electra-base-italian-xxl-cased-discriminator-sentence-splitter

This model is a fine-tuned version of dbmdz/electra-base-italian-xxl-cased-discriminator on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0116
• 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	0.0064	0.9771
No log	2.0	98	0.0039	0.9861
No log	3.0	147	0.0036	0.9922
No log	4.0	196	0.0079	0.9922
No log	5.0	245	0.0103	0.9907
No log	6.0	294	0.0021	0.9922
No log	7.0	343	0.0084	0.9907
No log	8.0	392	0.0028	0.9922
No log	9.0	441	0.0040	0.9922
No log	10.0	490	0.0035	0.9922
0.018	11.0	539	0.0040	0.9922
0.018	12.0	588	0.0019	0.9938
0.018	13.0	637	0.0028	0.9922
0.018	14.0	686	0.0059	0.9922
0.018	15.0	735	0.0134	0.9922
0.018	16.0	784	0.0073	0.9938
0.018	17.0	833	0.0099	0.9938
0.018	18.0	882	0.0070	0.9938
0.018	19.0	931	0.0066	0.9922
0.018	20.0	980	0.0095	0.9938
0.0004	21.0	1029	0.0099	0.9938
0.0004	22.0	1078	0.0115	0.9938
0.0004	23.0	1127	0.0114	0.9938
0.0004	24.0	1176	0.0106	0.9938
0.0004	25.0	1225	0.0114	0.9938
0.0004	26.0	1274	0.0115	0.9938
0.0004	27.0	1323	0.0116	0.9938
0.0004	28.0	1372	0.0116	0.9938
0.0004	29.0	1421	0.0116	0.9938
0.0004	30.0	1470	0.0116	0.9938

Framework versions

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