Sam4rano/nollysenti_xlm-roberta-base

results_xlm-roberta-base

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: 0.4399
• Accuracy: 0.8756
• F1: 0.8765
• Precision: 0.8834
• Recall: 0.8698
• Pred Classes: 2
• Label Classes: 2

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Pred Classes	Label Classes
0.6438	0.3546	100	0.5945	0.7294	0.71	0.7802	0.6514	2	2
0.5518	0.7092	200	0.5143	0.8009	0.8101	0.7867	0.8349	2	2
0.4907	1.0638	300	0.5096	0.8212	0.8034	0.9109	0.7187	2	2
0.4859	1.4184	400	0.4616	0.8476	0.8429	0.8855	0.8043	2	2
0.4554	1.7730	500	0.4339	0.8569	0.8526	0.8956	0.8135	2	2
0.434	2.1277	600	0.4736	0.8367	0.8205	0.9302	0.7339	2	2
0.4016	2.4823	700	0.4366	0.8663	0.8622	0.9057	0.8226	2	2
0.3876	2.8369	800	0.4126	0.8740	0.8674	0.9331	0.8104	2	2
0.345	3.1915	900	0.4329	0.8709	0.8752	0.8609	0.8899	2	2
0.3355	3.5461	1000	0.3980	0.8834	0.8830	0.9013	0.8654	2	2
0.3526	3.9007	1100	0.4057	0.8802	0.8764	0.9223	0.8349	2	2

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0