ModernBERT-base-ita-sentence-splitter

This model is a fine-tuned version of DeepMount00/ModernBERT-base-ita on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0080
• F1: 0.9938

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: 8
• eval_batch_size: 8
• 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
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	49	0.0152	0.9798
No log	2.0	98	0.0115	0.9770
No log	3.0	147	0.0105	0.9681
No log	4.0	196	0.0055	0.9800
No log	5.0	245	0.0052	0.9891
No log	6.0	294	0.0077	0.9922
No log	7.0	343	0.0104	0.9876
No log	8.0	392	0.0074	0.9922
No log	9.0	441	0.0074	0.9907
No log	10.0	490	0.0068	0.9938
0.0121	11.0	539	0.0068	0.9938
0.0121	12.0	588	0.0072	0.9938
0.0121	13.0	637	0.0073	0.9938
0.0121	14.0	686	0.0073	0.9938
0.0121	15.0	735	0.0075	0.9938
0.0121	16.0	784	0.0076	0.9938
0.0121	17.0	833	0.0077	0.9938
0.0121	18.0	882	0.0077	0.9938
0.0121	19.0	931	0.0077	0.9938
0.0121	20.0	980	0.0077	0.9938
0.0	21.0	1029	0.0079	0.9938
0.0	22.0	1078	0.0079	0.9938
0.0	23.0	1127	0.0079	0.9938
0.0	24.0	1176	0.0079	0.9938
0.0	25.0	1225	0.0080	0.9938
0.0	26.0	1274	0.0080	0.9938
0.0	27.0	1323	0.0080	0.9938
0.0	28.0	1372	0.0080	0.9938
0.0	29.0	1421	0.0080	0.9938
0.0	30.0	1470	0.0080	0.9938

Framework versions

• Transformers 4.55.2
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.4