ac21ac7bc7df8e82e75a0e7cfd28549c

This model is a fine-tuned version of albert/albert-xlarge-v1 on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 2.6626
• Data Size: 0.5
• Epoch Runtime: 638.5780
• Accuracy: 0.0714
• F1 Macro: 0.0095
• Rouge1: 0.0714
• Rouge2: 0.0
• Rougel: 0.0714
• Rougelsum: 0.0714

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	3.0904	0	44.3345	0.0839	0.0277	0.0839	0.0	0.0839	0.0840
0.2688	1	17500	0.1340	0.0078	54.4139	0.9715	0.9716	0.9715	0.0	0.9715	0.9715
0.3356	2	35000	1.3138	0.0156	62.9870	0.5628	0.6112	0.5628	0.0	0.5628	0.5628
0.1089	3	52500	0.1204	0.0312	81.3386	0.9800	0.9800	0.9799	0.0	0.9800	0.9800
2.6616	4	70000	2.6509	0.0625	119.0870	0.0714	0.0095	0.0714	0.0	0.0714	0.0714
2.6455	5	87500	2.6419	0.125	193.9502	0.0714	0.0095	0.0714	0.0	0.0715	0.0715
2.6394	6	105000	2.6418	0.25	343.1935	0.0714	0.0095	0.0714	0.0	0.0714	0.0714
0.0153	7	122500	2.6626	0.5	638.5780	0.0714	0.0095	0.0714	0.0	0.0714	0.0714

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1