Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wikigold_trained_no_DA – AI Model by DOOGLAK | AlphaNeural AI
You can deploy this model and start earning money today!
DOOGLAK
/
wikigold_trained_no_DA
like
0
transformers
pytorch
tensorboard
bert
token-classification
generated_from_trainer
wikigold_splits
apache-2.0
model-index
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
temp
This model is a fine-tuned version of
bert-base-cased
on the wikigold_splits dataset. It achieves the following results on the evaluation set:
Loss: 0.1322
Precision: 0.8517
Recall: 0.875
F1: 0.8632
Accuracy: 0.9607
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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Precision
Recall
F1
Accuracy
No log
1.0
167
0.1490
0.7583
0.7760
0.7671
0.9472
No log
2.0
334
0.1337
0.8519
0.8464
0.8491
0.9572
0.1569
3.0
501
0.1322
0.8517
0.875
0.8632
0.9607
Framework versions
Transformers 4.17.0
Pytorch 1.11.0+cu113
Datasets 2.4.0
Tokenizers 0.11.6
