anakin87 commited on
Commit
149a17c
·
verified ·
1 Parent(s): 6cc8e38

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -42,10 +42,12 @@ This is a checkpoint from 🎓 **[LLM RL Environments Lil Course](https://github
42
  | **Model vs random opponent** | **% Wins** | **% Draws** | **% Losses** | **% Follows format** | **% Games w invalid moves** |
43
  |------------------------------|------------|-------------|--------------|----------------------|---------------------|
44
  | LiquidAI/LFM2-2.6B | 40 | 11 | 49 | 27.8 | 40 |
 
45
  | anakin87/LFM2-2.6B-ttt-rl | 86 | 12 | 2 | 100 | 1 |
46
  | **anakin87/LFM2-2.6B-ttt-rl-2** | **90** | **10** | **0** | **100** | **0** |
47
  | | | | | | |
48
  | **Model vs optimal opponent** | **% Wins** | **% Draws** | **% Losses** | **% Follows format** | **% Games w invalid moves** |
49
  | LiquidAI/LFM2-2.6B | 0 | 11 | 89 | 24.7 | 43 |
 
50
  | anakin87/LFM2-2.6B-ttt-rl | 0 | 85 | 15 | 100 | 1 |
51
  | **anakin87/LFM2-2.6B-ttt-rl-2** | **0** | **97** | **3** | **99.8** | **0** |
 
42
  | **Model vs random opponent** | **% Wins** | **% Draws** | **% Losses** | **% Follows format** | **% Games w invalid moves** |
43
  |------------------------------|------------|-------------|--------------|----------------------|---------------------|
44
  | LiquidAI/LFM2-2.6B | 40 | 11 | 49 | 27.8 | 40 |
45
+ | anakin87/LFM2-2.6B-ttt-sft | 74 | 13 | 13 | 99.8 | 11 |
46
  | anakin87/LFM2-2.6B-ttt-rl | 86 | 12 | 2 | 100 | 1 |
47
  | **anakin87/LFM2-2.6B-ttt-rl-2** | **90** | **10** | **0** | **100** | **0** |
48
  | | | | | | |
49
  | **Model vs optimal opponent** | **% Wins** | **% Draws** | **% Losses** | **% Follows format** | **% Games w invalid moves** |
50
  | LiquidAI/LFM2-2.6B | 0 | 11 | 89 | 24.7 | 43 |
51
+ | anakin87/LFM2-2.6B-ttt-sft | 0 | 52 | 48 | 99 | 14 |
52
  | anakin87/LFM2-2.6B-ttt-rl | 0 | 85 | 15 | 100 | 1 |
53
  | **anakin87/LFM2-2.6B-ttt-rl-2** | **0** | **97** | **3** | **99.8** | **0** |