promotion commited on
Commit
473502a
·
verified ·
1 Parent(s): f39ed71

Upload seed_1004

Browse files
sft-n1000/seed_1004/config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feat_dim": 601,
3
+ "props": [
4
+ "Egc"
5
+ ],
6
+ "polybert": "HAYDERphd/polyBERT",
7
+ "results": {
8
+ "baselines": {
9
+ "single_step": {
10
+ "greedy_oracle": {
11
+ "n": 112,
12
+ "success": 0.7321428571428571,
13
+ "regret": 0.31967715220266063
14
+ },
15
+ "greedy_verifier": {
16
+ "n": 112,
17
+ "success": 0.41964285714285715,
18
+ "regret": 0.42894041932431165
19
+ },
20
+ "random": {
21
+ "n": 112,
22
+ "success": 0.08035714285714286,
23
+ "regret": 1.737012720901443
24
+ }
25
+ },
26
+ "multi_step": {
27
+ "greedy_oracle": {
28
+ "n": 36,
29
+ "success": 0.16666666666666666,
30
+ "regret": 0.9945511401860553
31
+ },
32
+ "greedy_verifier": {
33
+ "n": 36,
34
+ "success": 0.05555555555555555,
35
+ "regret": 1.165682165154792
36
+ },
37
+ "random": {
38
+ "n": 36,
39
+ "success": 0.0,
40
+ "regret": 1.9833265587133293
41
+ }
42
+ }
43
+ },
44
+ "sft": {
45
+ "single_step": {
46
+ "n": 112,
47
+ "success": 0.9196428571428571,
48
+ "regret": 0.04671440491645441
49
+ },
50
+ "multi_step": {
51
+ "n": 36,
52
+ "success": 0.9166666666666666,
53
+ "regret": 0.08947174373178052
54
+ }
55
+ },
56
+ "rl": null,
57
+ "props": [
58
+ "Egc"
59
+ ],
60
+ "verifier": "finetuned_polyBERT",
61
+ "val_rmse": {
62
+ "Egc": 0.5194427322526246
63
+ },
64
+ "n_train_req": 1000,
65
+ "n_base_req": 369,
66
+ "n_aug_req": 631,
67
+ "n_steps": 5145,
68
+ "sft_only": true,
69
+ "rl_algorithm": "reinforce",
70
+ "rl_config": {
71
+ "iters": 500,
72
+ "kl_beta": 0.0,
73
+ "grpo_batch": 8,
74
+ "grpo_group_size": 8,
75
+ "grpo_update_epochs": 2,
76
+ "grpo_clip_eps": 0.2
77
+ },
78
+ "seed": 1004,
79
+ "wandb_run": "https://wandb.ai/promotion-kim/polyedit/runs/oo3druvp"
80
+ }
81
+ }
sft-n1000/seed_1004/policy.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d1c8ad4b2a9a3ca84f19a89b471e23398df4f52375a40727a626c43cdef2ac7
3
+ size 883401
sft-n1000/seed_1004/sft_policy_bundle.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a5f33b87e2562e77af6e79ed1955198955e3232b913f770dba2f443be9fd8b
3
+ size 888985
sft-n1000/seed_1004/verifier_Egc_bundle.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:910770514350a43983829d917791219ff5723e8e73d39bec41d7cf1e64e9c800
3
+ size 100840835