Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
tiny-bert-sst2-distilled – AI Model by VincentWei1021 | AlphaNeural AI
You can deploy this model and start earning money today!
VincentWei1021
/
tiny-bert-sst2-distilled
like
0
transformers
pytorch
bert
text-classification
generated_from_trainer
glue
apache-2.0
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
tiny-bert-sst2-distilled
This model is a fine-tuned version of
google/bert_uncased_L-2_H-128_A-2
on the glue dataset. It achieves the following results on the evaluation set:
Loss: 1.7317
Accuracy: 0.8406
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: 0.0006313076279512913
train_batch_size: 1024
eval_batch_size: 1024
seed: 33
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
2.208
1.0
66
1.7965
0.8165
0.9055
2.0
132
1.7602
0.8291
0.6567
3.0
198
1.6973
0.8360
0.5417
4.0
264
1.7317
0.8406
Framework versions
Transformers 4.12.3
Pytorch 1.9.1
Datasets 1.15.1
Tokenizers 0.10.3
