distilbert_news_classifier – AI Model by HarsitM05 | AlphaNeural AI

You can deploy this model and start earning money today!

HarsitM05/
distilbert_news_classifier

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-cased

autotrain_compatible

endpoints_compatible

Views

No views yet

distilbert_news_classifier

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

Loss: 0.1191
Accuracy: 0.974

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
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: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4757	1.0	1250	0.4178	0.876
0.3574	2.0	2500	0.2445	0.928
0.2801	3.0	3750	0.2041	0.954
0.2701	4.0	5000	0.2429	0.956
0.199	5.0	6250	0.2502	0.958
0.1826	6.0	7500	0.1604	0.968
0.1469	7.0	8750	0.1278	0.972
0.0971	8.0	10000	0.1191	0.974

Framework versions

Transformers 4.48.3
Pytorch 2.7.0+cu118
Datasets 3.2.0
Tokenizers 0.21.0