djmango commited on
Commit
2e92517
·
verified ·
1 Parent(s): 90d0f07

Prune dense checkpoints (batch 6, 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_update1240.state.json +0 -133
  2. ppo_v10/policy_update12400.safetensors +0 -3
  3. ppo_v10/policy_update12400.state.json +0 -244
  4. ppo_v10/policy_update12405.safetensors +0 -3
  5. ppo_v10/policy_update12405.state.json +0 -244
  6. ppo_v10/policy_update12410.safetensors +0 -3
  7. ppo_v10/policy_update12410.state.json +0 -244
  8. ppo_v10/policy_update12415.safetensors +0 -3
  9. ppo_v10/policy_update12415.state.json +0 -244
  10. ppo_v10/policy_update12420.safetensors +0 -3
  11. ppo_v10/policy_update12420.state.json +0 -244
  12. ppo_v10/policy_update12425.safetensors +0 -3
  13. ppo_v10/policy_update12425.state.json +0 -244
  14. ppo_v10/policy_update12430.safetensors +0 -3
  15. ppo_v10/policy_update12430.state.json +0 -244
  16. ppo_v10/policy_update12435.safetensors +0 -3
  17. ppo_v10/policy_update12435.state.json +0 -244
  18. ppo_v10/policy_update12440.safetensors +0 -3
  19. ppo_v10/policy_update12440.state.json +0 -244
  20. ppo_v10/policy_update12445.safetensors +0 -3
  21. ppo_v10/policy_update12445.state.json +0 -244
  22. ppo_v10/policy_update1245.safetensors +0 -3
  23. ppo_v10/policy_update1245.state.json +0 -135
  24. ppo_v10/policy_update12450.safetensors +0 -3
  25. ppo_v10/policy_update12450.state.json +0 -244
  26. ppo_v10/policy_update12455.safetensors +0 -3
  27. ppo_v10/policy_update12455.state.json +0 -244
  28. ppo_v10/policy_update12460.safetensors +0 -3
  29. ppo_v10/policy_update12460.state.json +0 -244
  30. ppo_v10/policy_update12465.safetensors +0 -3
  31. ppo_v10/policy_update12465.state.json +0 -244
  32. ppo_v10/policy_update12470.safetensors +0 -3
  33. ppo_v10/policy_update12470.state.json +0 -244
  34. ppo_v10/policy_update12475.safetensors +0 -3
  35. ppo_v10/policy_update12475.state.json +0 -244
  36. ppo_v10/policy_update12480.safetensors +0 -3
  37. ppo_v10/policy_update12480.state.json +0 -244
  38. ppo_v10/policy_update12485.safetensors +0 -3
  39. ppo_v10/policy_update12485.state.json +0 -244
  40. ppo_v10/policy_update12490.safetensors +0 -3
  41. ppo_v10/policy_update12490.state.json +0 -244
  42. ppo_v10/policy_update12495.safetensors +0 -3
  43. ppo_v10/policy_update12495.state.json +0 -244
  44. ppo_v10/policy_update1250.safetensors +0 -3
  45. ppo_v10/policy_update1250.state.json +0 -136
  46. ppo_v10/policy_update12500.safetensors +0 -3
  47. ppo_v10/policy_update12500.state.json +0 -244
  48. ppo_v10/policy_update12505.safetensors +0 -3
  49. ppo_v10/policy_update12505.state.json +0 -244
  50. ppo_v10/policy_update12510.safetensors +0 -3
ppo_v10/policy_update1240.state.json DELETED
@@ -1,133 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1241,
5
- "stage": 5,
6
- "ent_scale": 2.181483438054286,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 3716608,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
56
- 0.0,
57
- 0.0,
58
- 0.0,
59
- 0.0,
60
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 0.0,
64
- 0.0
65
- ],
66
- "recent_deaths": [
67
- 1.0,
68
- 1.0,
69
- 0.0,
70
- 1.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 0.0,
76
- 1.0,
77
- 0.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 0.0,
82
- 0.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 0.0,
87
- 1.0,
88
- 0.0,
89
- 1.0,
90
- 1.0,
91
- 1.0,
92
- 0.0,
93
- 0.0,
94
- 0.0,
95
- 0.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 1.0
107
- ],
108
- "best_eval_win": null,
109
- "best_eval_score": null,
110
- "v81_curriculum": true,
111
- "curriculum_schedule": "v10",
112
- "reward_profile": "v10-anti-spiral-v1",
113
- "return_stats": null,
114
- "stage_env_targets": [
115
- 24,
116
- 24,
117
- 24,
118
- 24,
119
- 24,
120
- 24,
121
- 16,
122
- 12,
123
- 10,
124
- 12,
125
- 10,
126
- 8,
127
- 8,
128
- 8,
129
- 8
130
- ],
131
- "envs_per_shard": 14,
132
- "requested_env_target": null
133
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12400.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:784baf647680baeaf874cf11d41c113f9a03b6c1ecba41b0c602095926ec631e
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12400.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12401,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43737088,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
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
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
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
- 0.0,
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
- 0.0,
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
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 0.0,
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
- 0.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
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
- 1.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
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
- 1.0,
120
- 1.0,
121
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12405.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:caf1a0f12a83a26928f0854707f221aa05c30d4a296773cdb840a4ff36190696
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12405.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12406,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43757568,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 1.0,
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
- 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
- 0.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 0.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
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
- 0.0,
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
- 0.0,
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
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 1.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
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
- 1.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 1.0,
132
- 1.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12410.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a6acecc54f9a070bd5d7a923bc684ec93fb913c5ed80e1187aacafa63f5fd82
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12410.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12411,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43778048,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
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
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 0.0,
55
- 0.0,
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
- 0.0,
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
- 0.0,
83
- 0.0,
84
- 1.0,
85
- 0.0,
86
- 0.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
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
- 1.0,
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
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 1.0,
125
- 1.0,
126
- 1.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 0.0,
132
- 1.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12415.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b186b40376ec33eb18079188295fc6310527d3187c91d327b95e2cf32164f1d8
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12415.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12416,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43798528,
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
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
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
- 1.0,
53
- 1.0,
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
- 0.0,
66
- 0.0,
67
- 1.0,
68
- 0.0,
69
- 0.0,
70
- 0.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 0.0,
76
- 0.0,
77
- 0.0,
78
- 1.0,
79
- 0.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 0.0,
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
- 1.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 0.0,
106
- 0.0,
107
- 1.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 1.0,
112
- 1.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 0.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12420.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5743b66335faf81d4b5ff8de7738abfb0da06d9ebc2156e305cad25d46cd0bd
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12420.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12421,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43819008,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
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
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
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
- 0.0,
55
- 0.0,
56
- 0.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 0.0,
64
- 1.0,
65
- 0.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
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
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 0.0,
89
- 0.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
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
- 0.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12425.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8cfcc4b1fc788880725dce2a49b8e89b3e3116e1d578693772fa474104cf97e
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12425.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12426,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43839488,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 0.0,
54
- 1.0,
55
- 0.0,
56
- 0.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 0.0,
61
- 0.0,
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
- 0.0,
72
- 1.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 0.0,
78
- 0.0,
79
- 0.0,
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
- 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
- 1.0,
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
- 1.0,
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
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 0.0,
125
- 0.0,
126
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12430.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b5a75dc27c62c7ee40bc8eb4d76266f144953aaaf7bacf8317353a538478e7a
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12430.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12431,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43859968,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
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
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
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
- 0.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 0.0,
69
- 0.0,
70
- 1.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 0.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 0.0,
82
- 0.0,
83
- 0.0,
84
- 1.0,
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
- 1.0,
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
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
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
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12435.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba2e88a6925b66a78ab095a142e9e566e90b4cbc07da4ad2e812b42006a3f4e0
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12435.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12436,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43880448,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
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
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
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
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 0.0,
57
- 0.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 0.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 0.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
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
- 1.0,
84
- 1.0,
85
- 0.0,
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
- 1.0,
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
- 1.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 0.0,
117
- 1.0,
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
- 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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12440.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:292735a82a30c170d9c7272594aa05d68d7a575ca1152858e6ae09f286455a18
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12440.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12441,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43900928,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 0.0,
54
- 0.0,
55
- 1.0,
56
- 0.0,
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
- 0.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 0.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 0.0,
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
- 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
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 1.0,
105
- 0.0,
106
- 1.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 1.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12445.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:477499e65939490f695d8757fbae441de1dc511250d93dd717c73476a09e4936
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12445.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12446,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 43921408,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
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
- 0.0,
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
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 0.0,
62
- 0.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
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
- 1.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
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
- 1.0,
116
- 0.0,
117
- 1.0,
118
- 1.0,
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
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update1245.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc6a35e9eef5acb11c0a3d8621fa5d458bd75937bb81a837d5868e82c6a62d23
3
- size 48494336
 
 
 
 
ppo_v10/policy_update1245.state.json DELETED
@@ -1,135 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1246,
5
- "stage": 5,
6
- "ent_scale": 1.7092493554331083,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 3734528,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
56
- 0.0,
57
- 0.0,
58
- 0.0,
59
- 0.0,
60
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 0.0,
64
- 0.0,
65
- 0.0,
66
- 0.0
67
- ],
68
- "recent_deaths": [
69
- 0.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 0.0,
78
- 1.0,
79
- 0.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 0.0,
85
- 0.0,
86
- 0.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 0.0,
92
- 0.0,
93
- 0.0,
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 0.0
109
- ],
110
- "best_eval_win": null,
111
- "best_eval_score": null,
112
- "v81_curriculum": true,
113
- "curriculum_schedule": "v10",
114
- "reward_profile": "v10-anti-spiral-v1",
115
- "return_stats": null,
116
- "stage_env_targets": [
117
- 24,
118
- 24,
119
- 24,
120
- 24,
121
- 24,
122
- 24,
123
- 16,
124
- 12,
125
- 10,
126
- 12,
127
- 10,
128
- 8,
129
- 8,
130
- 8,
131
- 8
132
- ],
133
- "envs_per_shard": 14,
134
- "requested_env_target": null
135
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12450.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:80567b80bfa07836eff4672acfb20e0dbc1ffa6d669ee4696d57a97774dbda2d
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12450.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12451,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.00002,
8
- "total_env_steps": 43941888,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
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
- 0.0,
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
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 0.0,
62
- 0.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
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
- 1.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
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
- 1.0,
116
- 0.0,
117
- 1.0,
118
- 1.0,
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
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12455.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a19dd0ad7898fa12d7fa416321a0d766794ea6fc624a7e129b8cfa851238992
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12455.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12456,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000019,
8
- "total_env_steps": 43962368,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
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
- 1.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 0.0,
57
- 1.0,
58
- 0.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
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
- 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
- 1.0,
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
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 1.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 1.0,
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
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12460.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1f8d633b08f3c07674c4a452c476cbed786b8e0c02d32b1816951d77d91c064
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12460.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12461,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000013,
8
- "total_env_steps": 43982848,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
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
- 1.0,
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
- 0.0,
55
- 0.0,
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
- 0.0,
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
- 0.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 1.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 0.0,
117
- 0.0,
118
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12465.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:664319d5254678460410f2aeac50196da6df8390a1bd71bc7c706188706b3ba6
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12465.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12466,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000018,
8
- "total_env_steps": 44003328,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
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
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
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
- 0.0,
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
- 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
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
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
- 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
- 1.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 0.0,
132
- 1.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12470.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5034394684cf02fd2475890ac26f473a0d76f1abdd1fa902fd993005bbe7e70
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12470.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12471,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000024,
8
- "total_env_steps": 44023808,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
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
- 0.0,
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
- 0.0,
72
- 0.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 0.0,
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
- 0.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 1.0,
97
- 0.0,
98
- 1.0,
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
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 1.0,
113
- 1.0,
114
- 0.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 1.0,
127
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12475.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c69727c4a36d4456453ae61982d9d9c15753e764db50470aca7389b2934db7d4
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12475.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12476,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000023,
8
- "total_env_steps": 44044288,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 0.0,
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
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 1.0,
64
- 1.0,
65
- 0.0,
66
- 0.0,
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
- 0.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 0.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
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
- 1.0,
116
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 1.0,
120
- 1.0,
121
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 1.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12480.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b36f0d17ea19727f6b4e878ec84ba25a8b557ba94fabffd7f51762eba3a3c273
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12480.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12481,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000025,
8
- "total_env_steps": 44064768,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
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
- 0.0,
54
- 0.0,
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
- 0.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
72
- 0.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 0.0,
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
- 1.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
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
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 1.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12485.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e77a20493399e5fc5687fbf0f72f63606c8684b54ae9a8323d57969d85669b0f
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12485.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12486,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000021000000000000002,
8
- "total_env_steps": 44085248,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
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
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 0.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
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
- 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
- 0.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 0.0,
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
- 1.0,
108
- 1.0,
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
- 1.0,
121
- 0.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
127
- 0.0,
128
- 1.0,
129
- 1.0,
130
- 0.0,
131
- 1.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12490.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cad7f3596b99988e90f331e87112d44f877af420fcaaf56bf3a3256567c1a278
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12490.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12491,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000023,
8
- "total_env_steps": 44105728,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
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
- 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
- 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
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 0.0,
83
- 0.0,
84
- 1.0,
85
- 0.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 0.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 1.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 1.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12495.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:23875259626f36b624d50d96910f59e9600acfeabe126d48783bf6ede196970c
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12495.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12496,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000024,
8
- "total_env_steps": 44126208,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
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
- 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
- 0.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
73
- 0.0,
74
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 0.0,
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
- 0.0,
90
- 0.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 1.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 1.0,
117
- 1.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 1.0,
124
- 0.0,
125
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update1250.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:edac37b9c0685b70008d9c382f0ed53696bd66a4f58465d6878556c44be0cb93
3
- size 48494336
 
 
 
 
ppo_v10/policy_update1250.state.json DELETED
@@ -1,136 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1251,
5
- "stage": 5,
6
- "ent_scale": 1.3392415950011878,
7
- "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 3752448,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
56
- 0.0,
57
- 0.0,
58
- 0.0,
59
- 0.0,
60
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 0.0,
64
- 0.0,
65
- 0.0,
66
- 0.0,
67
- 0.0
68
- ],
69
- "recent_deaths": [
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 0.0,
76
- 0.0,
77
- 1.0,
78
- 0.0,
79
- 1.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 0.0,
85
- 0.0,
86
- 0.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 0.0,
92
- 0.0,
93
- 0.0,
94
- 0.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 1.0,
102
- 1.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 1.0
110
- ],
111
- "best_eval_win": null,
112
- "best_eval_score": null,
113
- "v81_curriculum": true,
114
- "curriculum_schedule": "v10",
115
- "reward_profile": "v10-anti-spiral-v1",
116
- "return_stats": null,
117
- "stage_env_targets": [
118
- 24,
119
- 24,
120
- 24,
121
- 24,
122
- 24,
123
- 24,
124
- 16,
125
- 12,
126
- 10,
127
- 12,
128
- 10,
129
- 8,
130
- 8,
131
- 8,
132
- 8
133
- ],
134
- "envs_per_shard": 14,
135
- "requested_env_target": null
136
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12500.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:62afcd628176f29f5ae7404f18b7cf06e5ad69190040a9546d62715d564c7d4d
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12500.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12501,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000022000000000000003,
8
- "total_env_steps": 44146688,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
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
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 0.0,
56
- 0.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 0.0,
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
- 0.0,
75
- 0.0,
76
- 0.0,
77
- 1.0,
78
- 0.0,
79
- 1.0,
80
- 0.0,
81
- 0.0,
82
- 0.0,
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
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
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
- 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
- 1.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
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
- 1.0,
127
- 0.0,
128
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12505.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6d4b437d60cac917119d26a2e1d32a3ac28579fa76e343a231f90ab229dfc88
3
- size 48494336
 
 
 
 
ppo_v10/policy_update12505.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 12506,
5
- "stage": 25,
6
- "ent_scale": 5.0,
7
- "lr_now": 0.000021000000000000002,
8
- "total_env_steps": 44167168,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
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
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
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
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 0.0,
68
- 0.0,
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
- 0.0,
78
- 1.0,
79
- 0.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 0.0,
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
- 1.0,
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
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 1.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
127
- 0.0,
128
- 1.0,
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
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
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
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
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
- 8,
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
- ],
242
- "envs_per_shard": 16,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v10/policy_update12510.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:84957f8af2a4550911cb1b3a38854447efcff32872c6747ff8231cc92446b533
3
- size 48494336