Hugging Face's logo

Spaces:
RUC-NLPIR
/
OmniEval
Running

App Files Community
zstanjj commited on
Commit
ee70019
•
1 Parent(s): b5a12e3

fix results

Browse files
Files changed (10) hide show
  1. eval-results/omnieval-auto/bge-large-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  2. eval-results/omnieval-auto/bge-m3_qwen2-72b/results_2023-12-08 15:46:20.425378.json +5 -5
  3. eval-results/omnieval-auto/e5-mistral-7b_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  4. eval-results/omnieval-auto/gte-qwen2-1.5b_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  5. eval-results/omnieval-auto/jina-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  6. eval-results/omnieval-human/bge-large-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  7. eval-results/omnieval-human/bge-m3_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  8. eval-results/omnieval-human/e5-mistral-7b_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  9. eval-results/omnieval-human/gte-qwen2-1.5b_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
  10. eval-results/omnieval-human/jina-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json +1 -1
eval-results/omnieval-auto/bge-large-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.16098924930699862,
13
  "accuracy": 0.3906427579239803,
14
  "completeness": 0.5930474914396308,
15
- "hallucination": 0.0,
16
  "utilization": 0.5045650189122212,
17
  "numerical_accuracy": 0.28149656401119877
18
  }
 
12
  "rougeL": 0.16098924930699862,
13
  "accuracy": 0.3906427579239803,
14
  "completeness": 0.5930474914396308,
15
+ "hallucination": 0.06504488096786783,
16
  "utilization": 0.5045650189122212,
17
  "numerical_accuracy": 0.28149656401119877
18
  }
eval-results/omnieval-auto/bge-m3_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -10,11 +10,11 @@
10
  "rouge1": 0.2542055585319881,
11
  "rouge2": 0.12967013110722864,
12
  "rougeL": 0.16623387811734364,
13
- "accuracy": 0.0,
14
- "completeness": 0.0,
15
- "hallucination": 0.0,
16
- "utilization": 0.0,
17
- "numerical_accuracy": 0.0
18
  }
19
  },
20
  "config": {
 
10
  "rouge1": 0.2542055585319881,
11
  "rouge2": 0.12967013110722864,
12
  "rougeL": 0.16623387811734364,
13
+ "accuracy": 0.4025188916876574,
14
+ "completeness": 0.6033108522378908,
15
+ "hallucination": 0.07283603096410979,
16
+ "utilization": 0.5141388174807198,
17
+ "numerical_accuracy": 0.3162303664921466
18
  }
19
  },
20
  "config": {
eval-results/omnieval-auto/e5-mistral-7b_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.1534679545927458,
13
  "accuracy": 0.37713095087763604,
14
  "completeness": 0.5855007473841555,
15
- "hallucination": 0.0,
16
  "utilization": 0.49136152656008253,
17
  "numerical_accuracy": 0.2582123758594347
18
  }
 
12
  "rougeL": 0.1534679545927458,
13
  "accuracy": 0.37713095087763604,
14
  "completeness": 0.5855007473841555,
15
+ "hallucination": 0.0676875562990606,
16
  "utilization": 0.49136152656008253,
17
  "numerical_accuracy": 0.2582123758594347
18
  }
eval-results/omnieval-auto/gte-qwen2-1.5b_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.1669344569228441,
13
  "accuracy": 0.40573304710190683,
14
  "completeness": 0.6131668895824045,
15
- "hallucination": 0.0,
16
  "utilization": 0.5346272891410885,
17
  "numerical_accuracy": 0.2971301335972291
18
  }
 
12
  "rougeL": 0.1669344569228441,
13
  "accuracy": 0.40573304710190683,
14
  "completeness": 0.6131668895824045,
15
+ "hallucination": 0.05456183245399562,
16
  "utilization": 0.5346272891410885,
17
  "numerical_accuracy": 0.2971301335972291
18
  }
eval-results/omnieval-auto/jina-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.1558018779014647,
13
  "accuracy": 0.3705644652102538,
14
  "completeness": 0.5820335932813437,
15
- "hallucination": 0.0,
16
  "utilization": 0.4738984364905027,
17
  "numerical_accuracy": 0.24648820567187915
18
  }
 
12
  "rougeL": 0.1558018779014647,
13
  "accuracy": 0.3705644652102538,
14
  "completeness": 0.5820335932813437,
15
+ "hallucination": 0.09210356820816695,
16
  "utilization": 0.4738984364905027,
17
  "numerical_accuracy": 0.24648820567187915
18
  }
eval-results/omnieval-human/bge-large-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.23230144566069125,
13
  "accuracy": 0.40888382687927105,
14
  "completeness": 0.6021044427123928,
15
- "hallucination": 0.0023391812865497076,
16
  "utilization": 0.5014637002341921,
17
  "numerical_accuracy": 0.3100358422939068
18
  }
 
12
  "rougeL": 0.23230144566069125,
13
  "accuracy": 0.40888382687927105,
14
  "completeness": 0.6021044427123928,
15
+ "hallucination": 0.08138173302107728,
16
  "utilization": 0.5014637002341921,
17
  "numerical_accuracy": 0.3100358422939068
18
  }
eval-results/omnieval-human/bge-m3_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.24141093461883717,
13
  "accuracy": 0.4271070615034169,
14
  "completeness": 0.6119287374128582,
15
- "hallucination": 0.0005847953216374269,
16
  "utilization": 0.5400116822429907,
17
  "numerical_accuracy": 0.3372093023255814
18
  }
 
12
  "rougeL": 0.24141093461883717,
13
  "accuracy": 0.4271070615034169,
14
  "completeness": 0.6119287374128582,
15
+ "hallucination": 0.07481005260081823,
16
  "utilization": 0.5400116822429907,
17
  "numerical_accuracy": 0.3372093023255814
18
  }
eval-results/omnieval-human/e5-mistral-7b_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.22225645997479143,
13
  "accuracy": 0.385250569476082,
14
  "completeness": 0.5877535101404057,
15
- "hallucination": 1.2922719349215572,
16
  "utilization": 0.4793244030285381,
17
  "numerical_accuracy": 0.28622540250447226
18
  }
 
12
  "rougeL": 0.22225645997479143,
13
  "accuracy": 0.385250569476082,
14
  "completeness": 0.5877535101404057,
15
+ "hallucination": 0.0924956369982548,
16
  "utilization": 0.4793244030285381,
17
  "numerical_accuracy": 0.28622540250447226
18
  }
eval-results/omnieval-human/gte-qwen2-1.5b_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.2383694455084706,
13
  "accuracy": 0.4145785876993166,
14
  "completeness": 0.598297213622291,
15
- "hallucination": 0.0011627906976744186,
16
  "utilization": 1.13922942206655,
17
  "numerical_accuracy": 0.3218694885361552
18
  }
 
12
  "rougeL": 0.2383694455084706,
13
  "accuracy": 0.4145785876993166,
14
  "completeness": 0.598297213622291,
15
+ "hallucination": 0.07213496218731821,
16
  "utilization": 1.13922942206655,
17
  "numerical_accuracy": 0.3218694885361552
18
  }
eval-results/omnieval-human/jina-zh_qwen2-72b/results_2023-12-08 15:46:20.425378.json CHANGED
@@ -12,7 +12,7 @@
12
  "rougeL": 0.22591939162851002,
13
  "accuracy": 0.3826879271070615,
14
  "completeness": 0.5793588741204065,
15
- "hallucination": 0.0017381228273464658,
16
  "utilization": 0.4855072463768116,
17
  "numerical_accuracy": 0.2663594470046083
18
  }
 
12
  "rougeL": 0.22591939162851002,
13
  "accuracy": 0.3826879271070615,
14
  "completeness": 0.5793588741204065,
15
+ "hallucination": 0.0897510133178923,
16
  "utilization": 0.4855072463768116,
17
  "numerical_accuracy": 0.2663594470046083
18
  }