	0.5493
0.1999	10.0	5340	2.7206	0.5357
0.1675	11.0	5874	2.7918	0.5412
0.1516	12.0	6408	3.0557	0.5480
0.1378	13.0	6942	3.3166	0.5579
0.1	14.0	7476	3.5216	0.5557
0.08	15.0	8010	3.5134	0.5498
0.079	16.0	8544	3.5634	0.5561
0.0585	17.0	9078	3.6683	0.5597
0.0467	18.0	9612	3.7607	0.5588
0.0381	19.0	10146	3.8188	0.5570
0.0227	20.0	10680	3.8534	0.5548

Framework versions

Transformers 4.32.1
Pytorch 2.1.1
Datasets 2.12.0
Tokenizers 0.13.3