You can deploy this model and start earning money today!

nimeshkanishka/
distilbert-toxic-comment-classifier

Name: distilbert-toxic-comment-classifier
Availability: InStock

Views

No views yet

distilbert-toxic-comment-classifier

This model is a fine-tuned version of distilbert/distilbert-base-uncased on a simplified version of the jigsaw-toxic-comment-classification-challenge dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Accuracy
0.1985	1.0	500	0.1628	0.0007	0.9365
0.093	2.0	1000	0.2337	0.0007	0.9305
0.0391	3.0	1500	0.2844	0.0007	0.9407
0.0106	4.0	2000	0.3741	0.0007	0.938
0.0036	5.0	2500	0.3995	0.0007	0.9395