CS221-xlm-roberta-base-orm-finetuned-finetuned-orm-tapt

This model is a fine-tuned version of Kuongan/xlm-roberta-base-orm-finetuned on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1585
• F1: 0.7761
• Roc Auc: 0.8594
• Accuracy: 0.8023

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.1357	1.0	226	0.1244	0.6851	0.8156	0.7894
0.1306	2.0	452	0.1244	0.6946	0.8366	0.8001
0.1151	3.0	678	0.1231	0.7179	0.8454	0.8087
0.1002	4.0	904	0.1351	0.7313	0.8424	0.7930
0.0801	5.0	1130	0.1574	0.7465	0.8632	0.7701
0.0784	6.0	1356	0.1402	0.7424	0.8525	0.7822
0.0731	7.0	1582	0.1521	0.7605	0.8529	0.7808
0.0547	8.0	1808	0.1619	0.7545	0.8614	0.7758
0.0375	9.0	2034	0.1509	0.7680	0.8729	0.7872
0.0314	10.0	2260	0.1711	0.7521	0.8667	0.7815
0.0313	11.0	2486	0.1585	0.7761	0.8594	0.8023
0.0242	12.0	2712	0.1686	0.7635	0.8732	0.7915
0.0194	13.0	2938	0.1706	0.7644	0.8690	0.7973
0.0167	14.0	3164	0.1669	0.7623	0.8659	0.7915

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0