valuable-squid-615 – AI Model by ElMad | AlphaNeural AI

You can deploy this model and start earning money today!

ElMad/
valuable-squid-615

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

valuable-squid-615

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

Loss: 0.1886
Hamming Loss: 0.0605
Zero One Loss: 0.4675
Jaccard Score: 0.4289
Hamming Loss Optimised: 0.0596
Hamming Loss Threshold: 0.5113
Zero One Loss Optimised: 0.4363
Zero One Loss Threshold: 0.4054
Jaccard Score Optimised: 0.3606
Jaccard Score Threshold: 0.3059

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: 2.6795250522175907e-05
train_batch_size: 32
eval_batch_size: 32
seed: 2024
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
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	0.2485	0.0774	0.6475	0.6308	0.0767	0.4029	0.5813	0.2602	0.5165	0.2275
No log	2.0	200	0.2005	0.0606	0.5	0.4601	0.0617	0.5541	0.4613	0.4187	0.3756	0.2803
No log	3.0	300	0.1886	0.0605	0.4675	0.4289	0.0596	0.5113	0.4363	0.4054	0.3606	0.3059

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.21.0