olid_training_no_clean_3 – AI Model by iTroned | AlphaNeural AI

You can deploy this model and start earning money today!

iTroned/
olid_training_no_clean_3

like

0

generated_from_trainer

distilbert/distilbert-base-uncased

endpoints_compatible

Views

No views yet

Visualize in Weights & Biases

olid_training_no_clean_3

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

Loss: 0.4365
Accuracy Offensive: 0.8565
F1 Offensive: 0.8548
Accuracy Targeted: 0.8338
F1 Targeted: 0.8222
Accuracy Stance: 0.7885
F1 Stance: 0.7648

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: 1e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Offensive	Accuracy Targeted	F1 Targeted	Accuracy Stance	F1 Stance
No log	1.0	373	0.5307	0.7991	0.7998	0.7651	0.7511	0.7455	0.7000
0.5511	2.0	746	0.5279	0.8029	0.8012	0.7757	0.7648	0.7530	0.7305
0.4487	3.0	1119	0.5698	0.7983	0.7896	0.7689	0.7480	0.7568	0.7280
0.4487	4.0	1492	0.5597	0.8006	0.7997	0.7749	0.7673	0.7545	0.7400

Framework versions

Transformers 4.45.2
Pytorch 2.5.0+cu124
Datasets 3.0.1
Tokenizers 0.20.1