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_quality_reviews_ft
    results: []

ModernBERT_wine_quality_reviews_ft

This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6800
Accuracy: 0.6953
F1: 0.6945

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.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_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.2688	0.0590	250	1.1315	0.4781	0.4463
1.0574	0.1181	500	0.9664	0.5575	0.5412
0.9229	0.1771	750	0.8647	0.6070	0.6007
0.8654	0.2361	1000	0.8665	0.6089	0.5922
0.8229	0.2952	1250	0.7857	0.6448	0.6448
0.8054	0.3542	1500	0.8515	0.6218	0.5993
0.786	0.4132	1750	0.7533	0.6601	0.6552
0.781	0.4723	2000	0.8133	0.6305	0.6278
0.7563	0.5313	2250	0.7770	0.6480	0.6473
0.7638	0.5903	2500	0.7248	0.6767	0.6769
0.7384	0.6494	2750	0.7520	0.6597	0.6574
0.7405	0.7084	3000	0.7615	0.6545	0.6515
0.7222	0.7674	3250	0.7191	0.6790	0.6716
0.7184	0.8264	3500	0.7037	0.6862	0.6837
0.6984	0.8855	3750	0.7264	0.6716	0.6678
0.6995	0.9445	4000	0.7455	0.6663	0.6646
0.713	1.0035	4250	0.7294	0.6752	0.6701
0.6508	1.0626	4500	0.6938	0.6872	0.6871
0.642	1.1216	4750	0.7266	0.6716	0.6691
0.635	1.1806	5000	0.6868	0.6913	0.6900
0.6278	1.2397	5250	0.6800	0.6953	0.6945

Framework versions

Transformers 4.48.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0