N_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: 1.5812
• Accuracy: 0.2308

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
1.5764	1.0	534	1.5927	0.2308
1.5738	2.0	1068	1.5804	0.2308
1.5736	3.0	1602	1.5860	0.2308
1.569	4.0	2136	1.5789	0.2308
1.5736	5.0	2670	1.5774	0.2864
1.5737	6.0	3204	1.5839	0.2308
1.5726	7.0	3738	1.5786	0.2308
1.5707	8.0	4272	1.5790	0.2308
1.5699	9.0	4806	1.5811	0.2308
1.5687	10.0	5340	1.5829	0.2308
1.5725	11.0	5874	1.5800	0.2308
1.5713	12.0	6408	1.5815	0.2308
1.5684	13.0	6942	1.5822	0.2308
1.5716	14.0	7476	1.5816	0.2308
1.5696	15.0	8010	1.5827	0.2308
1.5684	16.0	8544	1.5818	0.2308
1.5687	17.0	9078	1.5812	0.2308
1.5706	18.0	9612	1.5813	0.2308
1.5698	19.0	10146	1.5816	0.2308
1.5693	20.0	10680	1.5812	0.2308

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3