9bf9ddc254c9b36090eda65071e5518e

This model is a fine-tuned version of google-bert/bert-base-uncased on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5435
• Data Size: 1.0
• Epoch Runtime: 847.3748
• Accuracy: 0.8641
• F1 Macro: 0.8444
• Rouge1: 0.8642
• Rouge2: 0.0
• Rougel: 0.8642
• Rougelsum: 0.8642

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	2.6998	0	29.8279	0.0478	0.0297	0.0478	0.0	0.0479	0.0478
0.1754	1	17500	0.0732	0.0078	36.2888	0.9871	0.9871	0.9871	0.0	0.9871	0.9871
0.056	2	35000	0.0636	0.0156	41.8011	0.9870	0.9870	0.9870	0.0	0.9870	0.9870
0.0399	3	52500	0.0633	0.0312	54.3729	0.9874	0.9874	0.9874	0.0	0.9874	0.9874
0.05	4	70000	0.0632	0.0625	78.7061	0.9868	0.9868	0.9868	0.0	0.9868	0.9868
0.0583	5	87500	0.0642	0.125	135.1392	0.9877	0.9877	0.9878	0.0	0.9877	0.9878
0.0461	6	105000	0.0696	0.25	229.4951	0.9861	0.9861	0.9861	0.0	0.9861	0.9861
0.0004	7	122500	0.0495	0.5	428.1039	0.9887	0.9887	0.9887	0.0	0.9887	0.9887
0.0372	8.0	140000	0.0480	1.0	830.1501	0.9906	0.9906	0.9906	0.0	0.9906	0.9906
0.0247	9.0	157500	0.0694	1.0	829.1238	0.9892	0.9893	0.9893	0.0	0.9892	0.9893
0.0261	10.0	175000	0.0742	1.0	831.0987	0.9885	0.9885	0.9885	0.0	0.9885	0.9885
0.0441	11.0	192500	0.2382	1.0	835.1891	0.8949	0.8817	0.8950	0.0	0.8950	0.8949
0.0474	12.0	210000	0.5435	1.0	847.3748	0.8641	0.8444	0.8642	0.0	0.8642	0.8642

Framework versions

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