Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ model-index:
|
|
| 12 |
name: Romanian_Academic_Benchmarks
|
| 13 |
type: Romanian_Academic_Benchmarks
|
| 14 |
metrics:
|
| 15 |
-
- name: Average
|
| 16 |
type: accuracy
|
| 17 |
value: 38.033944444444444
|
| 18 |
- task:
|
|
@@ -21,7 +21,7 @@ model-index:
|
|
| 21 |
name: OpenLLM-Ro/ro_arc_challenge
|
| 22 |
type: OpenLLM-Ro/ro_arc_challenge
|
| 23 |
metrics:
|
| 24 |
-
- name: Average
|
| 25 |
type: accuracy
|
| 26 |
value: 37.945
|
| 27 |
- task:
|
|
@@ -30,7 +30,7 @@ model-index:
|
|
| 30 |
name: OpenLLM-Ro/ro_mmlu
|
| 31 |
type: OpenLLM-Ro/ro_mmlu
|
| 32 |
metrics:
|
| 33 |
-
- name: Average
|
| 34 |
type: accuracy
|
| 35 |
value: 27.2175
|
| 36 |
- task:
|
|
@@ -39,7 +39,7 @@ model-index:
|
|
| 39 |
name: OpenLLM-Ro/ro_winogrande
|
| 40 |
type: OpenLLM-Ro/ro_winogrande
|
| 41 |
metrics:
|
| 42 |
-
- name: Average
|
| 43 |
type: accuracy
|
| 44 |
value: 59.2925
|
| 45 |
- task:
|
|
@@ -48,7 +48,7 @@ model-index:
|
|
| 48 |
name: OpenLLM-Ro/ro_hellaswag
|
| 49 |
type: OpenLLM-Ro/ro_hellaswag
|
| 50 |
metrics:
|
| 51 |
-
- name: Average
|
| 52 |
type: accuracy
|
| 53 |
value: 57.222
|
| 54 |
- task:
|
|
@@ -57,7 +57,7 @@ model-index:
|
|
| 57 |
name: OpenLLM-Ro/ro_gsm8k
|
| 58 |
type: OpenLLM-Ro/ro_gsm8k
|
| 59 |
metrics:
|
| 60 |
-
- name: Average
|
| 61 |
type: accuracy
|
| 62 |
value: 2.526666666666667
|
| 63 |
- task:
|
|
@@ -66,7 +66,7 @@ model-index:
|
|
| 66 |
name: OpenLLM-Ro/ro_truthfulqa
|
| 67 |
type: OpenLLM-Ro/ro_truthfulqa
|
| 68 |
metrics:
|
| 69 |
-
- name: Average
|
| 70 |
type: accuracy
|
| 71 |
value: 44.0
|
| 72 |
- task:
|
|
@@ -75,7 +75,7 @@ model-index:
|
|
| 75 |
name: LaRoSeDa_binary
|
| 76 |
type: LaRoSeDa_binary
|
| 77 |
metrics:
|
| 78 |
-
- name: Average
|
| 79 |
type: macro-f1
|
| 80 |
value: 83.245
|
| 81 |
- task:
|
|
@@ -84,7 +84,7 @@ model-index:
|
|
| 84 |
name: LaRoSeDa_multiclass
|
| 85 |
type: LaRoSeDa_multiclass
|
| 86 |
metrics:
|
| 87 |
-
- name: Average
|
| 88 |
type: macro-f1
|
| 89 |
value: 61.040000000000006
|
| 90 |
- task:
|
|
@@ -93,7 +93,7 @@ model-index:
|
|
| 93 |
name: LaRoSeDa_binary_finetuned
|
| 94 |
type: LaRoSeDa_binary_finetuned
|
| 95 |
metrics:
|
| 96 |
-
- name: Average
|
| 97 |
type: macro-f1
|
| 98 |
value: 98.9666527738873
|
| 99 |
- task:
|
|
@@ -102,7 +102,7 @@ model-index:
|
|
| 102 |
name: LaRoSeDa_multiclass_finetuned
|
| 103 |
type: LaRoSeDa_multiclass_finetuned
|
| 104 |
metrics:
|
| 105 |
-
- name: Average
|
| 106 |
type: macro-f1
|
| 107 |
value: 87.7198050161592
|
| 108 |
- task:
|
|
@@ -111,7 +111,7 @@ model-index:
|
|
| 111 |
name: WMT_EN-RO
|
| 112 |
type: WMT_EN-RO
|
| 113 |
metrics:
|
| 114 |
-
- name: Average
|
| 115 |
type: bleu
|
| 116 |
value: 10.01
|
| 117 |
- task:
|
|
@@ -120,7 +120,7 @@ model-index:
|
|
| 120 |
name: WMT_RO-EN
|
| 121 |
type: WMT_RO-EN
|
| 122 |
metrics:
|
| 123 |
-
- name: Average
|
| 124 |
type: bleu
|
| 125 |
value: 13.032499999999999
|
| 126 |
- task:
|
|
@@ -129,7 +129,7 @@ model-index:
|
|
| 129 |
name: WMT_EN-RO_finetuned
|
| 130 |
type: WMT_EN-RO_finetuned
|
| 131 |
metrics:
|
| 132 |
-
- name: Average
|
| 133 |
type: bleu
|
| 134 |
value: 27.8468226696502
|
| 135 |
- task:
|
|
@@ -138,7 +138,7 @@ model-index:
|
|
| 138 |
name: WMT_RO-EN_finetuned
|
| 139 |
type: WMT_RO-EN_finetuned
|
| 140 |
metrics:
|
| 141 |
-
- name: Average
|
| 142 |
type: bleu
|
| 143 |
value: 39.300054525566104
|
| 144 |
- task:
|
|
@@ -147,7 +147,7 @@ model-index:
|
|
| 147 |
name: XQuAD
|
| 148 |
type: XQuAD
|
| 149 |
metrics:
|
| 150 |
-
- name: Average
|
| 151 |
type: exact_match
|
| 152 |
value: 30.14705
|
| 153 |
- task:
|
|
@@ -156,7 +156,7 @@ model-index:
|
|
| 156 |
name: XQuAD
|
| 157 |
type: XQuAD
|
| 158 |
metrics:
|
| 159 |
-
- name: Average
|
| 160 |
type: f1
|
| 161 |
value: 47.0304
|
| 162 |
- task:
|
|
@@ -165,7 +165,7 @@ model-index:
|
|
| 165 |
name: XQuAD_finetuned
|
| 166 |
type: XQuAD_finetuned
|
| 167 |
metrics:
|
| 168 |
-
- name: Average
|
| 169 |
type: exact_match
|
| 170 |
value: 67.0588235294117
|
| 171 |
- task:
|
|
@@ -174,7 +174,7 @@ model-index:
|
|
| 174 |
name: XQuAD
|
| 175 |
type: XQuAD
|
| 176 |
metrics:
|
| 177 |
-
- name: Average
|
| 178 |
type: f1
|
| 179 |
value: 79.9624140326139
|
| 180 |
- task:
|
|
@@ -183,7 +183,7 @@ model-index:
|
|
| 183 |
name: STS
|
| 184 |
type: STS
|
| 185 |
metrics:
|
| 186 |
-
- name: Average
|
| 187 |
type: spearman
|
| 188 |
value: 7.886666666666667
|
| 189 |
- task:
|
|
@@ -192,7 +192,7 @@ model-index:
|
|
| 192 |
name: STS
|
| 193 |
type: STS
|
| 194 |
metrics:
|
| 195 |
-
- name: Average
|
| 196 |
type: pearson
|
| 197 |
value: 7.976666666666667
|
| 198 |
- task:
|
|
@@ -201,7 +201,7 @@ model-index:
|
|
| 201 |
name: STS_finetuned
|
| 202 |
type: STS_finetuned
|
| 203 |
metrics:
|
| 204 |
-
- name: Average
|
| 205 |
type: spearman
|
| 206 |
value: 71.749068976055
|
| 207 |
- task:
|
|
@@ -210,7 +210,7 @@ model-index:
|
|
| 210 |
name: STS_finetuned
|
| 211 |
type: STS_finetuned
|
| 212 |
metrics:
|
| 213 |
-
- name: Average
|
| 214 |
type: pearson
|
| 215 |
value: 71.9866084841066
|
| 216 |
---
|
|
|
|
| 12 |
name: Romanian_Academic_Benchmarks
|
| 13 |
type: Romanian_Academic_Benchmarks
|
| 14 |
metrics:
|
| 15 |
+
- name: Average accuracy
|
| 16 |
type: accuracy
|
| 17 |
value: 38.033944444444444
|
| 18 |
- task:
|
|
|
|
| 21 |
name: OpenLLM-Ro/ro_arc_challenge
|
| 22 |
type: OpenLLM-Ro/ro_arc_challenge
|
| 23 |
metrics:
|
| 24 |
+
- name: Average accuracy
|
| 25 |
type: accuracy
|
| 26 |
value: 37.945
|
| 27 |
- task:
|
|
|
|
| 30 |
name: OpenLLM-Ro/ro_mmlu
|
| 31 |
type: OpenLLM-Ro/ro_mmlu
|
| 32 |
metrics:
|
| 33 |
+
- name: Average accuracy
|
| 34 |
type: accuracy
|
| 35 |
value: 27.2175
|
| 36 |
- task:
|
|
|
|
| 39 |
name: OpenLLM-Ro/ro_winogrande
|
| 40 |
type: OpenLLM-Ro/ro_winogrande
|
| 41 |
metrics:
|
| 42 |
+
- name: Average accuracy
|
| 43 |
type: accuracy
|
| 44 |
value: 59.2925
|
| 45 |
- task:
|
|
|
|
| 48 |
name: OpenLLM-Ro/ro_hellaswag
|
| 49 |
type: OpenLLM-Ro/ro_hellaswag
|
| 50 |
metrics:
|
| 51 |
+
- name: Average accuracy
|
| 52 |
type: accuracy
|
| 53 |
value: 57.222
|
| 54 |
- task:
|
|
|
|
| 57 |
name: OpenLLM-Ro/ro_gsm8k
|
| 58 |
type: OpenLLM-Ro/ro_gsm8k
|
| 59 |
metrics:
|
| 60 |
+
- name: Average accuracy
|
| 61 |
type: accuracy
|
| 62 |
value: 2.526666666666667
|
| 63 |
- task:
|
|
|
|
| 66 |
name: OpenLLM-Ro/ro_truthfulqa
|
| 67 |
type: OpenLLM-Ro/ro_truthfulqa
|
| 68 |
metrics:
|
| 69 |
+
- name: Average accuracy
|
| 70 |
type: accuracy
|
| 71 |
value: 44.0
|
| 72 |
- task:
|
|
|
|
| 75 |
name: LaRoSeDa_binary
|
| 76 |
type: LaRoSeDa_binary
|
| 77 |
metrics:
|
| 78 |
+
- name: Average macro-f1
|
| 79 |
type: macro-f1
|
| 80 |
value: 83.245
|
| 81 |
- task:
|
|
|
|
| 84 |
name: LaRoSeDa_multiclass
|
| 85 |
type: LaRoSeDa_multiclass
|
| 86 |
metrics:
|
| 87 |
+
- name: Average macro-f1
|
| 88 |
type: macro-f1
|
| 89 |
value: 61.040000000000006
|
| 90 |
- task:
|
|
|
|
| 93 |
name: LaRoSeDa_binary_finetuned
|
| 94 |
type: LaRoSeDa_binary_finetuned
|
| 95 |
metrics:
|
| 96 |
+
- name: Average macro-f1
|
| 97 |
type: macro-f1
|
| 98 |
value: 98.9666527738873
|
| 99 |
- task:
|
|
|
|
| 102 |
name: LaRoSeDa_multiclass_finetuned
|
| 103 |
type: LaRoSeDa_multiclass_finetuned
|
| 104 |
metrics:
|
| 105 |
+
- name: Average macro-f1
|
| 106 |
type: macro-f1
|
| 107 |
value: 87.7198050161592
|
| 108 |
- task:
|
|
|
|
| 111 |
name: WMT_EN-RO
|
| 112 |
type: WMT_EN-RO
|
| 113 |
metrics:
|
| 114 |
+
- name: Average bleu
|
| 115 |
type: bleu
|
| 116 |
value: 10.01
|
| 117 |
- task:
|
|
|
|
| 120 |
name: WMT_RO-EN
|
| 121 |
type: WMT_RO-EN
|
| 122 |
metrics:
|
| 123 |
+
- name: Average bleu
|
| 124 |
type: bleu
|
| 125 |
value: 13.032499999999999
|
| 126 |
- task:
|
|
|
|
| 129 |
name: WMT_EN-RO_finetuned
|
| 130 |
type: WMT_EN-RO_finetuned
|
| 131 |
metrics:
|
| 132 |
+
- name: Average bleu
|
| 133 |
type: bleu
|
| 134 |
value: 27.8468226696502
|
| 135 |
- task:
|
|
|
|
| 138 |
name: WMT_RO-EN_finetuned
|
| 139 |
type: WMT_RO-EN_finetuned
|
| 140 |
metrics:
|
| 141 |
+
- name: Average bleu
|
| 142 |
type: bleu
|
| 143 |
value: 39.300054525566104
|
| 144 |
- task:
|
|
|
|
| 147 |
name: XQuAD
|
| 148 |
type: XQuAD
|
| 149 |
metrics:
|
| 150 |
+
- name: Average exact_match
|
| 151 |
type: exact_match
|
| 152 |
value: 30.14705
|
| 153 |
- task:
|
|
|
|
| 156 |
name: XQuAD
|
| 157 |
type: XQuAD
|
| 158 |
metrics:
|
| 159 |
+
- name: Average f1
|
| 160 |
type: f1
|
| 161 |
value: 47.0304
|
| 162 |
- task:
|
|
|
|
| 165 |
name: XQuAD_finetuned
|
| 166 |
type: XQuAD_finetuned
|
| 167 |
metrics:
|
| 168 |
+
- name: Average exact_match
|
| 169 |
type: exact_match
|
| 170 |
value: 67.0588235294117
|
| 171 |
- task:
|
|
|
|
| 174 |
name: XQuAD
|
| 175 |
type: XQuAD
|
| 176 |
metrics:
|
| 177 |
+
- name: Average f1
|
| 178 |
type: f1
|
| 179 |
value: 79.9624140326139
|
| 180 |
- task:
|
|
|
|
| 183 |
name: STS
|
| 184 |
type: STS
|
| 185 |
metrics:
|
| 186 |
+
- name: Average spearman
|
| 187 |
type: spearman
|
| 188 |
value: 7.886666666666667
|
| 189 |
- task:
|
|
|
|
| 192 |
name: STS
|
| 193 |
type: STS
|
| 194 |
metrics:
|
| 195 |
+
- name: Average pearson
|
| 196 |
type: pearson
|
| 197 |
value: 7.976666666666667
|
| 198 |
- task:
|
|
|
|
| 201 |
name: STS_finetuned
|
| 202 |
type: STS_finetuned
|
| 203 |
metrics:
|
| 204 |
+
- name: Average spearman
|
| 205 |
type: spearman
|
| 206 |
value: 71.749068976055
|
| 207 |
- task:
|
|
|
|
| 210 |
name: STS_finetuned
|
| 211 |
type: STS_finetuned
|
| 212 |
metrics:
|
| 213 |
+
- name: Average pearson
|
| 214 |
type: pearson
|
| 215 |
value: 71.9866084841066
|
| 216 |
---
|