Hugging Face's logo

helenai
/
bert-base-uncased-squad-v1-jpqd-ov-int8

Transformers
OpenVINO
bert
Generated from Trainer
Model card Files Community
1
bert-base-uncased-squad-v1-jpqd-ov-int8 / README.md
helenai's picture
helenai
Update model to overflowfix version
8bfe414
preview code
|
raw
history blame contribute delete
1.1 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - squad
model-index:
  - name: bert-base-uncased-squad-v1-jpqd-ov-int8
    results: []

bert-base-uncased-squad-v1-jpqd-ov-int8

This model is a fine-tuned version of bert-base-uncased on the squad dataset. It was compressed using NNCF with Optimum Intel following the JPQD question-answering example.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 128
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8.0
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.2