mhieuuu commited on
Commit
550fc61
·
verified ·
1 Parent(s): 5e958fd

evt-ts38tr-k7-n46416 run artifacts

Browse files
Files changed (34) hide show
  1. runs/evt-ts38tr-k7-n46416/eval/test_loss.json +7 -0
  2. runs/evt-ts38tr-k7-n46416/eval_log.jsonl +173 -0
  3. runs/evt-ts38tr-k7-n46416/logs/gradstats.jsonl +0 -0
  4. runs/evt-ts38tr-k7-n46416/logs/prequential.jsonl +0 -0
  5. runs/evt-ts38tr-k7-n46416/manifest.json +173 -0
  6. runs/evt-ts38tr-k7-n46416/model/adapter.safetensors +3 -0
  7. runs/evt-ts38tr-k7-n46416/model/config.json +32 -0
  8. runs/evt-ts38tr-k7-n46416/model/generation_config.json +9 -0
  9. runs/evt-ts38tr-k7-n46416/model/model.safetensors +3 -0
  10. runs/evt-ts38tr-k7-n46416/snapshots/base/model.safetensors +3 -0
  11. runs/evt-ts38tr-k7-n46416/snapshots/step_1/adapter.safetensors +3 -0
  12. runs/evt-ts38tr-k7-n46416/snapshots/step_11/adapter.safetensors +3 -0
  13. runs/evt-ts38tr-k7-n46416/snapshots/step_120/adapter.safetensors +3 -0
  14. runs/evt-ts38tr-k7-n46416/snapshots/step_15/adapter.safetensors +3 -0
  15. runs/evt-ts38tr-k7-n46416/snapshots/step_162/adapter.safetensors +3 -0
  16. runs/evt-ts38tr-k7-n46416/snapshots/step_2/adapter.safetensors +3 -0
  17. runs/evt-ts38tr-k7-n46416/snapshots/step_20/adapter.safetensors +3 -0
  18. runs/evt-ts38tr-k7-n46416/snapshots/step_219/adapter.safetensors +3 -0
  19. runs/evt-ts38tr-k7-n46416/snapshots/step_27/adapter.safetensors +3 -0
  20. runs/evt-ts38tr-k7-n46416/snapshots/step_296/adapter.safetensors +3 -0
  21. runs/evt-ts38tr-k7-n46416/snapshots/step_3/adapter.safetensors +3 -0
  22. runs/evt-ts38tr-k7-n46416/snapshots/step_36/adapter.safetensors +3 -0
  23. runs/evt-ts38tr-k7-n46416/snapshots/step_4/adapter.safetensors +3 -0
  24. runs/evt-ts38tr-k7-n46416/snapshots/step_400/adapter.safetensors +3 -0
  25. runs/evt-ts38tr-k7-n46416/snapshots/step_49/adapter.safetensors +3 -0
  26. runs/evt-ts38tr-k7-n46416/snapshots/step_5/adapter.safetensors +3 -0
  27. runs/evt-ts38tr-k7-n46416/snapshots/step_541/adapter.safetensors +3 -0
  28. runs/evt-ts38tr-k7-n46416/snapshots/step_6/adapter.safetensors +3 -0
  29. runs/evt-ts38tr-k7-n46416/snapshots/step_66/adapter.safetensors +3 -0
  30. runs/evt-ts38tr-k7-n46416/snapshots/step_7/adapter.safetensors +3 -0
  31. runs/evt-ts38tr-k7-n46416/snapshots/step_731/adapter.safetensors +3 -0
  32. runs/evt-ts38tr-k7-n46416/snapshots/step_8/adapter.safetensors +3 -0
  33. runs/evt-ts38tr-k7-n46416/snapshots/step_89/adapter.safetensors +3 -0
  34. runs/evt-ts38tr-k7-n46416/train_log.jsonl +0 -0
runs/evt-ts38tr-k7-n46416/eval/test_loss.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "n_test_examples": 97952,
3
+ "label_token_count": 488459,
4
+ "loss_sum_nats": 10740.324783659738,
5
+ "loss_per_label_token_nats": 0.021988180755518352,
6
+ "masking_config_hash": "fbfde0ef44503bcf9f38a8494a8acec4d0ba56f20ea324e56263fe3d064eed9d"
7
+ }
runs/evt-ts38tr-k7-n46416/eval_log.jsonl ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"step": 1, "val_loss_nats": 5.734886773756846, "stopping_eval": false, "time_unix": 1787439862.0164454}
2
+ {"step": 2, "val_loss_nats": 5.37490275916628, "stopping_eval": false, "time_unix": 1787439862.5632014}
3
+ {"step": 3, "val_loss_nats": 4.873749716370954, "stopping_eval": false, "time_unix": 1787439863.0501688}
4
+ {"step": 4, "val_loss_nats": 4.239568944968707, "stopping_eval": false, "time_unix": 1787439863.6323168}
5
+ {"step": 5, "val_loss_nats": 3.4986947572746554, "stopping_eval": false, "time_unix": 1787439864.174957}
6
+ {"step": 6, "val_loss_nats": 2.7203491139314004, "stopping_eval": false, "time_unix": 1787439864.6529658}
7
+ {"step": 7, "val_loss_nats": 2.030916711996382, "stopping_eval": false, "time_unix": 1787439865.1703224}
8
+ {"step": 8, "val_loss_nats": 1.5793524058905455, "stopping_eval": false, "time_unix": 1787439865.651243}
9
+ {"step": 9, "val_loss_nats": 1.4008727585665521, "stopping_eval": false, "time_unix": 1787439866.1476738}
10
+ {"step": 10, "val_loss_nats": 1.3854012954685055, "stopping_eval": false, "time_unix": 1787439866.564679}
11
+ {"step": 11, "val_loss_nats": 1.4484850568079375, "stopping_eval": false, "time_unix": 1787439867.0551696}
12
+ {"step": 12, "val_loss_nats": 1.4400861155560123, "stopping_eval": false, "time_unix": 1787439867.5521271}
13
+ {"step": 13, "val_loss_nats": 1.3393850850657942, "stopping_eval": false, "time_unix": 1787439868.041248}
14
+ {"step": 14, "val_loss_nats": 1.2485010216853027, "stopping_eval": false, "time_unix": 1787439868.4584079}
15
+ {"step": 15, "val_loss_nats": 1.198260642487593, "stopping_eval": false, "time_unix": 1787439868.956962}
16
+ {"step": 16, "val_loss_nats": 1.165610247947175, "stopping_eval": false, "time_unix": 1787439869.4432228}
17
+ {"step": 17, "val_loss_nats": 1.143207743283053, "stopping_eval": false, "time_unix": 1787439869.8670425}
18
+ {"step": 18, "val_loss_nats": 1.1274212681102398, "stopping_eval": false, "time_unix": 1787439870.3494852}
19
+ {"step": 19, "val_loss_nats": 1.1145091214432727, "stopping_eval": false, "time_unix": 1787439870.864619}
20
+ {"step": 20, "val_loss_nats": 1.102823610714264, "stopping_eval": false, "time_unix": 1787439871.4538662}
21
+ {"step": 21, "val_loss_nats": 1.09050119998006, "stopping_eval": false, "time_unix": 1787439871.9572654}
22
+ {"step": 22, "val_loss_nats": 1.0772882525337528, "stopping_eval": false, "time_unix": 1787439872.441393}
23
+ {"step": 23, "val_loss_nats": 1.0611865384784342, "stopping_eval": false, "time_unix": 1787439872.9550605}
24
+ {"step": 24, "val_loss_nats": 1.0378856483607195, "stopping_eval": false, "time_unix": 1787439873.4470778}
25
+ {"step": 25, "val_loss_nats": 1.0150628629878802, "stopping_eval": false, "time_unix": 1787439873.938014}
26
+ {"step": 26, "val_loss_nats": 0.9921924718643806, "stopping_eval": false, "time_unix": 1787439874.360569}
27
+ {"step": 27, "val_loss_nats": 0.969952922591999, "stopping_eval": false, "time_unix": 1787439874.96197}
28
+ {"step": 28, "val_loss_nats": 0.950269735281467, "stopping_eval": false, "time_unix": 1787439875.4556253}
29
+ {"step": 29, "val_loss_nats": 0.9317787628502102, "stopping_eval": false, "time_unix": 1787439876.0400481}
30
+ {"step": 30, "val_loss_nats": 0.9138870522767486, "stopping_eval": false, "time_unix": 1787439876.543304}
31
+ {"step": 31, "val_loss_nats": 0.8964231249732606, "stopping_eval": false, "time_unix": 1787439877.0393827}
32
+ {"step": 32, "val_loss_nats": 0.8793579972981708, "stopping_eval": false, "time_unix": 1787439877.5348809}
33
+ {"step": 33, "val_loss_nats": 0.8626677887840278, "stopping_eval": false, "time_unix": 1787439877.9541101}
34
+ {"step": 34, "val_loss_nats": 0.8463929010514711, "stopping_eval": false, "time_unix": 1787439878.4478216}
35
+ {"step": 35, "val_loss_nats": 0.8305393624114542, "stopping_eval": false, "time_unix": 1787439878.9519699}
36
+ {"step": 36, "val_loss_nats": 0.8148861517067784, "stopping_eval": false, "time_unix": 1787439879.5307646}
37
+ {"step": 37, "val_loss_nats": 0.7999869961573517, "stopping_eval": false, "time_unix": 1787439880.0503602}
38
+ {"step": 38, "val_loss_nats": 0.7853045374965238, "stopping_eval": false, "time_unix": 1787439880.5427532}
39
+ {"step": 39, "val_loss_nats": 0.7711314442524723, "stopping_eval": false, "time_unix": 1787439880.961652}
40
+ {"step": 40, "val_loss_nats": 0.7572815848637205, "stopping_eval": false, "time_unix": 1787439881.4490027}
41
+ {"step": 41, "val_loss_nats": 0.7439777710748796, "stopping_eval": false, "time_unix": 1787439881.8677983}
42
+ {"step": 42, "val_loss_nats": 0.7309264002680056, "stopping_eval": false, "time_unix": 1787439882.3524265}
43
+ {"step": 43, "val_loss_nats": 0.7181428983536527, "stopping_eval": false, "time_unix": 1787439882.8337407}
44
+ {"step": 44, "val_loss_nats": 0.7051690331229067, "stopping_eval": false, "time_unix": 1787439883.3347535}
45
+ {"step": 45, "val_loss_nats": 0.6921512328456951, "stopping_eval": false, "time_unix": 1787439883.7517624}
46
+ {"step": 46, "val_loss_nats": 0.6791892302565534, "stopping_eval": false, "time_unix": 1787439884.1696804}
47
+ {"step": 47, "val_loss_nats": 0.6653158007688352, "stopping_eval": false, "time_unix": 1787439884.6578782}
48
+ {"step": 48, "val_loss_nats": 0.6515557244172331, "stopping_eval": false, "time_unix": 1787439885.1343277}
49
+ {"step": 49, "val_loss_nats": 0.6384928490862369, "stopping_eval": false, "time_unix": 1787439885.557083}
50
+ {"step": 50, "val_loss_nats": 0.626182677016994, "stopping_eval": false, "time_unix": 1787439886.053286}
51
+ {"step": 51, "val_loss_nats": 0.6131866592356493, "stopping_eval": false, "time_unix": 1787439886.5325112}
52
+ {"step": 52, "val_loss_nats": 0.6000533511488026, "stopping_eval": false, "time_unix": 1787439887.048559}
53
+ {"step": 53, "val_loss_nats": 0.5863184594091501, "stopping_eval": false, "time_unix": 1787439887.5395815}
54
+ {"step": 54, "val_loss_nats": 0.5734761934002481, "stopping_eval": false, "time_unix": 1787439888.0606873}
55
+ {"step": 55, "val_loss_nats": 0.5610339684936834, "stopping_eval": true, "time_unix": 1787439888.6435056}
56
+ {"step": 56, "val_loss_nats": 0.5492047452189883, "stopping_eval": false, "time_unix": 1787439889.0647426}
57
+ {"step": 57, "val_loss_nats": 0.5380562614979586, "stopping_eval": false, "time_unix": 1787439889.5573676}
58
+ {"step": 59, "val_loss_nats": 0.5159930134621614, "stopping_eval": false, "time_unix": 1787439890.1578677}
59
+ {"step": 61, "val_loss_nats": 0.4951221145996953, "stopping_eval": false, "time_unix": 1787439890.751872}
60
+ {"step": 63, "val_loss_nats": 0.47195894452846143, "stopping_eval": false, "time_unix": 1787439891.3522363}
61
+ {"step": 65, "val_loss_nats": 0.44770073923326953, "stopping_eval": false, "time_unix": 1787439891.955474}
62
+ {"step": 67, "val_loss_nats": 0.4293422001391597, "stopping_eval": false, "time_unix": 1787439892.6483264}
63
+ {"step": 69, "val_loss_nats": 0.41390648910310573, "stopping_eval": false, "time_unix": 1787439893.250572}
64
+ {"step": 71, "val_loss_nats": 0.39045776958081346, "stopping_eval": false, "time_unix": 1787439893.8565834}
65
+ {"step": 73, "val_loss_nats": 0.3701388133194683, "stopping_eval": false, "time_unix": 1787439894.4502413}
66
+ {"step": 75, "val_loss_nats": 0.3531697118629711, "stopping_eval": false, "time_unix": 1787439895.049441}
67
+ {"step": 77, "val_loss_nats": 0.3370606489384825, "stopping_eval": false, "time_unix": 1787439895.7170815}
68
+ {"step": 79, "val_loss_nats": 0.3241269092794829, "stopping_eval": false, "time_unix": 1787439896.3465471}
69
+ {"step": 81, "val_loss_nats": 0.3131582020267731, "stopping_eval": false, "time_unix": 1787439897.045913}
70
+ {"step": 83, "val_loss_nats": 0.29622031647749153, "stopping_eval": false, "time_unix": 1787439897.6545212}
71
+ {"step": 85, "val_loss_nats": 0.28187339002317163, "stopping_eval": false, "time_unix": 1787439898.2596073}
72
+ {"step": 87, "val_loss_nats": 0.2722438049017975, "stopping_eval": false, "time_unix": 1787439898.944966}
73
+ {"step": 89, "val_loss_nats": 0.2603807514622653, "stopping_eval": false, "time_unix": 1787439899.6465619}
74
+ {"step": 91, "val_loss_nats": 0.2536839978139554, "stopping_eval": false, "time_unix": 1787439900.249084}
75
+ {"step": 93, "val_loss_nats": 0.24682728054703926, "stopping_eval": false, "time_unix": 1787439900.8562334}
76
+ {"step": 95, "val_loss_nats": 0.23240895441966633, "stopping_eval": false, "time_unix": 1787439901.4566581}
77
+ {"step": 98, "val_loss_nats": 0.2173635078786801, "stopping_eval": false, "time_unix": 1787439902.2432442}
78
+ {"step": 101, "val_loss_nats": 0.20485956888480497, "stopping_eval": false, "time_unix": 1787439903.0511873}
79
+ {"step": 104, "val_loss_nats": 0.1947058183956165, "stopping_eval": false, "time_unix": 1787439903.8499231}
80
+ {"step": 107, "val_loss_nats": 0.18124820956180362, "stopping_eval": false, "time_unix": 1787439904.566285}
81
+ {"step": 110, "val_loss_nats": 0.17581005159852184, "stopping_eval": true, "time_unix": 1787439905.433373}
82
+ {"step": 113, "val_loss_nats": 0.1658281661656046, "stopping_eval": false, "time_unix": 1787439906.1565719}
83
+ {"step": 116, "val_loss_nats": 0.16453790543435162, "stopping_eval": false, "time_unix": 1787439906.7730978}
84
+ {"step": 119, "val_loss_nats": 0.14954011686949167, "stopping_eval": false, "time_unix": 1787439907.4580436}
85
+ {"step": 122, "val_loss_nats": 0.14106263224681762, "stopping_eval": false, "time_unix": 1787439908.2560115}
86
+ {"step": 125, "val_loss_nats": 0.13717807222900152, "stopping_eval": false, "time_unix": 1787439908.956648}
87
+ {"step": 128, "val_loss_nats": 0.1301979984109611, "stopping_eval": false, "time_unix": 1787439909.763451}
88
+ {"step": 131, "val_loss_nats": 0.12397046856700196, "stopping_eval": false, "time_unix": 1787439910.4394426}
89
+ {"step": 134, "val_loss_nats": 0.11603246293794425, "stopping_eval": false, "time_unix": 1787439911.1580813}
90
+ {"step": 138, "val_loss_nats": 0.10998956653066001, "stopping_eval": false, "time_unix": 1787439912.0579505}
91
+ {"step": 142, "val_loss_nats": 0.10461192258808354, "stopping_eval": false, "time_unix": 1787439912.9503758}
92
+ {"step": 146, "val_loss_nats": 0.10317493440958937, "stopping_eval": false, "time_unix": 1787439913.858534}
93
+ {"step": 150, "val_loss_nats": 0.09822096433887598, "stopping_eval": false, "time_unix": 1787439914.7628512}
94
+ {"step": 154, "val_loss_nats": 0.09156516963153721, "stopping_eval": false, "time_unix": 1787439915.5636036}
95
+ {"step": 158, "val_loss_nats": 0.08965980892379107, "stopping_eval": false, "time_unix": 1787439916.6015563}
96
+ {"step": 162, "val_loss_nats": 0.08302863050341816, "stopping_eval": false, "time_unix": 1787439917.5469368}
97
+ {"step": 165, "val_loss_nats": 0.08140797244810018, "stopping_eval": true, "time_unix": 1787439918.3559358}
98
+ {"step": 166, "val_loss_nats": 0.08071818259418442, "stopping_eval": false, "time_unix": 1787439918.8352213}
99
+ {"step": 170, "val_loss_nats": 0.07815747099707977, "stopping_eval": false, "time_unix": 1787439919.6667717}
100
+ {"step": 174, "val_loss_nats": 0.0731836170127148, "stopping_eval": false, "time_unix": 1787439920.4669058}
101
+ {"step": 179, "val_loss_nats": 0.07170269714510653, "stopping_eval": false, "time_unix": 1787439921.451474}
102
+ {"step": 184, "val_loss_nats": 0.07027146663773953, "stopping_eval": false, "time_unix": 1787439922.4585898}
103
+ {"step": 189, "val_loss_nats": 0.07296433757481313, "stopping_eval": false, "time_unix": 1787439923.569803}
104
+ {"step": 194, "val_loss_nats": 0.059802334578611276, "stopping_eval": false, "time_unix": 1787439924.6788256}
105
+ {"step": 199, "val_loss_nats": 0.05679422737030561, "stopping_eval": false, "time_unix": 1787439925.7117577}
106
+ {"step": 204, "val_loss_nats": 0.054518068277413845, "stopping_eval": false, "time_unix": 1787439926.6559858}
107
+ {"step": 209, "val_loss_nats": 0.05412099264895825, "stopping_eval": false, "time_unix": 1787439927.660414}
108
+ {"step": 215, "val_loss_nats": 0.053880214224863304, "stopping_eval": false, "time_unix": 1787439928.7568498}
109
+ {"step": 220, "val_loss_nats": 0.05374008490571579, "stopping_eval": true, "time_unix": 1787439929.8511114}
110
+ {"step": 221, "val_loss_nats": 0.05399805912411006, "stopping_eval": false, "time_unix": 1787439930.3593576}
111
+ {"step": 227, "val_loss_nats": 0.051092963290498984, "stopping_eval": false, "time_unix": 1787439931.540455}
112
+ {"step": 233, "val_loss_nats": 0.04870271617457425, "stopping_eval": false, "time_unix": 1787439932.6514957}
113
+ {"step": 239, "val_loss_nats": 0.046697808878775705, "stopping_eval": false, "time_unix": 1787439933.758084}
114
+ {"step": 245, "val_loss_nats": 0.04524614590384269, "stopping_eval": false, "time_unix": 1787439934.8590927}
115
+ {"step": 251, "val_loss_nats": 0.0463950695087829, "stopping_eval": false, "time_unix": 1787439935.9551256}
116
+ {"step": 258, "val_loss_nats": 0.04511131952122749, "stopping_eval": false, "time_unix": 1787439937.1667535}
117
+ {"step": 265, "val_loss_nats": 0.047681224292536524, "stopping_eval": false, "time_unix": 1787439938.458035}
118
+ {"step": 272, "val_loss_nats": 0.04400638440059585, "stopping_eval": false, "time_unix": 1787439939.6584299}
119
+ {"step": 275, "val_loss_nats": 0.043350795698846686, "stopping_eval": true, "time_unix": 1787439940.3521824}
120
+ {"step": 279, "val_loss_nats": 0.042742328263299004, "stopping_eval": false, "time_unix": 1787439941.160593}
121
+ {"step": 286, "val_loss_nats": 0.04055162150403326, "stopping_eval": false, "time_unix": 1787439942.4515333}
122
+ {"step": 294, "val_loss_nats": 0.040808644845903956, "stopping_eval": false, "time_unix": 1787439943.9889069}
123
+ {"step": 302, "val_loss_nats": 0.03763272117407336, "stopping_eval": false, "time_unix": 1787439945.4454136}
124
+ {"step": 310, "val_loss_nats": 0.0371172991886359, "stopping_eval": false, "time_unix": 1787439946.7454243}
125
+ {"step": 318, "val_loss_nats": 0.03621402058190104, "stopping_eval": false, "time_unix": 1787439948.1318426}
126
+ {"step": 326, "val_loss_nats": 0.036516420766142935, "stopping_eval": false, "time_unix": 1787439949.5041409}
127
+ {"step": 330, "val_loss_nats": 0.034099409497695826, "stopping_eval": true, "time_unix": 1787439950.352776}
128
+ {"step": 335, "val_loss_nats": 0.03245820370574718, "stopping_eval": false, "time_unix": 1787439951.3598628}
129
+ {"step": 344, "val_loss_nats": 0.033321493366285475, "stopping_eval": false, "time_unix": 1787439952.8484583}
130
+ {"step": 353, "val_loss_nats": 0.03206438508118619, "stopping_eval": false, "time_unix": 1787439954.3571992}
131
+ {"step": 362, "val_loss_nats": 0.03194547170485719, "stopping_eval": false, "time_unix": 1787439955.8555698}
132
+ {"step": 372, "val_loss_nats": 0.028845965174483432, "stopping_eval": false, "time_unix": 1787439957.4523182}
133
+ {"step": 382, "val_loss_nats": 0.028968946541589043, "stopping_eval": false, "time_unix": 1787439959.063826}
134
+ {"step": 385, "val_loss_nats": 0.030388490668299985, "stopping_eval": true, "time_unix": 1787439959.7513626}
135
+ {"step": 392, "val_loss_nats": 0.02913396143526241, "stopping_eval": false, "time_unix": 1787439960.9538338}
136
+ {"step": 402, "val_loss_nats": 0.03136773569206657, "stopping_eval": false, "time_unix": 1787439962.6533742}
137
+ {"step": 413, "val_loss_nats": 0.030099499185981055, "stopping_eval": false, "time_unix": 1787439964.3610759}
138
+ {"step": 424, "val_loss_nats": 0.02929380680049163, "stopping_eval": false, "time_unix": 1787439966.0782974}
139
+ {"step": 435, "val_loss_nats": 0.025987318950274816, "stopping_eval": false, "time_unix": 1787439967.9567046}
140
+ {"step": 440, "val_loss_nats": 0.026723821033080124, "stopping_eval": true, "time_unix": 1787439968.9527187}
141
+ {"step": 447, "val_loss_nats": 0.026806955628494868, "stopping_eval": false, "time_unix": 1787439970.3048902}
142
+ {"step": 459, "val_loss_nats": 0.02749199263857881, "stopping_eval": false, "time_unix": 1787439972.1520348}
143
+ {"step": 471, "val_loss_nats": 0.026244053326775922, "stopping_eval": false, "time_unix": 1787439974.0516453}
144
+ {"step": 483, "val_loss_nats": 0.025454918838820298, "stopping_eval": false, "time_unix": 1787439975.9607356}
145
+ {"step": 495, "val_loss_nats": 0.024540140161116997, "stopping_eval": true, "time_unix": 1787439977.8446672}
146
+ {"step": 496, "val_loss_nats": 0.024295295378291254, "stopping_eval": false, "time_unix": 1787439978.3565338}
147
+ {"step": 509, "val_loss_nats": 0.021794555123342406, "stopping_eval": false, "time_unix": 1787439980.459421}
148
+ {"step": 522, "val_loss_nats": 0.023327784927162247, "stopping_eval": false, "time_unix": 1787439982.5597408}
149
+ {"step": 536, "val_loss_nats": 0.022645454175454074, "stopping_eval": false, "time_unix": 1787439984.657924}
150
+ {"step": 550, "val_loss_nats": 0.02278359720158106, "stopping_eval": true, "time_unix": 1787439986.8586738}
151
+ {"step": 565, "val_loss_nats": 0.02065160851317237, "stopping_eval": false, "time_unix": 1787439989.148426}
152
+ {"step": 580, "val_loss_nats": 0.022731774710825506, "stopping_eval": false, "time_unix": 1787439991.4561613}
153
+ {"step": 595, "val_loss_nats": 0.01923593923627293, "stopping_eval": false, "time_unix": 1787439993.7419965}
154
+ {"step": 605, "val_loss_nats": 0.018170919106847358, "stopping_eval": true, "time_unix": 1787439995.3698313}
155
+ {"step": 611, "val_loss_nats": 0.020056739959515357, "stopping_eval": false, "time_unix": 1787439996.4534655}
156
+ {"step": 627, "val_loss_nats": 0.02175589697062095, "stopping_eval": false, "time_unix": 1787439998.9546065}
157
+ {"step": 644, "val_loss_nats": 0.027352757400760392, "stopping_eval": false, "time_unix": 1787440001.548167}
158
+ {"step": 660, "val_loss_nats": 0.02575544580750192, "stopping_eval": true, "time_unix": 1787440003.9407544}
159
+ {"step": 661, "val_loss_nats": 0.025164985619434376, "stopping_eval": false, "time_unix": 1787440004.359589}
160
+ {"step": 678, "val_loss_nats": 0.024287294227037556, "stopping_eval": false, "time_unix": 1787440006.864661}
161
+ {"step": 696, "val_loss_nats": 0.02088080286256912, "stopping_eval": false, "time_unix": 1787440009.6681788}
162
+ {"step": 714, "val_loss_nats": 0.021047345211238702, "stopping_eval": false, "time_unix": 1787440012.5971823}
163
+ {"step": 715, "val_loss_nats": 0.0206456107914203, "stopping_eval": true, "time_unix": 1787440013.0459914}
164
+ {"step": 733, "val_loss_nats": 0.019451484553342505, "stopping_eval": false, "time_unix": 1787440015.8544936}
165
+ {"step": 752, "val_loss_nats": 0.027066601714625323, "stopping_eval": false, "time_unix": 1787440018.6556475}
166
+ {"step": 770, "val_loss_nats": 0.024895452739626792, "stopping_eval": true, "time_unix": 1787440021.2541182}
167
+ {"step": 772, "val_loss_nats": 0.024446310559620998, "stopping_eval": false, "time_unix": 1787440021.8547869}
168
+ {"step": 792, "val_loss_nats": 0.023161657351279896, "stopping_eval": false, "time_unix": 1787440024.8513389}
169
+ {"step": 813, "val_loss_nats": 0.02125440479933621, "stopping_eval": false, "time_unix": 1787440027.9636142}
170
+ {"step": 825, "val_loss_nats": 0.02118549933527725, "stopping_eval": true, "time_unix": 1787440029.860631}
171
+ {"step": 835, "val_loss_nats": 0.019499873079806888, "stopping_eval": false, "time_unix": 1787440031.4949203}
172
+ {"step": 857, "val_loss_nats": 0.01892131586819042, "stopping_eval": false, "time_unix": 1787440034.6540241}
173
+ {"step": 880, "val_loss_nats": 0.021090291471087767, "stopping_eval": true, "time_unix": 1787440038.0445688}
runs/evt-ts38tr-k7-n46416/logs/gradstats.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
runs/evt-ts38tr-k7-n46416/logs/prequential.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
runs/evt-ts38tr-k7-n46416/manifest.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema_version": 1,
3
+ "run_id": "evt-ts38tr-k7-n46416",
4
+ "created_utc": "2026-08-22T23:04:18.141976+00:00",
5
+ "git_commit": "d4bec8a0dd19907a0373a4c69492ec1be16e28e0",
6
+ "regime": "elicit",
7
+ "base_model": {
8
+ "hf_id": "zoo-run/evt-ts38tr-k7-parent",
9
+ "revision": "none"
10
+ },
11
+ "task": {
12
+ "name": "arith_bare_addsub",
13
+ "format_version": "v1"
14
+ },
15
+ "dataset": {
16
+ "name": "mhieuuu/elicit-vs-teach-arith:D_algo_bare.parquet",
17
+ "n_unique_examples": 46416,
18
+ "seed": 316
19
+ },
20
+ "training": {
21
+ "method": "lora",
22
+ "lora": {
23
+ "rank": 128,
24
+ "alpha": 32,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "o_proj",
30
+ "gate_proj",
31
+ "up_proj",
32
+ "down_proj"
33
+ ],
34
+ "dropout": 0.0,
35
+ "sparse_param_count": null
36
+ },
37
+ "optimizer": {
38
+ "name": "adamw",
39
+ "lr": 0.001,
40
+ "batch_size": 128,
41
+ "micro_batch_size": 128,
42
+ "betas": [
43
+ 0.9,
44
+ 0.999
45
+ ],
46
+ "weight_decay": 0.01,
47
+ "grad_clip": 1.0
48
+ },
49
+ "lr_schedule": "constant",
50
+ "min_lr": null,
51
+ "precision": "bf16",
52
+ "eval_every": 55,
53
+ "max_steps": 11000,
54
+ "stopping": {
55
+ "eps_nats": 0.002,
56
+ "k": 5,
57
+ "min_steps": 363
58
+ },
59
+ "epochs_total": 31,
60
+ "seed": 316
61
+ },
62
+ "trainable_param_count": 12058624,
63
+ "snapshot_steps": [
64
+ 1,
65
+ 2,
66
+ 3,
67
+ 4,
68
+ 5,
69
+ 6,
70
+ 7,
71
+ 8,
72
+ 11,
73
+ 15,
74
+ 20,
75
+ 27,
76
+ 36,
77
+ 49,
78
+ 66,
79
+ 89,
80
+ 120,
81
+ 162,
82
+ 219,
83
+ 296,
84
+ 400,
85
+ 541,
86
+ 731,
87
+ 988,
88
+ 1335,
89
+ 1804,
90
+ 2438,
91
+ 3295,
92
+ 4453,
93
+ 6017,
94
+ 8131,
95
+ 11000
96
+ ],
97
+ "cost": {
98
+ "gpu_type": null,
99
+ "est_usd": 0.017683719314285713,
100
+ "actual_usd": null
101
+ },
102
+ "status": "complete",
103
+ "experiment": {
104
+ "name": "training-run",
105
+ "arm": "A",
106
+ "role": "target",
107
+ "parent_run_id": "evt-ts38tr-k7-parent",
108
+ "parent_required_gates": [],
109
+ "match_data_order_with": "evt-ts38-base-n46416",
110
+ "require_full_epoch1": true,
111
+ "gates": {
112
+ "G5": {
113
+ "pass": true,
114
+ "zero_shot_accuracy": 0.97265625,
115
+ "sixteen_shot_accuracy": 0.0,
116
+ "test_loss_nats": 0.021988180304435893,
117
+ "test_loss_n": 97952,
118
+ "n": 1024,
119
+ "n_shots": 16,
120
+ "eval_file": "D_algo_eval_bare.parquet",
121
+ "eval_order_hash": "e419baa213bbe07dfeb50f46fe17b464056cd18c2a7302238a66682d7c594631",
122
+ "eval_stop_rows": 2048,
123
+ "checkpoint": "/workspace/elicit-vs-teach/geode-store/runs/evt-ts38tr-k7-n46416/model",
124
+ "protocol": "token-prefix prompts of few-shot composed texts (exemplars + complete query, blank-line separated), greedy EOS-stopped first-line, fixed slices of the frozen D_target_eval reporting block (question-disjoint from all training data by construction), exact_match + shared-set masked NLL; evidence only, no pass bar"
125
+ }
126
+ },
127
+ "init_from": "/workspace/elicit-vs-teach/geode-store/runs/evt-ts38tr-k7-parent/model",
128
+ "masking_config_hash": "fbfde0ef44503bcf9f38a8494a8acec4d0ba56f20ea324e56263fe3d064eed9d",
129
+ "data_order_hash": "946b5d02a8f9260fec00ce68a4db42a12f16966f6b49f685269382ae7b4b6ace",
130
+ "n_examples": 46416,
131
+ "eval_data": {
132
+ "file": "D_algo_eval_bare.parquet",
133
+ "order_hash": "e419baa213bbe07dfeb50f46fe17b464056cd18c2a7302238a66682d7c594631",
134
+ "stop_rows": 2048
135
+ },
136
+ "target_result": {
137
+ "final_step": 880,
138
+ "stop_reason": "converged",
139
+ "best_val_nats": 0.018170919106847358,
140
+ "min_val_nats": 0.018170919106847358,
141
+ "edl_epoch1_nats": 66726.18012240842,
142
+ "edl_per_label_token_nats": 0.2914074221758695,
143
+ "edl_per_example_nats": 1.4375685134955278,
144
+ "epoch1_examples": 46416
145
+ }
146
+ },
147
+ "masking_config_hash": "fbfde0ef44503bcf9f38a8494a8acec4d0ba56f20ea324e56263fe3d064eed9d",
148
+ "snapshots_taken": [
149
+ 1,
150
+ 2,
151
+ 3,
152
+ 4,
153
+ 5,
154
+ 6,
155
+ 7,
156
+ 8,
157
+ 11,
158
+ 15,
159
+ 20,
160
+ 27,
161
+ 36,
162
+ 49,
163
+ 66,
164
+ 89,
165
+ 120,
166
+ 162,
167
+ 219,
168
+ 296,
169
+ 400,
170
+ 541,
171
+ 731
172
+ ]
173
+ }
runs/evt-ts38tr-k7-n46416/model/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779f150d359b6f88a2ae1c23c725878d83ce5c3dcec9c11d53e691a85cf04589
3
+ size 48246976
runs/evt-ts38tr-k7-n46416/model/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2048,
15
+ "max_position_embeddings": 1024,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": null,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000.0,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "5.15.1",
30
+ "use_cache": true,
31
+ "vocab_size": 10000
32
+ }
runs/evt-ts38tr-k7-n46416/model/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.15.1",
8
+ "use_cache": true
9
+ }
runs/evt-ts38tr-k7-n46416/model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ae4fc2d75c7646ce14197896ab7cbd2a28feb97d9fd7a4bb8e411b9d03209d
3
+ size 202988000
runs/evt-ts38tr-k7-n46416/snapshots/base/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4dc9c39da933560bdfd1d6dd803236d8b746b9809f4a124a244751f46fff89
3
+ size 154740928
runs/evt-ts38tr-k7-n46416/snapshots/step_1/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19774d0777a60a1e083365b4f6ff2293c7c402f6d65a037a3a24ccee59a158a
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_11/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397b099e2a21f7e3d877ea3abf0c09e93c58d8669672892ec8186154e81a3446
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_120/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbd236329c44e012e9e7e58cdf77790c6e87768fa6b12e64772e5d47826a40a
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_15/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f05fb5784ddb4076219baadedfeef510d7110658c150c73ad574295acb59e4
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_162/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c8be61bee7e125123e3cd624e3cc7bc512acbedb6db74211509b2b3a707696
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_2/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106dc38eda10a538721035905b328b433818208cc4a1e6d79ca9ed89cb2109bd
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_20/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3622fd6dc7e765653938dbf48370ddc55fcf102cc27c62843a35a1ba7b2250e3
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_219/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78aea74795d97d610f7a799317ac5eb727f69313ea0428f4c6e96d98fec768c8
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_27/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7d6af91c941b485b39da6ee83c4ac5467ec5c024ca5331829d14d502ebec79
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_296/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f543e0beba89821823768f5babefde8f4de0829dd5423dfaf2053933854e00
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_3/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e7fbb51f99858fdf3ccb2e561d39ebf317d268ede34c15c2d4da2513e87fd9
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_36/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51b91f70529c8d6a9b5753bb3a9f20279f2af0016d13f5a7b4c51140405f665
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_4/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129d64d9a1fa4012ff5570d8afbbd09b125ea6a81096f6ff3059749c3b09dbaf
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_400/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f72c896cc875cf4faeace0e8c6aa84cbdd8dc3092de260b7078bfae8e7816c2
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_49/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cabc3ac873e64ce5e473072ae3966f4ca3af5d5c9899f8e79d3d9064b534236e
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_5/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd88bdaf20981f8da67b0a4372d1e87fe36df0aa9a1d9581dc0043ad32a29c9a
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_541/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635468fcf2105a8cac8232b4eda340fec13626b57aa21456d6eeadb5c4c8962e
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_6/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b07c161de45ea6ab882f79ba60a0f322c74504a630baea47256cfe927495bec
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_66/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5450e8c551e5ab548752eff9fc741c2498c35248f523df2641a2052cf7fba269
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_7/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7747deae3058f4e3aea6594b12c619f6739dcb64da180be8e776812a4f5f35ae
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_731/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed0d2a2b650d02c5647395eaf80b79edad5e853dc0349eaa7ee777fe3e79060
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_8/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c886cddf995e1730ec65320fbe33f6bfeeee74ff583732bb770069512d6d49
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/snapshots/step_89/adapter.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c63edb847f02b60c5199aea5ccfb0e90197b7ec6dcbac24f287891921321bf3
3
+ size 48246856
runs/evt-ts38tr-k7-n46416/train_log.jsonl ADDED
The diff for this file is too large to render. See raw diff