autoevaluator
HF staff
Add evaluation results on the adversarialQA config and validation split of adversarial_qa
b1a87d7
metadata
language:
- en
license: cc-by-4.0
tags:
- generated_from_trainer
datasets:
- squad_v2
- conll2003
model_index:
- name: >-
bert-large-uncased-whole-word-masking-squad2-with-ner-conll2003-with-neg-with-repeat
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: squad_v2
type: squad_v2
args: conll2003
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
model-index:
- name: >-
andi611/bert-large-uncased-whole-word-masking-squad2-with-ner-conll2003-with-neg-with-repeat
results:
- task:
type: question-answering
name: Question Answering
dataset:
name: adversarial_qa
type: adversarial_qa
config: adversarialQA
split: validation
metrics:
- type: f1
value: 18.5493
name: F1
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDY3NjQ2ZDViNGU5OTA4YWRmNTA0NTNhOWJmNDQ3NzgwY2ZiYmYyYzAxYTE3YTgxNGZhMjBjY2YwODMwZGVhOSIsInZlcnNpb24iOjF9.mmxIAZ6p-fxKtLI49f9CvjB_LjNrgDJ-TU3esLiV5dv9y6HkRgZ5PAsF0VO6gbdfEJWxKWZFX0aBlNo9Vz_tBg
- type: exact_match
value: 13.3333
name: Exact Match
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWZlZWU3MDMzY2NkYTdkNTY2NTg5OTZiMzczNDVjYThjZmQ4NTlmZjQwM2VhMjVhOTZjZjliMTI4ZWFkMjA3ZSIsInZlcnNpb24iOjF9.HN7DglPZtzdAJ_vwyGleQLKKJJautl8b3jroS3FqUmz3dLQWNS9omjAFuu5i1G7pxom2DhKTXwZKFhIxwzReDA
- type: loss
value: 7.114065647125244
name: loss
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWZhODY3NTdhNDFiNTYyZGJhZjc0OWJjZGNkNDlkNzc2MTAxMzI2Yzg0NjkxYTRmOTY5YWZhNTI0NzE4MzI2ZiIsInZlcnNpb24iOjF9.wzZOasFqp8mrzS26Ubz8CQq2fnpyXJF0V0c1I6gjaiWcMoMwePNSapXK41cD4tB5orRqKeQFodvp2hW7xjtSCQ
bert-large-uncased-whole-word-masking-squad2-with-ner-conll2003-with-neg-with-repeat
This model is a fine-tuned version of deepset/bert-large-uncased-whole-word-masking-squad2 on the squad_v2 and the conll2003 datasets.
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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Framework versions
- Transformers 4.8.2
- Pytorch 1.8.1+cu111
- Datasets 1.8.0
- Tokenizers 0.10.3