moe_True_addTokens_False_clipLoss_True_cv_2

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

• Loss: 0.6525
• Model Preparation Time: 0.005
• F1: 0.0169
• Precision: 0.0093
• Recall: 0.0942
• Threshold: 0.9726
• Sim Ratio: 1.7929
• Pos Sim: 0.8971
• Neg Sim: 0.5003

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	F1	Precision	Recall	Threshold	Sim Ratio	Pos Sim	Neg Sim
0.6766	0.8	5000	0.6910	0.005	0.0172	0.0094	0.1027	0.9741	1.7595	0.9042	0.5139

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1
• Datasets 3.2.0
• Tokenizers 0.21.0