Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
distilbert-base-uncased-finetuned-ag_news – AI Model by TingTing0104 | AlphaNeural AI
You can deploy this model and start earning money today!
TingTing0104
/
distilbert-base-uncased-finetuned-ag_news
like
0
transformers
pytorch
tensorboard
distilbert
text-classification
generated_from_trainer
ag_news
apache-2.0
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
distilbert-base-uncased-finetuned-ag_news
This model is a fine-tuned version of
distilbert-base-uncased
on the ag_news dataset. It achieves the following results on the evaluation set:
Loss: 0.1691
Accuracy: 0.9443
F1: 0.9444
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: 2e-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: 2
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
F1
0.2253
1.0
3750
0.1749
0.9411
0.9413
0.1335
2.0
7500
0.1691
0.9443
0.9444
Framework versions
Transformers 4.16.2
Pytorch 2.1.0+cu121
Datasets 1.16.1
Tokenizers 0.15.0
