djmango commited on
Commit
d0e962a
·
verified ·
1 Parent(s): 98a6daa

Prune dense checkpoints (batch 16, 200 files)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. ppo_v10/policy_update6125.safetensors +0 -3
  2. ppo_v10/policy_update6125.state.json +0 -245
  3. ppo_v10/policy_update6130.safetensors +0 -3
  4. ppo_v10/policy_update6130.state.json +0 -245
  5. ppo_v10/policy_update6135.safetensors +0 -3
  6. ppo_v10/policy_update6135.state.json +0 -245
  7. ppo_v10/policy_update6140.safetensors +0 -3
  8. ppo_v10/policy_update6140.state.json +0 -245
  9. ppo_v10/policy_update6145.safetensors +0 -3
  10. ppo_v10/policy_update6145.state.json +0 -245
  11. ppo_v10/policy_update6150.safetensors +0 -3
  12. ppo_v10/policy_update6150.state.json +0 -245
  13. ppo_v10/policy_update6155.safetensors +0 -3
  14. ppo_v10/policy_update6155.state.json +0 -245
  15. ppo_v10/policy_update6160.safetensors +0 -3
  16. ppo_v10/policy_update6160.state.json +0 -245
  17. ppo_v10/policy_update6165.safetensors +0 -3
  18. ppo_v10/policy_update6165.state.json +0 -245
  19. ppo_v10/policy_update6170.safetensors +0 -3
  20. ppo_v10/policy_update6170.state.json +0 -245
  21. ppo_v10/policy_update6175.safetensors +0 -3
  22. ppo_v10/policy_update6175.state.json +0 -245
  23. ppo_v10/policy_update6180.safetensors +0 -3
  24. ppo_v10/policy_update6180.state.json +0 -245
  25. ppo_v10/policy_update6185.safetensors +0 -3
  26. ppo_v10/policy_update6185.state.json +0 -245
  27. ppo_v10/policy_update6190.safetensors +0 -3
  28. ppo_v10/policy_update6190.state.json +0 -245
  29. ppo_v10/policy_update6195.safetensors +0 -3
  30. ppo_v10/policy_update6195.state.json +0 -245
  31. ppo_v10/policy_update6200.safetensors +0 -3
  32. ppo_v10/policy_update6200.state.json +0 -245
  33. ppo_v10/policy_update6205.safetensors +0 -3
  34. ppo_v10/policy_update6205.state.json +0 -245
  35. ppo_v10/policy_update6210.safetensors +0 -3
  36. ppo_v10/policy_update6210.state.json +0 -245
  37. ppo_v10/policy_update6215.safetensors +0 -3
  38. ppo_v10/policy_update6215.state.json +0 -245
  39. ppo_v10/policy_update6220.safetensors +0 -3
  40. ppo_v10/policy_update6220.state.json +0 -245
  41. ppo_v10/policy_update6225.safetensors +0 -3
  42. ppo_v10/policy_update6225.state.json +0 -245
  43. ppo_v10/policy_update6230.safetensors +0 -3
  44. ppo_v10/policy_update6230.state.json +0 -245
  45. ppo_v10/policy_update6235.safetensors +0 -3
  46. ppo_v10/policy_update6235.state.json +0 -245
  47. ppo_v10/policy_update6240.safetensors +0 -3
  48. ppo_v10/policy_update6240.state.json +0 -245
  49. ppo_v10/policy_update6245.safetensors +0 -3
  50. ppo_v10/policy_update6245.state.json +0 -245
ppo_v10/policy_update6125.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bbba6c438e84036641ada88f5eb66569787741dc0ceae03ba88312c4f71b188
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6125.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6126,
5
- "stage": 27,
6
- "ent_scale": 3.3841968101434357,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21224448,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 0.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 0.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6130.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3e76d350c3d69c26fbe4a114266f13d369e5aad1e211d1cea7e7efe092542f
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6130.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6131,
5
- "stage": 27,
6
- "ent_scale": 2.651606753226473,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21242368,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 1.0,
43
- 1.0,
44
- 0.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 1.0,
65
- 0.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 1.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6135.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdd6185b58b85503903aaec39807310425bed6fef30a71b79f7c95643787d1e5
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6135.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6136,
5
- "stage": 27,
6
- "ent_scale": 2.8359284694705718,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21260288,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 1.0,
131
- 1.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6140.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:703e56275407f4b0d7a62971aaf52566205e48496d32d2692028558837d07f28
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6140.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6141,
5
- "stage": 27,
6
- "ent_scale": 3.0330629812160512,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21278208,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 0.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 1.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 1.0,
124
- 1.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6145.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:52306a453194c448d7b44242811428af20d5345e807b74997d2cbe695876dff5
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6145.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6146,
5
- "stage": 27,
6
- "ent_scale": 2.376484210329608,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21296128,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 0.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 0.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 1.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6150.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a5050c3e7950b1d1c437c2dbd9b5e4c05cfa01113d97f58b899ab9c413c9898
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6150.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6151,
5
- "stage": 27,
6
- "ent_scale": 2.5416812734845995,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21314048,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 0.0,
57
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 0.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
121
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 0.0,
125
- 0.0,
126
- 1.0,
127
- 0.0,
128
- 1.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 1.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6155.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aab0de1e1955fd2b8249d2a27526ace9efd3f898f82310eacebee9a98f38b32
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6155.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6156,
5
- "stage": 27,
6
- "ent_scale": 1.9914737845980583,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21331968,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6160.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:589b7ffe23fec0926f4c37b272ccdbe59d65c1d91e84b83b855a5600eef53bb6
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6160.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6161,
5
- "stage": 27,
6
- "ent_scale": 1.56037182006855,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21349888,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 0.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 1.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6165.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:74f6b13fd8c7f76ac89390a9a4570165cb447897605c50863fccdf382b75b311
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6165.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6166,
5
- "stage": 27,
6
- "ent_scale": 1.6688382853556818,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21367808,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 1.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6170.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9f5f87c95b68d9279735ca9a75fff9e7251791ef4f58e25779642114ea38459
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6170.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6171,
5
- "stage": 27,
6
- "ent_scale": 1.7848446036064283,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21385728,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 1.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6175.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:729dc9743aed7b2ee186e4000d4aa8f5b521d609c8c33c00d57072d32dbc8700
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6175.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6176,
5
- "stage": 27,
6
- "ent_scale": 3.556737953853354,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21403648,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 1.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
89
- 0.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 1.0,
131
- 0.0,
132
- 1.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6180.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0a380a64e5452ee381f4065ae2e25f0fe3fe19b905db47d285144b21f68ce0f
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6180.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6181,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21421568,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 0.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 1.0,
117
- 1.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6185.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8e8cd8a2c6d9fe691ee3617bef813476ba7701a6db47fb54452a83d7331fa10
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6185.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6186,
5
- "stage": 27,
6
- "ent_scale": 3.917630832342295,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21439488,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 0.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 0.0,
64
- 1.0,
65
- 0.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 1.0,
113
- 1.0,
114
- 1.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 1.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 1.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6190.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:759e11d45b8413cac0e45ae64f9a75d48f1681ebcb935a8576a2ef251776d65a
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6190.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6191,
5
- "stage": 27,
6
- "ent_scale": 4.535147392290249,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21457408,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 1.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6195.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb9fafabf0c6825e210b7fdddcabf4d4a4995fc4812bd23d6994d51b597a0e64
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6195.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6196,
5
- "stage": 27,
6
- "ent_scale": 3.5534066506506075,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21475328,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 0.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 1.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6200.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:af96cc850107155e0e28fc404ed692d247fe6dbf7dae0c3129dbd0f1fa30734d
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6200.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6201,
5
- "stage": 27,
6
- "ent_scale": 3.800415379061843,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21493248,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6205.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:db8312c0cba9904780eb3669002e2d0f50ae2b1715842e9a8ab77be5f880e20b
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6205.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6206,
5
- "stage": 27,
6
- "ent_scale": 2.9777248929441007,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21511168,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 0.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6210.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a2696346994335b7c2766fe0070e9eb7e04ba27c4b61633386ab998666d0627
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6210.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6211,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21529088,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 1.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 1.0,
132
- 1.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6215.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b847d5126ac35565edacd3238c16d844175ad9f71735518bbc42f018cc4d5c20
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6215.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6216,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21547008,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 0.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 1.0,
115
- 1.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 1.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 1.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6220.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0bd5163cfbee690ddecf1a9a107975a5867e3e256d3dc1660b7997bdb6a0a14
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6220.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6221,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21564928,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 0.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 1.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6225.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6158887fa589b7279aa665d0e95178be4497b532510af4ef142a655787fcac79
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6225.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6226,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21582848,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 0.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 0.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6230.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:851b1322b9d943890e4299dbcc3761ade574d80ee7c07ebf4f423a62ad2be45b
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6230.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6231,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21600768,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6235.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc48f7bc3b9d1f960da9cebb49fb25586bdc03ef7efa6cbd0f41d5bd687cdf28
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6235.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6236,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21618688,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
115
- 1.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6240.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d6794f076ea14a60dc40b14eaf0ec59980e25c833ddf4cd7215f2f765f847b3
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6240.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6241,
5
- "stage": 27,
6
- "ent_scale": 4.761904761904762,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21636608,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 0.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 1.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update6245.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1425245013c7573d9c727fc092039b53d2f475e49a73762f4d164aaf604454db
3
- size 48494336
 
 
 
 
ppo_v10/policy_update6245.state.json DELETED
@@ -1,245 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 6246,
5
- "stage": 27,
6
- "ent_scale": 5.0,
7
- "lr_now": 3.1063544045550495e-6,
8
- "total_env_steps": 21654528,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 0.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "v81_curriculum": true,
138
- "curriculum_schedule": "v10",
139
- "reward_profile": "v10-anti-spiral-v1",
140
- "return_stats": null,
141
- "stage_env_targets": [
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 24,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 20,
196
- 16,
197
- 16,
198
- 16,
199
- 16,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 12,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 10,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8,
241
- 8
242
- ],
243
- "envs_per_shard": 14,
244
- "requested_env_target": null
245
- }