3f7a37247639fe3f09bb3a4932372dab

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-dutch on the nyu-mll/glue [qqp] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6924
• Data Size: 1.0
• Epoch Runtime: 1796.4782
• Accuracy: 0.3680
• F1 Macro: 0.2690
• Rouge1: 0.3682
• Rouge2: 0.0
• Rougel: 0.3681
• Rougelsum: 0.3683

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.7199	0	53.7543	0.3707	0.2741	0.3708	0.0	0.3708	0.3709
0.6841	1	11370	0.7072	0.0078	67.6313	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6779	2	22740	0.6587	0.0156	81.9221	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6597	3	34110	0.6586	0.0312	109.2636	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6663	4	45480	0.6589	0.0625	163.0535	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6664	5	56850	0.6592	0.125	270.6797	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6599	6	68220	0.6579	0.25	485.1898	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6604	7	79590	0.6609	0.5	921.4053	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.651	8.0	90960	0.6797	1.0	1779.0471	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6509	9.0	102330	0.6887	1.0	1794.9813	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6528	10.0	113700	0.6924	1.0	1796.4782	0.3680	0.2690	0.3682	0.0	0.3681	0.3683

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1