djmango commited on
Commit
51b8ce2
·
verified ·
1 Parent(s): 75e34eb

Prune dense checkpoints (batch 25, 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_v11/policy_update1710.safetensors +0 -3
  2. ppo_v11/policy_update1710.state.json +0 -212
  3. ppo_v11/policy_update1715.safetensors +0 -3
  4. ppo_v11/policy_update1715.state.json +0 -212
  5. ppo_v11/policy_update1720.safetensors +0 -3
  6. ppo_v11/policy_update1720.state.json +0 -212
  7. ppo_v11/policy_update1725.safetensors +0 -3
  8. ppo_v11/policy_update1725.state.json +0 -212
  9. ppo_v11/policy_update1730.safetensors +0 -3
  10. ppo_v11/policy_update1730.state.json +0 -212
  11. ppo_v11/policy_update1735.safetensors +0 -3
  12. ppo_v11/policy_update1735.state.json +0 -212
  13. ppo_v11/policy_update1740.safetensors +0 -3
  14. ppo_v11/policy_update1740.state.json +0 -212
  15. ppo_v11/policy_update1745.safetensors +0 -3
  16. ppo_v11/policy_update1745.state.json +0 -212
  17. ppo_v11/policy_update175.safetensors +0 -3
  18. ppo_v11/policy_update175.state.json +0 -244
  19. ppo_v11/policy_update1750.safetensors +0 -3
  20. ppo_v11/policy_update1750.state.json +0 -212
  21. ppo_v11/policy_update1755.safetensors +0 -3
  22. ppo_v11/policy_update1755.state.json +0 -212
  23. ppo_v11/policy_update1760.safetensors +0 -3
  24. ppo_v11/policy_update1760.state.json +0 -212
  25. ppo_v11/policy_update1765.safetensors +0 -3
  26. ppo_v11/policy_update1765.state.json +0 -212
  27. ppo_v11/policy_update1770.safetensors +0 -3
  28. ppo_v11/policy_update1770.state.json +0 -212
  29. ppo_v11/policy_update1775.safetensors +0 -3
  30. ppo_v11/policy_update1775.state.json +0 -212
  31. ppo_v11/policy_update1780.safetensors +0 -3
  32. ppo_v11/policy_update1780.state.json +0 -120
  33. ppo_v11/policy_update1785.safetensors +0 -3
  34. ppo_v11/policy_update1785.state.json +0 -185
  35. ppo_v11/policy_update1790.safetensors +0 -3
  36. ppo_v11/policy_update1790.state.json +0 -192
  37. ppo_v11/policy_update1795.safetensors +0 -3
  38. ppo_v11/policy_update1795.state.json +0 -197
  39. ppo_v11/policy_update180.safetensors +0 -3
  40. ppo_v11/policy_update180.state.json +0 -244
  41. ppo_v11/policy_update1805.safetensors +0 -3
  42. ppo_v11/policy_update1805.state.json +0 -212
  43. ppo_v11/policy_update1810.safetensors +0 -3
  44. ppo_v11/policy_update1810.state.json +0 -212
  45. ppo_v11/policy_update1815.safetensors +0 -3
  46. ppo_v11/policy_update1815.state.json +0 -212
  47. ppo_v11/policy_update1820.safetensors +0 -3
  48. ppo_v11/policy_update1820.state.json +0 -212
  49. ppo_v11/policy_update1825.safetensors +0 -3
  50. ppo_v11/policy_update1825.state.json +0 -212
ppo_v11/policy_update1710.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f592806913620f098551b260743853799170654657a5ecd7035f0b0be492e41d
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1710.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1711,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10286592,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
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
- 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
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 1.0,
44
- 0.0,
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
- 1.0,
61
- 1.0,
62
- 0.0,
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
- 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
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
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
- 1.0,
114
- 0.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 1.0,
119
- 1.0,
120
- 1.0,
121
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 1.0,
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
- 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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1715.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfb7be3db8c9169a98421e28c19ff5682a228eb28cc06e0ef255fa2d9d13365a
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1715.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1716,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10324992,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
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
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
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
- 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
- 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
- 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
- 1.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 1.0,
113
- 0.0,
114
- 1.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 1.0,
125
- 1.0,
126
- 0.0,
127
- 0.0,
128
- 1.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1720.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8ba95c8ef7e5807e37330fb2c321fbbd1fc0850e8025a43e95a3ee0842acc2c
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1720.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1721,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10363392,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
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
- 1.0,
27
- 0.0,
28
- 0.0,
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
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
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
- 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
- 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
- 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
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
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
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 0.0,
111
- 1.0,
112
- 1.0,
113
- 0.0,
114
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
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
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1725.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:44a1b87c16a0c0307d7d94e4570fbb76477d4a1e04e58b656d4531a0f2eac1dd
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1725.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1726,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10401792,
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
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
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
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
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
- 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
- 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
- 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
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 1.0,
113
- 1.0,
114
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
128
- 1.0,
129
- 0.0,
130
- 0.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1730.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f60a6a6bd7c3402bcf2d917cec0c6ca8ad003165ec4c0fcab5ab03658a5b4f40
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1730.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1731,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10440192,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
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
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
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
- 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
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
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
- 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
- 1.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 0.0,
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
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1735.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:accb577f39e916c508234a79f93c8ce87dc89257ca3b886b48f7422be75b0859
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1735.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1736,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10478592,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
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
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
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
- 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
- 0.0,
55
- 1.0,
56
- 0.0,
57
- 0.0,
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
- 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
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
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
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
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
- 0.0,
113
- 1.0,
114
- 1.0,
115
- 1.0,
116
- 0.0,
117
- 0.0,
118
- 1.0,
119
- 1.0,
120
- 1.0,
121
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 1.0,
125
- 1.0,
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
- "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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1740.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:35051ba07d40b66ffab05b20cdb0f34f9e4855e6db11aa9ba7d6b8839e744283
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1740.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1741,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10516992,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
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
- 0.0,
47
- 0.0,
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
- 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
- 0.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 0.0,
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
- 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
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 1.0,
126
- 1.0,
127
- 0.0,
128
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1745.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aa6b6ce8ca32b056a49d3845bc77d5fd17875bfda6c4c28d71a6c2e0929a43d
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1745.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1746,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10555392,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
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
- 1.0,
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
- 0.0,
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
- 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
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
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
- 1.0,
73
- 0.0,
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
- 0.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 1.0,
102
- 0.0,
103
- 1.0,
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
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
127
- 0.0,
128
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update175.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:af7649ce802904b77b18006d978461007b25217003ccfd0ac983422695926471
3
- size 154490248
 
 
 
 
ppo_v11/policy_update175.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 176,
5
- "stage": 3,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00015353125,
8
- "total_env_steps": 463488,
9
- "recent_wins": [
10
- 0.0,
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
- 1.0,
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
- 1.0,
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
- 0.0,
40
- 1.0,
41
- 0.0,
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
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
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
- 0.0,
74
- 0.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 1.0,
86
- 0.0,
87
- 1.0,
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
- 0.0,
98
- 0.0,
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
- 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
- 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": 24,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1750.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8745414ae7a5614122c7035df32f4de2b47fbfea5ecdc4579fa4824de66de63a
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1750.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1751,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10593792,
9
- "recent_wins": [
10
- 1.0,
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
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
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
- 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
- 0.0,
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
- 0.0,
57
- 1.0,
58
- 0.0,
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
- 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
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
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
- 1.0,
99
- 1.0,
100
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 0.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 1.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 1.0,
121
- 0.0,
122
- 1.0,
123
- 1.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1755.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d92da0147d22188fcdb4109b388bb6d6e5ea6398b2e203010a8a889f64add2e
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1755.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1756,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10632192,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
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
- 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
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
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
- 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
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 0.0,
78
- 0.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
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
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 0.0,
100
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
113
- 1.0,
114
- 1.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1760.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb350036545dad6edb68c3b50cd5fe7458d9278acbf7969e71f68d3dcff75ce2
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1760.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1761,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10670592,
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
- 1.0,
20
- 0.0,
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
- 0.0,
33
- 0.0,
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
- 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
- 1.0,
53
- 0.0,
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
- 1.0,
65
- 0.0,
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
- 0.0,
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
- 0.0,
89
- 1.0,
90
- 0.0,
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
- 0.0,
104
- 1.0,
105
- 1.0,
106
- 0.0,
107
- 0.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
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
- 1.0,
124
- 1.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
128
- 1.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1765.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dab5a1d2714fb92a80c801257eab989beed27d1e39ef04bd7d0f564e5905f930
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1765.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1766,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10708992,
9
- "recent_wins": [
10
- 1.0,
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
- 1.0,
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
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 0.0,
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
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
71
- 0.0,
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
- 0.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 0.0,
86
- 0.0,
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
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 1.0,
101
- 1.0,
102
- 1.0,
103
- 0.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 0.0,
111
- 1.0,
112
- 1.0,
113
- 1.0,
114
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 1.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1770.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d81b75d966c1a09a5e7cdcf8d8b85c15a336b995383aaaa9043d023760f974e
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1770.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1771,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10747392,
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
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 1.0,
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
- 1.0,
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
- 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
- 0.0,
63
- 0.0,
64
- 0.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 0.0,
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
- 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
- 0.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 0.0,
100
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 0.0,
125
- 0.0,
126
- 1.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1775.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe2e628ad11a9754ddc84ddd1b931f7201389b501471bca7ac6d0c781bfa020f
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1775.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1776,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10785792,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
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
- 1.0,
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
- 1.0,
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
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 0.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 0.0,
68
- 1.0,
69
- 0.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 0.0,
74
- 0.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
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
- 0.0,
88
- 0.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 1.0,
109
- 0.0,
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
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 1.0,
126
- 0.0,
127
- 1.0,
128
- 1.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1780.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4b4af34b97bba0aa0a6edb431edeb70e19918fdf2b7bb3b79059821624365ed
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1780.state.json DELETED
@@ -1,120 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1781,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10824192,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 1.0
22
- ],
23
- "recent_conversions": [
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0
28
- ],
29
- "recent_deaths": [
30
- 1.0,
31
- 0.0,
32
- 1.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 0.0
42
- ],
43
- "best_eval_win": null,
44
- "best_eval_score": null,
45
- "curriculum_schedule": "v10",
46
- "reward_profile": "v10-anti-spiral-v1",
47
- "return_stats": null,
48
- "stage_env_targets": [
49
- 24,
50
- 24,
51
- 24,
52
- 24,
53
- 24,
54
- 24,
55
- 24,
56
- 24,
57
- 24,
58
- 24,
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 24,
68
- 24,
69
- 24,
70
- 24,
71
- 24,
72
- 24,
73
- 24,
74
- 24,
75
- 24,
76
- 24,
77
- 20,
78
- 20,
79
- 20,
80
- 16,
81
- 16,
82
- 16,
83
- 12,
84
- 12,
85
- 10,
86
- 10,
87
- 10,
88
- 10,
89
- 10,
90
- 10,
91
- 10,
92
- 10,
93
- 10,
94
- 10,
95
- 10,
96
- 10,
97
- 10,
98
- 10,
99
- 8,
100
- 8,
101
- 8,
102
- 8,
103
- 8,
104
- 8,
105
- 8,
106
- 8,
107
- 8,
108
- 8,
109
- 8,
110
- 8,
111
- 8,
112
- 8,
113
- 8,
114
- 8,
115
- 8,
116
- 8
117
- ],
118
- "envs_per_shard": 40,
119
- "requested_env_target": null
120
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1785.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:030acdc0bc4ea0a403ab34a14a94421213c67ca4a626d530038b1696cb3bcc30
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1785.state.json DELETED
@@ -1,185 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1786,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10862592,
9
- "recent_wins": [
10
- 1.0,
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
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
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
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
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
- 1.0,
53
- 1.0,
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
- ],
66
- "recent_deaths": [
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
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0,
92
- 1.0,
93
- 1.0,
94
- 0.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 1.0
107
- ],
108
- "best_eval_win": null,
109
- "best_eval_score": null,
110
- "curriculum_schedule": "v10",
111
- "reward_profile": "v10-anti-spiral-v1",
112
- "return_stats": null,
113
- "stage_env_targets": [
114
- 24,
115
- 24,
116
- 24,
117
- 24,
118
- 24,
119
- 24,
120
- 24,
121
- 24,
122
- 24,
123
- 24,
124
- 24,
125
- 24,
126
- 24,
127
- 24,
128
- 24,
129
- 24,
130
- 24,
131
- 24,
132
- 24,
133
- 24,
134
- 24,
135
- 24,
136
- 24,
137
- 24,
138
- 24,
139
- 24,
140
- 24,
141
- 24,
142
- 20,
143
- 20,
144
- 20,
145
- 16,
146
- 16,
147
- 16,
148
- 12,
149
- 12,
150
- 10,
151
- 10,
152
- 10,
153
- 10,
154
- 10,
155
- 10,
156
- 10,
157
- 10,
158
- 10,
159
- 10,
160
- 10,
161
- 10,
162
- 10,
163
- 10,
164
- 8,
165
- 8,
166
- 8,
167
- 8,
168
- 8,
169
- 8,
170
- 8,
171
- 8,
172
- 8,
173
- 8,
174
- 8,
175
- 8,
176
- 8,
177
- 8,
178
- 8,
179
- 8,
180
- 8,
181
- 8
182
- ],
183
- "envs_per_shard": 40,
184
- "requested_env_target": null
185
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1790.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8c00997c77c97c54df0bf1074918fa8a363ee781917de6a16308142d9f6576c
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1790.state.json DELETED
@@ -1,192 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1791,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10900992,
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
- 1.0,
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
- 1.0,
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
- 1.0,
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
- 0.0,
59
- 0.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 0.0,
68
- 1.0,
69
- 0.0,
70
- 1.0,
71
- 1.0
72
- ],
73
- "recent_deaths": [
74
- 0.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 0.0,
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
- 1.0,
93
- 1.0,
94
- 1.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 1.0
114
- ],
115
- "best_eval_win": null,
116
- "best_eval_score": null,
117
- "curriculum_schedule": "v10",
118
- "reward_profile": "v10-anti-spiral-v1",
119
- "return_stats": null,
120
- "stage_env_targets": [
121
- 24,
122
- 24,
123
- 24,
124
- 24,
125
- 24,
126
- 24,
127
- 24,
128
- 24,
129
- 24,
130
- 24,
131
- 24,
132
- 24,
133
- 24,
134
- 24,
135
- 24,
136
- 24,
137
- 24,
138
- 24,
139
- 24,
140
- 24,
141
- 24,
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 20,
150
- 20,
151
- 20,
152
- 16,
153
- 16,
154
- 16,
155
- 12,
156
- 12,
157
- 10,
158
- 10,
159
- 10,
160
- 10,
161
- 10,
162
- 10,
163
- 10,
164
- 10,
165
- 10,
166
- 10,
167
- 10,
168
- 10,
169
- 10,
170
- 10,
171
- 8,
172
- 8,
173
- 8,
174
- 8,
175
- 8,
176
- 8,
177
- 8,
178
- 8,
179
- 8,
180
- 8,
181
- 8,
182
- 8,
183
- 8,
184
- 8,
185
- 8,
186
- 8,
187
- 8,
188
- 8
189
- ],
190
- "envs_per_shard": 40,
191
- "requested_env_target": null
192
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1795.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:505cfe65c5e8472bdfe1b7aae2a05418281453d46536d3253dbd855ec021b9b9
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1795.state.json DELETED
@@ -1,197 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1796,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 10939392,
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
- 1.0,
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
- 1.0,
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
- 1.0,
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
- 0.0,
59
- 0.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 0.0,
68
- 1.0,
69
- 0.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 0.0,
74
- 1.0,
75
- 1.0,
76
- 1.0
77
- ],
78
- "recent_deaths": [
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 0.0,
86
- 0.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0,
92
- 1.0,
93
- 1.0,
94
- 1.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 0.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 1.0,
113
- 1.0,
114
- 1.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 1.0
119
- ],
120
- "best_eval_win": null,
121
- "best_eval_score": null,
122
- "curriculum_schedule": "v10",
123
- "reward_profile": "v10-anti-spiral-v1",
124
- "return_stats": null,
125
- "stage_env_targets": [
126
- 24,
127
- 24,
128
- 24,
129
- 24,
130
- 24,
131
- 24,
132
- 24,
133
- 24,
134
- 24,
135
- 24,
136
- 24,
137
- 24,
138
- 24,
139
- 24,
140
- 24,
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
- 20,
155
- 20,
156
- 20,
157
- 16,
158
- 16,
159
- 16,
160
- 12,
161
- 12,
162
- 10,
163
- 10,
164
- 10,
165
- 10,
166
- 10,
167
- 10,
168
- 10,
169
- 10,
170
- 10,
171
- 10,
172
- 10,
173
- 10,
174
- 10,
175
- 10,
176
- 8,
177
- 8,
178
- 8,
179
- 8,
180
- 8,
181
- 8,
182
- 8,
183
- 8,
184
- 8,
185
- 8,
186
- 8,
187
- 8,
188
- 8,
189
- 8,
190
- 8,
191
- 8,
192
- 8,
193
- 8
194
- ],
195
- "envs_per_shard": 40,
196
- "requested_env_target": null
197
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update180.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e78ab86b2e7a2d4b21790166600dc9c25d14b16c77e2128a38b20661ddb7a52f
3
- size 154490248
 
 
 
 
ppo_v11/policy_update180.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 181,
5
- "stage": 3,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00015353125,
8
- "total_env_steps": 475008,
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
- 0.0,
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
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
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
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
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
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 0.0,
69
- 0.0,
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
- 0.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
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
- 1.0,
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
- 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": 24,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1805.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1f031ece6774c4f554f70f763a03bed10f02fb2b04a4aec8bb4222ef56b8b07
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1805.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1806,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 11016192,
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
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
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
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
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
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
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
- 1.0,
72
- 0.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 0.0,
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
- 0.0,
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
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
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
- 1.0,
117
- 1.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 1.0,
125
- 1.0,
126
- 1.0,
127
- 0.0,
128
- 1.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1810.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:93d2a852ba5d86c674d18bfa04ac412f65badb7d331b4ac4ee5fc699670d5a9a
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1810.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1811,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 11054592,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
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
- 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
- 1.0,
39
- 1.0,
40
- 1.0,
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
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 0.0,
59
- 1.0,
60
- 0.0,
61
- 1.0,
62
- 0.0,
63
- 1.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 0.0,
74
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 0.0,
85
- 0.0,
86
- 0.0,
87
- 0.0,
88
- 0.0,
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
- 1.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 0.0,
107
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 1.0,
113
- 1.0,
114
- 1.0,
115
- 1.0,
116
- 0.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
128
- 0.0,
129
- 1.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1815.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e9e6960309c2bd251628ba0c927b08356de1ae647f1a69b92f1ab751defcae6
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1815.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1816,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 11092992,
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
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
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
- 0.0,
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
- 0.0,
55
- 1.0,
56
- 0.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 0.0,
66
- 0.0,
67
- 0.0,
68
- 0.0,
69
- 0.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 0.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 0.0,
80
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
89
- 0.0,
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
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 1.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 1.0,
121
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 0.0,
125
- 0.0,
126
- 1.0,
127
- 1.0,
128
- 1.0,
129
- 0.0,
130
- 1.0,
131
- 1.0,
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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1820.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d8063f6ba359dc8334de499c3918ec22cdda237c819a08383f4be47e5670a21
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1820.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1821,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 11131392,
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
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
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
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
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
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 0.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 0.0,
66
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 0.0,
70
- 1.0,
71
- 1.0,
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
- 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
- 1.0,
95
- 1.0,
96
- 0.0,
97
- 1.0,
98
- 1.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
113
- 1.0,
114
- 1.0,
115
- 1.0,
116
- 0.0,
117
- 1.0,
118
- 1.0,
119
- 1.0,
120
- 1.0,
121
- 0.0,
122
- 1.0,
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
- 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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1825.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:244cd2b1bc3ecabc16487fb25720eceeb8f8461c9e152be5bedb3fb6b699d199
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1825.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1826,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 11169792,
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
- 1.0,
23
- 1.0,
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
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
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
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 0.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 0.0,
63
- 0.0,
64
- 1.0,
65
- 0.0,
66
- 0.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
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
- 0.0,
81
- 1.0,
82
- 1.0,
83
- 0.0,
84
- 1.0,
85
- 0.0,
86
- 0.0,
87
- 0.0,
88
- 1.0,
89
- 0.0,
90
- 0.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 1.0,
113
- 1.0,
114
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 1.0,
120
- 0.0,
121
- 1.0,
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
- 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
- 20,
170
- 20,
171
- 20,
172
- 16,
173
- 16,
174
- 16,
175
- 12,
176
- 12,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 10,
184
- 10,
185
- 10,
186
- 10,
187
- 10,
188
- 10,
189
- 10,
190
- 10,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8,
201
- 8,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8
209
- ],
210
- "envs_per_shard": 40,
211
- "requested_env_target": null
212
- }