Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
hBERTv2_new_pretrain_w_init__rte – AI Model by gokuls | AlphaNeural AI
You can deploy this model and start earning money today!
gokuls
/
hBERTv2_new_pretrain_w_init__rte
like
0
transformers
pytorch
tensorboard
hybridbert
text-classification
generated_from_trainer
en
glue
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
hBERTv2_new_pretrain_w_init__rte
This model is a fine-tuned version of
gokuls/bert_12_layer_model_v2_complete_training_new_wt_init
on the GLUE RTE dataset. It achieves the following results on the evaluation set:
Loss: 0.6913
Accuracy: 0.5523
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: 4e-05
train_batch_size: 128
eval_batch_size: 128
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.7456
1.0
20
0.6913
0.5523
0.7047
2.0
40
0.7129
0.5271
0.6813
3.0
60
0.7151
0.5307
0.6329
4.0
80
0.7451
0.5235
0.5965
5.0
100
0.7838
0.5307
0.5075
6.0
120
0.8684
0.5487
Framework versions
Transformers 4.29.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3
