Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
ES_roberta_30_korquad_only – AI Model by nlp04 | AlphaNeural AI
You can deploy this model and start earning money today!
nlp04
/
ES_roberta_30_korquad_only
like
0
transformers
pytorch
roberta
question-answering
generated_from_trainer
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ES_roberta_30_korquad_only
This model is a fine-tuned version of
klue/roberta-large
on an unknown dataset. It achieves the following results on the evaluation set:
Exact Match: 88.1711
F1: 92.6666
Loss: 0.4495
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: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4.0
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Exact Match
F1
Validation Loss
0.7645
1.88
500
88.3097
92.8965
0.3851
0.1278
3.76
1000
88.1711
92.6666
0.4495
Framework versions
Transformers 4.25.1
Pytorch 1.13.0+cu117
Datasets 2.7.1
Tokenizers 0.13.2
