d54424a6456fb2d42d7c2b450684a002

This model is a fine-tuned version of google-bert/bert-large-cased-whole-word-masking-finetuned-squad on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 2.6462
• Data Size: 1.0
• Epoch Runtime: 1630.3083
• Accuracy: 0.0712
• F1 Macro: 0.0095
• Rouge1: 0.0712
• Rouge2: 0.0
• Rougel: 0.0712
• Rougelsum: 0.0712

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	2.7533	0	52.7593	0.0714	0.0095	0.0714	0.0	0.0715	0.0715
0.1274	1	17500	0.0839	0.0078	66.0586	0.9843	0.9843	0.9843	0.0	0.9842	0.9843
0.0709	2	35000	0.1048	0.0156	77.9998	0.9808	0.9808	0.9808	0.0	0.9808	0.9808
0.0896	3	52500	0.0950	0.0312	103.3439	0.9811	0.9810	0.9811	0.0	0.9811	0.9810
0.0762	4	70000	0.0681	0.0625	152.0249	0.9875	0.9875	0.9875	0.0	0.9875	0.9875
0.1085	5	87500	0.0867	0.125	249.9684	0.9846	0.9846	0.9846	0.0	0.9846	0.9846
0.2668	6	105000	0.2009	0.25	449.8807	0.9401	0.9368	0.9402	0.0	0.9402	0.9401
0.0152	7	122500	2.6473	0.5	840.7175	0.0714	0.0095	0.0714	0.0	0.0714	0.0714
2.6546	8.0	140000	2.6462	1.0	1630.3083	0.0712	0.0095	0.0712	0.0	0.0712	0.0712

Framework versions

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