Merge remote-tracking branch 'origin/main'
This commit is contained in:
Chandra Sekhar Gupta Aravapalli
Коммит
8239b9f5b8
|
|
@ -0,0 +1,6 @@
|
|||
name: evaluation
|
||||
version: auto
|
||||
type: environment
|
||||
spec: spec.yaml
|
||||
extra_config: environment.yaml
|
||||
categories: ["Models"]
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
FROM mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu22.04:{{latest-image-tag}}
|
||||
|
||||
RUN apt-get update && apt-get -y upgrade
|
||||
|
||||
WORKDIR /
|
||||
ENV CONDA_PREFIX=/azureml-envs/aoai-evaluation
|
||||
ENV CONDA_DEFAULT_ENV=$CONDA_PREFIX
|
||||
|
||||
COPY conda.yaml .
|
||||
# Create conda environment
|
||||
RUN conda env create -p $CONDA_PREFIX -f conda.yaml -q && \
|
||||
rm conda.yaml && \
|
||||
conda run -p $CONDA_PREFIX pip cache purge && \
|
||||
conda clean -a -y
|
||||
|
||||
# clean conda and pip caches
|
||||
RUN rm -rf ~/.cache/pip
|
||||
|
||||
# Prepend path to AzureML conda environment
|
||||
ENV PATH=$CONDA_PREFIX/bin:$PATH
|
||||
|
||||
# This is needed for mpi to locate libpython
|
||||
ENV LD_LIBRARY_PATH $CONDA_PREFIX/lib:$LD_LIBRARY_PATH
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
name: evaluation
|
||||
channels:
|
||||
- conda-forge
|
||||
- anaconda
|
||||
dependencies:
|
||||
- python=3.10
|
||||
- pip=23.1
|
||||
- pip:
|
||||
- azureml-mlflow=={{latest-pypi-version}}
|
||||
- azure-ai-ml=={{latest-pypi-version}}
|
||||
- azureml-core=={{latest-pypi-version}}
|
||||
- azureml-telemetry=={{latest-pypi-version}}
|
||||
- mltable=={{latest-pypi-version}}
|
||||
- azureml-automl-core=={{latest-pypi-version}}
|
||||
- rouge-score>=0.1.2
|
||||
- nltk>=3.9.1
|
||||
- pandas>=2.2.3
|
||||
- tiktoken>=0.8.0
|
||||
- openai>=1.52.2
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
image:
|
||||
name: azureml/curated/evaluation
|
||||
os: linux
|
||||
context:
|
||||
dir: context
|
||||
dockerfile: Dockerfile
|
||||
template_files:
|
||||
- Dockerfile
|
||||
- conda.yaml
|
||||
publish:
|
||||
location: mcr
|
||||
visibility: public
|
||||
|
|
@ -0,0 +1,15 @@
|
|||
$schema: https://azuremlschemas.azureedge.net/latest/environment.schema.json
|
||||
description: >-
|
||||
Environment for evaluating models.
|
||||
|
||||
name: "{{asset.name}}"
|
||||
version: "{{asset.version}}"
|
||||
|
||||
build:
|
||||
path: context/
|
||||
|
||||
os_type: linux
|
||||
|
||||
tags:
|
||||
OS: Ubuntu22.04
|
||||
Evaluation: ""
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
name: component
|
||||
version: auto
|
||||
type: environment
|
||||
spec: spec.yaml
|
||||
extra_config: environment.yaml
|
||||
categories: ["Designer", "Python"]
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
FROM mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu22.04:{{latest-image-tag}}
|
||||
|
||||
WORKDIR /
|
||||
|
||||
ENV CONDA_PREFIX=/azureml-envs/component-sdk
|
||||
ENV CONDA_DEFAULT_ENV=$CONDA_PREFIX
|
||||
ENV PATH=$CONDA_PREFIX/bin:$PATH
|
||||
# This is needed for mpi to locate libpython
|
||||
ENV LD_LIBRARY_PATH=$CONDA_PREFIX/lib:$LD_LIBRARY_PATH
|
||||
|
||||
# Create conda environment
|
||||
COPY conda_dependencies.yaml .
|
||||
RUN conda env create -p $CONDA_PREFIX -f conda_dependencies.yaml -q && \
|
||||
rm conda_dependencies.yaml && \
|
||||
conda run -p $CONDA_PREFIX pip cache purge && \
|
||||
conda clean -a -y
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
name: component
|
||||
channels:
|
||||
- conda-forge
|
||||
dependencies:
|
||||
- python=3.9
|
||||
- pip=24.0
|
||||
- pip:
|
||||
- azure-ml-component=={{latest-pypi-version}}
|
||||
- azureml-defaults=={{latest-pypi-version}}
|
||||
- pyarrow>=14.0.1
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
image:
|
||||
name: azureml/curated/component
|
||||
os: linux
|
||||
context:
|
||||
dir: context
|
||||
dockerfile: Dockerfile
|
||||
template_files:
|
||||
- Dockerfile
|
||||
- conda_dependencies.yaml
|
||||
publish:
|
||||
location: mcr
|
||||
visibility: public
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
$schema: https://azuremlschemas.azureedge.net/latest/environment.schema.json
|
||||
|
||||
description: >-
|
||||
An environment for built-in component that can dynamically evaluate python expression for 1P request feature.
|
||||
|
||||
name: "{{asset.name}}"
|
||||
version: "{{asset.version}}"
|
||||
|
||||
build:
|
||||
path: "{{image.context.path}}"
|
||||
dockerfile_path: "{{image.dockerfile.path}}"
|
||||
|
||||
os_type: linux
|
||||
|
||||
tags:
|
||||
OS: Ubuntu22.04
|
||||
Python: 3.9
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_cohere-embed-v3-english_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_cohere-embed-v3-english_classification
|
||||
description: cohere-embed-v3-english run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-english
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.927643
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_cohere-embed-v3-multilingual_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_cohere-embed-v3-multilingual_classification
|
||||
description: cohere-embed-v3-multilingual run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-multilingual
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.912307
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_text-embedding-3-large_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_text-embedding-3-large_classification
|
||||
description: text-embedding-3-large run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.92868975
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_text-embedding-3-small_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_text-embedding-3-small_classification
|
||||
description: text-embedding-3-small run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-small
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.90878075
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_text-embedding-ada-002_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_text-embedding-ada-002_classification
|
||||
description: text-embedding-ada-002 run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-ada-002
|
||||
azure_latest_model_version: 2
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
metrics:
|
||||
accuracy: 0.867263
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arguana_cohere-embed-v3-english_retrieval
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_cohere-embed-v3-english_retrieval
|
||||
description: cohere-embed-v3-english run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: retrieval
|
||||
primary_metric: ndcg_at_10
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-english
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/1
|
||||
|
||||
metrics:
|
||||
ndcg_at_10: 0.57529
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arguana_cohere-embed-v3-multilingual_retrieval
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_cohere-embed-v3-multilingual_retrieval
|
||||
description: cohere-embed-v3-multilingual run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: retrieval
|
||||
primary_metric: ndcg_at_10
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-multilingual
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/1
|
||||
|
||||
metrics:
|
||||
ndcg_at_10: 0.57989
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arguana_text-embedding-3-large_retrieval
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_text-embedding-3-large_retrieval
|
||||
description: text-embedding-3-large run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: retrieval
|
||||
primary_metric: ndcg_at_10
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
metrics:
|
||||
ndcg_at_10: 0.58013
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arguana_text-embedding-3-small_retrieval
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_text-embedding-3-small_retrieval
|
||||
description: text-embedding-3-small run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: retrieval
|
||||
primary_metric: ndcg_at_10
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-small
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
metrics:
|
||||
ndcg_at_10: 0.55694
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arguana_text-embedding-ada-002_retrieval
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_text-embedding-ada-002_retrieval
|
||||
description: text-embedding-ada-002 run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: retrieval
|
||||
primary_metric: ndcg_at_10
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-ada-002
|
||||
azure_latest_model_version: 2
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
metrics:
|
||||
ndcg_at_10: 0.57455
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_cohere-embed-v3-english_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringP2P.v2_cohere-embed-v3-english_clustering
|
||||
description: cohere-embed-v3-english run for ArxivClusteringP2P.v2 dataset
|
||||
dataset_name: ArxivClusteringP2P.v2
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-english
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.5081042703542442
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_cohere-embed-v3-multilingual_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringP2P.v2_cohere-embed-v3-multilingual_clustering
|
||||
description: cohere-embed-v3-multilingual run for ArxivClusteringP2P.v2 dataset
|
||||
dataset_name: ArxivClusteringP2P.v2
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-multilingual
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.5029184573976476
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_text-embedding-3-large_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringP2P.v2_text-embedding-3-large_clustering
|
||||
description: text-embedding-3-large run for ArxivClusteringP2P.v2 dataset
|
||||
dataset_name: ArxivClusteringP2P.v2
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.519053128352996
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_text-embedding-3-small_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringP2P.v2_text-embedding-3-small_clustering
|
||||
description: text-embedding-3-small run for ArxivClusteringP2P.v2 dataset
|
||||
dataset_name: ArxivClusteringP2P.v2
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-small
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.496692276507199
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_text-embedding-ada-002_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringP2P.v2_text-embedding-ada-002_clustering
|
||||
description: text-embedding-ada-002 run for ArxivClusteringP2P.v2 dataset
|
||||
dataset_name: ArxivClusteringP2P.v2
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-ada-002
|
||||
azure_latest_model_version: 2
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
metrics:
|
||||
v_measure: 0.4794210912494528
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_cohere-embed-v3-english_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_cohere-embed-v3-english_clustering
|
||||
description: cohere-embed-v3-english run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-english
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.38872349524931893
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_cohere-embed-v3-multilingual_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_cohere-embed-v3-multilingual_clustering
|
||||
description: cohere-embed-v3-multilingual run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-multilingual
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.3910885755785807
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_text-embedding-3-large_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_text-embedding-3-large_clustering
|
||||
description: text-embedding-3-large run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.4429783426306228
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_text-embedding-3-small_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_text-embedding-3-small_clustering
|
||||
description: text-embedding-3-small run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-small
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
metrics:
|
||||
v_measure: 0.3940951744128959
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_text-embedding-ada-002_clustering
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_text-embedding-ada-002_clustering
|
||||
description: text-embedding-ada-002 run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: clustering
|
||||
primary_metric: v_measure
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-ada-002
|
||||
azure_latest_model_version: 2
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
metrics:
|
||||
v_measure: 0.3719179506563676
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_cohere-embed-v3-english_classification
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_cohere-embed-v3-english_classification
|
||||
description: cohere-embed-v3-english run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-english
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.7934415584415586
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_cohere-embed-v3-multilingual_classification
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_cohere-embed-v3-multilingual_classification
|
||||
description: cohere-embed-v3-multilingual run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-multilingual
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.7934415584415585
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_text-embedding-3-large_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_text-embedding-3-large_classification
|
||||
description: text-embedding-3-large run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8572402597402597
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_text-embedding-3-small_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_text-embedding-3-small_classification
|
||||
description: text-embedding-3-small run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-small
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8299025974025973
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_text-embedding-ada-002_classification
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_text-embedding-ada-002_classification
|
||||
description: text-embedding-ada-002 run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-ada-002
|
||||
azure_latest_model_version: 2
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8053246753246753
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: boolq__gpt-4-0125-preview__question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: boolq__gpt-4-0125-Preview__chat_completion
|
||||
description: Benchmark__gpt40125__hf_boolq__chat_completion
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-4-0125-Preview
|
||||
model_version: "4"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4-0125-Preview/versions/4
|
||||
model_version: "0125-Preview"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/0125-Preview
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4-0125-Preview/versions/4
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/0125-Preview
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.904892966
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq__meta-llama-3_1-70b-instruct__question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: boolq__Meta-Llama-3_1-70B-Instruct__chat_completion
|
||||
description: Benchmark__Llama-3-1-70B-Instruct-bench__hf_boolq__chat_completion
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3.1-70B-Instruct
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3.1-70B-Instruct/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.909785933
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq__meta-llama-3_1-8b-instruct__question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: boolq__Meta-Llama-3_1-8B-Instruct__chat_completion
|
||||
description: Benchmark__meta-llama-3-1-8b-instruct-1__hf_boolq__chat_completion
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3.1-8B-Instruct
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3.1-8B-Instruct/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.868501529
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: boolq_cohere_command_r_plus_question_answering
|
||||
version: 2.30.04
|
||||
version: 2.04.11
|
||||
display_name: boolq_Cohere_command_r_plus_question_answering
|
||||
description: Cohere-command-r-plus run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Cohere-command-r-plus
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/3
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/3
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/1
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-command-r-plus
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.909480122
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: boolq_cohere_command_r_question_answering
|
||||
version: 2.30.04
|
||||
version: 2.04.11
|
||||
display_name: boolq_Cohere_command_r_question_answering
|
||||
description: Cohere-command-r run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Cohere-command-r
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/3
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/3
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/1
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-command-r
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8819571865443425
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_databricks-dbrx-base_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_databricks-dbrx-base_question_answering
|
||||
description: databricks-dbrx-base run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-restricted
|
||||
azure_model_name: databricks-dbrx-base
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-restricted/models/databricks-dbrx-base/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.9159021
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_databricks-dbrx-instruct_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_databricks-dbrx-instruct_question_answering
|
||||
description: databricks-dbrx-instruct run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-restricted
|
||||
azure_model_name: databricks-dbrx-instruct
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-restricted/models/databricks-dbrx-instruct/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.9051988
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt-4-turbo-2024-04-09_chat_completion
|
||||
version: 2.07.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt-4-turbo-2024-04-09_chat_completion
|
||||
description: boolq_gpt-4-turbo-2024-04-09_chat_completion
|
||||
dataset_family: boolq
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: boolq
|
|||
|
||||
model_name: gpt-4-turbo-2024-04-09
|
||||
model_version: "turbo-2024-04-09"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.9125382262996942
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt-4o_question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt-4o_question_answering
|
||||
description: gpt-4o run for boolq
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-4o
|
||||
model_version: "5/13/2024"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4o/versions/1
|
||||
model_name: gpt-4o-2024-05-13
|
||||
model_version: "2024-05-13"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4o/versions/2024-05-13
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4o/versions/1
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4o/versions/2024-05-13
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4o
|
||||
azure_latest_model_version: 2024-08-06
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4o/versions/2024-08-06
|
||||
|
||||
metrics:
|
||||
accuracy: 0.908562691
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_35_turbo_0301_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_35_turbo_0301_question_answering
|
||||
description: gpt-35-turbo-0301 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: boolq
|
|||
|
||||
model_name: gpt-35-turbo-0301
|
||||
model_version: "0301"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0301
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0301
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-35-turbo
|
||||
azure_latest_model_version: 0125
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0125
|
||||
|
||||
metrics:
|
||||
accuracy: 0.867
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_35_turbo_0613_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_35_turbo_0613_question_answering
|
||||
description: gpt-35-turbo-0613 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: boolq
|
|||
|
||||
model_name: gpt-35-turbo-0613
|
||||
model_version: "0613"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0613
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0613
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-35-turbo
|
||||
azure_latest_model_version: 0125
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0125
|
||||
|
||||
metrics:
|
||||
accuracy: 0.864
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_0314_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_4_0314_question_answering
|
||||
description: gpt-4-0314 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.911
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_0613_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_4_0613_question_answering
|
||||
description: gpt-4-0613 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: boolq
|
|||
|
||||
model_name: gpt-4-0613
|
||||
model_version: "0613"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/0613
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/0613
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.912
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_32k_0314_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_4_32k_0314_question_answering
|
||||
description: gpt-4-32k-0314 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: boolq
|
|||
|
||||
model_name: gpt-4-32k-0314
|
||||
model_version: "0314"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4-32k/versions/315
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4-32k/versions/0314
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4-32k/versions/315
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4-32k/versions/0314
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4-32k
|
||||
azure_latest_model_version: 0613
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4-32k/versions/0613
|
||||
|
||||
metrics:
|
||||
accuracy: 0.913
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_32k_0613_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_4_32k_0613_question_answering
|
||||
description: gpt-4-32k-0613 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: boolq
|
|||
|
||||
model_name: gpt-4-32k-0613
|
||||
model_version: "0613"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4-32k/versions/315
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4-32k/versions/0613
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4-32k/versions/315
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4-32k/versions/0613
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4-32k
|
||||
azure_latest_model_version: 0613
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4-32k/versions/0613
|
||||
|
||||
metrics:
|
||||
accuracy: 0.911
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_13b_chat_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_13b_chat_question_answering
|
||||
description: llama-2-13b-chat run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Llama-2-13b-chat
|
||||
azure_latest_model_version: 20
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Llama-2-13b-chat/versions/20
|
||||
|
||||
metrics:
|
||||
accuracy: 0.801
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_13b_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_13b_question_answering
|
||||
description: llama-2-13b run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Llama-2-13b
|
||||
azure_latest_model_version: 23
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Llama-2-13b/versions/23
|
||||
|
||||
metrics:
|
||||
accuracy: 0.723
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_70b_chat_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_70b_chat_question_answering
|
||||
description: llama-2-70b-chat run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Llama-2-70b-chat
|
||||
azure_latest_model_version: 20
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Llama-2-70b-chat/versions/20
|
||||
|
||||
metrics:
|
||||
accuracy: 0.826
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_70b_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_70b_question_answering
|
||||
description: llama-2-70b run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Llama-2-70b
|
||||
azure_latest_model_version: 24
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Llama-2-70b/versions/24
|
||||
|
||||
metrics:
|
||||
accuracy: 0.853
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_7b_chat_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_7b_chat_question_answering
|
||||
description: llama-2-7b-chat run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Llama-2-7b-chat
|
||||
azure_latest_model_version: 24
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Llama-2-7b-chat/versions/24
|
||||
|
||||
metrics:
|
||||
accuracy: 0.771
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_7b_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_7b_question_answering
|
||||
description: llama-2-7b run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Llama-2-7b
|
||||
azure_latest_model_version: 22
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Llama-2-7b/versions/22
|
||||
|
||||
metrics:
|
||||
accuracy: 0.628
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-70b-instruct_question_answering
|
||||
version: 2.07.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_Meta-Llama-3-70B-Instruct_question_answering
|
||||
description: Meta-Llama-3-70B-Instruct run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3-70B-Instruct
|
||||
azure_latest_model_version: 8
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-70B-Instruct/versions/8
|
||||
|
||||
metrics:
|
||||
accuracy: 0.9027522935779817
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-70b_question_answering
|
||||
version: 2.22.04
|
||||
version: 2.04.11
|
||||
display_name: boolq_Meta-Llama-3-70B_question_answering
|
||||
description: Meta-Llama-3-70B run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3-70B
|
||||
azure_latest_model_version: 6
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-70B/versions/6
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8917431192660551
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-8b-instruct_question_answering
|
||||
version: 2.07.05
|
||||
version: 2.04.11
|
||||
display_name: boolq_Meta-Llama-3-8B-Instruct_question_answering
|
||||
description: Meta-Llama-3-8B-Instruct run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,9 +18,13 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3-8B-Instruct
|
||||
azure_latest_model_version: 8
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-8B-Instruct/versions/8
|
||||
|
||||
metrics:
|
||||
accuracy: 0.863302752293578
|
||||
accuracy: 0.863302752
|
||||
|
||||
|
||||
properties:
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-8b_question_answering
|
||||
version: 2.22.04
|
||||
version: 2.04.11
|
||||
display_name: boolq_Meta-Llama-3-8B_question_answering
|
||||
description: Meta-Llama-3-8B run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3-8B
|
||||
azure_latest_model_version: 7
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-8B/versions/7
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8198776758409786
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3_1-405b-instruct_question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: boolq_Meta-Llama-3_1-405B-Instruct_question_answering
|
||||
description: Meta-Llama-3.1-405B-Instruct run for boolq
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3.1-405B-Instruct
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3.1-405B-Instruct/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.920489297
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_microsoft_phi_2_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_microsoft_phi_2_question_answering
|
||||
description: microsoft-phi-2 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-msr
|
||||
azure_model_name: microsoft-phi-2
|
||||
azure_latest_model_version: 19
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-msr/models/microsoft-phi-2/versions/19
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8079999999999999
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistral-community-mixtral-8x22b-v0-1_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistral-community-Mixtral-8x22B-v0-1_question_answering
|
||||
description: mistral-community-Mixtral-8x22B-v0-1 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistral-community-Mixtral-8x22B-v0-1
|
||||
azure_latest_model_version: 5
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistral-community-Mixtral-8x22B-v0-1/versions/5
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8954128
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistral_7b_instruct_v01_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistral_7b_instruct_v01_question_answering
|
||||
description: mistralai-mistral-7b-instruct-v01 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistralai-Mistral-7B-Instruct-v01
|
||||
azure_latest_model_version: 10
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistralai-Mistral-7B-Instruct-v01/versions/10
|
||||
|
||||
metrics:
|
||||
accuracy: 0.777
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistral_7b_v01_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistral_7b_v01_question_answering
|
||||
description: mistralai-mistral-7b-v01 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistralai-Mistral-7B-v01
|
||||
azure_latest_model_version: 17
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistralai-Mistral-7B-v01/versions/17
|
||||
|
||||
metrics:
|
||||
accuracy: 0.828
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistral_large_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistral_large_question_answering
|
||||
description: mistral-large run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-mistral
|
||||
azure_model_name: Mistral-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-mistral/models/Mistral-large/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8993884
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistralai-mistral-7b-instruct-v0-2_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistralai-Mistral-7B-Instruct-v0-2_question_answering
|
||||
description: mistralai-Mistral-7B-Instruct-v0-2 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistralai-Mistral-7B-Instruct-v0-2
|
||||
azure_latest_model_version: 5
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistralai-Mistral-7B-Instruct-v0-2/versions/5
|
||||
|
||||
metrics:
|
||||
accuracy: 0.795107
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistralai-mixtral-8x22b-instruct-v0-1_question_answering
|
||||
version: 2.22.04
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistralai-Mixtral-8x22B-Instruct-v0-1_question_answering
|
||||
description: mistralai-Mixtral-8x22B-Instruct-v0-1 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistralai-Mixtral-8x22B-Instruct-v0-1
|
||||
azure_latest_model_version: 4
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistralai-Mixtral-8x22B-Instruct-v0-1/versions/4
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8749235474006116
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistralai-mixtral-8x22b-v0-1_question_answering
|
||||
version: 2.22.04
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistralai-Mixtral-8x22B-v0-1_question_answering
|
||||
description: mistralai-Mixtral-8x22B-v0-1 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistralai-Mixtral-8x22B-v0-1
|
||||
azure_latest_model_version: 4
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistralai-Mixtral-8x22B-v0-1/versions/4
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8975535168195719
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistralai-mixtral-8x7b-instruct-v01_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistralai-Mixtral-8x7B-Instruct-v01_question_answering
|
||||
description: mistralai-Mixtral-8x7B-Instruct-v01 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistralai-Mixtral-8x7B-Instruct-v01
|
||||
azure_latest_model_version: 9
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistralai-Mixtral-8x7B-Instruct-v01/versions/9
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8345566
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_mistralai-mixtral-8x7b-v01_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: boolq_mistralai-Mixtral-8x7B-v01_question_answering
|
||||
description: mistralai-Mixtral-8x7B-v01 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: mistralai-Mixtral-8x7B-v01
|
||||
azure_latest_model_version: 14
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/mistralai-Mixtral-8x7B-v01/versions/14
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8724771
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_phi-3-medium-128k-instruct_question_answering
|
||||
version: 2.06.18
|
||||
version: 2.04.11
|
||||
display_name: boolq_Phi-3-medium-128k-instruct_question_answering
|
||||
description: boolq_Phi-3-medium-128k-instruct_question_answering
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: Phi-3-medium-128k-instruct
|
||||
azure_latest_model_version: 5
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/Phi-3-medium-128k-instruct/versions/5
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8795107033639143
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_phi-3-medium-4k-instruct_question_answering
|
||||
version: 2.06.18
|
||||
version: 2.04.11
|
||||
display_name: boolq_Phi-3-medium-4k-instruct_question_answering
|
||||
description: boolq_Phi-3-medium-4k-instruct_question_answering
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: Phi-3-medium-4k-instruct
|
||||
azure_latest_model_version: 4
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/Phi-3-medium-4k-instruct/versions/4
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8819571865443425
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_phi-3-mini-128k-instruct_chat_completion
|
||||
version: 2.06.21
|
||||
version: 2.04.11
|
||||
display_name: boolq_phi-3-mini-128k-instruct_chat_completion
|
||||
description: boolq_phi-3-mini-128k-instruct_chat_completion
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: Phi-3-mini-128k-instruct
|
||||
azure_latest_model_version: 11
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/Phi-3-mini-128k-instruct/versions/11
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8492354740061162
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_phi-3-mini-4k-instruct_chat_completion
|
||||
version: 2.06.21
|
||||
version: 2.04.11
|
||||
display_name: boolq_phi-3-mini-4k-instruct_chat_completion
|
||||
description: boolq_phi-3-mini-4k-instruct_chat_completion
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml
|
||||
azure_model_name: Phi-3-mini-4k-instruct
|
||||
azure_latest_model_version: 13
|
||||
azure_latest_model_asset_id: azureml://registries/azureml/models/Phi-3-mini-4k-instruct/versions/13
|
||||
|
||||
metrics:
|
||||
accuracy: 0.850764526
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_phi-3-small-128k-instruct_question_answering
|
||||
version: 2.06.18
|
||||
version: 2.04.11
|
||||
display_name: boolq_Phi-3-small-128k-instruct_question_answering
|
||||
description: Phi-3-small-128k-instruct run for boolq dataset
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: models-staging
|
||||
azure_model_name: Phi-3-small-128k-instruct
|
||||
azure_latest_model_version: 7
|
||||
azure_latest_model_asset_id: azureml://registries/models-staging/models/Phi-3-small-128k-instruct/versions/7
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8764525993883792
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: boolq_phi-3-small-8k-instruct_question_answering
|
||||
version: 2.06.18
|
||||
version: 2.04.11
|
||||
display_name: boolq_Phi-3-small-8k-instruct_question_answering
|
||||
description: boolq_Phi-3-small-8k-instruct_question_answering
|
||||
dataset_family: boolq
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: models-staging
|
||||
azure_model_name: Phi-3-small-8k-instruct
|
||||
azure_latest_model_version: 7
|
||||
azure_latest_model_asset_id: azureml://registries/models-staging/models/Phi-3-small-8k-instruct/versions/7
|
||||
|
||||
metrics:
|
||||
accuracy: 0.8681957186544342
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: bucc_cohere-embed-v3-english_bitext_mining
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: BUCC_cohere-embed-v3-english_bitext_mining
|
||||
description: cohere-embed-v3-english run for BUCC dataset
|
||||
dataset_name: BUCC
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: bitext_mining
|
||||
primary_metric: f1_score
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-english
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/1
|
||||
|
||||
metrics:
|
||||
f1_score: 0.293725473226098
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: bucc_cohere-embed-v3-multilingual_bitext_mining
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: BUCC_cohere-embed-v3-multilingual_bitext_mining
|
||||
description: cohere-embed-v3-multilingual run for BUCC dataset
|
||||
dataset_name: BUCC
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: bitext_mining
|
||||
primary_metric: f1_score
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-multilingual
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/1
|
||||
|
||||
metrics:
|
||||
f1_score: 0.9837602031657908
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: bucc_text-embedding-3-large_bitext_mining
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: BUCC_text-embedding-3-large_bitext_mining
|
||||
description: text-embedding-3-large run for BUCC dataset
|
||||
dataset_name: BUCC
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: bitext_mining
|
||||
primary_metric: f1_score
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
metrics:
|
||||
f1_score: 0.9891511897531617
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: bucc_text-embedding-3-small_bitext_mining
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: BUCC_text-embedding-3-small_bitext_mining
|
||||
description: text-embedding-3-small run for BUCC dataset
|
||||
dataset_name: BUCC
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: bitext_mining
|
||||
primary_metric: f1_score
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-small
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
metrics:
|
||||
f1_score: 0.9820643057041419
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: bucc_text-embedding-ada-002_bitext_mining
|
||||
version: 2.22.05
|
||||
version: 2.04.11
|
||||
display_name: BUCC_text-embedding-ada-002_bitext_mining
|
||||
description: text-embedding-ada-002 run for BUCC dataset
|
||||
dataset_name: BUCC
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: bitext_mining
|
||||
primary_metric: f1_score
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-ada-002
|
||||
azure_latest_model_version: 2
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
metrics:
|
||||
f1_score: 0.9765893479830264
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: emotionclassification_cohere-embed-v3-english_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: EmotionClassification_cohere-embed-v3-english_classification
|
||||
description: cohere-embed-v3-english run for EmotionClassification dataset
|
||||
dataset_name: EmotionClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-english
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.5219999999999999
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: emotionclassification_cohere-embed-v3-multilingual_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: EmotionClassification_cohere-embed-v3-multilingual_classification
|
||||
description: cohere-embed-v3-multilingual run for EmotionClassification dataset
|
||||
dataset_name: EmotionClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-embed-v3-multilingual
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.5022499999999999
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: emotionclassification_text-embedding-3-large_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: EmotionClassification_text-embedding-3-large_classification
|
||||
description: text-embedding-3-large run for EmotionClassification dataset
|
||||
dataset_name: EmotionClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-large
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.5149
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: emotionclassification_text-embedding-3-small_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: EmotionClassification_text-embedding-3-small_classification
|
||||
description: text-embedding-3-small run for EmotionClassification dataset
|
||||
dataset_name: EmotionClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-3-small
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.5061500000000001
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: emotionclassification_text-embedding-ada-002_classification
|
||||
version: 2.07.22
|
||||
version: 2.04.11
|
||||
display_name: EmotionClassification_text-embedding-ada-002_classification
|
||||
description: text-embedding-ada-002 run for EmotionClassification dataset
|
||||
dataset_name: EmotionClassification
|
||||
|
|
@ -17,6 +17,10 @@ tags:
|
|||
evaluation_type: text_embeddings
|
||||
task: classification
|
||||
primary_metric: accuracy
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: text-embedding-ada-002
|
||||
azure_latest_model_version: 2
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
metrics:
|
||||
accuracy: 0.48785
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k__gpt-4-0125-preview__question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: gsm8k__gpt-4-0125-Preview__chat_completion
|
||||
description: Benchmark__gpt40125__hf_gsm8k__chat_completion
|
||||
dataset_family: gsm8k
|
||||
dataset_name: gsm8k
|
||||
|
||||
model_name: gpt-4-0125-Preview
|
||||
model_version: "4"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4-0125-Preview/versions/4
|
||||
model_version: "0125-Preview"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/0125-Preview
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4-0125-Preview/versions/4
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/0125-Preview
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.93555724
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k__meta-llama-3_1-70b-instruct__question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: gsm8k__Meta-Llama-3_1-70B-Instruct__chat_completion
|
||||
description: Benchmark__Llama-3-1-70B-Instruct-bench__hf_gsm8k__chat_completion
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3.1-70B-Instruct
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3.1-70B-Instruct/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.946929492
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k__meta-llama-3_1-8b-instruct__question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: gsm8k__Meta-Llama-3_1-8B-Instruct__chat_completion
|
||||
description: Benchmark__meta-llama-3-1-8b-instruct-1__hf_gsm8k__chat_completion
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-meta
|
||||
azure_model_name: Meta-Llama-3.1-8B-Instruct
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3.1-8B-Instruct/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.843062926
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_cohere_command_r_plus_question_answering
|
||||
version: 2.30.04
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_Cohere_command_r_plus_question_answering
|
||||
description: Cohere-command-r-plus run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
dataset_name: gsm8k
|
||||
|
||||
model_name: Cohere-command-r-plus
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/3
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/3
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/1
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-command-r-plus
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r-plus/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.7626990144048522
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_cohere_command_r_question_answering
|
||||
version: 2.30.04
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_Cohere_command_r_question_answering
|
||||
description: Cohere-command-r run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
dataset_name: gsm8k
|
||||
|
||||
model_name: Cohere-command-r
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/3
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/3
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/1
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-cohere
|
||||
azure_model_name: Cohere-command-r
|
||||
azure_latest_model_version: 1
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-cohere/models/Cohere-command-r/versions/1
|
||||
|
||||
metrics:
|
||||
accuracy: 0.5981804397270659
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_databricks-dbrx-base_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_databricks-dbrx-base_question_answering
|
||||
description: databricks-dbrx-base run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-restricted
|
||||
azure_model_name: databricks-dbrx-base
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-restricted/models/databricks-dbrx-base/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.702047
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_databricks-dbrx-instruct_question_answering
|
||||
version: 2.19.040
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_databricks-dbrx-instruct_question_answering
|
||||
description: databricks-dbrx-instruct run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azureml-restricted
|
||||
azure_model_name: databricks-dbrx-instruct
|
||||
azure_latest_model_version: 3
|
||||
azure_latest_model_asset_id: azureml://registries/azureml-restricted/models/databricks-dbrx-instruct/versions/3
|
||||
|
||||
metrics:
|
||||
accuracy: 0.7202426
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_gpt-4-turbo-2024-04-09_chat_completion
|
||||
version: 2.07.05
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_gpt-4-turbo-2024-04-09_chat_completion
|
||||
description: gsm8k_gpt-4-turbo-2024-04-09_chat_completion
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: gsm8k
|
|||
|
||||
model_name: gpt-4-turbo-2024-04-09
|
||||
model_version: "turbo-2024-04-09"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.9484457922668689
|
||||
|
|
|
|||
|
|
@ -1,23 +1,27 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_gpt-4o_question_answering
|
||||
version: 2.12.08
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_gpt-4o_question_answering
|
||||
description: gpt-4o run for gsm8k
|
||||
dataset_family: gsm8k
|
||||
dataset_name: gsm8k
|
||||
|
||||
model_name: gpt-4o
|
||||
model_version: "5/13/2024"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4o/versions/1
|
||||
model_name: gpt-4o-2024-05-13
|
||||
model_version: "2024-05-13"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4o/versions/2024-05-13
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4o/versions/1
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4o/versions/2024-05-13
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4o
|
||||
azure_latest_model_version: 2024-08-06
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4o/versions/2024-08-06
|
||||
|
||||
metrics:
|
||||
accuracy: 0.945413192
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_gpt_35_turbo_0301_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_gpt_35_turbo_0301_question_answering
|
||||
description: gpt-35-turbo-0301 run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: gsm8k
|
|||
|
||||
model_name: gpt-35-turbo-0301
|
||||
model_version: "0301"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0301
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0301
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-35-turbo
|
||||
azure_latest_model_version: 0125
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0125
|
||||
|
||||
metrics:
|
||||
accuracy: 0.826
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_gpt_35_turbo_0613_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_gpt_35_turbo_0613_question_answering
|
||||
description: gpt-35-turbo-0613 run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: gsm8k
|
|||
|
||||
model_name: gpt-35-turbo-0613
|
||||
model_version: "0613"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0613
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/2
|
||||
assetId: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0613
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-35-turbo
|
||||
azure_latest_model_version: 0125
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-35-turbo/versions/0125
|
||||
|
||||
metrics:
|
||||
accuracy: 0.782
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_gpt_4_0314_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_gpt_4_0314_question_answering
|
||||
description: gpt-4-0314 run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -18,6 +18,10 @@ tags:
|
|||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.945
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
type: evaluationresult
|
||||
name: gsm8k_gpt_4_0613_question_answering
|
||||
version: 2.03.05
|
||||
version: 2.04.11
|
||||
display_name: gsm8k_gpt_4_0613_question_answering
|
||||
description: gpt-4-0613 run for gsm8k dataset
|
||||
dataset_family: gsm8k
|
||||
|
|
@ -8,16 +8,20 @@ dataset_name: gsm8k
|
|||
|
||||
model_name: gpt-4-0613
|
||||
model_version: "0613"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/0613
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/0613
|
||||
|
||||
tags:
|
||||
evaluation_type: text_generation
|
||||
task: question-answering
|
||||
accuracy_metric_name: exact_match
|
||||
azure_registry_name: azure-openai
|
||||
azure_model_name: gpt-4
|
||||
azure_latest_model_version: turbo-2024-04-09
|
||||
azure_latest_model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/turbo-2024-04-09
|
||||
|
||||
metrics:
|
||||
accuracy: 0.938
|
||||
|
|
|
|||
Некоторые файлы не были показаны из-за слишком большого количества измененных файлов Показать больше
Загрузка…
Ссылка в новой задаче