35ca03bbb1349f57adee654ef11e1e74

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-english on the fancyzhx/dbpedia_14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1961
• Data Size: 0.125
• Epoch Runtime: 420.4894
• Accuracy: 0.9688
• F1 Macro: 0.9687
• Rouge1: 0.9688
• Rouge2: 0.0
• Rougel: 0.9688
• Rougelsum: 0.9688

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	2.6275	0	91.8639	0.0617	0.0249	0.0617	0.0	0.0617	0.0616
0.2213	1	17500	0.1156	0.0078	114.7160	0.9735	0.9734	0.9735	0.0	0.9735	0.9735
0.1299	2	35000	0.1663	0.0156	134.2341	0.9670	0.9671	0.9670	0.0	0.9670	0.9670
0.1229	3	52500	0.1240	0.0312	174.8644	0.9781	0.9780	0.9781	0.0	0.9781	0.9781
0.1547	4	70000	0.1629	0.0625	256.3406	0.9733	0.9733	0.9734	0.0	0.9733	0.9733
0.1681	5	87500	0.1961	0.125	420.4894	0.9688	0.9687	0.9688	0.0	0.9688	0.9688

Framework versions

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