nilu_baseline_full_dataset – AI Model by iTroned | AlphaNeural AI

You can deploy this model and start earning money today!

iTroned/
nilu_baseline_full_dataset

like

0

generated_from_trainer

google-bert/bert-base-uncased

endpoints_compatible

Views

No views yet

Visualize in Weights & Biases

nilu_baseline_full_dataset

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4677
Accuracy Offensive: 0.8407
F1 Macro Offensive: 0.8097
F1 Weighted Offensive: 0.8436

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-06
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: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Macro Offensive	F1 Weighted Offensive
0.5387	1.0	3310	0.4077	0.8488	0.8003	0.8438
0.5014	2.0	6620	0.4677	0.8407	0.8097	0.8436
0.492	3.0	9930	0.6760	0.8465	0.7947	0.8403
0.3449	4.0	13240	0.7868	0.8267	0.7935	0.8301
0.263	5.0	16550	0.9527	0.8372	0.7899	0.8340
0.1987	6.0	19860	1.1646	0.8186	0.7811	0.8211

Framework versions

Transformers 4.50.2
Pytorch 2.6.0+cu124
Datasets 3.0.1
Tokenizers 0.21.1