9f87a81ddabfcb2678fa1fc682149cb7

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

• Loss: 0.0860
• Data Size: 1.0
• Epoch Runtime: 896.7964
• Accuracy: 0.9864
• F1 Macro: 0.9864
• Rouge1: 0.9865
• Rouge2: 0.0
• Rougel: 0.9864
• Rougelsum: 0.9864

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	2.6421	0	30.0875	0.0592	0.0268	0.0592	0.0	0.0593	0.0593
0.1465	1	17500	0.0837	0.0078	36.8623	0.9849	0.9849	0.9849	0.0	0.9849	0.9849
0.0911	2	35000	0.0905	0.0156	43.6860	0.9825	0.9825	0.9825	0.0	0.9825	0.9825
0.0578	3	52500	0.0916	0.0312	57.2460	0.9833	0.9833	0.9834	0.0	0.9833	0.9833
0.0893	4	70000	0.0682	0.0625	85.7469	0.9868	0.9868	0.9868	0.0	0.9868	0.9868
0.0555	5	87500	0.0795	0.125	138.0981	0.9851	0.9851	0.9852	0.0	0.9851	0.9851
0.1027	6	105000	0.0844	0.25	252.0205	0.9854	0.9854	0.9854	0.0	0.9854	0.9854
0.0005	7	122500	0.0841	0.5	467.4738	0.9864	0.9864	0.9864	0.0	0.9864	0.9864
0.0786	8.0	140000	0.0860	1.0	896.7964	0.9864	0.9864	0.9865	0.0	0.9864	0.9864

Framework versions

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