1d8c4c14908782235aa07b0d2ba44ea0

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

• Loss: 0.4909
• Data Size: 1.0
• Epoch Runtime: 1910.5884
• Accuracy: 0.9059
• F1 Macro: 0.8837
• Rouge1: 0.9059
• Rouge2: 0.0
• Rougel: 0.9059
• Rougelsum: 0.9060

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	3.3533	0	64.7177	0.0554	0.0185	0.0553	0.0	0.0554	0.0554
0.1305	1	17500	0.0835	0.0078	78.9267	0.9858	0.9858	0.9858	0.0	0.9858	0.9858
0.0783	2	35000	0.0715	0.0156	93.2574	0.9866	0.9865	0.9866	0.0	0.9866	0.9866
0.0396	3	52500	0.0643	0.0312	122.0541	0.9865	0.9865	0.9865	0.0	0.9865	0.9865
0.0671	4	70000	0.0613	0.0625	179.6137	0.9855	0.9855	0.9855	0.0	0.9855	0.9855
0.0481	5	87500	0.0603	0.125	294.6314	0.9862	0.9862	0.9862	0.0	0.9862	0.9862
0.0987	6	105000	0.0552	0.25	524.6220	0.9870	0.9870	0.9870	0.0	0.9870	0.9870
0.0019	7	122500	0.2291	0.5	985.8954	0.9362	0.9317	0.9363	0.0	0.9363	0.9362
0.1947	8.0	140000	0.1725	1.0	1905.6505	0.9744	0.9744	0.9744	0.0	0.9744	0.9744
0.1094	9.0	157500	0.1205	1.0	1906.6377	0.9825	0.9825	0.9826	0.0	0.9825	0.9826
0.1944	10.0	175000	0.4909	1.0	1910.5884	0.9059	0.8837	0.9059	0.0	0.9059	0.9060

Framework versions

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