modernbert-match-user-52407 – AI Model by matiashoyl | AlphaNeural AI

You can deploy this model and start earning money today!

matiashoyl/
modernbert-match-user-52407

like

0

text-classification

generated_from_trainer

answerdotai/ModernBERT-base

autotrain_compatible

endpoints_compatible

Views

No views yet

modernbert-match-user-52407

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: 1.5029
Accuracy: 0.5133
F1: 0.4132
Precision: 0.4815
Recall: 0.5133
F1 Class 0: 0.0667
F1 Class 1: 0.08
F1 Class 2: 0.25
F1 Class 3: 0.1176
F1 Class 4: 0.6961

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: 4
eval_batch_size: 4
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: cosine_with_restarts
lr_scheduler_warmup_steps: 150
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	F1 Class 0	F1 Class 1	F1 Class 2	F1 Class 3	F1 Class 4
1.3029	1.0	150	1.2976	0.5067	0.3408	0.2567	0.5067	0.0	0.0	0.0	0.0	0.6726
1.2027	2.0	300	1.2794	0.5733	0.4624	0.3875	0.5733	0.4262	0.0	0.0	0.0	0.7725
1.1452	3.0	450	1.4829	0.5267	0.4081	0.3738	0.5267	0.2703	0.0	0.0952	0.0	0.6952
1.0579	4.0	600	1.5029	0.5133	0.4132	0.4815	0.5133	0.0667	0.08	0.25	0.1176	0.6961

Framework versions

Transformers 4.49.0
Pytorch 2.6.0
Datasets 2.21.0
Tokenizers 0.21.0