24778e6b42c60af81ac4b440b07a09de

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

• Loss: 0.6840
• Data Size: 1.0
• Epoch Runtime: 1940.2411
• 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	0.7149	0	62.9061	0.3680	0.2690	0.3682	0.0	0.3681	0.3683
0.6826	1	11370	0.6832	0.0078	79.3395	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6574	2	22740	0.6660	0.0156	94.6840	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6571	3	34110	0.6703	0.0312	126.1846	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.669	4	45480	0.6654	0.0625	185.7774	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6637	5	56850	0.6593	0.125	308.7243	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.658	6	68220	0.6689	0.25	554.4712	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6633	7	79590	0.6610	0.5	1048.6980	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6516	8.0	90960	0.7359	1.0	1946.5839	0.3680	0.2690	0.3682	0.0	0.3681	0.3683
0.6523	9.0	102330	0.6840	1.0	1940.2411	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