AGnews_DistilledBERT_baseline – AI Model by perfectsquare123 | AlphaNeural AI

You can deploy this model and start earning money today!

perfectsquare123/
AGnews_DistilledBERT_baseline

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

AGnews_DistilledBERT_baseline

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: 0.2038

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: 32
eval_batch_size: 64
seed: 42
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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.182	1.0	3750	0.1699
0.0927	2.0	7500	0.1696
0.0608	3.0	11250	0.2038

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0