roberta-base-ppaverb-500000-1e-06-128

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

• Loss: 0.6631

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: 1e-06
• train_batch_size: 512
• eval_batch_size: 1024
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
0.6859	1.0	977	0.6755
0.6792	2.0	1954	0.6704
0.6756	3.0	2931	0.6678
0.6741	4.0	3908	0.6658
0.6733	5.0	4885	0.6660
0.6721	6.0	5862	0.6645
0.6716	7.0	6839	0.6637
0.6707	8.0	7816	0.6635
0.6688	9.0	8793	0.6640
0.668	10.0	9770	0.6637
0.6669	11.0	10747	0.6630
0.6665	12.0	11724	0.6631
0.6654	13.0	12701	0.6628
0.6657	14.0	13678	0.6628
0.6643	15.0	14655	0.6633
0.6628	16.0	15632	0.6634
0.6637	17.0	16609	0.6631

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1