djmango commited on
Commit
ec96e9e
·
verified ·
1 Parent(s): e7f2906

Prune dense checkpoints (batch 27, 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_update450.safetensors +0 -3
  2. ppo_v11/policy_update450.state.json +0 -130
  3. ppo_v11/policy_update455.safetensors +0 -3
  4. ppo_v11/policy_update455.state.json +0 -183
  5. ppo_v11/policy_update460.safetensors +0 -3
  6. ppo_v11/policy_update460.state.json +0 -224
  7. ppo_v11/policy_update465.safetensors +0 -3
  8. ppo_v11/policy_update465.state.json +0 -139
  9. ppo_v11/policy_update490.safetensors +0 -3
  10. ppo_v11/policy_update490.state.json +0 -144
  11. ppo_v11/policy_update50.safetensors +0 -3
  12. ppo_v11/policy_update50.state.json +0 -244
  13. ppo_v11/policy_update515.safetensors +0 -3
  14. ppo_v11/policy_update515.state.json +0 -121
  15. ppo_v11/policy_update545.safetensors +0 -3
  16. ppo_v11/policy_update545.state.json +0 -127
  17. ppo_v11/policy_update55.safetensors +0 -3
  18. ppo_v11/policy_update55.state.json +0 -244
  19. ppo_v11/policy_update570.safetensors +0 -3
  20. ppo_v11/policy_update570.state.json +0 -127
  21. ppo_v11/policy_update60.safetensors +0 -3
  22. ppo_v11/policy_update60.state.json +0 -244
  23. ppo_v11/policy_update605.safetensors +0 -3
  24. ppo_v11/policy_update605.state.json +0 -223
  25. ppo_v11/policy_update65.safetensors +0 -3
  26. ppo_v11/policy_update65.state.json +0 -244
  27. ppo_v11/policy_update650.safetensors +0 -3
  28. ppo_v11/policy_update650.state.json +0 -121
  29. ppo_v11/policy_update675.safetensors +0 -3
  30. ppo_v11/policy_update675.state.json +0 -89
  31. ppo_v11/policy_update680.safetensors +0 -3
  32. ppo_v11/policy_update680.state.json +0 -206
  33. ppo_v11/policy_update685.safetensors +0 -3
  34. ppo_v11/policy_update685.state.json +0 -201
  35. ppo_v11/policy_update690.safetensors +0 -3
  36. ppo_v11/policy_update690.state.json +0 -200
  37. ppo_v11/policy_update695.safetensors +0 -3
  38. ppo_v11/policy_update695.state.json +0 -173
  39. ppo_v11/policy_update70.safetensors +0 -3
  40. ppo_v11/policy_update70.state.json +0 -244
  41. ppo_v11/policy_update705.safetensors +0 -3
  42. ppo_v11/policy_update705.state.json +0 -212
  43. ppo_v11/policy_update710.safetensors +0 -3
  44. ppo_v11/policy_update710.state.json +0 -212
  45. ppo_v11/policy_update715.safetensors +0 -3
  46. ppo_v11/policy_update715.state.json +0 -212
  47. ppo_v11/policy_update720.safetensors +0 -3
  48. ppo_v11/policy_update720.state.json +0 -212
  49. ppo_v11/policy_update725.safetensors +0 -3
  50. ppo_v11/policy_update725.state.json +0 -212
ppo_v11/policy_update450.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:43b780e4c6fe97e3db3ad6b0a0bd4a1e7204ebf78c8985631edf8b800a199200
3
- size 154490248
 
 
 
 
ppo_v11/policy_update450.state.json DELETED
@@ -1,130 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 451,
5
- "stage": 15,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000021838554775312908,
8
- "total_env_steps": 1097088,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0
12
- ],
13
- "recent_conversions": [
14
- 1.0,
15
- 1.0
16
- ],
17
- "recent_deaths": [
18
- 0.0,
19
- 0.0
20
- ],
21
- "best_eval_win": null,
22
- "best_eval_score": null,
23
- "curriculum_schedule": "v10",
24
- "reward_profile": "v10-anti-spiral-v1",
25
- "return_stats": null,
26
- "stage_env_targets": [
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
- 24,
47
- 24,
48
- 24,
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
- 20,
74
- 20,
75
- 20,
76
- 20,
77
- 20,
78
- 20,
79
- 20,
80
- 20,
81
- 16,
82
- 16,
83
- 16,
84
- 16,
85
- 12,
86
- 12,
87
- 12,
88
- 12,
89
- 12,
90
- 12,
91
- 12,
92
- 12,
93
- 12,
94
- 12,
95
- 10,
96
- 10,
97
- 10,
98
- 10,
99
- 10,
100
- 10,
101
- 10,
102
- 10,
103
- 10,
104
- 10,
105
- 10,
106
- 10,
107
- 10,
108
- 10,
109
- 8,
110
- 8,
111
- 8,
112
- 8,
113
- 8,
114
- 8,
115
- 8,
116
- 8,
117
- 8,
118
- 8,
119
- 8,
120
- 8,
121
- 8,
122
- 8,
123
- 8,
124
- 8,
125
- 8,
126
- 8
127
- ],
128
- "envs_per_shard": 24,
129
- "requested_env_target": null
130
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update455.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5936f327f6eaad8ee036ce01f1d6ca38385a95067451738dbff56ea2c255dd5
3
- size 154490248
 
 
 
 
ppo_v11/policy_update455.state.json DELETED
@@ -1,183 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 456,
5
- "stage": 15,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000021838554775312908,
8
- "total_env_steps": 1108608,
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
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 1.0
30
- ],
31
- "recent_conversions": [
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
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 0.0,
50
- 1.0
51
- ],
52
- "recent_deaths": [
53
- 0.0,
54
- 0.0,
55
- 0.0,
56
- 0.0,
57
- 0.0,
58
- 0.0,
59
- 0.0,
60
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 0.0,
64
- 0.0,
65
- 0.0,
66
- 0.0,
67
- 0.0,
68
- 0.0,
69
- 0.0,
70
- 0.0,
71
- 0.0,
72
- 0.0
73
- ],
74
- "best_eval_win": null,
75
- "best_eval_score": null,
76
- "curriculum_schedule": "v10",
77
- "reward_profile": "v10-anti-spiral-v1",
78
- "return_stats": null,
79
- "stage_env_targets": [
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
- 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
- 20,
127
- 20,
128
- 20,
129
- 20,
130
- 20,
131
- 20,
132
- 20,
133
- 20,
134
- 16,
135
- 16,
136
- 16,
137
- 16,
138
- 12,
139
- 12,
140
- 12,
141
- 12,
142
- 12,
143
- 12,
144
- 12,
145
- 12,
146
- 12,
147
- 12,
148
- 10,
149
- 10,
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
- 8,
163
- 8,
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
- ],
181
- "envs_per_shard": 24,
182
- "requested_env_target": null
183
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update460.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1da026a47425e35610aebd7df75bb75a4ae91eee0421622e2bb863d74e17df9d
3
- size 154490248
 
 
 
 
ppo_v11/policy_update460.state.json DELETED
@@ -1,224 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 461,
5
- "stage": 15,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000021838554775312908,
8
- "total_env_steps": 1120128,
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
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0
44
- ],
45
- "recent_conversions": [
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
- 0.0,
61
- 1.0,
62
- 1.0,
63
- 0.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 1.0,
74
- 1.0,
75
- 1.0,
76
- 1.0,
77
- 0.0
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
- 0.0
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
- 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
- 20,
168
- 20,
169
- 20,
170
- 20,
171
- 20,
172
- 20,
173
- 20,
174
- 20,
175
- 16,
176
- 16,
177
- 16,
178
- 16,
179
- 12,
180
- 12,
181
- 12,
182
- 12,
183
- 12,
184
- 12,
185
- 12,
186
- 12,
187
- 12,
188
- 12,
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
- 10,
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
- 8
221
- ],
222
- "envs_per_shard": 24,
223
- "requested_env_target": null
224
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update465.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:79befaa6fdcb5437932cf2b62979332b08b9850982f2a42d3dcc608cc7adae08
3
- size 154490248
 
 
 
 
ppo_v11/policy_update465.state.json DELETED
@@ -1,139 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 466,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 1131648,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 1.0
15
- ],
16
- "recent_conversions": [
17
- 0.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 1.0
22
- ],
23
- "recent_deaths": [
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0
29
- ],
30
- "best_eval_win": null,
31
- "best_eval_score": null,
32
- "curriculum_schedule": "v10",
33
- "reward_profile": "v10-anti-spiral-v1",
34
- "return_stats": null,
35
- "stage_env_targets": [
36
- 24,
37
- 24,
38
- 24,
39
- 24,
40
- 24,
41
- 24,
42
- 24,
43
- 24,
44
- 24,
45
- 24,
46
- 24,
47
- 24,
48
- 24,
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
- 24,
78
- 24,
79
- 24,
80
- 24,
81
- 24,
82
- 20,
83
- 20,
84
- 20,
85
- 20,
86
- 20,
87
- 20,
88
- 20,
89
- 20,
90
- 16,
91
- 16,
92
- 16,
93
- 16,
94
- 12,
95
- 12,
96
- 12,
97
- 12,
98
- 12,
99
- 12,
100
- 12,
101
- 12,
102
- 12,
103
- 12,
104
- 10,
105
- 10,
106
- 10,
107
- 10,
108
- 10,
109
- 10,
110
- 10,
111
- 10,
112
- 10,
113
- 10,
114
- 10,
115
- 10,
116
- 10,
117
- 10,
118
- 8,
119
- 8,
120
- 8,
121
- 8,
122
- 8,
123
- 8,
124
- 8,
125
- 8,
126
- 8,
127
- 8,
128
- 8,
129
- 8,
130
- 8,
131
- 8,
132
- 8,
133
- 8,
134
- 8,
135
- 8
136
- ],
137
- "envs_per_shard": 24,
138
- "requested_env_target": null
139
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update490.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c6d3cb4a9086b4f278a1a11f5cd12f6d8249544d3bed674c58079b897af66d2
3
- size 154490248
 
 
 
 
ppo_v11/policy_update490.state.json DELETED
@@ -1,144 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 491,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 1266048,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 1.0
17
- ],
18
- "recent_conversions": [
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 1.0
25
- ],
26
- "recent_deaths": [
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0
34
- ],
35
- "best_eval_win": null,
36
- "best_eval_score": null,
37
- "curriculum_schedule": "v10",
38
- "reward_profile": "v10-anti-spiral-v1",
39
- "return_stats": null,
40
- "stage_env_targets": [
41
- 24,
42
- 24,
43
- 24,
44
- 24,
45
- 24,
46
- 24,
47
- 24,
48
- 24,
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
- 24,
78
- 24,
79
- 24,
80
- 24,
81
- 24,
82
- 24,
83
- 24,
84
- 24,
85
- 24,
86
- 24,
87
- 20,
88
- 20,
89
- 20,
90
- 20,
91
- 20,
92
- 20,
93
- 20,
94
- 20,
95
- 16,
96
- 16,
97
- 16,
98
- 16,
99
- 12,
100
- 12,
101
- 12,
102
- 12,
103
- 12,
104
- 12,
105
- 12,
106
- 12,
107
- 12,
108
- 12,
109
- 10,
110
- 10,
111
- 10,
112
- 10,
113
- 10,
114
- 10,
115
- 10,
116
- 10,
117
- 10,
118
- 10,
119
- 10,
120
- 10,
121
- 10,
122
- 10,
123
- 8,
124
- 8,
125
- 8,
126
- 8,
127
- 8,
128
- 8,
129
- 8,
130
- 8,
131
- 8,
132
- 8,
133
- 8,
134
- 8,
135
- 8,
136
- 8,
137
- 8,
138
- 8,
139
- 8,
140
- 8
141
- ],
142
- "envs_per_shard": 32,
143
- "requested_env_target": null
144
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update50.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd49fac5eaa98b1166bff400ccedd3fd781159e089405545ef1b63e9809d8652
3
- size 154490248
 
 
 
 
ppo_v11/policy_update50.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 51,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 156672,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 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
- 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
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 1.0,
56
- 0.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 0.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 0.0,
65
- 0.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 1.0,
73
- 0.0,
74
- 1.0,
75
- 0.0,
76
- 0.0,
77
- 0.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 0.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 1.0,
88
- 1.0,
89
- 1.0,
90
- 1.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 1.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 1.0,
108
- 1.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 1.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "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_update515.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:46ceb04766b3c33f9479ff42149520575182df451d90ee21bc8e72f91c27e070
3
- size 154490248
 
 
 
 
ppo_v11/policy_update515.state.json DELETED
@@ -1,121 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 516,
5
- "stage": 17,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000015778355825163578,
8
- "total_env_steps": 1406592,
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
- 24,
47
- 24,
48
- 24,
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
- 20,
65
- 20,
66
- 20,
67
- 20,
68
- 20,
69
- 20,
70
- 20,
71
- 20,
72
- 16,
73
- 16,
74
- 16,
75
- 16,
76
- 12,
77
- 12,
78
- 12,
79
- 12,
80
- 12,
81
- 12,
82
- 12,
83
- 12,
84
- 12,
85
- 12,
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
- 10,
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
- 8
118
- ],
119
- "envs_per_shard": 32,
120
- "requested_env_target": null
121
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update545.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f62bb8b9bf0e880d1b735e1696efd5561a1c3feb65a8a6e30d43e4c9effc788
3
- size 154490248
 
 
 
 
ppo_v11/policy_update545.state.json DELETED
@@ -1,127 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 546,
5
- "stage": 18,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001341160245138904,
8
- "total_env_steps": 1571712,
9
- "recent_wins": [
10
- 1.0
11
- ],
12
- "recent_conversions": [
13
- 1.0
14
- ],
15
- "recent_deaths": [
16
- 0.0
17
- ],
18
- "best_eval_win": null,
19
- "best_eval_score": null,
20
- "curriculum_schedule": "v10",
21
- "reward_profile": "v10-anti-spiral-v1",
22
- "return_stats": null,
23
- "stage_env_targets": [
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
- 24,
47
- 24,
48
- 24,
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
- 20,
71
- 20,
72
- 20,
73
- 20,
74
- 20,
75
- 20,
76
- 20,
77
- 20,
78
- 16,
79
- 16,
80
- 16,
81
- 16,
82
- 12,
83
- 12,
84
- 12,
85
- 12,
86
- 12,
87
- 12,
88
- 12,
89
- 12,
90
- 12,
91
- 12,
92
- 10,
93
- 10,
94
- 10,
95
- 10,
96
- 10,
97
- 10,
98
- 10,
99
- 10,
100
- 10,
101
- 10,
102
- 10,
103
- 10,
104
- 10,
105
- 10,
106
- 8,
107
- 8,
108
- 8,
109
- 8,
110
- 8,
111
- 8,
112
- 8,
113
- 8,
114
- 8,
115
- 8,
116
- 8,
117
- 8,
118
- 8,
119
- 8,
120
- 8,
121
- 8,
122
- 8,
123
- 8
124
- ],
125
- "envs_per_shard": 32,
126
- "requested_env_target": null
127
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update55.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ee154e7c48bb3f2b4fafbd57dadc35f5b77d6e2a5255f49f1ffa88f12ad3af
3
- size 154490248
 
 
 
 
ppo_v11/policy_update55.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 56,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 172032,
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
- 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
- 1.0,
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
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 1.0,
55
- 1.0,
56
- 1.0,
57
- 0.0,
58
- 0.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 0.0,
69
- 0.0,
70
- 0.0,
71
- 0.0,
72
- 0.0,
73
- 1.0,
74
- 0.0,
75
- 1.0,
76
- 1.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0,
84
- 1.0,
85
- 1.0,
86
- 1.0,
87
- 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
- 1.0,
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
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 1.0,
128
- 0.0,
129
- 0.0,
130
- 0.0,
131
- 1.0,
132
- 1.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 8,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8
241
- ],
242
- "envs_per_shard": 24,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update570.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f214921aac793070b4f96425bccde7e8097d21e53effaa86c5b71bf2f04f6f1
3
- size 154490248
 
 
 
 
ppo_v11/policy_update570.state.json DELETED
@@ -1,127 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 571,
5
- "stage": 19,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000011399862083680684,
8
- "total_env_steps": 1712256,
9
- "recent_wins": [
10
- 1.0
11
- ],
12
- "recent_conversions": [
13
- 1.0
14
- ],
15
- "recent_deaths": [
16
- 0.0
17
- ],
18
- "best_eval_win": null,
19
- "best_eval_score": null,
20
- "curriculum_schedule": "v10",
21
- "reward_profile": "v10-anti-spiral-v1",
22
- "return_stats": null,
23
- "stage_env_targets": [
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
- 24,
47
- 24,
48
- 24,
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
- 20,
71
- 20,
72
- 20,
73
- 20,
74
- 20,
75
- 20,
76
- 20,
77
- 20,
78
- 16,
79
- 16,
80
- 16,
81
- 16,
82
- 12,
83
- 12,
84
- 12,
85
- 12,
86
- 12,
87
- 12,
88
- 12,
89
- 12,
90
- 12,
91
- 12,
92
- 10,
93
- 10,
94
- 10,
95
- 10,
96
- 10,
97
- 10,
98
- 10,
99
- 10,
100
- 10,
101
- 10,
102
- 10,
103
- 10,
104
- 10,
105
- 10,
106
- 8,
107
- 8,
108
- 8,
109
- 8,
110
- 8,
111
- 8,
112
- 8,
113
- 8,
114
- 8,
115
- 8,
116
- 8,
117
- 8,
118
- 8,
119
- 8,
120
- 8,
121
- 8,
122
- 8,
123
- 8
124
- ],
125
- "envs_per_shard": 32,
126
- "requested_env_target": null
127
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update60.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:37a00d1e9f45548fb890602e10500da7f78e523a0827ab07a8a52f9f8dd011e3
3
- size 154490248
 
 
 
 
ppo_v11/policy_update60.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 61,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 187392,
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
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
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
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 0.0,
59
- 1.0,
60
- 0.0,
61
- 0.0,
62
- 0.0,
63
- 0.0,
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
- 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
- 0.0,
90
- 0.0,
91
- 1.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 0.0,
104
- 0.0,
105
- 0.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 0.0,
111
- 0.0,
112
- 0.0,
113
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 0.0,
127
- 0.0,
128
- 0.0,
129
- 1.0,
130
- 0.0,
131
- 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_update605.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec982707334fc0e09bc297b9fdc5d01f052c0c192a4ee4565a5c7b48d2f30db4
3
- size 154490248
 
 
 
 
ppo_v11/policy_update605.state.json DELETED
@@ -1,223 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 606,
5
- "stage": 20,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 1908096,
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": 32,
222
- "requested_env_target": null
223
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update65.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b9c55641336ec2e873f6ff64ef0971eb2d4e1a22e6b7a64db049e614dc10205
3
- size 154490248
 
 
 
 
ppo_v11/policy_update65.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 66,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 202752,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
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
- 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
- 0.0,
80
- 1.0,
81
- 0.0,
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
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 0.0,
113
- 1.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 0.0,
120
- 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
- 1.0,
131
- 0.0,
132
- 0.0,
133
- 0.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 24,
170
- 24,
171
- 24,
172
- 24,
173
- 24,
174
- 24,
175
- 24,
176
- 24,
177
- 24,
178
- 24,
179
- 24,
180
- 24,
181
- 24,
182
- 24,
183
- 24,
184
- 24,
185
- 24,
186
- 24,
187
- 20,
188
- 20,
189
- 20,
190
- 20,
191
- 20,
192
- 20,
193
- 20,
194
- 20,
195
- 16,
196
- 16,
197
- 16,
198
- 16,
199
- 12,
200
- 12,
201
- 12,
202
- 12,
203
- 12,
204
- 12,
205
- 12,
206
- 12,
207
- 12,
208
- 12,
209
- 10,
210
- 10,
211
- 10,
212
- 10,
213
- 10,
214
- 10,
215
- 10,
216
- 10,
217
- 10,
218
- 10,
219
- 10,
220
- 10,
221
- 10,
222
- 10,
223
- 8,
224
- 8,
225
- 8,
226
- 8,
227
- 8,
228
- 8,
229
- 8,
230
- 8,
231
- 8,
232
- 8,
233
- 8,
234
- 8,
235
- 8,
236
- 8,
237
- 8,
238
- 8,
239
- 8,
240
- 8
241
- ],
242
- "envs_per_shard": 24,
243
- "requested_env_target": null
244
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update650.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d97a4ec67f728d8546b5309407512e5d9e11d70dfd6c1e32ed22a2cf4da09b6
3
- size 154490248
 
 
 
 
ppo_v11/policy_update650.state.json DELETED
@@ -1,121 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 651,
5
- "stage": 21,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00001,
8
- "total_env_steps": 2186112,
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
- 24,
47
- 24,
48
- 24,
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
- 20,
65
- 20,
66
- 20,
67
- 20,
68
- 20,
69
- 20,
70
- 20,
71
- 20,
72
- 16,
73
- 16,
74
- 16,
75
- 16,
76
- 12,
77
- 12,
78
- 12,
79
- 12,
80
- 12,
81
- 12,
82
- 12,
83
- 12,
84
- 12,
85
- 12,
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
- 10,
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
- 8
118
- ],
119
- "envs_per_shard": 40,
120
- "requested_env_target": null
121
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update675.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1f057a819aae4a4c1d981e347ad14834abbca8c6f1623bcd926901d8f0a1179
3
- size 154490248
 
 
 
 
ppo_v11/policy_update675.state.json DELETED
@@ -1,89 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 676,
5
- "stage": 13,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00003022637339143656,
8
- "total_env_steps": 2337792,
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_update680.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:36d50714c16c606c4881fcfb4e5b84c4801e5f8f3b114e07db9cec592edf5bbf
3
- size 154490248
 
 
 
 
ppo_v11/policy_update680.state.json DELETED
@@ -1,206 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 681,
5
- "stage": 13,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00003022637339143656,
8
- "total_env_steps": 2376192,
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
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0
48
- ],
49
- "recent_conversions": [
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
- 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
- ],
89
- "recent_deaths": [
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
- 0.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 0.0,
118
- 0.0,
119
- 0.0,
120
- 0.0,
121
- 0.0,
122
- 0.0,
123
- 0.0,
124
- 0.0,
125
- 0.0,
126
- 0.0,
127
- 0.0
128
- ],
129
- "best_eval_win": null,
130
- "best_eval_score": null,
131
- "curriculum_schedule": "v10",
132
- "reward_profile": "v10-anti-spiral-v1",
133
- "return_stats": null,
134
- "stage_env_targets": [
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
- 20,
164
- 20,
165
- 20,
166
- 16,
167
- 16,
168
- 16,
169
- 12,
170
- 12,
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
- 10,
184
- 10,
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
- 8,
202
- 8
203
- ],
204
- "envs_per_shard": 40,
205
- "requested_env_target": null
206
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update685.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5cfb7604e0d9c908a2ed69e988fe9031b96e471235d2bba994b0bb9e47482e3
3
- size 154490248
 
 
 
 
ppo_v11/policy_update685.state.json DELETED
@@ -1,201 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 686,
5
- "stage": 14,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00002569241738272107,
8
- "total_env_steps": 2414592,
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
- 0.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 0.0
48
- ],
49
- "recent_conversions": [
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
- 1.0,
79
- 1.0,
80
- 1.0,
81
- 1.0,
82
- 1.0
83
- ],
84
- "recent_deaths": [
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
- 1.0,
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
- 1.0,
122
- 0.0
123
- ],
124
- "best_eval_win": null,
125
- "best_eval_score": null,
126
- "curriculum_schedule": "v10",
127
- "reward_profile": "v10-anti-spiral-v1",
128
- "return_stats": null,
129
- "stage_env_targets": [
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
- 20,
159
- 20,
160
- 20,
161
- 16,
162
- 16,
163
- 16,
164
- 12,
165
- 12,
166
- 10,
167
- 10,
168
- 10,
169
- 10,
170
- 10,
171
- 10,
172
- 10,
173
- 10,
174
- 10,
175
- 10,
176
- 10,
177
- 10,
178
- 10,
179
- 10,
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
- 8,
195
- 8,
196
- 8,
197
- 8
198
- ],
199
- "envs_per_shard": 40,
200
- "requested_env_target": null
201
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update690.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa390eea469ce1f3101f147d52e330ea7a28b9bf6908a7a5055cd4d8922b8003
3
- size 154490248
 
 
 
 
ppo_v11/policy_update690.state.json DELETED
@@ -1,200 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 691,
5
- "stage": 15,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000021838554775312908,
8
- "total_env_steps": 2452992,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 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
- 1.0,
44
- 1.0,
45
- 1.0
46
- ],
47
- "recent_conversions": [
48
- 1.0,
49
- 0.0,
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
- 0.0,
62
- 1.0,
63
- 1.0,
64
- 1.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 0.0,
69
- 0.0,
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
- 1.0,
81
- 1.0,
82
- 1.0,
83
- 1.0
84
- ],
85
- "recent_deaths": [
86
- 0.0,
87
- 1.0,
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
- 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
- 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
- ],
123
- "best_eval_win": null,
124
- "best_eval_score": null,
125
- "curriculum_schedule": "v10",
126
- "reward_profile": "v10-anti-spiral-v1",
127
- "return_stats": null,
128
- "stage_env_targets": [
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
- 20,
158
- 20,
159
- 20,
160
- 16,
161
- 16,
162
- 16,
163
- 12,
164
- 12,
165
- 10,
166
- 10,
167
- 10,
168
- 10,
169
- 10,
170
- 10,
171
- 10,
172
- 10,
173
- 10,
174
- 10,
175
- 10,
176
- 10,
177
- 10,
178
- 10,
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
- 8,
195
- 8,
196
- 8
197
- ],
198
- "envs_per_shard": 40,
199
- "requested_env_target": null
200
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update695.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:07787852d284786847c112a88ebd0b4b3a372f7a9bcf9e6a8aa2c8d49bc379b6
3
- size 154490248
 
 
 
 
ppo_v11/policy_update695.state.json DELETED
@@ -1,173 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 696,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 2491392,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0
39
- ],
40
- "recent_conversions": [
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
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
- 0.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 1.0
64
- ],
65
- "recent_deaths": [
66
- 0.0,
67
- 0.0,
68
- 0.0,
69
- 0.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 1.0,
74
- 0.0,
75
- 0.0,
76
- 0.0,
77
- 0.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
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
- 1.0,
92
- 0.0,
93
- 0.0,
94
- 0.0
95
- ],
96
- "best_eval_win": null,
97
- "best_eval_score": null,
98
- "curriculum_schedule": "v10",
99
- "reward_profile": "v10-anti-spiral-v1",
100
- "return_stats": null,
101
- "stage_env_targets": [
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
- 20,
131
- 20,
132
- 20,
133
- 16,
134
- 16,
135
- 16,
136
- 12,
137
- 12,
138
- 10,
139
- 10,
140
- 10,
141
- 10,
142
- 10,
143
- 10,
144
- 10,
145
- 10,
146
- 10,
147
- 10,
148
- 10,
149
- 10,
150
- 10,
151
- 10,
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
- 8,
167
- 8,
168
- 8,
169
- 8
170
- ],
171
- "envs_per_shard": 40,
172
- "requested_env_target": null
173
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v11/policy_update70.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0323fcfec7af376c19aac55eb32daa797261eb37e38c6df2acd0fc1641dc72e1
3
- size 154490248
 
 
 
 
ppo_v11/policy_update70.state.json DELETED
@@ -1,244 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 71,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 218112,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
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
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 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
- 0.0,
53
- 1.0,
54
- 0.0,
55
- 1.0,
56
- 1.0,
57
- 1.0,
58
- 1.0,
59
- 1.0,
60
- 1.0,
61
- 1.0,
62
- 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
- 0.0,
78
- 0.0,
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
- 0.0,
95
- 0.0,
96
- 0.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 1.0,
102
- 0.0,
103
- 0.0,
104
- 0.0,
105
- 1.0,
106
- 1.0,
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
- 1.0,
117
- 0.0,
118
- 1.0,
119
- 0.0,
120
- 0.0,
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
- 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_update705.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8f6991fbcab60201b7a751d99a3a522bd324fd4a2cadbf1af6630ddd1b1150
3
- size 154490248
 
 
 
 
ppo_v11/policy_update705.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 706,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 2568192,
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
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
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
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 0.0,
53
- 1.0,
54
- 1.0,
55
- 0.0,
56
- 0.0,
57
- 0.0,
58
- 0.0,
59
- 1.0,
60
- 1.0,
61
- 0.0,
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
- 1.0,
72
- 1.0,
73
- 0.0,
74
- 0.0,
75
- 0.0,
76
- 1.0,
77
- 0.0,
78
- 1.0,
79
- 0.0,
80
- 0.0,
81
- 1.0,
82
- 0.0,
83
- 0.0,
84
- 1.0,
85
- 1.0,
86
- 0.0,
87
- 1.0,
88
- 0.0,
89
- 1.0,
90
- 1.0,
91
- 0.0
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
- 1.0,
103
- 1.0,
104
- 0.0,
105
- 0.0,
106
- 1.0,
107
- 0.0,
108
- 1.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 1.0,
113
- 1.0,
114
- 0.0,
115
- 0.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 0.0,
122
- 1.0,
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
- 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_update710.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:293a00b1c965205c50e64fa71947581b0e4553763cda102b09e44fa6478e94b0
3
- size 154490248
 
 
 
 
ppo_v11/policy_update710.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 711,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 2606592,
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
- 0.0,
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
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [
52
- 1.0,
53
- 0.0,
54
- 0.0,
55
- 0.0,
56
- 1.0,
57
- 0.0,
58
- 1.0,
59
- 0.0,
60
- 0.0,
61
- 1.0,
62
- 0.0,
63
- 0.0,
64
- 1.0,
65
- 1.0,
66
- 0.0,
67
- 1.0,
68
- 0.0,
69
- 1.0,
70
- 1.0,
71
- 0.0,
72
- 1.0,
73
- 1.0,
74
- 0.0,
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
- 0.0,
85
- 1.0,
86
- 0.0,
87
- 1.0,
88
- 0.0,
89
- 0.0,
90
- 1.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 0.0,
96
- 1.0,
97
- 1.0,
98
- 0.0,
99
- 1.0,
100
- 1.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 1.0,
105
- 1.0,
106
- 0.0,
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
- 0.0,
118
- 0.0,
119
- 1.0,
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
- 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_update715.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d649c60a03dc48cf6e38086c2e55e66d42d555809f8215e06f64982f92cdaf2
3
- size 154490248
 
 
 
 
ppo_v11/policy_update715.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 716,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 2644992,
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
- 0.0,
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
- 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
- 1.0,
42
- 0.0,
43
- 0.0,
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
- 0.0,
54
- 1.0,
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
- 0.0,
64
- 1.0,
65
- 0.0,
66
- 1.0,
67
- 0.0,
68
- 0.0,
69
- 1.0,
70
- 0.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 0.0,
75
- 0.0,
76
- 0.0,
77
- 1.0,
78
- 0.0,
79
- 0.0,
80
- 1.0,
81
- 0.0,
82
- 0.0,
83
- 0.0,
84
- 0.0,
85
- 0.0,
86
- 0.0,
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
- 1.0,
97
- 1.0,
98
- 1.0,
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
- 0.0,
108
- 1.0,
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
- 0.0,
118
- 0.0,
119
- 1.0,
120
- 0.0,
121
- 1.0,
122
- 1.0,
123
- 0.0,
124
- 1.0,
125
- 0.0,
126
- 1.0,
127
- 1.0,
128
- 1.0,
129
- 1.0,
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_update720.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d15bf10308df40cc822e33fa066b20fb7c95576003df4273c8146e233f982db
3
- size 154490248
 
 
 
 
ppo_v11/policy_update720.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 721,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 2683392,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
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
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
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
- 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
- 0.0,
56
- 1.0,
57
- 0.0,
58
- 0.0,
59
- 0.0,
60
- 0.0,
61
- 0.0,
62
- 1.0,
63
- 0.0,
64
- 0.0,
65
- 1.0,
66
- 0.0,
67
- 0.0,
68
- 0.0,
69
- 0.0,
70
- 0.0,
71
- 0.0,
72
- 1.0,
73
- 0.0,
74
- 0.0,
75
- 1.0,
76
- 0.0,
77
- 1.0,
78
- 1.0,
79
- 1.0,
80
- 0.0,
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
- 0.0,
90
- 0.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 1.0,
95
- 1.0,
96
- 1.0,
97
- 0.0,
98
- 0.0,
99
- 0.0,
100
- 0.0,
101
- 0.0,
102
- 1.0,
103
- 0.0,
104
- 1.0,
105
- 0.0,
106
- 0.0,
107
- 1.0,
108
- 0.0,
109
- 1.0,
110
- 1.0,
111
- 0.0,
112
- 1.0,
113
- 0.0,
114
- 0.0,
115
- 1.0,
116
- 0.0,
117
- 1.0,
118
- 0.0,
119
- 1.0,
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
- 1.0,
129
- 1.0,
130
- 1.0,
131
- 0.0,
132
- 1.0,
133
- 1.0
134
- ],
135
- "best_eval_win": null,
136
- "best_eval_score": null,
137
- "curriculum_schedule": "v10",
138
- "reward_profile": "v10-anti-spiral-v1",
139
- "return_stats": null,
140
- "stage_env_targets": [
141
- 24,
142
- 24,
143
- 24,
144
- 24,
145
- 24,
146
- 24,
147
- 24,
148
- 24,
149
- 24,
150
- 24,
151
- 24,
152
- 24,
153
- 24,
154
- 24,
155
- 24,
156
- 24,
157
- 24,
158
- 24,
159
- 24,
160
- 24,
161
- 24,
162
- 24,
163
- 24,
164
- 24,
165
- 24,
166
- 24,
167
- 24,
168
- 24,
169
- 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_update725.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bcb12c3b0300bc7ea5aac9e499a599603db10cce30ca4746ae4e9de2357aee6
3
- size 154490248
 
 
 
 
ppo_v11/policy_update725.state.json DELETED
@@ -1,212 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 3,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 726,
5
- "stage": 16,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.000018562771559015974,
8
- "total_env_steps": 2721792,
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
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 1.0,
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
- 1.0,
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
- 0.0,
54
- 0.0,
55
- 1.0,
56
- 0.0,
57
- 0.0,
58
- 1.0,
59
- 0.0,
60
- 1.0,
61
- 1.0,
62
- 1.0,
63
- 0.0,
64
- 0.0,
65
- 1.0,
66
- 1.0,
67
- 1.0,
68
- 1.0,
69
- 1.0,
70
- 1.0,
71
- 1.0,
72
- 0.0,
73
- 0.0,
74
- 0.0,
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
- 0.0,
85
- 0.0,
86
- 1.0,
87
- 0.0,
88
- 1.0,
89
- 1.0,
90
- 0.0,
91
- 0.0
92
- ],
93
- "recent_deaths": [
94
- 0.0,
95
- 1.0,
96
- 1.0,
97
- 0.0,
98
- 1.0,
99
- 1.0,
100
- 0.0,
101
- 0.0,
102
- 0.0,
103
- 1.0,
104
- 0.0,
105
- 1.0,
106
- 0.0,
107
- 0.0,
108
- 0.0,
109
- 0.0,
110
- 1.0,
111
- 0.0,
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
- 0.0,
122
- 1.0,
123
- 0.0,
124
- 0.0,
125
- 1.0,
126
- 1.0,
127
- 0.0,
128
- 1.0,
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
- }