update evaluation results from azureml-assets to azureml-asset repo.
This commit is contained in:
Chandra Sekhar Gupta Aravapalli
Родитель
142476f1c2
Коммит
797f4b28fb
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_cohere-embed-v3-english_classification
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_cohere-embed-v3-english_classification
|
||||
description: cohere-embed-v3-english run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
dataset_family: AmazonPolarityClassification
|
||||
|
||||
model_name: cohere-embed-v3-english
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_cohere-embed-v3-multilingual_classification
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_cohere-embed-v3-multilingual_classification
|
||||
description: cohere-embed-v3-multilingual run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
dataset_family: AmazonPolarityClassification
|
||||
|
||||
model_name: cohere-embed-v3-multilingual
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_text-embedding-3-large_classification
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_text-embedding-3-large_classification
|
||||
description: text-embedding-3-large run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
dataset_family: AmazonPolarityClassification
|
||||
|
||||
model_name: text-embedding-3-large
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_text-embedding-3-small_classification
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_text-embedding-3-small_classification
|
||||
description: text-embedding-3-small run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
dataset_family: AmazonPolarityClassification
|
||||
|
||||
model_name: text-embedding-3-small
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: amazonpolarityclassification_text-embedding-ada-002_classification
|
||||
version: 2.04.11
|
||||
display_name: AmazonPolarityClassification_text-embedding-ada-002_classification
|
||||
description: text-embedding-ada-002 run for AmazonPolarityClassification dataset
|
||||
dataset_name: AmazonPolarityClassification
|
||||
dataset_family: AmazonPolarityClassification
|
||||
|
||||
model_name: text-embedding-ada-002
|
||||
model_version: "2"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arguana_cohere-embed-v3-english_retrieval
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_cohere-embed-v3-english_retrieval
|
||||
description: cohere-embed-v3-english run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
dataset_family: ArguAna
|
||||
|
||||
model_name: cohere-embed-v3-english
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arguana_cohere-embed-v3-multilingual_retrieval
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_cohere-embed-v3-multilingual_retrieval
|
||||
description: cohere-embed-v3-multilingual run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
dataset_family: ArguAna
|
||||
|
||||
model_name: cohere-embed-v3-multilingual
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arguana_text-embedding-3-large_retrieval
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_text-embedding-3-large_retrieval
|
||||
description: text-embedding-3-large run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
dataset_family: ArguAna
|
||||
|
||||
model_name: text-embedding-3-large
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arguana_text-embedding-3-small_retrieval
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_text-embedding-3-small_retrieval
|
||||
description: text-embedding-3-small run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
dataset_family: ArguAna
|
||||
|
||||
model_name: text-embedding-3-small
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arguana_text-embedding-ada-002_retrieval
|
||||
version: 2.04.11
|
||||
display_name: ArguAna_text-embedding-ada-002_retrieval
|
||||
description: text-embedding-ada-002 run for ArguAna dataset
|
||||
dataset_name: ArguAna
|
||||
dataset_family: ArguAna
|
||||
|
||||
model_name: text-embedding-ada-002
|
||||
model_version: "2"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_cohere-embed-v3-english_clustering
|
||||
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
|
||||
dataset_family: ArxivClusteringP2P.v2
|
||||
|
||||
model_name: cohere-embed-v3-english
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_cohere-embed-v3-multilingual_clustering
|
||||
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
|
||||
dataset_family: ArxivClusteringP2P.v2
|
||||
|
||||
model_name: cohere-embed-v3-multilingual
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_text-embedding-3-large_clustering
|
||||
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
|
||||
dataset_family: ArxivClusteringP2P.v2
|
||||
|
||||
model_name: text-embedding-3-large
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_text-embedding-3-small_clustering
|
||||
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
|
||||
dataset_family: ArxivClusteringP2P.v2
|
||||
|
||||
model_name: text-embedding-3-small
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusteringp2p.v2_text-embedding-ada-002_clustering
|
||||
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
|
||||
dataset_family: ArxivClusteringP2P.v2
|
||||
|
||||
model_name: text-embedding-ada-002
|
||||
model_version: "2"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_cohere-embed-v3-english_clustering
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_cohere-embed-v3-english_clustering
|
||||
description: cohere-embed-v3-english run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
dataset_family: ArxivClusteringS2S
|
||||
|
||||
model_name: cohere-embed-v3-english
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_cohere-embed-v3-multilingual_clustering
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_cohere-embed-v3-multilingual_clustering
|
||||
description: cohere-embed-v3-multilingual run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
dataset_family: ArxivClusteringS2S
|
||||
|
||||
model_name: cohere-embed-v3-multilingual
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_text-embedding-3-large_clustering
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_text-embedding-3-large_clustering
|
||||
description: text-embedding-3-large run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
dataset_family: ArxivClusteringS2S
|
||||
|
||||
model_name: text-embedding-3-large
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_text-embedding-3-small_clustering
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_text-embedding-3-small_clustering
|
||||
description: text-embedding-3-small run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
dataset_family: ArxivClusteringS2S
|
||||
|
||||
model_name: text-embedding-3-small
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: arxivclusterings2s_text-embedding-ada-002_clustering
|
||||
version: 2.04.11
|
||||
display_name: ArxivClusteringS2S_text-embedding-ada-002_clustering
|
||||
description: text-embedding-ada-002 run for ArxivClusteringS2S dataset
|
||||
dataset_name: ArxivClusteringS2S
|
||||
dataset_family: ArxivClusteringS2S
|
||||
|
||||
model_name: text-embedding-ada-002
|
||||
model_version: "2"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_cohere-embed-v3-english_classification
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_cohere-embed-v3-english_classification
|
||||
description: cohere-embed-v3-english run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
dataset_family: Banking77Classification
|
||||
|
||||
model_name: cohere-embed-v3-english
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-english/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_cohere-embed-v3-multilingual_classification
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_cohere-embed-v3-multilingual_classification
|
||||
description: cohere-embed-v3-multilingual run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
dataset_family: Banking77Classification
|
||||
|
||||
model_name: cohere-embed-v3-multilingual
|
||||
model_version: "3"
|
||||
model_asset_id: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-cohere/models/Cohere-embed-v3-multilingual/versions/3
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_text-embedding-3-large_classification
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_text-embedding-3-large_classification
|
||||
description: text-embedding-3-large run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
dataset_family: Banking77Classification
|
||||
|
||||
model_name: text-embedding-3-large
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-large/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_text-embedding-3-small_classification
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_text-embedding-3-small_classification
|
||||
description: text-embedding-3-small run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
dataset_family: Banking77Classification
|
||||
|
||||
model_name: text-embedding-3-small
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-3-small/versions/1
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: banking77classification_text-embedding-ada-002_classification
|
||||
version: 2.04.11
|
||||
display_name: Banking77Classification_text-embedding-ada-002_classification
|
||||
description: text-embedding-ada-002 run for Banking77Classification dataset
|
||||
dataset_name: Banking77Classification
|
||||
dataset_family: Banking77Classification
|
||||
|
||||
model_name: text-embedding-ada-002
|
||||
model_version: "2"
|
||||
model_asset_id: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/text-embedding-ada-002/versions/2
|
||||
|
||||
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
|
||||
|
||||
properties: {}
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq__gpt-4-0125-preview__question_answering
|
||||
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: "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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq__meta-llama-3_1-70b-instruct__question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Meta-Llama-3.1-70B-Instruct
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3.1-70B-Instruct/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Meta-Llama-3.1-70B-Instruct/versions/1
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq__meta-llama-3_1-8b-instruct__question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Meta-Llama-3.1-8B-Instruct
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3.1-8B-Instruct/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Meta-Llama-3.1-8B-Instruct/versions/1
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_cohere_command_r_plus_question_answering
|
||||
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: "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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_cohere_command_r_question_answering
|
||||
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: "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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_databricks-dbrx-base_question_answering
|
||||
version: 2.04.11
|
||||
display_name: boolq_databricks-dbrx-base_question_answering
|
||||
description: databricks-dbrx-base run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: databricks-dbrx-base
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-restricted/models/databricks-dbrx-base/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-restricted/models/databricks-dbrx-base/versions/1
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_databricks-dbrx-instruct_question_answering
|
||||
version: 2.04.11
|
||||
display_name: boolq_databricks-dbrx-instruct_question_answering
|
||||
description: databricks-dbrx-instruct run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: databricks-dbrx-instruct
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-restricted/models/databricks-dbrx-instruct/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-restricted/models/databricks-dbrx-instruct/versions/1
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt-4-turbo-2024-04-09_chat_completion
|
||||
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
|
||||
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/turbo-2024-04-09
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt-4o_question_answering
|
||||
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-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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_35_turbo_0301_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-35-turbo-0301
|
||||
model_version: "0301"
|
||||
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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_35_turbo_0613_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-35-turbo-0613
|
||||
model_version: "0613"
|
||||
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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_0314_question_answering
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_4_0314_question_answering
|
||||
description: gpt-4-0314 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-4-0314
|
||||
model_version: "0314"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azure-openai/models/gpt-4/versions/4
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_0613_question_answering
|
||||
version: 2.04.11
|
||||
display_name: boolq_gpt_4_0613_question_answering
|
||||
description: gpt-4-0613 run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-4-0613
|
||||
model_version: "0613"
|
||||
model_asset_id: azureml://registries/azure-openai/models/gpt-4/versions/0613
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_32k_0314_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-4-32k-0314
|
||||
model_version: "0314"
|
||||
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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_gpt_4_32k_0613_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: gpt-4-32k-0613
|
||||
model_version: "0613"
|
||||
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/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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_13b_chat_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: llama-2-13b-chat
|
||||
model_version: "12"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Llama-2-13b-chat/versions/12
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Llama-2-13b-chat/versions/12
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_13b_question_answering
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_13b_question_answering
|
||||
description: llama-2-13b run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: llama-2-13b
|
||||
model_version: "12"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Llama-2-13b/versions/12
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Llama-2-13b/versions/12
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_70b_chat_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: llama-2-70b-chat
|
||||
model_version: "12"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Llama-2-70b-chat/versions/12
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Llama-2-70b-chat/versions/12
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_70b_question_answering
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_70b_question_answering
|
||||
description: llama-2-70b run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: llama-2-70b
|
||||
model_version: "13"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Llama-2-70b/versions/13
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Llama-2-70b/versions/13
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_7b_chat_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: llama-2-7b-chat
|
||||
model_version: "14"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Llama-2-7b-chat/versions/14
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Llama-2-7b-chat/versions/14
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_llama_2_7b_question_answering
|
||||
version: 2.04.11
|
||||
display_name: boolq_llama_2_7b_question_answering
|
||||
description: llama-2-7b run for boolq dataset
|
||||
dataset_family: boolq
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: llama-2-7b
|
||||
model_version: "12"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Llama-2-7b/versions/12
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Llama-2-7b/versions/12
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-70b-instruct_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Meta-Llama-3-70B-Instruct
|
||||
model_version: "2"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-70B-Instruct/versions/2
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Meta-Llama-3-70B-Instruct/versions/2
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-70b_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Meta-Llama-3-70B
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-70B/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Meta-Llama-3-70B/versions/1
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-8b-instruct_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Meta-Llama-3-8B-Instruct
|
||||
model_version: "2"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-8B-Instruct/versions/2
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Meta-Llama-3-8B-Instruct/versions/2
|
||||
|
||||
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: 0.863302752
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
type: evaluationresult
|
||||
spec: spec.yaml
|
||||
categories: ["EvaluationResult"]
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
type: evaluationresult
|
||||
name: boolq_meta-llama-3-8b_question_answering
|
||||
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
|
||||
dataset_name: boolq
|
||||
|
||||
model_name: Meta-Llama-3-8B
|
||||
model_version: "1"
|
||||
model_asset_id: azureml://registries/azureml-meta/models/Meta-Llama-3-8B/versions/1
|
||||
|
||||
relationships:
|
||||
- relationshipType: Source
|
||||
assetId: azureml://registries/azureml-meta/models/Meta-Llama-3-8B/versions/1
|
||||
|
||||
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
|
||||
|
||||
|
||||
properties:
|
||||
n_shot: 5
|
||||
evaluation_sampling_ratio: 1.0
|
||||
evaluation_split: "validation"
|
||||
fewshot_sampling_ratio: 1.0
|
||||
fewshot_split: "train"
|
||||
Некоторые файлы не были показаны из-за слишком большого количества измененных файлов Показать больше
Загрузка…
Ссылка в новой задаче