RobertaLr4e-6Wd0.02

This model is a fine-tuned version of deepset/roberta-base-squad2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5157

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: 4e-06
• 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: 12

Training results

Training Loss	Epoch	Step	Validation Loss
1.4964	1.0	72	1.0927
1.0103	2.0	144	0.7867
0.692	3.0	216	0.7018
0.9064	4.0	288	0.5812
0.372	5.0	360	0.5688
0.0685	6.0	432	0.5499
0.2826	7.0	504	0.5483
0.5693	8.0	576	0.5524
0.0256	9.0	648	0.5061
0.3215	10.0	720	0.5095
0.0493	11.0	792	0.5184
0.1331	12.0	864	0.5157

Framework versions

• Transformers 4.41.2
• Pytorch 2.4.0
• Datasets 2.20.0
• Tokenizers 0.19.1