9fef5c63c33210ec80921422795f2b2e

This model is a fine-tuned version of FacebookAI/roberta-large on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 2.6440
• Data Size: 0.25
• Epoch Runtime: 692.4468
• Accuracy: 0.0714
• F1 Macro: 0.0095
• Rouge1: 0.0714
• Rouge2: 0.0
• Rougel: 0.0714
• Rougelsum: 0.0715

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	2.6831	0	90.3737	0.0714	0.0095	0.0714	0.0	0.0715	0.0715
0.1197	1	17500	0.1218	0.0078	109.3356	0.9754	0.9755	0.9755	0.0	0.9754	0.9754
0.0899	2	35000	0.1032	0.0156	128.4563	0.9816	0.9816	0.9816	0.0	0.9815	0.9816
0.1161	3	52500	0.1165	0.0312	167.2515	0.9824	0.9825	0.9824	0.0	0.9824	0.9824
0.1348	4	70000	0.1064	0.0625	241.5921	0.9815	0.9816	0.9815	0.0	0.9815	0.9815
0.1269	5	87500	0.1153	0.125	392.9796	0.9818	0.9818	0.9818	0.0	0.9818	0.9818
2.6527	6	105000	2.6440	0.25	692.4468	0.0714	0.0095	0.0714	0.0	0.0714	0.0715

Framework versions

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