Muqeeth commited on
Commit
041c824
·
verified ·
1 Parent(s): 6f7254b

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. seed_1000/Qwen/Qwen2.5-7B-Instruct/adapters/agent_adapter/adapter_model.safetensors +3 -0
  2. seed_1000/Qwen/Qwen2.5-7B-Instruct/adapters/critic_adapter/adapter_model.safetensors +3 -0
  3. seed_1000/iteration_203/agent:Alice_rewards.csv +64 -0
  4. seed_1000/iteration_203/agent:Bob_rewards.csv +64 -0
  5. seed_1000/iteration_203/agent_trainer_log/basic_training_metrics_2025-08-20___11-23-33.json +44 -0
  6. seed_1000/iteration_203/mgid:10325083_rollout_tree.json +0 -0
  7. seed_1000/iteration_203/mgid:10734618_rollout_tree.json +0 -0
  8. seed_1000/iteration_203/mgid:10766163_rollout_tree.json +0 -0
  9. seed_1000/iteration_203/mgid:13745237_rollout_tree.json +0 -0
  10. seed_1000/iteration_203/mgid:14572779_rollout_tree.json +0 -0
  11. seed_1000/iteration_203/mgid:14976481_rollout_tree.json +0 -0
  12. seed_1000/iteration_203/mgid:15330477_rollout_tree.json +0 -0
  13. seed_1000/iteration_203/mgid:16586675_rollout_tree.json +0 -0
  14. seed_1000/iteration_203/mgid:17182004_rollout_tree.json +0 -0
  15. seed_1000/iteration_203/mgid:17686856_rollout_tree.json +0 -0
  16. seed_1000/iteration_203/mgid:19294302_rollout_tree.json +0 -0
  17. seed_1000/iteration_203/mgid:19664880_rollout_tree.json +0 -0
  18. seed_1000/iteration_203/mgid:20213699_rollout_tree.json +0 -0
  19. seed_1000/iteration_203/mgid:20705589_rollout_tree.json +0 -0
  20. seed_1000/iteration_203/mgid:20725924_rollout_tree.json +0 -0
  21. seed_1000/iteration_203/mgid:22765178_rollout_tree.json +0 -0
  22. seed_1000/iteration_203/mgid:25388944_rollout_tree.json +0 -0
  23. seed_1000/iteration_203/mgid:26609376_rollout_tree.json +0 -0
  24. seed_1000/iteration_203/mgid:26637128_rollout_tree.json +0 -0
  25. seed_1000/iteration_203/mgid:26697386_rollout_tree.json +0 -0
  26. seed_1000/iteration_203/mgid:27333400_rollout_tree.json +0 -0
  27. seed_1000/iteration_203/mgid:27436142_rollout_tree.json +0 -0
  28. seed_1000/iteration_203/mgid:29766991_rollout_tree.json +0 -0
  29. seed_1000/iteration_203/mgid:30011300_rollout_tree.json +0 -0
  30. seed_1000/iteration_203/mgid:30866693_rollout_tree.json +0 -0
  31. seed_1000/iteration_203/mgid:33927981_rollout_tree.json +0 -0
  32. seed_1000/iteration_203/mgid:38635163_rollout_tree.json +0 -0
  33. seed_1000/iteration_203/mgid:39267496_rollout_tree.json +0 -0
  34. seed_1000/iteration_203/mgid:54132135_rollout_tree.json +0 -0
  35. seed_1000/iteration_203/mgid:65350407_rollout_tree.json +0 -0
  36. seed_1000/iteration_203/mgid:66921585_rollout_tree.json +0 -0
  37. seed_1000/iteration_203/mgid:69710468_rollout_tree.json +0 -0
  38. seed_1000/iteration_204/mgid:12057724_rollout_tree.json +0 -0
  39. seed_1000/iteration_204/mgid:12535169_rollout_tree.json +0 -0
  40. seed_1000/iteration_204/mgid:13826315_rollout_tree.json +0 -0
  41. seed_1000/iteration_204/mgid:15011992_rollout_tree.json +0 -0
  42. seed_1000/iteration_204/mgid:15732769_rollout_tree.json +0 -0
  43. seed_1000/iteration_204/mgid:16830915_rollout_tree.json +0 -0
  44. seed_1000/iteration_204/mgid:17105344_rollout_tree.json +0 -0
  45. seed_1000/iteration_204/mgid:17901406_rollout_tree.json +0 -0
  46. seed_1000/iteration_204/mgid:19213424_rollout_tree.json +0 -0
  47. seed_1000/iteration_204/mgid:19498981_rollout_tree.json +0 -0
  48. seed_1000/iteration_204/mgid:19576719_rollout_tree.json +0 -0
  49. seed_1000/iteration_204/mgid:20257213_rollout_tree.json +0 -0
  50. seed_1000/iteration_204/mgid:20763820_rollout_tree.json +0 -0
seed_1000/Qwen/Qwen2.5-7B-Instruct/adapters/agent_adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859854342305251da1361c8a2282e80839474b93b7757d4717e9a045700e16a3
3
+ size 323014168
seed_1000/Qwen/Qwen2.5-7B-Instruct/adapters/critic_adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c412dc57a77c2aa3d89bf7033b4b49b1b64013134d23ae37916825053067dce5
3
+ size 323014168
seed_1000/iteration_203/agent:Alice_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,0,1,1,1,1,1,1,1,1
2
+ 1,3,1,3,1,3,1,3,1,3
3
+ 1,3,1,3,1,3,1,3,1,3
4
+ 1,3,1,3,1,3,1,3,1,3
5
+ 1,3,1,3,1,3,1,3,1,3
6
+ 1,3,1,3,1,3,1,3,1,3
7
+ 1,0,1,1,1,1,1,1,1,1
8
+ 1,3,1,3,1,3,1,3,1,3
9
+ 1,3,1,3,1,3,1,3,1,3
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,3,1,3,1,3,1,3,1,3
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,3,1,3,1,3,1,3
14
+ 1,5,1,5,1,5,1,5,1,5
15
+ 1,0,1,0,1,0,1,0,1,0
16
+ 1,3,1,3,1,3,1,3,1,3
17
+ 1,3,1,3,1,3,1,3,1,3
18
+ 1,3,1,3,1,3,1,3,1,3
19
+ 1,3,1,3,1,3,1,3,1,3
20
+ 1,0,1,1,1,1,1,1,1,1
21
+ 1,3,1,3,1,3,1,3,1,3
22
+ 1,3,1,3,1,3,1,3,1,3
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,0,1,3,1,3,1,3,1,3
25
+ 1,0,0,1,5,5,1,0,5,5
26
+ 1,0,1,1,1,1,1,1,1,1
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,3,1,3,1,3,1,3
29
+ 1,3,1,3,1,3,1,3,1,3
30
+ 1,5,1,5,1,5,1,5,1,5
31
+ 1,3,1,3,1,3,1,3,1,3
32
+ 1,5,1,1,1,1,1,1,1,1
33
+ 1,3,1,3,1,3,1,3,1,3
34
+ 1,3,1,3,1,3,1,3,1,3
35
+ 1,3,1,3,1,3,1,3,1,3
36
+ 1,3,1,0,5,1,0,5,1,0
37
+ 1,3,1,3,1,3,1,3,1,3
38
+ 1,0,1,1,1,1,1,1,1,1
39
+ 1,5,3,1,1,1,1,1,1,1
40
+ 1,3,1,3,1,3,1,3,1,3
41
+ 1,3,1,3,1,3,1,3,1,3
42
+ 1,3,1,3,1,3,1,3,1,3
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,3,1,3,1,3,1,3,1,3
45
+ 1,3,1,3,1,3,1,3,1,3
46
+ 1,3,1,3,1,3,1,3,1,3
47
+ 1,3,1,3,1,3,1,3,1,3
48
+ 1,3,1,3,1,3,1,3,1,3
49
+ 1,5,1,3,0,1,3,0,1,3
50
+ 1,3,1,3,1,3,1,3,1,3
51
+ 1,3,1,3,1,3,1,3,1,3
52
+ 1,3,1,3,1,3,1,3,1,3
53
+ 1,3,1,3,1,3,1,3,1,3
54
+ 1,3,1,3,1,3,1,3,1,3
55
+ 1,0,0,1,1,1,1,1,1,1
56
+ 1,3,1,3,1,3,1,3,1,3
57
+ 1,0,1,0,1,0,1,0,1,0
58
+ 1,3,1,3,1,3,1,3,1,3
59
+ 1,0,1,3,1,5,0,1,5,0
60
+ 1,3,1,3,1,3,1,3,1,3
61
+ 1,3,1,3,1,3,1,3,1,3
62
+ 1,0,1,3,1,5,0,1,5,0
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,3,1,3,1,3,1,3,1,3
seed_1000/iteration_203/agent:Bob_rewards.csv ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 1,5,1,1,1,1,1,1,1,1
2
+ 1,3,1,3,1,3,1,3,1,3
3
+ 1,3,1,3,1,3,1,3,1,3
4
+ 1,3,1,3,1,3,1,3,1,3
5
+ 1,3,1,3,1,3,1,3,1,3
6
+ 1,3,1,3,1,3,1,3,1,3
7
+ 1,5,1,1,1,1,1,1,1,1
8
+ 1,3,1,3,1,3,1,3,1,3
9
+ 1,3,1,3,1,3,1,3,1,3
10
+ 1,3,1,3,1,3,1,3,1,3
11
+ 1,3,1,3,1,3,1,3,1,3
12
+ 1,3,1,3,1,3,1,3,1,3
13
+ 1,3,1,3,1,3,1,3,1,3
14
+ 1,0,1,0,1,0,1,0,1,0
15
+ 1,5,1,5,1,5,1,5,1,5
16
+ 1,3,1,3,1,3,1,3,1,3
17
+ 1,3,1,3,1,3,1,3,1,3
18
+ 1,3,1,3,1,3,1,3,1,3
19
+ 1,3,1,3,1,3,1,3,1,3
20
+ 1,5,1,1,1,1,1,1,1,1
21
+ 1,3,1,3,1,3,1,3,1,3
22
+ 1,3,1,3,1,3,1,3,1,3
23
+ 1,3,1,3,1,3,1,3,1,3
24
+ 1,5,1,3,1,3,1,3,1,3
25
+ 1,5,5,1,0,0,1,5,0,0
26
+ 1,5,1,1,1,1,1,1,1,1
27
+ 1,3,1,3,1,3,1,3,1,3
28
+ 1,3,1,3,1,3,1,3,1,3
29
+ 1,3,1,3,1,3,1,3,1,3
30
+ 1,0,1,0,1,0,1,0,1,0
31
+ 1,3,1,3,1,3,1,3,1,3
32
+ 1,0,1,1,1,1,1,1,1,1
33
+ 1,3,1,3,1,3,1,3,1,3
34
+ 1,3,1,3,1,3,1,3,1,3
35
+ 1,3,1,3,1,3,1,3,1,3
36
+ 1,3,1,5,0,1,5,0,1,5
37
+ 1,3,1,3,1,3,1,3,1,3
38
+ 1,5,1,1,1,1,1,1,1,1
39
+ 1,0,3,1,1,1,1,1,1,1
40
+ 1,3,1,3,1,3,1,3,1,3
41
+ 1,3,1,3,1,3,1,3,1,3
42
+ 1,3,1,3,1,3,1,3,1,3
43
+ 1,3,1,3,1,3,1,3,1,3
44
+ 1,3,1,3,1,3,1,3,1,3
45
+ 1,3,1,3,1,3,1,3,1,3
46
+ 1,3,1,3,1,3,1,3,1,3
47
+ 1,3,1,3,1,3,1,3,1,3
48
+ 1,3,1,3,1,3,1,3,1,3
49
+ 1,0,1,3,5,1,3,5,1,3
50
+ 1,3,1,3,1,3,1,3,1,3
51
+ 1,3,1,3,1,3,1,3,1,3
52
+ 1,3,1,3,1,3,1,3,1,3
53
+ 1,3,1,3,1,3,1,3,1,3
54
+ 1,3,1,3,1,3,1,3,1,3
55
+ 1,5,5,1,1,1,1,1,1,1
56
+ 1,3,1,3,1,3,1,3,1,3
57
+ 1,5,1,5,1,5,1,5,1,5
58
+ 1,3,1,3,1,3,1,3,1,3
59
+ 1,5,1,3,1,0,5,1,0,5
60
+ 1,3,1,3,1,3,1,3,1,3
61
+ 1,3,1,3,1,3,1,3,1,3
62
+ 1,5,1,3,1,0,5,1,0,5
63
+ 1,3,1,3,1,3,1,3,1,3
64
+ 1,3,1,3,1,3,1,3,1,3
seed_1000/iteration_203/agent_trainer_log/basic_training_metrics_2025-08-20___11-23-33.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nb_rollouts": [
3
+ 128
4
+ ],
5
+ "loss_mb_total": {
6
+ "value_mb_total": [
7
+ 0.6859726309776306,
8
+ -0.9424233436584473,
9
+ -0.44868355989456177,
10
+ 0.6859726309776306,
11
+ -0.7253817915916443,
12
+ -0.3183947801589966,
13
+ 0.6859726309776306,
14
+ 0.6859726309776306,
15
+ 0.1801784634590149,
16
+ -0.20640133321285248,
17
+ -0.01460232026875019,
18
+ 0.6859726309776306,
19
+ -9.505908012390137,
20
+ -1.0423940420150757,
21
+ -0.3104172945022583,
22
+ 0.6859726309776306,
23
+ 0.3066078722476959,
24
+ -4.949148178100586,
25
+ 0.4500212073326111,
26
+ 0.3066078722476959,
27
+ -0.12917408347129822,
28
+ -0.590844452381134,
29
+ 0.3066078722476959,
30
+ 0.3066078722476959,
31
+ 0.5845448970794678,
32
+ -0.5477323532104492,
33
+ 0.20866350829601288,
34
+ 0.3066078722476959,
35
+ -1.7220414876937866,
36
+ -4.848804473876953,
37
+ 0.4001830518245697,
38
+ 0.3066078722476959
39
+ ]
40
+ },
41
+ "gradient_norm": [
42
+ 21.300567626953125
43
+ ]
44
+ }
seed_1000/iteration_203/mgid:10325083_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:10734618_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:10766163_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:13745237_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:14572779_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:14976481_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:15330477_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:16586675_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:17182004_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:17686856_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:19294302_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:19664880_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:20213699_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:20705589_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:20725924_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:22765178_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:25388944_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:26609376_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:26637128_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:26697386_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:27333400_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:27436142_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:29766991_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:30011300_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:30866693_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:33927981_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:38635163_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:39267496_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:54132135_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:65350407_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:66921585_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_203/mgid:69710468_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:12057724_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:12535169_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:13826315_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:15011992_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:15732769_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:16830915_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:17105344_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:17901406_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:19213424_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:19498981_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:19576719_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:20257213_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff
 
seed_1000/iteration_204/mgid:20763820_rollout_tree.json ADDED
The diff for this file is too large to render. See raw diff