Update README.md
Browse files
README.md
CHANGED
|
@@ -44,13 +44,14 @@ hf (pretrained=Lambent/Falcon3-Continued-0.3-10B-Base), gen_kwargs: (None), limi
|
|
| 44 |
| | |none | 0|acc_norm|↑ |0.9500|± |0.0069|
|
| 45 |
|winogrande | 1|none | 0|acc |↑ |0.7332|± |0.0124|
|
| 46 |
|
| 47 |
-
MuSR
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
-
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | murder mysteries | cot+ | 145 / 250 | (run cost = 0.00, iteration cost = 0.00): 100%|█| 250/250 [2:
|
| 50 |
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | murder mysteries | cot+ | 145 / 250 | 58.0
|
| 51 |
-
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | object placements | cot+ | 83 / 256 | (run cost = 0.00, iteration cost = 0.00): 100%|█| 64/64 [3:02:07
|
| 52 |
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | object placements | cot+ | 83 / 256 | 32.4
|
| 53 |
-
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | team allocation | cot+ | 112 / 250 | (run cost = 0.00, iteration cost = 0.00): 100%|█| 250/250 [2:37:1
|
| 54 |
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | team allocation | cot+ | 112 / 250 | 44.8
|
| 55 |
|
| 56 |
Original under same conditions:
|
|
@@ -76,4 +77,14 @@ hf (pretrained=tiiuae/Falcon3-10B-Base), gen_kwargs: (None), limit: None, num_fe
|
|
| 76 |
| | |none | 0|acc_norm|↑ |0.7949|± |0.0094|
|
| 77 |
|sciq | 1|none | 0|acc |↑ |0.9610|± |0.0061|
|
| 78 |
| | |none | 0|acc_norm|↑ |0.9360|± |0.0077|
|
| 79 |
-
|winogrande | 1|none | 0|acc |↑ |0.7364|± |0.0124|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
| | |none | 0|acc_norm|↑ |0.9500|± |0.0069|
|
| 45 |
|winogrande | 1|none | 0|acc |↑ |0.7332|± |0.0124|
|
| 46 |
|
| 47 |
+
MuSR:
|
| 48 |
+
|
| 49 |
+
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | murder mysteries | regular | 134 / 250 | 53.6
|
| 50 |
+
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | object placements | regular | 130 / 256 | 50.8
|
| 51 |
+
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | team allocation | regular | 100 / 250 | 40.0
|
| 52 |
|
|
|
|
| 53 |
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | murder mysteries | cot+ | 145 / 250 | 58.0
|
|
|
|
| 54 |
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | object placements | cot+ | 83 / 256 | 32.4
|
|
|
|
| 55 |
RUNNING | Lambent/Falcon3-Continued-0.3-10B-Base | team allocation | cot+ | 112 / 250 | 44.8
|
| 56 |
|
| 57 |
Original under same conditions:
|
|
|
|
| 77 |
| | |none | 0|acc_norm|↑ |0.7949|± |0.0094|
|
| 78 |
|sciq | 1|none | 0|acc |↑ |0.9610|± |0.0061|
|
| 79 |
| | |none | 0|acc_norm|↑ |0.9360|± |0.0077|
|
| 80 |
+
|winogrande | 1|none | 0|acc |↑ |0.7364|± |0.0124|
|
| 81 |
+
|
| 82 |
+
MuSR:
|
| 83 |
+
|
| 84 |
+
RUNNING | tiiuae/Falcon3-10B-Base | murder mysteries | regular | 144 / 250 | 57.6
|
| 85 |
+
RUNNING | tiiuae/Falcon3-10B-Base | object placements | regular | 124 / 256 | 48.4
|
| 86 |
+
RUNNING | tiiuae/Falcon3-10B-Base | team allocation | regular | 126 / 250 | 50.4
|
| 87 |
+
|
| 88 |
+
RUNNING | tiiuae/Falcon3-10B-Base | murder mysteries | cot+ | 140 / 250 | 56.0
|
| 89 |
+
RUNNING | tiiuae/Falcon3-10B-Base | object placements | cot+ | 139 / 256 | 54.3
|
| 90 |
+
RUNNING | tiiuae/Falcon3-10B-Base | team allocation | cot+ | 118 / 250 | 47.2
|