eurobert210m_Mobilite_v1

This model is a fine-tuned version of EuroBERT/EuroBERT-210m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0135
• Accuracy: 0.9942
• F1: 0.9942

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.2363	1.0	124	0.8864	0.6790	0.6323
0.588	2.0	248	0.3959	0.8901	0.8796
0.3365	3.0	372	0.1947	0.9506	0.9502
0.2177	4.0	496	0.1856	0.9549	0.9540
0.1708	5.0	620	0.1072	0.9786	0.9786
0.1455	6.0	744	0.1288	0.9713	0.9716
0.1217	7.0	868	0.0800	0.9836	0.9837
0.0986	8.0	992	0.0599	0.9874	0.9874
0.0735	9.0	1116	0.0480	0.9892	0.9892
0.0577	10.0	1240	0.0305	0.9922	0.9922
0.0619	11.0	1364	0.0475	0.9897	0.9897
0.0449	12.0	1488	0.0991	0.9816	0.9814
0.0566	13.0	1612	0.0215	0.9932	0.9932
0.0473	14.0	1736	0.0228	0.9939	0.9939
0.0344	15.0	1860	0.0336	0.9922	0.9922
0.04	16.0	1984	0.0426	0.9909	0.9909
0.0353	17.0	2108	0.0191	0.9945	0.9945
0.0448	18.0	2232	0.0193	0.9932	0.9932
0.0359	19.0	2356	0.0184	0.9942	0.9942
0.0314	20.0	2480	0.0146	0.9942	0.9942
0.0257	21.0	2604	0.0173	0.9942	0.9942
0.0208	22.0	2728	0.0144	0.9942	0.9942
0.0334	23.0	2852	0.0135	0.9942	0.9942

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0