Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
tiny_bert_km_10_v1_rte – AI Model by Hartunka | AlphaNeural AI
You can deploy this model and start earning money today!
Hartunka
/
tiny_bert_km_10_v1_rte
like
0
transformers
tensorboard
safetensors
distilbert
text-classification
generated_from_trainer
en
glue
Hartunka/tiny_bert_km_10_v1
finetune
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
tiny_bert_km_10_v1_rte
This model is a fine-tuned version of
Hartunka/tiny_bert_km_10_v1
on the GLUE RTE dataset. It achieves the following results on the evaluation set:
Loss: 0.6871
Accuracy: 0.5307
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: 256
eval_batch_size: 256
seed: 10
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: 50
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.7014
1.0
10
0.6871
0.5307
0.6871
2.0
20
0.6927
0.4838
0.6715
3.0
30
0.6880
0.5487
0.654
4.0
40
0.6973
0.5307
0.6228
5.0
50
0.7095
0.5487
0.5753
6.0
60
0.7562
0.5415
Framework versions
Transformers 4.50.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.21.1
