Skip to content

Update ORT to 1.5.1 in Bert Quantization Notebook#5396

Merged
yufenglee merged 2 commits intomasterfrom
roli/bert-quant-notebook
Oct 8, 2020
Merged

Update ORT to 1.5.1 in Bert Quantization Notebook#5396
yufenglee merged 2 commits intomasterfrom
roli/bert-quant-notebook

Conversation

@yufenglee
Copy link
Member

Description: Describe your changes.
Update ORT to 1.5.1 in Bert Quantization Notebook

@yufenglee yufenglee requested a review from a team as a code owner October 7, 2020 06:00
"| PyTorch 1.6 | 32.8 | 25.5 |\n",
"| ORT 1.4 | 25.6 | 19.5 |"
"| PyTorch 1.6 | 33.8 | 22.5 |\n",
"| ORT 1.4 | 26.0 | 19.5 |"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ORT 1.5?

@yufenglee
Copy link
Member Author

/azp run Linux CPU x64 NoContribops CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline ,MacOS CI Pipeline,MacOS NoContribops CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline

@yufenglee
Copy link
Member Author

/azp run centos7_cpu,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,Linux CPU CI Pipeline

@azure-pipelines
Copy link

Azure Pipelines successfully started running 4 pipeline(s).

@azure-pipelines
Copy link

Azure Pipelines successfully started running 9 pipeline(s).

"| PyTorch 1.6 | 32.8 | 25.5 |\n",
"| ORT 1.4 | 25.6 | 19.5 |"
"| PyTorch 1.6 | 33.8 | 22.5 |\n",
"| ORT 1.5 | 26.0 | 19.5 |"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
"| ORT 1.5 | 26.0 | 19.5 |"
"| ORT 1.5.1 | 26.0 | 19.5 |"

"| --- | --- | --- |\n",
"| PyTorch 1.6 | 417.7 | 173.1 |\n",
"| ORT 1.4 | 417.7 | 106.5 |\n",
"| ORT 1.5 | 417.7 | 106.5 |\n",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
"| ORT 1.5 | 417.7 | 106.5 |\n",
"| ORT 1.5.1 | 417.7 | 106.5 |\n",

"OnnxRuntime achieves a little bit better accuracy and F1 score, even though it has small model size.\n",
"\n",
"| Metrics | Full Precision | PyTorch 1.6 Quantization | ORT 1.4 Quantization |\n",
"| Metrics | Full Precision | PyTorch 1.6 Quantization | ORT 1.5 Quantization |\n",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
"| Metrics | Full Precision | PyTorch 1.6 Quantization | ORT 1.5 Quantization |\n",
"| Metrics | Full Precision | PyTorch 1.6 Quantization | ORT 1.5.1 Quantization |\n",

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Usually, patch version is not specified in benchmark

@yufenglee yufenglee merged commit b04cf2d into master Oct 8, 2020
@yufenglee yufenglee deleted the roli/bert-quant-notebook branch October 8, 2020 16:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants