Update README.md
Browse files
README.md
CHANGED
@@ -104,27 +104,29 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
|
|
104 |
|
105 |
#### Summary Metrics Comparison
|
106 |
|
107 |
-
|
108 |
-
|
109 |
-
|
|
110 |
-
|
111 |
-
|
|
112 |
-
|
|
113 |
-
|
|
|
|
|
|
114 |
|
115 |
-
*(Middle column usage = c
|
116 |
|
117 |
#### Move Distribution Comparison
|
118 |
|
119 |
-
| Column | Lyte/QuadConnect2.5-0.5B-v0.0.6b (Count, %) | Lyte/QuadConnect2.5-0.5B-v0.0.8b (Count, %) | Lyte/QuadConnect2.5-0.0.9b (Count, %) |
|
120 |
-
|
121 |
-
| a | 603 (19.02%) | 3 (0.12%) | 1447 (38.72%) |
|
122 |
-
| b | 111 (3.50%) | 4 (0.16%) | 644 (17.23%) |
|
123 |
-
| c | 785 (24.76%) | 463 (17.96%) | 648 (17.34%) |
|
124 |
-
| d | 1304 (41.14%) | 1743 (67.61%) | 101 (2.70%) |
|
125 |
-
| e | 290 (9.15%) | 360 (13.96%) | 338 (9.04%) |
|
126 |
-
| f | 50 (1.58%) | 3 (0.12%) | 310 (8.30%) |
|
127 |
-
| g | 27 (0.85%) | 2 (0.08%) | 249 (6.66%) |
|
128 |
|
129 |
|
130 |
|
|
|
104 |
|
105 |
#### Summary Metrics Comparison
|
106 |
|
107 |
+
#### Summary Metrics Comparison
|
108 |
+
|
109 |
+
| Metric | Lyte/QuadConnect2.5-0.5B-v0.0.6b | Lyte/QuadConnect2.5-0.5B-v0.0.8b | Lyte/QuadConnect2.5-0.0.9b (Temp 0.6) | Lyte/QuadConnect2.5-0.0.9b (Temp 0.8) |
|
110 |
+
|-----------------------|--------------------------------|--------------------------------|--------------------------------|--------------------------------|
|
111 |
+
| Total games evaluated | 5082 | 5082 | 5082 | 5082 |
|
112 |
+
| Correct predictions | 518 | 394 | 516 | **713** |
|
113 |
+
| Accuracy | 10.19% | 7.75% | 10.15% | **14.03%** |
|
114 |
+
| Most common move | d (41.14%) | d (67.61%) | a (38.72%) | **a (31.01%)** |
|
115 |
+
| Middle column usage | 75.05% | 99.53% | 29.08% | **35.43%** |
|
116 |
|
117 |
+
*(Middle column usage = c + d + e → 20.11% + 4.05% + 11.27% = 35.43%)*
|
118 |
|
119 |
#### Move Distribution Comparison
|
120 |
|
121 |
+
| Column | Lyte/QuadConnect2.5-0.5B-v0.0.6b (Count, %) | Lyte/QuadConnect2.5-0.5B-v0.0.8b (Count, %) | Lyte/QuadConnect2.5-0.0.9b (Temp 0.6) (Count, %) | Lyte/QuadConnect2.5-0.0.9b (Temp 0.8) (Count, %) |
|
122 |
+
|--------|-----------------------------------|-----------------------------------|------------------------------|------------------------------|
|
123 |
+
| a | 603 (19.02%) | 3 (0.12%) | 1447 (38.72%) | 1547 (31.01%) |
|
124 |
+
| b | 111 (3.50%) | 4 (0.16%) | 644 (17.23%) | 924 (18.52%) |
|
125 |
+
| c | 785 (24.76%) | 463 (17.96%) | 648 (17.34%) | 1003 (20.11%) |
|
126 |
+
| d | 1304 (41.14%) | 1743 (67.61%) | 101 (2.70%) | 202 (4.05%) |
|
127 |
+
| e | 290 (9.15%) | 360 (13.96%) | 338 (9.04%) | 562 (11.27%) |
|
128 |
+
| f | 50 (1.58%) | 3 (0.12%) | 310 (8.30%) | 408 (8.18%) |
|
129 |
+
| g | 27 (0.85%) | 2 (0.08%) | 249 (6.66%) | 342 (6.86%) |
|
130 |
|
131 |
|
132 |
|