djmango commited on
Commit
75e34eb
·
verified ·
1 Parent(s): 5f35a64

Prune dense checkpoints (batch 24, 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_update1240.safetensors +0 -3
  2. ppo_v11/policy_update1240.state.json +0 -212
  3. ppo_v11/policy_update1245.safetensors +0 -3
  4. ppo_v11/policy_update1245.state.json +0 -212
  5. ppo_v11/policy_update125.safetensors +0 -3
  6. ppo_v11/policy_update125.state.json +0 -169
  7. ppo_v11/policy_update1250.safetensors +0 -3
  8. ppo_v11/policy_update1250.state.json +0 -212
  9. ppo_v11/policy_update1255.safetensors +0 -3
  10. ppo_v11/policy_update1255.state.json +0 -212
  11. ppo_v11/policy_update1260.safetensors +0 -3
  12. ppo_v11/policy_update1260.state.json +0 -212
  13. ppo_v11/policy_update1265.safetensors +0 -3
  14. ppo_v11/policy_update1265.state.json +0 -212
  15. ppo_v11/policy_update1270.safetensors +0 -3
  16. ppo_v11/policy_update1270.state.json +0 -212
  17. ppo_v11/policy_update1275.safetensors +0 -3
  18. ppo_v11/policy_update1275.state.json +0 -212
  19. ppo_v11/policy_update1280.safetensors +0 -3
  20. ppo_v11/policy_update1280.state.json +0 -212
  21. ppo_v11/policy_update1285.safetensors +0 -3
  22. ppo_v11/policy_update1285.state.json +0 -212
  23. ppo_v11/policy_update1290.safetensors +0 -3
  24. ppo_v11/policy_update1290.state.json +0 -212
  25. ppo_v11/policy_update1295.safetensors +0 -3
  26. ppo_v11/policy_update1295.state.json +0 -212
  27. ppo_v11/policy_update130.safetensors +0 -3
  28. ppo_v11/policy_update130.state.json +0 -196
  29. ppo_v11/policy_update1305.safetensors +0 -3
  30. ppo_v11/policy_update1305.state.json +0 -89
  31. ppo_v11/policy_update1310.safetensors +0 -3
  32. ppo_v11/policy_update1310.state.json +0 -204
  33. ppo_v11/policy_update1315.safetensors +0 -3
  34. ppo_v11/policy_update1315.state.json +0 -212
  35. ppo_v11/policy_update1320.safetensors +0 -3
  36. ppo_v11/policy_update1320.state.json +0 -212
  37. ppo_v11/policy_update1325.safetensors +0 -3
  38. ppo_v11/policy_update1325.state.json +0 -212
  39. ppo_v11/policy_update1330.safetensors +0 -3
  40. ppo_v11/policy_update1330.state.json +0 -212
  41. ppo_v11/policy_update1335.safetensors +0 -3
  42. ppo_v11/policy_update1335.state.json +0 -212
  43. ppo_v11/policy_update1340.safetensors +0 -3
  44. ppo_v11/policy_update1340.state.json +0 -212
  45. ppo_v11/policy_update1345.safetensors +0 -3
  46. ppo_v11/policy_update1345.state.json +0 -212
  47. ppo_v11/policy_update135.safetensors +0 -3
  48. ppo_v11/policy_update135.state.json +0 -223
  49. ppo_v11/policy_update1350.safetensors +0 -3
  50. ppo_v11/policy_update1350.state.json +0 -212
ppo_v11/policy_update1240.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbd88d281a210c7e49f74e0168468b6b63f484a259ff52a871daa59368473690
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1240.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1241,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6676992,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
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
- 1.0,
43
- 1.0,
44
- 0.0,
45
- 1.0,
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
- 0.0,
64
- 1.0,
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
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 0.0,
97
- 1.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 0.0,
104
- 1.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 1.0,
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
- 1.0,
129
- 0.0,
130
- 1.0,
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
- 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_update1245.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cca5485d2df13a4d345e912b3067ff2c3136f9dc7bbb5319136ad193836bd04c
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1245.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1246,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6715392,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 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
- 1.0,
96
- 0.0,
97
- 1.0,
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
- 1.0,
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
- 1.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "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_update125.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4d40b040ce16ab35acd287ad30d97878458c172113a1402dc7f76f2d7ca80cc
3
- size 154490248
 
 
 
 
ppo_v11/policy_update125.state.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 126,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 348288,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0
25
- ],
26
- "recent_conversions": [
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0
42
- ],
43
- "recent_deaths": [
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0,
50
- 0.0,
51
- 0.0,
52
- 0.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
56
- 0.0,
57
- 0.0,
58
- 0.0
59
- ],
60
- "best_eval_win": null,
61
- "best_eval_score": null,
62
- "curriculum_schedule": "v10",
63
- "reward_profile": "v10-anti-spiral-v1",
64
- "return_stats": null,
65
- "stage_env_targets": [
66
- 24,
67
- 24,
68
- 24,
69
- 24,
70
- 24,
71
- 24,
72
- 24,
73
- 24,
74
- 24,
75
- 24,
76
- 24,
77
- 24,
78
- 24,
79
- 24,
80
- 24,
81
- 24,
82
- 24,
83
- 24,
84
- 24,
85
- 24,
86
- 24,
87
- 24,
88
- 24,
89
- 24,
90
- 24,
91
- 24,
92
- 24,
93
- 24,
94
- 24,
95
- 24,
96
- 24,
97
- 24,
98
- 24,
99
- 24,
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 24,
107
- 24,
108
- 24,
109
- 24,
110
- 24,
111
- 24,
112
- 20,
113
- 20,
114
- 20,
115
- 20,
116
- 20,
117
- 20,
118
- 20,
119
- 20,
120
- 16,
121
- 16,
122
- 16,
123
- 16,
124
- 12,
125
- 12,
126
- 12,
127
- 12,
128
- 12,
129
- 12,
130
- 12,
131
- 12,
132
- 12,
133
- 12,
134
- 10,
135
- 10,
136
- 10,
137
- 10,
138
- 10,
139
- 10,
140
- 10,
141
- 10,
142
- 10,
143
- 10,
144
- 10,
145
- 10,
146
- 10,
147
- 10,
148
- 8,
149
- 8,
150
- 8,
151
- 8,
152
- 8,
153
- 8,
154
- 8,
155
- 8,
156
- 8,
157
- 8,
158
- 8,
159
- 8,
160
- 8,
161
- 8,
162
- 8,
163
- 8,
164
- 8,
165
- 8
166
- ],
167
- "envs_per_shard": 24,
168
- "requested_env_target": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1250.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec23595bf18d19d36c0968e7d01af0d15cf6a8a8c9d96943317e46a5c282f57e
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1250.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1251,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6753792,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
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
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
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
- 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
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
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
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 1.0,
131
- 0.0,
132
- 1.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "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_update1255.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:245b012eaa8520ecd86a782bf1eb783329ad420fd81e255e5034da0510ec9146
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1255.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1256,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6792192,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 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
- 0.0,
68
- 0.0,
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
- 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
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 0.0,
111
- 0.0,
112
- 1.0,
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
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 1.0,
129
- 0.0,
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_update1260.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:280b3771fe586981bb1c95f4c8511fa2c7da44804f70b0e98853e30bf94b4f92
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1260.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1261,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6830592,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
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
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 0.0,
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
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
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
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 1.0,
121
- 0.0,
122
- 0.0,
123
- 1.0,
124
- 1.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 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_update1265.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcf0988644ed5b9616a2281e163fa31fe894c958e574fdac50ce26a3239ce2c5
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1265.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1266,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6868992,
9
- "recent_wins": [
10
- 1.0,
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
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
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
- 0.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 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
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 0.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 0.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
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
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 1.0,
110
- 0.0,
111
- 1.0,
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
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 1.0,
131
- 0.0,
132
- 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_update1270.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:257de39df1f5dcf9d7b3e0cd28df638656f4c564da1f23cb51d51ea2bcf89c7f
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1270.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1271,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6907392,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 1.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
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
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
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
- 1.0,
71
- 0.0,
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
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
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
- 0.0,
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
- 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_update1275.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d4b2f2e701fc865d5c024688c20e220de27e302d907dcc82c9b6bf6aa442eac
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1275.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1276,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6945792,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
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
- 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
- 1.0,
75
- 0.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 1.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 1.0,
111
- 1.0,
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
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 1.0,
129
- 0.0,
130
- 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_update1280.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cadd50f18f12938fc1f31023968dc99d74fd26dade2bd123b52e483102287a47
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1280.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1281,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 6984192,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
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
- 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
- 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
- 0.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
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
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
115
- 1.0,
116
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
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
- 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_update1285.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab6bf6ad019b6227a7cf1402f768fc9a2f506a92feed284ee0c8d1ed6e631d20
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1285.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1286,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7022592,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
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
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
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
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 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
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 0.0,
66
- 1.0,
67
- 0.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 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
- 0.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 1.0,
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
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
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
- 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
- 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_update1290.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:164efb4f78f9775572139de953ebb89051fc55e90dbd2fc4a09f51e7d91415ff
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1290.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1291,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7060992,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
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
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
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
- 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
- 0.0,
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
- 0.0,
95
- 1.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 0.0,
104
- 1.0,
105
- 0.0,
106
- 1.0,
107
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
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
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
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
- 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_update1295.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c819d8f102471a0794fe4f0bde48d38a3c0bbf6822adc083f8318ae142977f48
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1295.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1296,
5
- "stage": 23,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7099392,
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
- 1.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
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
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 0.0,
47
- 0.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
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
- 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
- 0.0,
83
- 1.0,
84
- 0.0,
85
- 0.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 1.0,
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
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 0.0,
124
- 1.0,
125
- 1.0,
126
- 0.0,
127
- 0.0,
128
- 1.0,
129
- 0.0,
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_update130.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ce8fa2af7e36e9e8a349337d80a49c2344a20d0a52fcaa4e9da4c128f1e7ad1
3
- size 154490248
 
 
 
 
ppo_v11/policy_update130.state.json DELETED
@@ -1,196 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 131,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 359808,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0
34
- ],
35
- "recent_conversions": [
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0,
50
- 1.0,
51
- 1.0,
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
- ],
61
- "recent_deaths": [
62
- 0.0,
63
- 0.0,
64
- 0.0,
65
- 0.0,
66
- 0.0,
67
- 0.0,
68
- 0.0,
69
- 0.0,
70
- 0.0,
71
- 0.0,
72
- 0.0,
73
- 0.0,
74
- 0.0,
75
- 0.0,
76
- 0.0,
77
- 0.0,
78
- 0.0,
79
- 0.0,
80
- 0.0,
81
- 0.0,
82
- 0.0,
83
- 0.0,
84
- 0.0,
85
- 0.0
86
- ],
87
- "best_eval_win": null,
88
- "best_eval_score": null,
89
- "curriculum_schedule": "v10",
90
- "reward_profile": "v10-anti-spiral-v1",
91
- "return_stats": null,
92
- "stage_env_targets": [
93
- 24,
94
- 24,
95
- 24,
96
- 24,
97
- 24,
98
- 24,
99
- 24,
100
- 24,
101
- 24,
102
- 24,
103
- 24,
104
- 24,
105
- 24,
106
- 24,
107
- 24,
108
- 24,
109
- 24,
110
- 24,
111
- 24,
112
- 24,
113
- 24,
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
- 20,
140
- 20,
141
- 20,
142
- 20,
143
- 20,
144
- 20,
145
- 20,
146
- 20,
147
- 16,
148
- 16,
149
- 16,
150
- 16,
151
- 12,
152
- 12,
153
- 12,
154
- 12,
155
- 12,
156
- 12,
157
- 12,
158
- 12,
159
- 12,
160
- 12,
161
- 10,
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
- 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
- 8,
190
- 8,
191
- 8,
192
- 8
193
- ],
194
- "envs_per_shard": 24,
195
- "requested_env_target": null
196
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1305.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f8dfc5be4d8062573fee4e9332d5dac858706689e33b03381a87a2e646ef5ef
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1305.state.json DELETED
@@ -1,89 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1306,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7176192,
9
- "recent_wins": [],
10
- "recent_conversions": [],
11
- "recent_deaths": [],
12
- "best_eval_win": null,
13
- "best_eval_score": null,
14
- "curriculum_schedule": "v10",
15
- "reward_profile": "v10-anti-spiral-v1",
16
- "return_stats": null,
17
- "stage_env_targets": [
18
- 24,
19
- 24,
20
- 24,
21
- 24,
22
- 24,
23
- 24,
24
- 24,
25
- 24,
26
- 24,
27
- 24,
28
- 24,
29
- 24,
30
- 24,
31
- 24,
32
- 24,
33
- 24,
34
- 24,
35
- 24,
36
- 24,
37
- 24,
38
- 24,
39
- 24,
40
- 24,
41
- 24,
42
- 24,
43
- 24,
44
- 24,
45
- 24,
46
- 20,
47
- 20,
48
- 20,
49
- 16,
50
- 16,
51
- 16,
52
- 12,
53
- 12,
54
- 10,
55
- 10,
56
- 10,
57
- 10,
58
- 10,
59
- 10,
60
- 10,
61
- 10,
62
- 10,
63
- 10,
64
- 10,
65
- 10,
66
- 10,
67
- 10,
68
- 8,
69
- 8,
70
- 8,
71
- 8,
72
- 8,
73
- 8,
74
- 8,
75
- 8,
76
- 8,
77
- 8,
78
- 8,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8,
84
- 8,
85
- 8
86
- ],
87
- "envs_per_shard": 40,
88
- "requested_env_target": null
89
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1310.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4124c285f50e759b21d704795b457225d14654f556300e5d7e6e3a7ebf9b59d9
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1310.state.json DELETED
@@ -1,204 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1311,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7214592,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
45
- 1.0,
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
- 1.0,
60
- 1.0,
61
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
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
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 1.0
84
- ],
85
- "recent_deaths": [
86
- 0.0,
87
- 0.0,
88
- 0.0,
89
- 0.0,
90
- 0.0,
91
- 1.0,
92
- 0.0,
93
- 0.0,
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 1.0,
111
- 1.0,
112
- 0.0,
113
- 1.0,
114
- 1.0,
115
- 0.0,
116
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 1.0,
125
- 0.0
126
- ],
127
- "best_eval_win": null,
128
- "best_eval_score": null,
129
- "curriculum_schedule": "v10",
130
- "reward_profile": "v10-anti-spiral-v1",
131
- "return_stats": null,
132
- "stage_env_targets": [
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
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 20,
162
- 20,
163
- 20,
164
- 16,
165
- 16,
166
- 16,
167
- 12,
168
- 12,
169
- 10,
170
- 10,
171
- 10,
172
- 10,
173
- 10,
174
- 10,
175
- 10,
176
- 10,
177
- 10,
178
- 10,
179
- 10,
180
- 10,
181
- 10,
182
- 10,
183
- 8,
184
- 8,
185
- 8,
186
- 8,
187
- 8,
188
- 8,
189
- 8,
190
- 8,
191
- 8,
192
- 8,
193
- 8,
194
- 8,
195
- 8,
196
- 8,
197
- 8,
198
- 8,
199
- 8,
200
- 8
201
- ],
202
- "envs_per_shard": 40,
203
- "requested_env_target": null
204
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1315.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8f5a4e5c423f71f5d26ff56a1cc23a8d6ad1fed8c33756802cbc63a0e1a2bef
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1315.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1316,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7252992,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
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
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 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
- 0.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 1.0,
97
- 1.0,
98
- 1.0,
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
- 0.0,
110
- 1.0,
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
- 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
- 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_update1320.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2edb24c6fbfeabfe7484a137747f6576c17cd70f39f607c4570464c0478ae2d
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1320.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1321,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7291392,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
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
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
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
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
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
- 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
- 0.0,
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
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 0.0,
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
- 0.0,
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
- 0.0,
107
- 1.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
112
- 1.0,
113
- 1.0,
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
- 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
- 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
- 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_update1325.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:00629a0583a6418161a2c750975c85c24e4249126de181b52bfcf25213e5cccb
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1325.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1326,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7329792,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 1.0,
15
- 0.0,
16
- 1.0,
17
- 1.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
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
- 0.0,
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
- 0.0,
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
- 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
- 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
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 0.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 0.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 0.0,
117
- 1.0,
118
- 1.0,
119
- 1.0,
120
- 0.0,
121
- 1.0,
122
- 0.0,
123
- 1.0,
124
- 1.0,
125
- 0.0,
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_update1330.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:011768fe3e841df3b5ed1b3c0a0b7a76b6dfbb373f3851154c6dccbd4d392503
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1330.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1331,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7368192,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 1.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
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
- 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
- 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
- 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
- 1.0,
97
- 1.0,
98
- 1.0,
99
- 1.0,
100
- 0.0,
101
- 1.0,
102
- 1.0,
103
- 0.0,
104
- 1.0,
105
- 0.0,
106
- 1.0,
107
- 1.0,
108
- 1.0,
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
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 1.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 1.0,
128
- 1.0,
129
- 0.0,
130
- 1.0,
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
- 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_update1335.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5db3a45e3e0520f3a0cb9b708e905a6e6f37892f70e7b979a1abee10f290a9c6
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1335.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1336,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7406592,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
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
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
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
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 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
- 0.0,
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
- 1.0,
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
- 1.0,
107
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
115
- 0.0,
116
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 0.0,
120
- 1.0,
121
- 1.0,
122
- 1.0,
123
- 0.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
127
- 1.0,
128
- 0.0,
129
- 0.0,
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
- 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_update1340.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4de83a11624947634948ddd8eba1f811901a079480dd1c4f9ab9de7e10f5b46
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1340.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1341,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7444992,
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
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
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
- 1.0,
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
- 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
- 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
- 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
- 1.0,
97
- 1.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
107
- 1.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 1.0,
121
- 1.0,
122
- 1.0,
123
- 1.0,
124
- 1.0,
125
- 0.0,
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
- 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_update1345.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8a6dccc85e8697df6cd86287dd49fab7b394eddea6977c1228303c46ac2a1f0
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1345.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1346,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7483392,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
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
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
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
- 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
- 0.0,
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
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 0.0,
89
- 0.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 1.0,
101
- 1.0,
102
- 1.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 0.0,
110
- 1.0,
111
- 1.0,
112
- 0.0,
113
- 0.0,
114
- 1.0,
115
- 1.0,
116
- 1.0,
117
- 1.0,
118
- 1.0,
119
- 1.0,
120
- 0.0,
121
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 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_update135.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:98fc48a3bc4505330d5b173843f656636934b2b27a05a7e83650ec731ac8454c
3
- size 154490248
 
 
 
 
ppo_v11/policy_update135.state.json DELETED
@@ -1,223 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 136,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 371328,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0
43
- ],
44
- "recent_conversions": [
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0,
50
- 1.0,
51
- 1.0,
52
- 1.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0
78
- ],
79
- "recent_deaths": [
80
- 0.0,
81
- 0.0,
82
- 0.0,
83
- 0.0,
84
- 0.0,
85
- 0.0,
86
- 0.0,
87
- 0.0,
88
- 0.0,
89
- 0.0,
90
- 0.0,
91
- 0.0,
92
- 0.0,
93
- 0.0,
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0
113
- ],
114
- "best_eval_win": null,
115
- "best_eval_score": null,
116
- "curriculum_schedule": "v10",
117
- "reward_profile": "v10-anti-spiral-v1",
118
- "return_stats": null,
119
- "stage_env_targets": [
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
- 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
- 20,
167
- 20,
168
- 20,
169
- 20,
170
- 20,
171
- 20,
172
- 20,
173
- 20,
174
- 16,
175
- 16,
176
- 16,
177
- 16,
178
- 12,
179
- 12,
180
- 12,
181
- 12,
182
- 12,
183
- 12,
184
- 12,
185
- 12,
186
- 12,
187
- 12,
188
- 10,
189
- 10,
190
- 10,
191
- 10,
192
- 10,
193
- 10,
194
- 10,
195
- 10,
196
- 10,
197
- 10,
198
- 10,
199
- 10,
200
- 10,
201
- 10,
202
- 8,
203
- 8,
204
- 8,
205
- 8,
206
- 8,
207
- 8,
208
- 8,
209
- 8,
210
- 8,
211
- 8,
212
- 8,
213
- 8,
214
- 8,
215
- 8,
216
- 8,
217
- 8,
218
- 8,
219
- 8
220
- ],
221
- "envs_per_shard": 24,
222
- "requested_env_target": null
223
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update1350.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8160c92479e72e2912b37a99441960602db49104e71c1cb225f58f4f8e1cfe73
3
- size 154490248
 
 
 
 
ppo_v11/policy_update1350.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 1351,
5
- "stage": 24,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 7521792,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
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
- 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
- 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
- 0.0,
67
- 1.0,
68
- 1.0,
69
- 0.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 0.0,
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
- 1.0,
98
- 1.0,
99
- 0.0,
100
- 1.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 1.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
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
- 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
- }