d15ba461e14101827753cffa5c13783a

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

• Loss: 0.6952
• Data Size: 0.5
• Epoch Runtime: 7.4697
• Accuracy: 0.3594
• F1 Macro: 0.3318
• Rouge1: 0.3594
• Rouge2: 0.0
• Rougel: 0.3594
• Rougelsum: 0.3594

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	0.7093	0	0.6691	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	1	19	0.7757	0.0078	1.1886	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
No log	2	38	0.6889	0.0156	1.8996	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
No log	3	57	0.6873	0.0312	3.0235	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
No log	4	76	0.6938	0.0625	4.1049	0.4844	0.3915	0.4844	0.0	0.4844	0.4844
No log	5	95	0.6889	0.125	5.0355	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
0.081	6	114	0.6974	0.25	6.5158	0.4688	0.4603	0.4688	0.0	0.4688	0.4688
0.081	7	133	0.6952	0.5	7.4697	0.3594	0.3318	0.3594	0.0	0.3594	0.3594

Framework versions

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