6d4194d5a1e30dd7f7e9636743761b6d

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

• Loss: 0.6836
• Data Size: 0.5
• Epoch Runtime: 915.3940
• Accuracy: 0.6320
• F1 Macro: 0.3872
• Rouge1: 0.6318
• Rouge2: 0.0
• Rougel: 0.6319
• Rougelsum: 0.6317

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	0.6672	0	53.2898	0.6325	0.3908	0.6323	0.0	0.6324	0.6323
0.6775	1	11370	0.6614	0.0078	67.4915	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6631	2	22740	0.6625	0.0156	82.6611	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.659	3	34110	0.6608	0.0312	109.5800	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6654	4	45480	0.6627	0.0625	165.3688	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6669	5	56850	0.6711	0.125	272.3387	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6602	6	68220	0.6629	0.25	488.3198	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6599	7	79590	0.6836	0.5	915.3940	0.6320	0.3872	0.6318	0.0	0.6319	0.6317

Framework versions

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