e65d04a15dc1f3b4a05c99c4a9031f13

This model is a fine-tuned version of openai-community/gpt2 on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0544
• Data Size: 1.0
• Epoch Runtime: 1235.1415
• Accuracy: 0.9913
• F1 Macro: 0.9913
• Rouge1: 0.9914
• Rouge2: 0.0
• Rougel: 0.9914
• Rougelsum: 0.9914

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	8.0053	0	57.5130	0.0730	0.0128	0.0729	0.0	0.0729	0.0730
0.168	1	17500	0.1390	0.0078	67.2352	0.9669	0.9663	0.9669	0.0	0.9669	0.9669
0.0846	2	35000	0.0933	0.0156	75.8686	0.9799	0.9799	0.9799	0.0	0.9799	0.9799
0.0252	3	52500	0.0827	0.0312	94.0026	0.9831	0.9830	0.9831	0.0	0.9831	0.9831
0.0632	4	70000	0.0700	0.0625	130.7640	0.9848	0.9848	0.9848	0.0	0.9848	0.9848
0.0453	5	87500	0.0515	0.125	209.3457	0.9891	0.9891	0.9891	0.0	0.9891	0.9891
0.0529	6	105000	0.0429	0.25	367.3666	0.9898	0.9898	0.9898	0.0	0.9898	0.9898
0.0002	7	122500	0.0413	0.5	669.7772	0.9899	0.9899	0.9899	0.0	0.9899	0.9899
0.031	8.0	140000	0.0354	1.0	1247.4283	0.9914	0.9914	0.9914	0.0	0.9914	0.9914
0.01	9.0	157500	0.0389	1.0	1242.6175	0.9912	0.9912	0.9912	0.0	0.9912	0.9912
0.0121	10.0	175000	0.0422	1.0	1255.6531	0.9911	0.9911	0.9911	0.0	0.9911	0.9911
0.0125	11.0	192500	0.0493	1.0	1246.6888	0.9915	0.9915	0.9916	0.0	0.9916	0.9916
0.004	12.0	210000	0.0544	1.0	1235.1415	0.9913	0.9913	0.9914	0.0	0.9914	0.9914

Framework versions

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