roberta-case-clean-25

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1783
• Accuracy: 0.88

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: 224
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	44	0.7612	0.8867
No log	2.0	88	1.0991	0.8667
No log	3.0	132	1.0580	0.8867
No log	4.0	176	1.4624	0.8533
No log	5.0	220	1.1583	0.88
No log	6.0	264	1.1773	0.88
No log	7.0	308	1.1942	0.8733
No log	8.0	352	1.2109	0.8733
No log	9.0	396	1.2206	0.88
No log	10.0	440	1.3737	0.8667
No log	11.0	484	1.0994	0.8733
0.0093	12.0	528	1.2048	0.88
0.0093	13.0	572	1.1263	0.8733
0.0093	14.0	616	1.1459	0.88
0.0093	15.0	660	1.1525	0.88
0.0093	16.0	704	1.1575	0.88
0.0093	17.0	748	1.1619	0.88
0.0093	18.0	792	1.1657	0.88
0.0093	19.0	836	1.1688	0.88
0.0093	20.0	880	1.1717	0.88
0.0093	21.0	924	1.1738	0.88
0.0093	22.0	968	1.1758	0.88
0.0034	23.0	1012	1.1772	0.88
0.0034	24.0	1056	1.1780	0.88
0.0034	25.0	1100	1.1783	0.88

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0