Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
safechat-distilroberta-toxic-v1 – AI Model by Tewodros-Berhane | AlphaNeural AI
You can deploy this model and start earning money today!
Tewodros-Berhane
/
safechat-distilroberta-toxic-v1
like
0
transformers
safetensors
roberta
text-classification
generated_from_trainer
distilbert/distilroberta-base
finetune
apache-2.0
text-embeddings-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
safechat-distilroberta-toxic-v1
This model is a fine-tuned version of
distilroberta-base
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.1067
Accuracy: 0.9645
F1: 0.6346
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-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use 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: 2
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
F1
0.1098
1.0
112805
0.1188
0.9633
0.6387
0.112
2.0
225610
0.1067
0.9645
0.6346
Framework versions
Transformers 4.57.3
Pytorch 2.5.1+cu121
Datasets 4.4.1
Tokenizers 0.22.1
