README.md

metadata

library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: modernbert-tr-classifier
    results: []

modernbert-tr-classifier

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

• Loss: 0.8739
• F1: 0.8061
• Accuracy: 0.8082

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: 8e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy
4.0021	1.0	19	1.9146	0.0636	0.1469
3.6752	2.0	38	1.7785	0.3022	0.3388
3.2521	3.0	57	1.4559	0.4311	0.4735
2.6907	4.0	76	1.1927	0.5475	0.5714
2.2003	5.0	95	0.9852	0.6614	0.6571
1.7928	6.0	114	0.8017	0.7147	0.7102
1.4909	7.0	133	0.8603	0.7070	0.7020
1.3136	8.0	152	0.6970	0.7395	0.7429
1.1483	9.0	171	0.5679	0.7774	0.7755
0.903	10.0	190	0.9122	0.7078	0.7061
0.886	11.0	209	0.6270	0.7707	0.7755
0.7609	12.0	228	0.6756	0.8038	0.8082
0.6929	13.0	247	0.5790	0.8290	0.8327
0.4927	14.0	266	0.7072	0.8067	0.8082
0.3282	15.0	285	0.6293	0.8490	0.8490
0.2706	16.0	304	0.8920	0.7867	0.7878
0.2311	17.0	323	0.7759	0.8466	0.8490
0.1268	18.0	342	0.7496	0.8324	0.8327
0.1276	18.9730	360	0.8739	0.8061	0.8082

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu118
• Datasets 3.1.0
• Tokenizers 0.21.0