xlm-roberta-base-orm-finetuned

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: 0.3548
• F1: 0.4488
• Roc Auc: 0.6931
• Accuracy: 0.5087

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
0.358	1.0	147	0.3575	0.0786	0.5225	0.3171
0.3248	2.0	294	0.3283	0.1009	0.5356	0.3641
0.3002	3.0	441	0.3139	0.1816	0.5677	0.4338
0.2758	4.0	588	0.2968	0.2087	0.5733	0.4390
0.2252	5.0	735	0.2916	0.3080	0.6210	0.4774
0.208	6.0	882	0.3036	0.3613	0.6439	0.5035
0.1856	7.0	1029	0.3072	0.4059	0.6574	0.5244
0.1731	8.0	1176	0.3202	0.4286	0.6734	0.5035
0.1529	9.0	1323	0.3290	0.4000	0.6585	0.5122
0.1251	10.0	1470	0.3258	0.4290	0.6699	0.5017
0.1321	11.0	1617	0.3239	0.4378	0.6723	0.5035
0.1206	12.0	1764	0.3433	0.4430	0.6831	0.5105
0.1014	13.0	1911	0.3508	0.4323	0.6795	0.5087
0.0975	14.0	2058	0.3548	0.4488	0.6931	0.5087
0.0753	15.0	2205	0.3533	0.4481	0.6880	0.5
0.0809	16.0	2352	0.3656	0.4427	0.6886	0.5105
0.0912	17.0	2499	0.3657	0.4369	0.6831	0.5017
0.0784	18.0	2646	0.3688	0.4435	0.6869	0.5139

Framework versions

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