RobertaLr3.024030044726418e-06Wd0.004218621374361941E20

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: 0.2435

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: 3.024030044726418e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.0186	1.0	510	0.6067
1.0125	2.0	1020	0.4395
0.1619	3.0	1530	0.3656
0.2597	4.0	2040	0.3204
0.006	5.0	2550	0.2991
0.0046	6.0	3060	0.2798
0.0456	7.0	3570	0.2706
0.0833	8.0	4080	0.2442
0.0061	9.0	4590	0.2366
0.0636	10.0	5100	0.2461
0.4491	11.0	5610	0.2436
0.0047	12.0	6120	0.2466
0.3552	13.0	6630	0.2422
0.0023	14.0	7140	0.2441
0.0001	15.0	7650	0.2419
0.0007	16.0	8160	0.2595
0.001	17.0	8670	0.2407
0.0383	18.0	9180	0.2411
0.002	19.0	9690	0.2433
0.0114	20.0	10200	0.2435

Framework versions

• Transformers 4.41.2
• Pytorch 2.5.1
• Datasets 2.19.1
• Tokenizers 0.19.1