Initial commit + new eval

README.md

@@ -29,6 +29,75 @@ model-index:
       value: 29.128
     - type: f1
       value: 28.657401543151707
+  - task:
+      type: Retrieval
+    dataset:
+      type: arguana
+      name: MTEB ArguAna
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 24.111
+    - type: map_at_10
+      value: 40.083
+    - type: map_at_100
+      value: 41.201
+    - type: map_at_1000
+      value: 41.215
+    - type: map_at_3
+      value: 35.325
+    - type: map_at_5
+      value: 37.796
+    - type: mrr_at_1
+      value: 25.036
+    - type: mrr_at_10
+      value: 40.436
+    - type: mrr_at_100
+      value: 41.554
+    - type: mrr_at_1000
+      value: 41.568
+    - type: mrr_at_3
+      value: 35.644999999999996
+    - type: mrr_at_5
+      value: 38.141000000000005
+    - type: ndcg_at_1
+      value: 24.111
+    - type: ndcg_at_10
+      value: 49.112
+    - type: ndcg_at_100
+      value: 53.669999999999995
+    - type: ndcg_at_1000
+      value: 53.944
+    - type: ndcg_at_3
+      value: 39.035
+    - type: ndcg_at_5
+      value: 43.503
+    - type: precision_at_1
+      value: 24.111
+    - type: precision_at_10
+      value: 7.817
+    - type: precision_at_100
+      value: 0.976
+    - type: precision_at_1000
+      value: 0.1
+    - type: precision_at_3
+      value: 16.596
+    - type: precision_at_5
+      value: 12.134
+    - type: recall_at_1
+      value: 24.111
+    - type: recall_at_10
+      value: 78.16499999999999
+    - type: recall_at_100
+      value: 97.58200000000001
+    - type: recall_at_1000
+      value: 99.57300000000001
+    - type: recall_at_3
+      value: 49.787
+    - type: recall_at_5
+      value: 60.669
   - task:
       type: Classification
     dataset:
@@ -111,6 +180,75 @@ model-index:
       value: 68.691
     - type: recall_at_5
       value: 80.742
+  - task:
+      type: Retrieval
+    dataset:
+      type: nfcorpus
+      name: MTEB NFCorpus
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 4.124
+    - type: map_at_10
+      value: 10.206999999999999
+    - type: map_at_100
+      value: 13.181000000000001
+    - type: map_at_1000
+      value: 14.568
+    - type: map_at_3
+      value: 7.2620000000000005
+    - type: map_at_5
+      value: 8.622
+    - type: mrr_at_1
+      value: 39.009
+    - type: mrr_at_10
+      value: 48.144
+    - type: mrr_at_100
+      value: 48.746
+    - type: mrr_at_1000
+      value: 48.789
+    - type: mrr_at_3
+      value: 45.356
+    - type: mrr_at_5
+      value: 47.152
+    - type: ndcg_at_1
+      value: 36.533
+    - type: ndcg_at_10
+      value: 29.643000000000004
+    - type: ndcg_at_100
+      value: 27.893
+    - type: ndcg_at_1000
+      value: 37.307
+    - type: ndcg_at_3
+      value: 33.357
+    - type: ndcg_at_5
+      value: 32.25
+    - type: precision_at_1
+      value: 38.7
+    - type: precision_at_10
+      value: 22.941
+    - type: precision_at_100
+      value: 7.303
+    - type: precision_at_1000
+      value: 2.028
+    - type: precision_at_3
+      value: 31.889
+    - type: precision_at_5
+      value: 29.04
+    - type: recall_at_1
+      value: 4.124
+    - type: recall_at_10
+      value: 14.443
+    - type: recall_at_100
+      value: 29.765000000000004
+    - type: recall_at_1000
+      value: 63.074
+    - type: recall_at_3
+      value: 8.516
+    - type: recall_at_5
+      value: 10.979
   - task:
       type: Retrieval
     dataset: