modernbert-20m-sentences-combined-fixed

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

• Loss: 0.2021
• Accuracy: 0.9189
• F1: 0.9188
• Precision: 0.9191
• Recall: 0.9189
• F1 Class 0: 0.9213
• Precision Class 0: 0.9105
• Recall Class 0: 0.9323
• F1 Class 1: 0.9163
• Precision Class 1: 0.9280
• Recall Class 1: 0.9050

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: 1e-05
• train_batch_size: 1000
• eval_batch_size: 1000
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8000
• total_eval_batch_size: 8000
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	F1 Class 0	Precision Class 0	Recall Class 0	F1 Class 1	Precision Class 1	Recall Class 1
1.707	1.0	2739	0.2117	0.9149	0.9149	0.9149	0.9149	0.9162	0.9180	0.9145	0.9134	0.9117	0.9152
1.5938	2.0	5478	0.2021	0.9189	0.9188	0.9191	0.9189	0.9213	0.9105	0.9323	0.9163	0.9280	0.9050

Framework versions

• Transformers 4.54.1
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4