xlm-roberta-base-ibo-noaug

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

• Loss: 0.2856
• F1: 0.4680
• Roc Auc: 0.6918
• Accuracy: 0.5157

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
0.39	1.0	90	0.3806	0.0	0.5	0.2150
0.3728	2.0	180	0.3656	0.0510	0.5150	0.2422
0.3231	3.0	270	0.3226	0.1942	0.5631	0.3319
0.2991	4.0	360	0.3165	0.2341	0.5958	0.3758
0.2755	5.0	450	0.2943	0.3184	0.6272	0.4071
0.2501	6.0	540	0.2854	0.4121	0.6688	0.4718
0.2378	7.0	630	0.2813	0.4179	0.6570	0.4864
0.2215	8.0	720	0.2819	0.4211	0.6601	0.4760
0.2015	9.0	810	0.2794	0.4439	0.6769	0.5136
0.1798	10.0	900	0.2846	0.4495	0.6794	0.4990
0.1732	11.0	990	0.2885	0.4586	0.6794	0.4948
0.1613	12.0	1080	0.2856	0.4680	0.6918	0.5157
0.1561	13.0	1170	0.2907	0.4543	0.6797	0.4864
0.1427	14.0	1260	0.2920	0.4676	0.6861	0.5136
0.1304	15.0	1350	0.2990	0.4654	0.6894	0.4885
0.1257	16.0	1440	0.3001	0.4636	0.6853	0.4969

Framework versions

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