autoevaluator
HF staff
Add evaluation results on the squad_v2 config and validation split of squad_v2
d85bd2d
metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: distilbert-base-uncased-finetuned-squad
results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_v2
type: squad_v2
config: squad_v2
split: validation
metrics:
- name: Exact Match
type: exact_match
value: 46.4111
verified: true
- name: F1
type: f1
value: 50.7154
verified: true
distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of distilbert-base-uncased on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 2.4285
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: 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: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.5169 | 1.0 | 1642 | 1.6958 |
1.1326 | 2.0 | 3284 | 2.0009 |
0.8638 | 3.0 | 4926 | 2.4285 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.15.1
- Tokenizers 0.10.3