Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
d34e1a7
·
verified ·
1 Parent(s): e71f0ce

Prune dense checkpoints (batch 32, 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_v9/policy_update35.state.json +0 -87
  2. ppo_v9/policy_update350.safetensors +0 -3
  3. ppo_v9/policy_update350.state.json +0 -87
  4. ppo_v9/policy_update355.safetensors +0 -3
  5. ppo_v9/policy_update355.state.json +0 -87
  6. ppo_v9/policy_update360.safetensors +0 -3
  7. ppo_v9/policy_update360.state.json +0 -87
  8. ppo_v9/policy_update365.safetensors +0 -3
  9. ppo_v9/policy_update365.state.json +0 -87
  10. ppo_v9/policy_update370.safetensors +0 -3
  11. ppo_v9/policy_update370.state.json +0 -87
  12. ppo_v9/policy_update375.safetensors +0 -3
  13. ppo_v9/policy_update375.state.json +0 -87
  14. ppo_v9/policy_update385.safetensors +0 -3
  15. ppo_v9/policy_update385.state.json +0 -87
  16. ppo_v9/policy_update390.safetensors +0 -3
  17. ppo_v9/policy_update390.state.json +0 -87
  18. ppo_v9/policy_update395.safetensors +0 -3
  19. ppo_v9/policy_update395.state.json +0 -87
  20. ppo_v9/policy_update40.safetensors +0 -3
  21. ppo_v9/policy_update40.state.json +0 -87
  22. ppo_v9/policy_update400.safetensors +0 -3
  23. ppo_v9/policy_update400.state.json +0 -87
  24. ppo_v9/policy_update405.safetensors +0 -3
  25. ppo_v9/policy_update405.state.json +0 -87
  26. ppo_v9/policy_update410.safetensors +0 -3
  27. ppo_v9/policy_update410.state.json +0 -87
  28. ppo_v9/policy_update415.safetensors +0 -3
  29. ppo_v9/policy_update415.state.json +0 -87
  30. ppo_v9/policy_update420.safetensors +0 -3
  31. ppo_v9/policy_update420.state.json +0 -87
  32. ppo_v9/policy_update425.safetensors +0 -3
  33. ppo_v9/policy_update435.safetensors +0 -3
  34. ppo_v9/policy_update435.state.json +0 -87
  35. ppo_v9/policy_update440.safetensors +0 -3
  36. ppo_v9/policy_update440.state.json +0 -87
  37. ppo_v9/policy_update445.safetensors +0 -3
  38. ppo_v9/policy_update445.state.json +0 -87
  39. ppo_v9/policy_update45.safetensors +0 -3
  40. ppo_v9/policy_update45.state.json +0 -87
  41. ppo_v9/policy_update450.safetensors +0 -3
  42. ppo_v9/policy_update450.state.json +0 -87
  43. ppo_v9/policy_update455.safetensors +0 -3
  44. ppo_v9/policy_update455.state.json +0 -87
  45. ppo_v9/policy_update460.safetensors +0 -3
  46. ppo_v9/policy_update460.state.json +0 -87
  47. ppo_v9/policy_update465.safetensors +0 -3
  48. ppo_v9/policy_update465.state.json +0 -87
  49. ppo_v9/policy_update470.safetensors +0 -3
  50. ppo_v9/policy_update470.state.json +0 -87
ppo_v9/policy_update35.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 36,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 138240,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 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
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update350.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9d0b9e8e4bab13da836baadc4a192174673f5c2cd4cf9d4852ef54060cb0730
3
- size 48494336
 
 
 
 
ppo_v9/policy_update350.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 351,
5
- "stage": 0,
6
- "ent_scale": 1.6900000000000002,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1347840,
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
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 0.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update355.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f0f4b0a1e6b231933d214c20a2dc0eac35c703a0cb2a1ace336190a6b89f8f3
3
- size 48494336
 
 
 
 
ppo_v9/policy_update355.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 356,
5
- "stage": 0,
6
- "ent_scale": 1.6095238095238098,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1367040,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
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
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update360.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e21d54d86265ebf0a42a9d633b15eaf9f077ba6b013d0c352728ad32379037
3
- size 48494336
 
 
 
 
ppo_v9/policy_update360.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 361,
5
- "stage": 0,
6
- "ent_scale": 1.122988878090919,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1386240,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
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
- 1.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update365.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3ddd8e32f47e646e75d519f62c9b24b34e678d27d710816c6af6a8096b1278b
3
- size 48494336
 
 
 
 
ppo_v9/policy_update365.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 366,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1405440,
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
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 0.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 0.0,
38
- 0.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update370.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c3902553a24f35496738395d5061898dae5aa15b08e4b4b9cb2dea27e831d64
3
- size 48494336
 
 
 
 
ppo_v9/policy_update370.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 371,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1424640,
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
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 1.0,
22
- 1.0,
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
- 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
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update375.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd3fc05be794a6e5d5a2857a44ef7c40dbaa5fafc16a95c40c3bf4df0f9daebd
3
- size 48494336
 
 
 
 
ppo_v9/policy_update375.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 376,
5
- "stage": 0,
6
- "ent_scale": 1.4598855415181946,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1443840,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
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
- 0.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
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
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 1.0,
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
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update385.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e7ff4a7239ad531e4ed19f8dfdbfa11532025028eb2c6fc962ff0b46ce81a77
3
- size 48494336
 
 
 
 
ppo_v9/policy_update385.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 386,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1482240,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 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
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update390.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:210470b32678bdfc9ddd397fb83c6569d45a3242d5778550edaa2b4ff4c3bb1c
3
- size 48494336
 
 
 
 
ppo_v9/policy_update390.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 391,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1501440,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 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
- 1.0,
37
- 0.0,
38
- 1.0,
39
- 1.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update395.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b11e2777662011b1746770b9b730c878ed0386c3e431a6cc0b71f3d7b431c39f
3
- size 48494336
 
 
 
 
ppo_v9/policy_update395.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 396,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1520640,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 1.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update40.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1d41b82d44532a4a4902c8b73c7f2f32ce6b8152e6272e123702988e6d87fd2
3
- size 48494336
 
 
 
 
ppo_v9/policy_update40.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 41,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 157440,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 1.0,
44
- 1.0,
45
- 1.0,
46
- 0.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update400.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf9c73128c3b121a53d027f88e2c7f9b4f08b97339c00bc77ff695380e6ff67a
3
- size 48494336
 
 
 
 
ppo_v9/policy_update400.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 401,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1539840,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 1.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update405.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:031445e8d822ea33de0c22ff11df2ea869e1a5f19855ca5d2ff3e1ed773c6ec2
3
- size 48494336
 
 
 
 
ppo_v9/policy_update405.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 406,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1559040,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update410.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:70ca31f89d187ee548e77691ccd16a8071b01b3488782dc27f90344c0d97ee1d
3
- size 48494336
 
 
 
 
ppo_v9/policy_update410.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 411,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1578240,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 0.0,
39
- 0.0,
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
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update415.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16fd876cd673fb64d10694a487b2ae1b7d586dff48fa079f34e63b0a1c0bd4f9
3
- size 48494336
 
 
 
 
ppo_v9/policy_update415.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 416,
5
- "stage": 0,
6
- "ent_scale": 2.856100000000001,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1597440,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 0.0,
14
- 1.0,
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
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update420.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c63737b544329d0bb927518b899df9eac967037b4db609a35d8b68cb5c1a2d0
3
- size 48494336
 
 
 
 
ppo_v9/policy_update420.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 421,
5
- "stage": 0,
6
- "ent_scale": 4.169579095130116,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1616640,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 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
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update425.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:04cca215e65de91a0499c0ad01f0e83a399ffe8a9f983234d10373ffd1e1073e
3
- size 48494336
 
 
 
 
ppo_v9/policy_update435.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce2a778b84ea16a310d8a557e4c0a5054ac0021a6e5aa5b708b9e6ff57b07da0
3
- size 48494336
 
 
 
 
ppo_v9/policy_update435.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 436,
5
- "stage": 0,
6
- "ent_scale": 1.3084123179596376,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1674240,
9
- "recent_wins": [
10
- 0.0,
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
- 0.0,
20
- 1.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
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
- 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
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update440.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee25e3942c3412201c63925b5df15b742709351249a8fbd9151335867651dd26
3
- size 48494336
 
 
 
 
ppo_v9/policy_update440.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 441,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1693440,
9
- "recent_wins": [
10
- 1.0,
11
- 0.0,
12
- 1.0,
13
- 0.0,
14
- 0.0,
15
- 1.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 0.0,
28
- 1.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
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
- 0.0,
41
- 0.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 0.0,
46
- 1.0,
47
- 1.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update445.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:33de4342eca60564b97cf7e72dcef63a0588c13b1686dc90eb340c2a6c1cfdf4
3
- size 48494336
 
 
 
 
ppo_v9/policy_update445.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 446,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1712640,
9
- "recent_wins": [
10
- 0.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 1.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
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
- 0.0,
31
- 1.0,
32
- 1.0,
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
- 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
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update45.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e61a6716495dfe0c293deb51d205252dae8480dd3688e4ecac7c351c9a6642b
3
- size 48494336
 
 
 
 
ppo_v9/policy_update45.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 46,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 176640,
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
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 1.0,
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
- 1.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update450.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fce953f52289bc04e8c135207bb0e88a8430e4394beeb15ee48e7a2b5906388
3
- size 48494336
 
 
 
 
ppo_v9/policy_update450.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 451,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1731840,
9
- "recent_wins": [
10
- 0.0,
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
- 0.0,
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
- 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
- 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
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update455.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:32475dcb52f899746ef8e4e2a2d7d3e0f597b27ac69060da80562d95b7892b7b
3
- size 48494336
 
 
 
 
ppo_v9/policy_update455.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 456,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1751040,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 1.0,
21
- 0.0,
22
- 1.0,
23
- 0.0,
24
- 1.0,
25
- 0.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 1.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 1.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 0.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update460.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b73142d123bac3705cd4c5d1af11217286955a32118dc631c13776a629c66e06
3
- size 48494336
 
 
 
 
ppo_v9/policy_update460.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 461,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1770240,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 1.0,
13
- 0.0,
14
- 1.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 0.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 1.0,
31
- 1.0,
32
- 1.0,
33
- 0.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
39
- 1.0,
40
- 1.0,
41
- 0.0,
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
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update465.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:acc2bcdf54c3f1dfc6d9544b66e6891fecfd1ca9ab0d16220612c6b0fd1f667b
3
- size 48494336
 
 
 
 
ppo_v9/policy_update465.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 466,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1789440,
9
- "recent_wins": [
10
- 1.0,
11
- 1.0,
12
- 0.0,
13
- 1.0,
14
- 0.0,
15
- 1.0,
16
- 1.0,
17
- 1.0,
18
- 1.0,
19
- 1.0,
20
- 0.0,
21
- 1.0,
22
- 1.0,
23
- 1.0,
24
- 1.0,
25
- 1.0,
26
- 1.0,
27
- 1.0,
28
- 1.0,
29
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 1.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
36
- 0.0,
37
- 1.0,
38
- 1.0,
39
- 0.0,
40
- 0.0,
41
- 1.0,
42
- 1.0,
43
- 0.0,
44
- 1.0,
45
- 1.0,
46
- 1.0,
47
- 1.0,
48
- 1.0,
49
- 1.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ppo_v9/policy_update470.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4d6823d2ff93afb3782252290b07074a4b83c2e478d3bbf9e3cf40ad2cc53fc
3
- size 48494336
 
 
 
 
ppo_v9/policy_update470.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 471,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 1808640,
9
- "recent_wins": [
10
- 1.0,
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
- 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
- 0.0,
30
- 0.0,
31
- 1.0,
32
- 0.0,
33
- 1.0,
34
- 1.0,
35
- 0.0,
36
- 1.0,
37
- 1.0,
38
- 1.0,
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
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "best_eval_win": null,
53
- "best_eval_score": null,
54
- "v81_curriculum": true,
55
- "curriculum_schedule": "v9",
56
- "reward_profile": "v9-sparse-win-v1",
57
- "return_stats": null,
58
- "stage_env_targets": [
59
- 24,
60
- 24,
61
- 24,
62
- 24,
63
- 24,
64
- 24,
65
- 24,
66
- 24,
67
- 20,
68
- 20,
69
- 16,
70
- 16,
71
- 12,
72
- 12,
73
- 10,
74
- 10,
75
- 10,
76
- 8,
77
- 8,
78
- 10,
79
- 8,
80
- 8,
81
- 8,
82
- 8,
83
- 8
84
- ],
85
- "envs_per_shard": 20,
86
- "requested_env_target": null
87
- }