README.md

metadata

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

modernbert-wine-classification

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: 0.6234
• Accuracy: 0.9414
• F1: 0.9411

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: 192
• eval_batch_size: 192
• 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
• lr_scheduler_warmup_ratio: 0.08
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.7318	0.2591	100	0.8266	0.6828	0.7221
0.8015	0.5181	200	0.5297	0.8188	0.8271
0.6969	0.7772	300	0.4705	0.8342	0.8482
0.5794	1.0363	400	0.4594	0.8686	0.8714
0.4761	1.2953	500	0.4386	0.8736	0.8777
0.4406	1.5544	600	0.4049	0.8858	0.8874
0.4279	1.8135	700	0.4328	0.8955	0.8965
0.4206	2.0725	800	0.4511	0.9006	0.9011
0.2375	2.3316	900	0.4064	0.9018	0.9034
0.1855	2.5907	1000	0.4421	0.9099	0.9109
0.1951	2.8497	1100	0.3979	0.9140	0.9150
0.1464	3.1088	1200	0.5462	0.9253	0.9253
0.0533	3.3679	1300	0.5703	0.9313	0.9314
0.0508	3.6269	1400	0.5185	0.9343	0.9342
0.0488	3.8860	1500	0.5403	0.9378	0.9375
0.0268	4.1451	1600	0.5958	0.9399	0.9396
0.007	4.4041	1700	0.5955	0.9379	0.9377
0.0052	4.6632	1800	0.6330	0.9400	0.9397
0.0049	4.9223	1900	0.6234	0.9414	0.9411

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0