Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
67c799b
·
verified ·
1 Parent(s): d34e1a7

Prune dense checkpoints (batch 33, 77 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_update820.safetensors +0 -3
  2. ppo_v9/policy_update820.state.json +0 -87
  3. ppo_v9/policy_update825.safetensors +0 -3
  4. ppo_v9/policy_update825.state.json +0 -87
  5. ppo_v9/policy_update830.safetensors +0 -3
  6. ppo_v9/policy_update830.state.json +0 -87
  7. ppo_v9/policy_update835.safetensors +0 -3
  8. ppo_v9/policy_update835.state.json +0 -87
  9. ppo_v9/policy_update840.safetensors +0 -3
  10. ppo_v9/policy_update840.state.json +0 -87
  11. ppo_v9/policy_update845.safetensors +0 -3
  12. ppo_v9/policy_update845.state.json +0 -87
  13. ppo_v9/policy_update85.safetensors +0 -3
  14. ppo_v9/policy_update85.state.json +0 -87
  15. ppo_v9/policy_update850.safetensors +0 -3
  16. ppo_v9/policy_update850.state.json +0 -87
  17. ppo_v9/policy_update855.safetensors +0 -3
  18. ppo_v9/policy_update855.state.json +0 -87
  19. ppo_v9/policy_update860.safetensors +0 -3
  20. ppo_v9/policy_update865.safetensors +0 -3
  21. ppo_v9/policy_update865.state.json +0 -87
  22. ppo_v9/policy_update870.safetensors +0 -3
  23. ppo_v9/policy_update870.state.json +0 -87
  24. ppo_v9/policy_update875.safetensors +0 -3
  25. ppo_v9/policy_update875.state.json +0 -87
  26. ppo_v9/policy_update880.safetensors +0 -3
  27. ppo_v9/policy_update880.state.json +0 -87
  28. ppo_v9/policy_update885.safetensors +0 -3
  29. ppo_v9/policy_update885.state.json +0 -87
  30. ppo_v9/policy_update890.safetensors +0 -3
  31. ppo_v9/policy_update890.state.json +0 -87
  32. ppo_v9/policy_update895.safetensors +0 -3
  33. ppo_v9/policy_update895.state.json +0 -87
  34. ppo_v9/policy_update90.safetensors +0 -3
  35. ppo_v9/policy_update90.state.json +0 -87
  36. ppo_v9/policy_update900.safetensors +0 -3
  37. ppo_v9/policy_update905.safetensors +0 -3
  38. ppo_v9/policy_update905.state.json +0 -87
  39. ppo_v9/policy_update910.safetensors +0 -3
  40. ppo_v9/policy_update910.state.json +0 -87
  41. ppo_v9/policy_update915.safetensors +0 -3
  42. ppo_v9/policy_update915.state.json +0 -87
  43. ppo_v9/policy_update920.safetensors +0 -3
  44. ppo_v9/policy_update920.state.json +0 -87
  45. ppo_v9/policy_update925.safetensors +0 -3
  46. ppo_v9/policy_update925.state.json +0 -87
  47. ppo_v9/policy_update930.safetensors +0 -3
  48. ppo_v9/policy_update930.state.json +0 -87
  49. ppo_v9/policy_update935.safetensors +0 -3
  50. ppo_v9/policy_update935.state.json +0 -87
ppo_v9/policy_update820.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f96ac420e08f3d308c4f9848e2280dcf782ef50ee870cc29b1589e63db2525a
3
- size 48494336
 
 
 
 
ppo_v9/policy_update820.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 821,
5
- "stage": 2,
6
- "ent_scale": 4.761904761904762,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3152640,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 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
- 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_update825.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fb4c9218660e6f92a9c86b0fc23a4026ec8f0ab3a0773b1b1c41dbb93c55ff9
3
- size 48494336
 
 
 
 
ppo_v9/policy_update825.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 826,
5
- "stage": 2,
6
- "ent_scale": 1.9659481077184253,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3171840,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update830.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:66a29ec897a0b5e555013985ce1dc66e8634180762d117f21d23a6b82f0cb052
3
- size 48494336
 
 
 
 
ppo_v9/policy_update830.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 831,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3191040,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update835.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a000079092402f99337e073a0e4ac4cdabe0c74522c1615110311fde9fc874d
3
- size 48494336
 
 
 
 
ppo_v9/policy_update835.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 836,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3210240,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update840.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:35b829e4c2fa7cac1c7ae1ff4ca506e3272b93837385c5a03f1aa5460797df3c
3
- size 48494336
 
 
 
 
ppo_v9/policy_update840.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 841,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3229440,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update845.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d869d95f5014caf84588c1ac69feb30e1edb6f4327b90078dc9a98f913d8f488
3
- size 48494336
 
 
 
 
ppo_v9/policy_update845.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 846,
5
- "stage": 2,
6
- "ent_scale": 2.1970000000000005,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3248640,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update85.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:38965f8eb8322bf56d580b728a48d9d23c0aba110c29b4fb59901f56afd41b40
3
- size 48494336
 
 
 
 
ppo_v9/policy_update85.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 86,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 330240,
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
- 0.0,
25
- 1.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 1.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 1.0,
34
- 0.0,
35
- 1.0,
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
- 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_update850.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:771e3cae33cd6d1b69c2dc708ce6a12c62c2aa6d06e5082b07ce9e634cae26d1
3
- size 48494336
 
 
 
 
ppo_v9/policy_update850.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 851,
5
- "stage": 2,
6
- "ent_scale": 4.378058049886622,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3267840,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update855.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b5feadca198b0f369f48fc63f7c34b5076407a6225fc682254880bf0974337c
3
- size 48494336
 
 
 
 
ppo_v9/policy_update855.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 856,
5
- "stage": 2,
6
- "ent_scale": 2.2378290840505657,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3287040,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update860.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:06614b7bfdfb464793e8c651c154ec5b554c0452e8f9f04efbbe80fa94988a94
3
- size 48494336
 
 
 
 
ppo_v9/policy_update865.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:695089eec436d259d39fd7a12aa29a2179d857fbb1087185c2b016b4ce43c478
3
- size 48494336
 
 
 
 
ppo_v9/policy_update865.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 866,
5
- "stage": 2,
6
- "ent_scale": 1.8410675256096507,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3325440,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update870.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d139c73a3b7d667aa917f0d340f3b4dfa091c3f05f44752d55ce719566eb8ca3
3
- size 48494336
 
 
 
 
ppo_v9/policy_update870.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 871,
5
- "stage": 2,
6
- "ent_scale": 2.6877478615962076,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3344640,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 1.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update875.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a034c72f1ea4040db42edcb8628ff8268c501f0d3e83dec03f81226c6c862f59
3
- size 48494336
 
 
 
 
ppo_v9/policy_update875.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 876,
5
- "stage": 2,
6
- "ent_scale": 2.874581862557325,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3363840,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update880.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:591078921cebb977f50aaa1a439ea167e724e676b623eb88824c91dc1aba76f2
3
- size 48494336
 
 
 
 
ppo_v9/policy_update880.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 881,
5
- "stage": 2,
6
- "ent_scale": 4.196560499057882,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3383040,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update885.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:629ca8c883f6d0715e7d7b5bbac6004fec4f53ac1edf0a4251593646d2f62829
3
- size 48494336
 
 
 
 
ppo_v9/policy_update885.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 886,
5
- "stage": 2,
6
- "ent_scale": 3.288114960179785,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3402240,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update890.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5b870e357cabea252b1b05b95cb2b91e4272d1d261223506b962d3066dd87a7
3
- size 48494336
 
 
 
 
ppo_v9/policy_update890.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 891,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3421440,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update895.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d85dba11c6fdb315e68378b80b3b63a9a1519dd9916d7deda638d7af3b09aef
3
- size 48494336
 
 
 
 
ppo_v9/policy_update895.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 896,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3440640,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update90.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cb1fefc286fcf7099cfe9e8ffb920f356289573e908e191e093d73ea34f1996
3
- size 48494336
 
 
 
 
ppo_v9/policy_update90.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 91,
5
- "stage": 0,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00025,
8
- "total_env_steps": 349440,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 1.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 1.0,
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
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 1.0,
41
- 1.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 1.0,
47
- 0.0,
48
- 1.0,
49
- 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_update900.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b8d131c30677921eeace51a8e42f96f23cfdcd26ec1b4006899275d89f14143
3
- size 48494336
 
 
 
 
ppo_v9/policy_update905.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd26c9eb7968dbe634e764f3e0397ca5da816d6b1c73683eff3b04644c206693
3
- size 48494336
 
 
 
 
ppo_v9/policy_update905.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 906,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3479040,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update910.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:396b3b0cb9e8d4a4d521684d2c8c759202e2f515fece27d58f7214525f3680f8
3
- size 48494336
 
 
 
 
ppo_v9/policy_update910.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 911,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3498240,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update915.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5751c756b62466acee9b104e911fcd1be8c03e3bb5b69e29eed7fe96979342c
3
- size 48494336
 
 
 
 
ppo_v9/policy_update915.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 916,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3517440,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update920.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:570edb4887bf718475e52029c02b6b57b9d336716f3acca23b82b8e219747a49
3
- size 48494336
 
 
 
 
ppo_v9/policy_update920.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 921,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3536640,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update925.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:77143a24840d8a65b0c744fd2928a3ac177042278063bccc1b0fbdd799f54a09
3
- size 48494336
 
 
 
 
ppo_v9/policy_update925.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 926,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3555840,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update930.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a29747a5abe72adbe17931e64f32a7d2da7e78200b3fcc73a16ce76ac30dbcac
3
- size 48494336
 
 
 
 
ppo_v9/policy_update930.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 931,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3575040,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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_update935.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:14dcfbe9f999d469c0a9442502571a4132d23000ae3b94c0b4fa4e8c45b68048
3
- size 48494336
 
 
 
 
ppo_v9/policy_update935.state.json DELETED
@@ -1,87 +0,0 @@
1
- {
2
- "checkpoint_schema_version": 2,
3
- "hidden_reset_policy": "episode_done",
4
- "update": 936,
5
- "stage": 2,
6
- "ent_scale": 1.0,
7
- "lr_now": 0.00018062499999999999,
8
- "total_env_steps": 3594240,
9
- "recent_wins": [
10
- 0.0,
11
- 0.0,
12
- 0.0,
13
- 0.0,
14
- 0.0,
15
- 0.0,
16
- 0.0,
17
- 0.0,
18
- 0.0,
19
- 0.0,
20
- 0.0,
21
- 0.0,
22
- 0.0,
23
- 0.0,
24
- 0.0,
25
- 0.0,
26
- 0.0,
27
- 0.0,
28
- 0.0,
29
- 0.0,
30
- 0.0,
31
- 0.0,
32
- 0.0,
33
- 0.0,
34
- 0.0,
35
- 0.0,
36
- 0.0,
37
- 0.0,
38
- 0.0,
39
- 0.0,
40
- 0.0,
41
- 0.0,
42
- 0.0,
43
- 0.0,
44
- 0.0,
45
- 0.0,
46
- 0.0,
47
- 0.0,
48
- 0.0,
49
- 0.0
50
- ],
51
- "recent_conversions": [],
52
- "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
- }