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: 1.1409
• Accuracy: 0.7115
• F1: 0.7184

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: 5e-05
• train_batch_size: 256
• eval_batch_size: 256
• 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: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
5.0513	0.3333	226	4.6666	0.0150	0.0139
2.9839	0.6667	452	2.4637	0.2933	0.3601
2.0766	1.0	678	1.8938	0.4410	0.5005
1.5464	1.3333	904	1.6542	0.4547	0.5265
1.4301	1.6667	1130	1.4822	0.4976	0.5625
1.2864	2.0	1356	1.3587	0.4388	0.5155
0.7659	2.3333	1582	1.2553	0.5637	0.6038
0.7489	2.6667	1808	1.1776	0.5639	0.6072
0.658	3.0	2034	1.1178	0.5851	0.6249
0.3545	3.3333	2260	1.0968	0.6086	0.6372
0.3468	3.6667	2486	1.1013	0.6502	0.6693
0.3072	4.0	2712	1.0774	0.6637	0.6816
0.1741	4.3333	2938	1.1204	0.6946	0.7043
0.1531	4.6667	3164	1.1361	0.7065	0.7134
0.1556	5.0	3390	1.1409	0.7115	0.7184

Framework versions

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