roberta_sst2_padding100model – AI Model by Realgon | AlphaNeural AI | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
roberta_sst2_padding100model

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

roberta_sst2_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: 0.4756
Accuracy: 0.9467

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	0.1945	0.9193
0.347	2.0	866	0.4578	0.9121
0.2005	3.0	1299	0.2934	0.9319
0.1211	4.0	1732	0.3157	0.9407
0.0719	5.0	2165	0.3519	0.9396
0.0425	6.0	2598	0.3947	0.9379
0.028	7.0	3031	0.5409	0.9275
0.028	8.0	3464	0.5252	0.9275
0.0204	9.0	3897	0.4965	0.9341
0.03	10.0	4330	0.4417	0.9401
0.0189	11.0	4763	0.3982	0.9429
0.0146	12.0	5196	0.4508	0.9429
0.0075	13.0	5629	0.4806	0.9407
0.0106	14.0	6062	0.4549	0.9456
0.0106	15.0	6495	0.4606	0.9478
0.0072	16.0	6928	0.5123	0.9407
0.0071	17.0	7361	0.4453	0.9500
0.0017	18.0	7794	0.5241	0.9440
0.0023	19.0	8227	0.4587	0.9473
0.0017	20.0	8660	0.4756	0.9467

Framework versions

Transformers 4.32.1
Pytorch 2.1.1
Datasets 2.12.0
Tokenizers 0.13.3