Lyte commited on
Commit
315fefc
·
verified ·
1 Parent(s): 90a0b17

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -17
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
- | Metric | Lyte/QuadConnect2.5-0.5B-v0.0.6b | Lyte/QuadConnect2.5-0.5B-v0.0.8b | New Evaluation (Lyte/QuadConnect2.5-0.0.9b)[*here*] |
108
- |-----------------------|--------------------------------|--------------------------------|--------------------------------|
109
- | Total games evaluated | 5082 | 5082 | 5082 |
110
- | Correct predictions | 518 | 394 | 516 |
111
- | Accuracy | 10.19% | 7.75% | 10.15% |
112
- | Most common move | d (41.14%) | d (67.61%) | a (38.72%) |
113
- | Middle column usage | 75.05% | 99.53% | 29.08% |
 
 
114
 
115
- *(Middle column usage = c (17.34%) + d (2.70%) + e (9.04%) = 27.38%)*
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