200d7925e828b953950b343704e3853b

This model is a fine-tuned version of Qwen/Qwen2.5-7B on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3536
• Data Size: 1.0
• Epoch Runtime: 15740.8193
• Accuracy: 0.9874
• F1 Macro: 0.9874
• Rouge1: 0.9874
• Rouge2: 0.0
• Rougel: 0.9874
• Rougelsum: 0.9874

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	45.5454	0	256.5897	0.0633	0.0352	0.0633	0.0	0.0633	0.0632
1.8023	1	17500	3.4176	0.0078	381.9670	0.8897	0.8958	0.8896	0.0	0.8896	0.8896
0.7961	2	35000	1.1612	0.0156	499.5849	0.9497	0.9504	0.9497	0.0	0.9498	0.9497
0.6936	3	52500	0.6629	0.0312	752.2167	0.9664	0.9664	0.9664	0.0	0.9663	0.9664
0.7796	4	70000	0.5469	0.0625	1224.2531	0.9710	0.9710	0.9710	0.0	0.9710	0.9710
0.419	5	87500	0.6000	0.125	2195.2986	0.9760	0.9760	0.9761	0.0	0.9760	0.9761
0.3693	6	105000	0.3344	0.25	4131.0681	0.9854	0.9854	0.9854	0.0	0.9854	0.9854
0.0017	7	122500	0.3028	0.5	7990.3075	0.9848	0.9848	0.9848	0.0	0.9848	0.9848
0.1104	8.0	140000	0.2665	1.0	15730.7727	0.9888	0.9888	0.9888	0.0	0.9888	0.9888
0.0517	9.0	157500	0.2891	1.0	15711.7084	0.9882	0.9882	0.9882	0.0	0.9882	0.9882
0.0421	10.0	175000	0.2867	1.0	15831.5157	0.9884	0.9884	0.9884	0.0	0.9884	0.9884
0.1499	11.0	192500	0.3411	1.0	15734.7999	0.9880	0.9880	0.9880	0.0	0.9880	0.9880
0.0354	12.0	210000	0.3536	1.0	15740.8193	0.9874	0.9874	0.9874	0.0	0.9874	0.9874

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1