roberta-base-pp-1000000-1e-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: 0.6606

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
0.679	1.0	1954	0.6700
0.676	2.0	3908	0.6643
0.6728	3.0	5862	0.6632
0.6722	4.0	7816	0.6622
0.67	5.0	9770	0.6610
0.6691	6.0	11724	0.6608
0.6681	7.0	13678	0.6606
0.6663	8.0	15632	0.6602
0.6654	9.0	17586	0.6603
0.6646	10.0	19540	0.6599
0.6649	11.0	21494	0.6598
0.6637	12.0	23448	0.6605
0.6632	13.0	25402	0.6603
0.6623	14.0	27356	0.6606

Framework versions

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