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: 1.2880
• F1: 0.8888
• Accuracy: 0.8898

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: 32
• eval_batch_size: 32
• seed: 42
• 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
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy
1.3439	1.0	146	0.7811	0.7564	0.7510
0.5346	2.0	292	0.5727	0.8162	0.8163
0.2959	3.0	438	0.5732	0.8061	0.8082
0.1828	4.0	584	0.5832	0.8494	0.8490
0.1113	5.0	730	0.8149	0.8564	0.8571
0.0811	6.0	876	0.9747	0.8366	0.8367
0.0427	7.0	1022	1.0021	0.8812	0.8816
0.0493	8.0	1168	1.0971	0.8614	0.8612
0.0494	9.0	1314	1.3082	0.8454	0.8449
0.0205	10.0	1460	1.2811	0.8588	0.8571
0.0079	11.0	1606	1.2820	0.8534	0.8531
0.0214	12.0	1752	1.0864	0.8622	0.8612
0.0113	13.0	1898	1.0554	0.8853	0.8857
0.005	14.0	2044	1.3213	0.8784	0.8776
0.0023	15.0	2190	1.2395	0.8734	0.8735
0.0007	16.0	2336	1.3468	0.8870	0.8857
0.0006	17.0	2482	1.3490	0.8813	0.8816
0.0007	18.0	2628	1.2886	0.8888	0.8898
0.0004	19.0	2774	1.2850	0.8888	0.8898
0.0003	20.0	2920	1.2880	0.8888	0.8898

Framework versions

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