nli-professional-status

This model is a fine-tuned version of EuroBERT/EuroBERT-610m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5105
• Accuracy: 0.8906
• Precision Binary: 0.5169
• Recall Binary: 0.3770
• F1 Binary: 0.4360
• Precision Micro: 0.8906
• Recall Micro: 0.8906
• F1 Micro: 0.8906
• F1 Macro: 0.6877
• Pr Auc: 0.8671
• Cohen Kappa: 0.3771

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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Binary	Recall Binary	F1 Binary	Precision Micro	Recall Micro	F1 Micro	F1 Macro	Pr Auc	Cohen Kappa
0.4706	1.0	544	0.3099	0.8925	0.5472	0.2377	0.3314	0.8925	0.8925	0.8925	0.6365	0.8528	0.2827
0.3256	2.0	1088	0.4521	0.8998	0.6275	0.2623	0.3699	0.8998	0.8998	0.8998	0.6578	0.8660	0.3253
0.2073	3.0	1632	0.5105	0.8906	0.5169	0.3770	0.4360	0.8906	0.8906	0.8906	0.6877	0.8671	0.3771

Framework versions

• Transformers 4.52.2
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1