Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bert_base_km_50_v2_wnli – AI Model by Hartunka | AlphaNeural AI
You can deploy this model and start earning money today!
Hartunka
/
bert_base_km_50_v2_wnli
like
0
transformers
tensorboard
safetensors
distilbert
text-classification
generated_from_trainer
en
glue
Hartunka/bert_base_km_50_v2
finetune
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bert_base_km_50_v2_wnli
This model is a fine-tuned version of
Hartunka/bert_base_km_50_v2
on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
Loss: 0.7401
Accuracy: 0.3239
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
0.7427
1.0
3
0.7401
0.3239
0.7038
2.0
6
0.7573
0.3099
0.6955
3.0
9
0.7738
0.2394
0.6899
4.0
12
0.7935
0.3521
0.6767
5.0
15
0.8292
0.1408
0.6828
6.0
18
0.8703
0.2113
Framework versions
Transformers 4.50.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.21.1
