metadata

license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - squad_v2
model-index:
  - name: bert-base-uncased-finetuned-squad2
    results: []
pipeline_tag: question-answering
metrics:
  - exact_match
  - f1
language:
  - en

bert-base-uncased-finetuned-squad2

This model is a fine-tuned version of bert-base-uncased on the squad_v2 dataset. It achieves the following results on the evaluation set:

Loss: 1.3537

Model description

BERTbase fine-tuned on SQuAD 2.0 : Encoder-based Transformer Language model, pretrained with Masked Language Modeling and Next Sentence Prediction.
Suitable for Question-Answering tasks, predicts answer spans within the context provided.

Training data: Train-set SQuAD2.0
Evaluation data: Validation-set SQuAD2.0
Hardware Accelerator used: GPU Tesla T4

Intended uses & limitations

For Question-Answering -

from transformers import pipeline

# Replace this with your own checkpoint
model_checkpoint = "IProject-10/bert-base-uncased-finetuned-squad2"
question_answerer = pipeline("question-answering", model=model_checkpoint)

context = """
🤗 Transformers is backed by the three most popular deep learning libraries — Jax, PyTorch and TensorFlow — with a seamless integration
between them. It's straightforward to train your models with one before loading them for inference with the other.
"""
question = "Which deep learning libraries back 🤗 Transformers?"
question_answerer(question=question, context=context)

Results

Evaluation on SQuAD 2.0 validation dataset:

 'exact': 73.5029057525478,
 'f1': 76.79224102466394,
 'total': 11873,
 'HasAns_exact': 73.46491228070175,
 'HasAns_f1': 80.05301580395327,
 'HasAns_total': 5928,
 'NoAns_exact': 73.5407905803196,
 'NoAns_f1': 73.5407905803196,
 'NoAns_total': 5945,
 'best_exact': 73.5029057525478,
 'best_exact_thresh': 0.9997851848602295,
 'best_f1': 76.79224102466425,
 'best_f1_thresh': 0.9997851848602295,
 'total_time_in_seconds': 209.65395342100004,
 'samples_per_second': 56.63141479692573,
 'latency_in_seconds': 0.01765804374808389}

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-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
1.0122	1.0	8235	1.0740
0.6805	2.0	16470	1.0820
0.4542	3.0	24705	1.3537

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.14.2
Tokenizers 0.13.3