bright-roo-721 – AI Model by ElMad | AlphaNeural AI

You can deploy this model and start earning money today!

ElMad/
bright-roo-721

like

0

generated_from_trainer

answerdotai/ModernBERT-base

Views

No views yet

bright-roo-721

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: 0.3285
Hamming Loss: 0.1111
Zero One Loss: 0.9888
Jaccard Score: 0.9888
Hamming Loss Optimised: 0.1064
Hamming Loss Threshold: 0.3442
Zero One Loss Optimised: 0.7812
Zero One Loss Threshold: 0.2207
Jaccard Score Optimised: 0.7600
Jaccard Score Threshold: 0.1740

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: 9.055163976709184e-05
train_batch_size: 32
eval_batch_size: 32
seed: 2024
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9193487616565937,0.8674368975945644) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Hamming Loss	Zero One Loss	Jaccard Score	Hamming Loss Optimised	Hamming Loss Threshold	Zero One Loss Optimised	Zero One Loss Threshold	Jaccard Score Optimised	Jaccard Score Threshold
No log	1.0	100	0.3464	0.1125	1.0	1.0	0.1123	0.6700	0.7987	0.2346	0.7682	0.2122
No log	2.0	200	0.3331	0.1118	0.995	0.995	0.109	0.3622	0.7825	0.2206	0.7645	0.1738
No log	3.0	300	0.3285	0.1111	0.9888	0.9888	0.1064	0.3442	0.7812	0.2207	0.7600	0.1740

Framework versions

PEFT 0.13.2
Transformers 4.48.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.21.0