roberta_sst2_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: 0.5439
• Accuracy: 0.9401

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	0.2015	0.9308
0.3269	2.0	866	0.3417	0.9083
0.1879	3.0	1299	0.2749	0.9357
0.109	4.0	1732	0.4100	0.9357
0.0667	5.0	2165	0.4702	0.9253
0.0426	6.0	2598	0.4966	0.9325
0.0255	7.0	3031	0.4133	0.9357
0.0255	8.0	3464	0.4515	0.9429
0.0222	9.0	3897	0.4046	0.9445
0.0278	10.0	4330	0.5288	0.9357
0.0119	11.0	4763	0.5001	0.9385
0.0085	12.0	5196	0.5208	0.9374
0.0138	13.0	5629	0.5213	0.9368
0.0097	14.0	6062	0.5023	0.9407
0.0097	15.0	6495	0.5428	0.9319
0.0111	16.0	6928	0.5067	0.9407
0.0041	17.0	7361	0.5007	0.9440
0.0053	18.0	7794	0.5224	0.9396
0.0009	19.0	8227	0.5436	0.9407
0.0019	20.0	8660	0.5439	0.9401

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.1
• Datasets 2.12.0
• Tokenizers 0.13.3