da143fb2eb162f6cb510b31a625e2de5

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

• Loss: 2.6451
• Data Size: 0.25
• Epoch Runtime: 786.6545
• Accuracy: 0.0714
• F1 Macro: 0.0095
• Rouge1: 0.0714
• Rouge2: 0.0
• Rougel: 0.0715
• 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	2.6653	0	91.9549	0.0710	0.0099	0.0711	0.0	0.0711	0.0711
0.2051	1	17500	0.2182	0.0078	112.2171	0.9505	0.9508	0.9505	0.0	0.9505	0.9505
0.1523	2	35000	0.0972	0.0156	133.2370	0.9808	0.9808	0.9808	0.0	0.9808	0.9808
0.1441	3	52500	0.1003	0.0312	176.6600	0.9818	0.9818	0.9819	0.0	0.9819	0.9818
0.1435	4	70000	1.1946	0.0625	256.1582	0.6707	0.6442	0.6708	0.0	0.6706	0.6707
2.6545	5	87500	2.6551	0.125	431.1323	0.0714	0.0095	0.0714	0.0	0.0715	0.0715
2.6525	6	105000	2.6451	0.25	786.6545	0.0714	0.0095	0.0714	0.0	0.0715	0.0715

Framework versions

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