jasonfan commited on
Commit
3077e89
·
verified ·
1 Parent(s): 276a1c1

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. checkpoints/fst_medium/_checkpoint_log.tsv +225 -0
  2. checkpoints/fst_medium/epoch_004_step_000010000_tokens_57.1b_val=0.2468.pt +3 -0
  3. checkpoints/fst_medium/epoch_004_step_000011000_tokens_58b_val=0.2467.pt +3 -0
  4. checkpoints/fst_medium/epoch_004_step_000012000_tokens_58.8b_val=0.2467.pt +3 -0
  5. checkpoints/fst_medium/epoch_004_step_000013000_tokens_59.7b_val=0.2467.pt +3 -0
  6. checkpoints/fst_medium/epoch_004_step_000014000_tokens_60.6b_val=0.2467.pt +3 -0
  7. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000011000_tokens_58b_val=0.2467.txt +0 -0
  8. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank1.txt +0 -0
  9. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank2.txt +0 -0
  10. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank4.txt +0 -0
  11. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank5.txt +0 -0
  12. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank6.txt +0 -0
  13. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank7.txt +0 -0
  14. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467.txt +0 -0
  15. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank0.txt +0 -0
  16. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank1.txt +0 -0
  17. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank2.txt +0 -0
  18. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank3.txt +0 -0
  19. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank4.txt +0 -0
  20. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank5.txt +0 -0
  21. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank6.txt +0 -0
  22. checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank7.txt +0 -0
  23. checkpoints/fst_medium/metrics_summary_epoch4_top5.csv +1 -0
  24. checkpoints/fst_medium/verification_epoch_004_step_000011000_tokens_58b_val=0.2467.txt +8 -0
  25. checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank1.txt +5 -0
  26. checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank2.txt +5 -0
  27. checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank4.txt +5 -0
  28. checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank5.txt +5 -0
  29. checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank6.txt +5 -0
  30. checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank7.txt +5 -0
  31. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467.txt +8 -0
  32. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank0.txt +5 -0
  33. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank1.txt +5 -0
  34. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank2.txt +5 -0
  35. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank3.txt +5 -0
  36. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank4.txt +5 -0
  37. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank5.txt +5 -0
  38. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank6.txt +5 -0
  39. checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank7.txt +5 -0
checkpoints/fst_medium/_checkpoint_log.tsv ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Time Checkpoint_Type Epoch Step Train_Loss Val_Loss Tokens_Trained
2
+ 2025-12-11 08:46:10 recent 000 000001000 0.5415580123662949 0.5145518183708191 860160000
3
+ 2025-12-11 08:46:12 step 000 000001000 0.5415580123662949 0.5145518183708191 860160000
4
+ 2025-12-11 08:46:14 best 000 000001000 0.5415580123662949 0.5145518183708191 860160000
5
+ 2025-12-11 09:00:44 recent 000 000002000 0.41473153233528137 0.4067922830581665 1720320000
6
+ 2025-12-11 09:00:46 step 000 000002000 0.41473153233528137 0.4067922830581665 1720320000
7
+ 2025-12-11 09:00:49 best 000 000002000 0.41473153233528137 0.4067922830581665 1720320000
8
+ 2025-12-11 09:15:28 recent 000 000003000 0.3819531947374344 0.37025946378707886 2580480000
9
+ 2025-12-11 09:15:30 step 000 000003000 0.3819531947374344 0.37025946378707886 2580480000
10
+ 2025-12-11 09:15:33 best 000 000003000 0.3819531947374344 0.37025946378707886 2580480000
11
+ 2025-12-11 09:30:10 recent 000 000004000 0.37235739827156067 0.3497309684753418 3440640000
12
+ 2025-12-11 09:30:13 step 000 000004000 0.37235739827156067 0.3497309684753418 3440640000
13
+ 2025-12-11 09:30:15 best 000 000004000 0.37235739827156067 0.3497309684753418 3440640000
14
+ 2025-12-11 09:44:52 recent 000 000005000 0.3328295797109604 0.3346906900405884 4300800000
15
+ 2025-12-11 09:44:54 step 000 000005000 0.3328295797109604 0.3346906900405884 4300800000
16
+ 2025-12-11 09:44:56 best 000 000005000 0.3328295797109604 0.3346906900405884 4300800000
17
+ 2025-12-11 09:59:31 recent 000 000006000 0.3250560611486435 0.32419225573539734 5160960000
18
+ 2025-12-11 09:59:33 step 000 000006000 0.3250560611486435 0.32419225573539734 5160960000
19
+ 2025-12-11 09:59:36 best 000 000006000 0.3250560611486435 0.32419225573539734 5160960000
20
+ 2025-12-11 10:14:08 recent 000 000007000 0.30086350440979004 0.3168307840824127 6021120000
21
+ 2025-12-11 10:14:10 step 000 000007000 0.30086350440979004 0.3168307840824127 6021120000
22
+ 2025-12-11 10:14:13 best 000 000007000 0.30086350440979004 0.3168307840824127 6021120000
23
+ 2025-12-11 10:28:50 recent 000 000008000 0.291317917406559 0.3106359839439392 6881280000
24
+ 2025-12-11 10:28:53 step 000 000008000 0.291317917406559 0.3106359839439392 6881280000
25
+ 2025-12-11 10:28:55 best 000 000008000 0.291317917406559 0.3106359839439392 6881280000
26
+ 2025-12-11 10:43:32 recent 000 000009000 0.32681500911712646 0.3056332767009735 7741440000
27
+ 2025-12-11 10:43:34 step 000 000009000 0.32681500911712646 0.3056332767009735 7741440000
28
+ 2025-12-11 10:43:37 best 000 000009000 0.32681500911712646 0.3056332767009735 7741440000
29
+ 2025-12-11 10:58:12 recent 000 000010000 0.32460615038871765 0.3014771342277527 8601600000
30
+ 2025-12-11 10:58:14 step 000 000010000 0.32460615038871765 0.3014771342277527 8601600000
31
+ 2025-12-11 10:58:16 best 000 000010000 0.32460615038871765 0.3014771342277527 8601600000
32
+ 2025-12-11 11:12:47 recent 000 000011000 0.31390294432640076 0.2985464334487915 9461760000
33
+ 2025-12-11 11:12:50 step 000 000011000 0.31390294432640076 0.2985464334487915 9461760000
34
+ 2025-12-11 11:12:52 best 000 000011000 0.31390294432640076 0.2985464334487915 9461760000
35
+ 2025-12-11 11:27:27 recent 000 000012000 0.3407209515571594 0.2952793836593628 10321920000
36
+ 2025-12-11 11:27:29 step 000 000012000 0.3407209515571594 0.2952793836593628 10321920000
37
+ 2025-12-11 11:27:32 best 000 000012000 0.3407209515571594 0.2952793836593628 10321920000
38
+ 2025-12-11 11:42:09 recent 000 000013000 0.2931080758571625 0.2925594449043274 11182080000
39
+ 2025-12-11 11:42:11 step 000 000013000 0.2931080758571625 0.2925594449043274 11182080000
40
+ 2025-12-11 11:42:14 best 000 000013000 0.2931080758571625 0.2925594449043274 11182080000
41
+ 2025-12-11 11:56:49 recent 000 000014000 0.296756349503994 0.2900623083114624 12042240000
42
+ 2025-12-11 11:56:52 step 000 000014000 0.296756349503994 0.2900623083114624 12042240000
43
+ 2025-12-11 11:56:54 best 000 000014000 0.296756349503994 0.2900623083114624 12042240000
44
+ 2025-12-11 11:59:14 recent 001 000000000 0.31290731579065323 0.2898723781108856 12129976320
45
+ 2025-12-11 11:59:16 epoch 001 000000000 0.31290731579065323 0.2898723781108856 12129976320
46
+ 2025-12-11 11:59:19 best 001 000000000 0.31290731579065323 0.2898723781108856 12129976320
47
+ 2025-12-11 12:13:57 recent 001 000001000 0.29751477390527725 0.28774142265319824 12990136320
48
+ 2025-12-11 12:13:59 step 001 000001000 0.29751477390527725 0.28774142265319824 12990136320
49
+ 2025-12-11 12:14:02 best 001 000001000 0.29751477390527725 0.28774142265319824 12990136320
50
+ 2025-12-11 12:28:33 recent 001 000002000 0.29401592165231705 0.2859119474887848 13850296320
51
+ 2025-12-11 12:28:35 step 001 000002000 0.29401592165231705 0.2859119474887848 13850296320
52
+ 2025-12-11 12:28:38 best 001 000002000 0.29401592165231705 0.2859119474887848 13850296320
53
+ 2025-12-11 12:43:14 recent 001 000003000 0.2833290100097656 0.28425541520118713 14710456320
54
+ 2025-12-11 12:43:17 step 001 000003000 0.2833290100097656 0.28425541520118713 14710456320
55
+ 2025-12-11 12:43:19 best 001 000003000 0.2833290100097656 0.28425541520118713 14710456320
56
+ 2025-12-11 12:57:55 recent 001 000004000 0.31157561391592026 0.2825104594230652 15570616320
57
+ 2025-12-11 12:57:57 step 001 000004000 0.31157561391592026 0.2825104594230652 15570616320
58
+ 2025-12-11 12:58:00 best 001 000004000 0.31157561391592026 0.2825104594230652 15570616320
59
+ 2025-12-11 13:12:37 recent 001 000005000 0.2954292893409729 0.2810085713863373 16430776320
60
+ 2025-12-11 13:12:39 step 001 000005000 0.2954292893409729 0.2810085713863373 16430776320
61
+ 2025-12-11 13:12:42 best 001 000005000 0.2954292893409729 0.2810085713863373 16430776320
62
+ 2025-12-11 13:27:16 recent 001 000006000 0.27245182543992996 0.27944013476371765 17290936320
63
+ 2025-12-11 13:27:18 step 001 000006000 0.27245182543992996 0.27944013476371765 17290936320
64
+ 2025-12-11 13:27:21 best 001 000006000 0.27245182543992996 0.27944013476371765 17290936320
65
+ 2025-12-11 13:41:53 recent 001 000007000 0.2931659445166588 0.2779275178909302 18151096320
66
+ 2025-12-11 13:41:55 step 001 000007000 0.2931659445166588 0.2779275178909302 18151096320
67
+ 2025-12-11 13:41:58 best 001 000007000 0.2931659445166588 0.2779275178909302 18151096320
68
+ 2025-12-11 13:56:33 recent 001 000008000 0.3077904209494591 0.2766604721546173 19011256320
69
+ 2025-12-11 13:56:35 step 001 000008000 0.3077904209494591 0.2766604721546173 19011256320
70
+ 2025-12-11 13:56:37 best 001 000008000 0.3077904209494591 0.2766604721546173 19011256320
71
+ 2025-12-11 14:11:16 recent 001 000009000 0.2656656503677368 0.27528905868530273 19871416320
72
+ 2025-12-11 14:11:18 step 001 000009000 0.2656656503677368 0.27528905868530273 19871416320
73
+ 2025-12-11 14:11:21 best 001 000009000 0.2656656503677368 0.27528905868530273 19871416320
74
+ 2025-12-11 14:25:59 recent 001 000010000 0.3070940300822258 0.27423983812332153 20731576320
75
+ 2025-12-11 14:26:01 step 001 000010000 0.3070940300822258 0.27423983812332153 20731576320
76
+ 2025-12-11 14:26:04 best 001 000010000 0.3070940300822258 0.27423983812332153 20731576320
77
+ 2025-12-11 14:40:35 recent 001 000011000 0.2973811775445938 0.27301135659217834 21591736320
78
+ 2025-12-11 14:40:37 step 001 000011000 0.2973811775445938 0.27301135659217834 21591736320
79
+ 2025-12-11 14:40:40 best 001 000011000 0.2973811775445938 0.27301135659217834 21591736320
80
+ 2025-12-11 14:55:18 recent 001 000012000 0.28227975964546204 0.2719024419784546 22451896320
81
+ 2025-12-11 14:55:21 step 001 000012000 0.28227975964546204 0.2719024419784546 22451896320
82
+ 2025-12-11 14:55:24 best 001 000012000 0.28227975964546204 0.2719024419784546 22451896320
83
+ 2025-12-11 15:09:59 recent 001 000013000 0.2930072098970413 0.27090704441070557 23312056320
84
+ 2025-12-11 15:10:01 step 001 000013000 0.2930072098970413 0.27090704441070557 23312056320
85
+ 2025-12-11 15:10:03 best 001 000013000 0.2930072098970413 0.27090704441070557 23312056320
86
+ 2025-12-11 15:24:40 recent 001 000014000 0.2886788547039032 0.26980167627334595 24172216320
87
+ 2025-12-11 15:24:42 step 001 000014000 0.2886788547039032 0.26980167627334595 24172216320
88
+ 2025-12-11 15:24:45 best 001 000014000 0.2886788547039032 0.26980167627334595 24172216320
89
+ 2025-12-11 15:26:56 recent 002 000000000 0.29480114579200745 0.26953426003456116 24259952640
90
+ 2025-12-11 15:26:58 epoch 002 000000000 0.29480114579200745 0.26953426003456116 24259952640
91
+ 2025-12-11 15:27:01 best 002 000000000 0.29480114579200745 0.26953426003456116 24259952640
92
+ 2025-12-11 15:41:39 recent 002 000001000 0.25820205360651016 0.2682429850101471 25120112640
93
+ 2025-12-11 15:41:41 step 002 000001000 0.25820205360651016 0.2682429850101471 25120112640
94
+ 2025-12-11 15:41:44 best 002 000001000 0.25820205360651016 0.2682429850101471 25120112640
95
+ 2025-12-11 15:56:14 recent 002 000002000 0.2932390719652176 0.2674706280231476 25980272640
96
+ 2025-12-11 15:56:16 step 002 000002000 0.2932390719652176 0.2674706280231476 25980272640
97
+ 2025-12-11 15:56:18 best 002 000002000 0.2932390719652176 0.2674706280231476 25980272640
98
+ 2025-12-11 16:10:56 recent 002 000003000 0.2662067636847496 0.26644331216812134 26840432640
99
+ 2025-12-11 16:10:58 step 002 000003000 0.2662067636847496 0.26644331216812134 26840432640
100
+ 2025-12-11 16:11:01 best 002 000003000 0.2662067636847496 0.26644331216812134 26840432640
101
+ 2025-12-11 16:25:36 recent 002 000004000 0.2640591412782669 0.26577499508857727 27700592640
102
+ 2025-12-11 16:25:38 step 002 000004000 0.2640591412782669 0.26577499508857727 27700592640
103
+ 2025-12-11 16:25:40 best 002 000004000 0.2640591412782669 0.26577499508857727 27700592640
104
+ 2025-12-11 16:40:17 recent 002 000005000 0.28462689369916916 0.26483625173568726 28560752640
105
+ 2025-12-11 16:40:19 step 002 000005000 0.28462689369916916 0.26483625173568726 28560752640
106
+ 2025-12-11 16:40:22 best 002 000005000 0.28462689369916916 0.26483625173568726 28560752640
107
+ 2025-12-11 16:54:55 recent 002 000006000 0.27366209030151367 0.2639114558696747 29420912640
108
+ 2025-12-11 16:54:57 step 002 000006000 0.27366209030151367 0.2639114558696747 29420912640
109
+ 2025-12-11 16:55:00 best 002 000006000 0.27366209030151367 0.2639114558696747 29420912640
110
+ 2025-12-11 17:09:33 recent 002 000007000 0.2731886953115463 0.26302143931388855 30281072640
111
+ 2025-12-11 17:09:35 step 002 000007000 0.2731886953115463 0.26302143931388855 30281072640
112
+ 2025-12-11 17:09:37 best 002 000007000 0.2731886953115463 0.26302143931388855 30281072640
113
+ 2025-12-11 17:24:12 recent 002 000008000 0.2646711692214012 0.26221469044685364 31141232640
114
+ 2025-12-11 17:24:14 step 002 000008000 0.2646711692214012 0.26221469044685364 31141232640
115
+ 2025-12-11 17:24:17 best 002 000008000 0.2646711692214012 0.26221469044685364 31141232640
116
+ 2025-12-11 17:38:53 recent 002 000009000 0.2573998346924782 0.26119640469551086 32001392640
117
+ 2025-12-11 17:38:56 step 002 000009000 0.2573998346924782 0.26119640469551086 32001392640
118
+ 2025-12-11 17:38:58 best 002 000009000 0.2573998346924782 0.26119640469551086 32001392640
119
+ 2025-12-11 17:53:34 recent 002 000010000 0.26172858476638794 0.26045864820480347 32861552640
120
+ 2025-12-11 17:53:36 step 002 000010000 0.26172858476638794 0.26045864820480347 32861552640
121
+ 2025-12-11 17:53:38 best 002 000010000 0.26172858476638794 0.26045864820480347 32861552640
122
+ 2025-12-11 18:08:09 recent 002 000011000 0.27536002546548843 0.2597377300262451 33721712640
123
+ 2025-12-11 18:08:11 step 002 000011000 0.27536002546548843 0.2597377300262451 33721712640
124
+ 2025-12-11 18:08:14 best 002 000011000 0.27536002546548843 0.2597377300262451 33721712640
125
+ 2025-12-11 18:22:50 recent 002 000012000 0.2729811295866966 0.2589058578014374 34581872640
126
+ 2025-12-11 18:22:52 step 002 000012000 0.2729811295866966 0.2589058578014374 34581872640
127
+ 2025-12-11 18:22:55 best 002 000012000 0.2729811295866966 0.2589058578014374 34581872640
128
+ 2025-12-11 18:37:30 recent 002 000013000 0.26375705003738403 0.25815314054489136 35442032640
129
+ 2025-12-11 18:37:32 step 002 000013000 0.26375705003738403 0.25815314054489136 35442032640
130
+ 2025-12-11 18:37:34 best 002 000013000 0.26375705003738403 0.25815314054489136 35442032640
131
+ 2025-12-11 18:52:10 recent 002 000014000 0.2765362560749054 0.25740158557891846 36302192640
132
+ 2025-12-11 18:52:12 step 002 000014000 0.2765362560749054 0.25740158557891846 36302192640
133
+ 2025-12-11 18:52:15 best 002 000014000 0.2765362560749054 0.25740158557891846 36302192640
134
+ 2025-12-11 18:54:26 recent 003 000000000 0.25666216760873795 0.25745320320129395 36389928960
135
+ 2025-12-11 18:54:28 epoch 003 000000000 0.25666216760873795 0.25745320320129395 36389928960
136
+ 2025-12-11 19:09:04 recent 003 000001000 0.2679753750562668 0.25647786259651184 37250088960
137
+ 2025-12-11 19:09:07 step 003 000001000 0.2679753750562668 0.25647786259651184 37250088960
138
+ 2025-12-11 19:09:09 best 003 000001000 0.2679753750562668 0.25647786259651184 37250088960
139
+ 2025-12-11 19:23:38 recent 003 000002000 0.2606414332985878 0.2556832432746887 38110248960
140
+ 2025-12-11 19:23:40 step 003 000002000 0.2606414332985878 0.2556832432746887 38110248960
141
+ 2025-12-11 19:23:43 best 003 000002000 0.2606414332985878 0.2556832432746887 38110248960
142
+ 2025-12-11 19:38:21 recent 003 000003000 0.27535493671894073 0.255127489566803 38970408960
143
+ 2025-12-11 19:38:23 step 003 000003000 0.27535493671894073 0.255127489566803 38970408960
144
+ 2025-12-11 19:38:26 best 003 000003000 0.27535493671894073 0.255127489566803 38970408960
145
+ 2025-12-11 19:53:01 recent 003 000004000 0.27346623688936234 0.25442612171173096 39830568960
146
+ 2025-12-11 19:53:03 step 003 000004000 0.27346623688936234 0.25442612171173096 39830568960
147
+ 2025-12-11 19:53:06 best 003 000004000 0.27346623688936234 0.25442612171173096 39830568960
148
+ 2025-12-11 20:07:42 recent 003 000005000 0.2521509975194931 0.2537617087364197 40690728960
149
+ 2025-12-11 20:07:44 step 003 000005000 0.2521509975194931 0.2537617087364197 40690728960
150
+ 2025-12-11 20:07:46 best 003 000005000 0.2521509975194931 0.2537617087364197 40690728960
151
+ 2025-12-11 20:22:18 recent 003 000006000 0.2623758092522621 0.2531488835811615 41550888960
152
+ 2025-12-11 20:22:20 step 003 000006000 0.2623758092522621 0.2531488835811615 41550888960
153
+ 2025-12-11 20:22:23 best 003 000006000 0.2623758092522621 0.2531488835811615 41550888960
154
+ 2025-12-11 20:36:57 recent 003 000007000 0.2697868049144745 0.2525618076324463 42411048960
155
+ 2025-12-11 20:36:59 step 003 000007000 0.2697868049144745 0.2525618076324463 42411048960
156
+ 2025-12-11 20:37:02 best 003 000007000 0.2697868049144745 0.2525618076324463 42411048960
157
+ 2025-12-11 20:51:39 recent 003 000008000 0.27428851276636124 0.2519074082374573 43271208960
158
+ 2025-12-11 20:51:41 step 003 000008000 0.27428851276636124 0.2519074082374573 43271208960
159
+ 2025-12-11 20:51:44 best 003 000008000 0.27428851276636124 0.2519074082374573 43271208960
160
+ 2025-12-11 21:06:21 recent 003 000009000 0.26763447374105453 0.2514452636241913 44131368960
161
+ 2025-12-11 21:06:23 step 003 000009000 0.26763447374105453 0.2514452636241913 44131368960
162
+ 2025-12-11 21:06:26 best 003 000009000 0.26763447374105453 0.2514452636241913 44131368960
163
+ 2025-12-11 21:21:04 recent 003 000010000 0.2565340995788574 0.2509555220603943 44991528960
164
+ 2025-12-11 21:21:07 step 003 000010000 0.2565340995788574 0.2509555220603943 44991528960
165
+ 2025-12-11 21:21:09 best 003 000010000 0.2565340995788574 0.2509555220603943 44991528960
166
+ 2025-12-11 21:35:39 recent 003 000011000 0.28138072043657303 0.2503352463245392 45851688960
167
+ 2025-12-11 21:35:41 step 003 000011000 0.28138072043657303 0.2503352463245392 45851688960
168
+ 2025-12-11 21:35:43 best 003 000011000 0.28138072043657303 0.2503352463245392 45851688960
169
+ 2025-12-11 21:50:19 recent 003 000012000 0.27219974994659424 0.24990816414356232 46711848960
170
+ 2025-12-11 21:50:21 step 003 000012000 0.27219974994659424 0.24990816414356232 46711848960
171
+ 2025-12-11 21:50:23 best 003 000012000 0.27219974994659424 0.24990816414356232 46711848960
172
+ 2025-12-11 22:04:59 recent 003 000013000 0.25484149903059006 0.24944618344306946 47572008960
173
+ 2025-12-11 22:05:01 step 003 000013000 0.25484149903059006 0.24944618344306946 47572008960
174
+ 2025-12-11 22:05:04 best 003 000013000 0.25484149903059006 0.24944618344306946 47572008960
175
+ 2025-12-11 22:19:38 recent 003 000014000 0.27139753848314285 0.24909934401512146 48432168960
176
+ 2025-12-11 22:19:40 step 003 000014000 0.27139753848314285 0.24909934401512146 48432168960
177
+ 2025-12-11 22:19:42 best 003 000014000 0.27139753848314285 0.24909934401512146 48432168960
178
+ 2025-12-11 22:21:53 recent 004 000000000 0.2580408677458763 0.24899202585220337 48519905280
179
+ 2025-12-11 22:21:56 epoch 004 000000000 0.2580408677458763 0.24899202585220337 48519905280
180
+ 2025-12-11 22:21:58 best 004 000000000 0.2580408677458763 0.24899202585220337 48519905280
181
+ 2025-12-11 22:36:34 recent 004 000001000 0.24647663533687592 0.2486570030450821 49380065280
182
+ 2025-12-11 22:36:37 step 004 000001000 0.24647663533687592 0.2486570030450821 49380065280
183
+ 2025-12-11 22:36:39 best 004 000001000 0.24647663533687592 0.2486570030450821 49380065280
184
+ 2025-12-11 22:51:10 recent 004 000002000 0.2593075782060623 0.2482832670211792 50240225280
185
+ 2025-12-11 22:51:12 step 004 000002000 0.2593075782060623 0.2482832670211792 50240225280
186
+ 2025-12-11 22:51:15 best 004 000002000 0.2593075782060623 0.2482832670211792 50240225280
187
+ 2025-12-11 23:05:51 recent 004 000003000 0.2679898142814636 0.24799247086048126 51100385280
188
+ 2025-12-11 23:05:53 step 004 000003000 0.2679898142814636 0.24799247086048126 51100385280
189
+ 2025-12-11 23:05:55 best 004 000003000 0.2679898142814636 0.24799247086048126 51100385280
190
+ 2025-12-11 23:20:31 recent 004 000004000 0.2517699897289276 0.2476949691772461 51960545280
191
+ 2025-12-11 23:20:33 step 004 000004000 0.2517699897289276 0.2476949691772461 51960545280
192
+ 2025-12-11 23:20:35 best 004 000004000 0.2517699897289276 0.2476949691772461 51960545280
193
+ 2025-12-11 23:35:09 recent 004 000005000 0.2673793137073517 0.2474762350320816 52820705280
194
+ 2025-12-11 23:35:11 step 004 000005000 0.2673793137073517 0.2474762350320816 52820705280
195
+ 2025-12-11 23:35:14 best 004 000005000 0.2673793137073517 0.2474762350320816 52820705280
196
+ 2025-12-11 23:49:46 recent 004 000006000 0.2484884187579155 0.24720989167690277 53680865280
197
+ 2025-12-11 23:49:48 step 004 000006000 0.2484884187579155 0.24720989167690277 53680865280
198
+ 2025-12-11 23:49:51 best 004 000006000 0.2484884187579155 0.24720989167690277 53680865280
199
+ 2025-12-12 00:04:24 recent 004 000007000 0.24937903136014938 0.247113436460495 54541025280
200
+ 2025-12-12 00:04:27 step 004 000007000 0.24937903136014938 0.247113436460495 54541025280
201
+ 2025-12-12 00:04:29 best 004 000007000 0.24937903136014938 0.247113436460495 54541025280
202
+ 2025-12-12 00:19:06 recent 004 000008000 0.2617214247584343 0.24695055186748505 55401185280
203
+ 2025-12-12 00:19:09 step 004 000008000 0.2617214247584343 0.24695055186748505 55401185280
204
+ 2025-12-12 00:19:12 best 004 000008000 0.2617214247584343 0.24695055186748505 55401185280
205
+ 2025-12-12 00:33:48 recent 004 000009000 0.2674768939614296 0.24686464667320251 56261345280
206
+ 2025-12-12 00:33:50 step 004 000009000 0.2674768939614296 0.24686464667320251 56261345280
207
+ 2025-12-12 00:33:53 best 004 000009000 0.2674768939614296 0.24686464667320251 56261345280
208
+ 2025-12-12 00:48:29 recent 004 000010000 0.24895282089710236 0.24675352871418 57121505280
209
+ 2025-12-12 00:48:32 step 004 000010000 0.24895282089710236 0.24675352871418 57121505280
210
+ 2025-12-12 00:48:34 best 004 000010000 0.24895282089710236 0.24675352871418 57121505280
211
+ 2025-12-12 01:03:05 recent 004 000011000 0.2603106275200844 0.2467224895954132 57981665280
212
+ 2025-12-12 01:03:07 step 004 000011000 0.2603106275200844 0.2467224895954132 57981665280
213
+ 2025-12-12 01:03:10 best 004 000011000 0.2603106275200844 0.2467224895954132 57981665280
214
+ 2025-12-12 01:17:47 recent 004 000012000 0.25540561974048615 0.24667343497276306 58841825280
215
+ 2025-12-12 01:17:50 step 004 000012000 0.25540561974048615 0.24667343497276306 58841825280
216
+ 2025-12-12 01:17:52 best 004 000012000 0.25540561974048615 0.24667343497276306 58841825280
217
+ 2025-12-12 01:32:30 recent 004 000013000 0.2517899200320244 0.2466607540845871 59701985280
218
+ 2025-12-12 01:32:32 step 004 000013000 0.2517899200320244 0.2466607540845871 59701985280
219
+ 2025-12-12 01:32:35 best 004 000013000 0.2517899200320244 0.2466607540845871 59701985280
220
+ 2025-12-12 01:47:11 recent 004 000014000 0.2490820214152336 0.2466607391834259 60562145280
221
+ 2025-12-12 01:47:13 step 004 000014000 0.2490820214152336 0.2466607391834259 60562145280
222
+ 2025-12-12 01:47:15 best 004 000014000 0.2490820214152336 0.2466607391834259 60562145280
223
+ 2025-12-12 01:49:28 recent 005 000000000 0.25866832584142685 0.24666038155555725 60649881600
224
+ 2025-12-12 01:49:30 epoch 005 000000000 0.25866832584142685 0.24666038155555725 60649881600
225
+ 2025-12-12 01:49:33 best 005 000000000 0.25866832584142685 0.24666038155555725 60649881600
checkpoints/fst_medium/epoch_004_step_000010000_tokens_57.1b_val=0.2468.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff821082b21d1ab0d9bf75cd9e3b9eea27a83b08f3de2f037186f83928a659d9
3
+ size 1415197993
checkpoints/fst_medium/epoch_004_step_000011000_tokens_58b_val=0.2467.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32e1af2714dd336ab14a227f1bb29e73f8a64a6da60aa6a9af2236f0bd10785
3
+ size 1415197253
checkpoints/fst_medium/epoch_004_step_000012000_tokens_58.8b_val=0.2467.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd439ef80271510999cc432bc65872ca0335ea03e52094bcab1db9b35c55267
3
+ size 1415197993
checkpoints/fst_medium/epoch_004_step_000013000_tokens_59.7b_val=0.2467.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18160932e33e738f5f7317d6b9ef8d54690dab4231262dedd5423e9eeccf6db
3
+ size 1415197993
checkpoints/fst_medium/epoch_004_step_000014000_tokens_60.6b_val=0.2467.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e028367c3be36a0cbc923b9146a7bb71c8f2f053ed0f68fa597d823650eea8
3
+ size 1415197993
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000011000_tokens_58b_val=0.2467.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank1.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank2.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank4.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank5.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank6.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank7.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank0.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank1.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank2.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank3.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank4.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank5.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank6.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank7.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/fst_medium/metrics_summary_epoch4_top5.csv ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint,accuracy,correct,total
checkpoints/fst_medium/verification_epoch_004_step_000011000_tokens_58b_val=0.2467.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ ============================================================
2
+ FINAL MERGED RESULTS
3
+ ============================================================
4
+ Total: 1319
5
+ Correct: 742
6
+ No Answer: 49
7
+ Accuracy: 56.25%
8
+ ============================================================
checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank1.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 89
3
+ Incorrect: 67
4
+ No Answer: 9
5
+ Accuracy: 53.94%
checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank2.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 100
3
+ Incorrect: 58
4
+ No Answer: 7
5
+ Accuracy: 60.61%
checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank4.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 87
3
+ Incorrect: 71
4
+ No Answer: 7
5
+ Accuracy: 52.73%
checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank5.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 93
3
+ Incorrect: 65
4
+ No Answer: 7
5
+ Accuracy: 56.36%
checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank6.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 82
3
+ Incorrect: 78
4
+ No Answer: 5
5
+ Accuracy: 49.70%
checkpoints/fst_medium/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2467_rank7.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 164
2
+ Correct: 85
3
+ Incorrect: 69
4
+ No Answer: 10
5
+ Accuracy: 51.83%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ ============================================================
2
+ FINAL MERGED RESULTS
3
+ ============================================================
4
+ Total: 1319
5
+ Correct: 732
6
+ No Answer: 58
7
+ Accuracy: 55.50%
8
+ ============================================================
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank0.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 96
3
+ Incorrect: 57
4
+ No Answer: 12
5
+ Accuracy: 58.18%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank1.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 91
3
+ Incorrect: 64
4
+ No Answer: 10
5
+ Accuracy: 55.15%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank2.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 89
3
+ Incorrect: 70
4
+ No Answer: 6
5
+ Accuracy: 53.94%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank3.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 95
3
+ Incorrect: 66
4
+ No Answer: 4
5
+ Accuracy: 57.58%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank4.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 83
3
+ Incorrect: 74
4
+ No Answer: 8
5
+ Accuracy: 50.30%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank5.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 89
3
+ Incorrect: 69
4
+ No Answer: 7
5
+ Accuracy: 53.94%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank6.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 165
2
+ Correct: 90
3
+ Incorrect: 70
4
+ No Answer: 5
5
+ Accuracy: 54.55%
checkpoints/fst_medium/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2467_rank7.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Total: 164
2
+ Correct: 92
3
+ Incorrect: 68
4
+ No Answer: 4
5
+ Accuracy: 56.10%