Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
review_classification_bert_base_jp_v3_ratio1_1_2label_add_dropout-epoch6_v4 – AI Model by kt220 | AlphaNeural AI
You can deploy this model and start earning money today!
kt220
/
review_classification_bert_base_jp_v3_ratio1_1_2label_add_dropout-epoch6_v4
like
0
transformers
tensorboard
safetensors
bert
text-classification
generated_from_trainer
tohoku-nlp/bert-base-japanese-v3
finetune
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
review_classification_bert_base_jp_v3_ratio1_1_2label_add_dropout-epoch6_v4
This model is a fine-tuned version of
cl-tohoku/bert-base-japanese-v3
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.5077
Accuracy: 0.7655
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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 6
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
No log
1.0
52
0.5087
0.7429
No log
2.0
104
0.4974
0.7514
No log
3.0
156
0.4870
0.7599
No log
4.0
208
0.4924
0.7655
No log
5.0
260
0.5034
0.7740
No log
6.0
312
0.5077
0.7655
Framework versions
Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0
