63de38cd5e6c69b5eecdc94a0a4d74ad

This model is a fine-tuned version of studio-ousia/mluke-large on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 2.9776
• Data Size: 1.0
• Epoch Runtime: 2951.5125
• Accuracy: 0.0714
• F1 Macro: 0.0095
• Rouge1: 0.0714
• Rouge2: 0.0
• Rougel: 0.0715
• Rougelsum: 0.0715

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	2.6378	0	101.8170	0.0804	0.0297	0.0804	0.0	0.0803	0.0804
0.3408	1	17500	0.0951	0.0078	124.8267	0.9803	0.9802	0.9803	0.0	0.9803	0.9803
0.0722	2	35000	0.0990	0.0156	147.9930	0.9841	0.9841	0.9841	0.0	0.9841	0.9841
0.0903	3	52500	0.1333	0.0312	194.6177	0.9786	0.9786	0.9786	0.0	0.9786	0.9786
0.1075	4	70000	0.0787	0.0625	282.4741	0.9848	0.9848	0.9848	0.0	0.9848	0.9848
0.0432	5	87500	0.0730	0.125	463.4988	0.9863	0.9863	0.9863	0.0	0.9863	0.9863
0.2837	6	105000	0.0767	0.25	828.8068	0.9855	0.9855	0.9856	0.0	0.9855	0.9855
0.015	7	122500	2.8810	0.5	1552.2375	0.0714	0.0095	0.0714	0.0	0.0715	0.0715
2.6262	8.0	140000	2.8861	1.0	3013.4107	0.0714	0.0095	0.0714	0.0	0.0715	0.0715
2.6198	9.0	157500	2.9776	1.0	2951.5125	0.0714	0.0095	0.0714	0.0	0.0715	0.0715

Framework versions

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