cutelemonlili commited on
Commit
141e283
·
verified ·
1 Parent(s): 8f70f49

Add files using upload-large-folder tool

Browse files
Files changed (1) hide show
  1. trainer_log.jsonl +284 -0
trainer_log.jsonl ADDED
@@ -0,0 +1,284 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 486, "loss": 0.3826, "lr": 9.999895536228031e-06, "epoch": 0.00411522633744856, "percentage": 0.21, "elapsed_time": "0:00:02", "remaining_time": "0:18:25"}
2
+ {"current_steps": 2, "total_steps": 486, "loss": 0.4082, "lr": 9.999582149277188e-06, "epoch": 0.00823045267489712, "percentage": 0.41, "elapsed_time": "0:00:05", "remaining_time": "0:21:18"}
3
+ {"current_steps": 3, "total_steps": 486, "loss": 0.4232, "lr": 9.999059852242508e-06, "epoch": 0.012345679012345678, "percentage": 0.62, "elapsed_time": "0:00:06", "remaining_time": "0:16:57"}
4
+ {"current_steps": 4, "total_steps": 486, "loss": 0.3567, "lr": 9.998328666948437e-06, "epoch": 0.01646090534979424, "percentage": 0.82, "elapsed_time": "0:00:07", "remaining_time": "0:14:43"}
5
+ {"current_steps": 5, "total_steps": 486, "loss": 0.3346, "lr": 9.997388623947927e-06, "epoch": 0.0205761316872428, "percentage": 1.03, "elapsed_time": "0:00:08", "remaining_time": "0:13:23"}
6
+ {"current_steps": 6, "total_steps": 486, "loss": 0.3472, "lr": 9.996239762521152e-06, "epoch": 0.024691358024691357, "percentage": 1.23, "elapsed_time": "0:00:09", "remaining_time": "0:12:30"}
7
+ {"current_steps": 7, "total_steps": 486, "loss": 0.3643, "lr": 9.994882130673869e-06, "epoch": 0.02880658436213992, "percentage": 1.44, "elapsed_time": "0:00:10", "remaining_time": "0:11:54"}
8
+ {"current_steps": 8, "total_steps": 486, "loss": 0.3465, "lr": 9.993315785135417e-06, "epoch": 0.03292181069958848, "percentage": 1.65, "elapsed_time": "0:00:11", "remaining_time": "0:11:26"}
9
+ {"current_steps": 9, "total_steps": 486, "loss": 0.33, "lr": 9.991540791356342e-06, "epoch": 0.037037037037037035, "percentage": 1.85, "elapsed_time": "0:00:12", "remaining_time": "0:11:03"}
10
+ {"current_steps": 10, "total_steps": 486, "loss": 0.3418, "lr": 9.989557223505661e-06, "epoch": 0.0411522633744856, "percentage": 2.06, "elapsed_time": "0:00:13", "remaining_time": "0:10:45"}
11
+ {"current_steps": 11, "total_steps": 486, "loss": 0.3775, "lr": 9.987365164467767e-06, "epoch": 0.04526748971193416, "percentage": 2.26, "elapsed_time": "0:00:14", "remaining_time": "0:10:29"}
12
+ {"current_steps": 12, "total_steps": 486, "loss": 0.3358, "lr": 9.98496470583896e-06, "epoch": 0.04938271604938271, "percentage": 2.47, "elapsed_time": "0:00:15", "remaining_time": "0:10:17"}
13
+ {"current_steps": 13, "total_steps": 486, "loss": 0.3573, "lr": 9.98235594792363e-06, "epoch": 0.053497942386831275, "percentage": 2.67, "elapsed_time": "0:00:16", "remaining_time": "0:10:05"}
14
+ {"current_steps": 14, "total_steps": 486, "loss": 0.3067, "lr": 9.979538999730047e-06, "epoch": 0.05761316872427984, "percentage": 2.88, "elapsed_time": "0:00:17", "remaining_time": "0:09:55"}
15
+ {"current_steps": 15, "total_steps": 486, "loss": 0.3186, "lr": 9.976513978965829e-06, "epoch": 0.06172839506172839, "percentage": 3.09, "elapsed_time": "0:00:18", "remaining_time": "0:09:47"}
16
+ {"current_steps": 16, "total_steps": 486, "loss": 0.3271, "lr": 9.973281012033009e-06, "epoch": 0.06584362139917696, "percentage": 3.29, "elapsed_time": "0:00:19", "remaining_time": "0:09:39"}
17
+ {"current_steps": 17, "total_steps": 486, "loss": 0.3474, "lr": 9.96984023402275e-06, "epoch": 0.06995884773662552, "percentage": 3.5, "elapsed_time": "0:00:20", "remaining_time": "0:09:32"}
18
+ {"current_steps": 18, "total_steps": 486, "loss": 0.3426, "lr": 9.966191788709716e-06, "epoch": 0.07407407407407407, "percentage": 3.7, "elapsed_time": "0:00:21", "remaining_time": "0:09:26"}
19
+ {"current_steps": 19, "total_steps": 486, "loss": 0.3486, "lr": 9.962335828546049e-06, "epoch": 0.07818930041152264, "percentage": 3.91, "elapsed_time": "0:00:22", "remaining_time": "0:09:20"}
20
+ {"current_steps": 20, "total_steps": 486, "loss": 0.3423, "lr": 9.958272514655006e-06, "epoch": 0.0823045267489712, "percentage": 4.12, "elapsed_time": "0:00:23", "remaining_time": "0:09:16"}
21
+ {"current_steps": 21, "total_steps": 486, "loss": 0.3451, "lr": 9.954002016824226e-06, "epoch": 0.08641975308641975, "percentage": 4.32, "elapsed_time": "0:00:24", "remaining_time": "0:09:11"}
22
+ {"current_steps": 22, "total_steps": 486, "loss": 0.3653, "lr": 9.949524513498636e-06, "epoch": 0.09053497942386832, "percentage": 4.53, "elapsed_time": "0:00:25", "remaining_time": "0:09:06"}
23
+ {"current_steps": 23, "total_steps": 486, "loss": 0.3496, "lr": 9.944840191772987e-06, "epoch": 0.09465020576131687, "percentage": 4.73, "elapsed_time": "0:00:26", "remaining_time": "0:09:02"}
24
+ {"current_steps": 24, "total_steps": 486, "loss": 0.3305, "lr": 9.939949247384046e-06, "epoch": 0.09876543209876543, "percentage": 4.94, "elapsed_time": "0:00:27", "remaining_time": "0:08:58"}
25
+ {"current_steps": 25, "total_steps": 486, "loss": 0.3905, "lr": 9.934851884702415e-06, "epoch": 0.102880658436214, "percentage": 5.14, "elapsed_time": "0:00:29", "remaining_time": "0:08:55"}
26
+ {"current_steps": 26, "total_steps": 486, "loss": 0.3255, "lr": 9.929548316723983e-06, "epoch": 0.10699588477366255, "percentage": 5.35, "elapsed_time": "0:00:30", "remaining_time": "0:08:51"}
27
+ {"current_steps": 27, "total_steps": 486, "loss": 0.3122, "lr": 9.924038765061042e-06, "epoch": 0.1111111111111111, "percentage": 5.56, "elapsed_time": "0:00:31", "remaining_time": "0:08:48"}
28
+ {"current_steps": 28, "total_steps": 486, "loss": 0.355, "lr": 9.918323459933006e-06, "epoch": 0.11522633744855967, "percentage": 5.76, "elapsed_time": "0:00:32", "remaining_time": "0:08:45"}
29
+ {"current_steps": 29, "total_steps": 486, "loss": 0.3414, "lr": 9.912402640156812e-06, "epoch": 0.11934156378600823, "percentage": 5.97, "elapsed_time": "0:00:33", "remaining_time": "0:08:42"}
30
+ {"current_steps": 30, "total_steps": 486, "loss": 0.3337, "lr": 9.906276553136924e-06, "epoch": 0.12345679012345678, "percentage": 6.17, "elapsed_time": "0:00:34", "remaining_time": "0:08:39"}
31
+ {"current_steps": 31, "total_steps": 486, "loss": 0.3257, "lr": 9.899945454855007e-06, "epoch": 0.12757201646090535, "percentage": 6.38, "elapsed_time": "0:00:35", "remaining_time": "0:08:36"}
32
+ {"current_steps": 32, "total_steps": 486, "loss": 0.3093, "lr": 9.893409609859221e-06, "epoch": 0.13168724279835392, "percentage": 6.58, "elapsed_time": "0:00:36", "remaining_time": "0:08:34"}
33
+ {"current_steps": 33, "total_steps": 486, "loss": 0.3434, "lr": 9.886669291253178e-06, "epoch": 0.13580246913580246, "percentage": 6.79, "elapsed_time": "0:00:37", "remaining_time": "0:08:31"}
34
+ {"current_steps": 34, "total_steps": 486, "loss": 0.3045, "lr": 9.879724780684518e-06, "epoch": 0.13991769547325103, "percentage": 7.0, "elapsed_time": "0:00:38", "remaining_time": "0:08:29"}
35
+ {"current_steps": 35, "total_steps": 486, "loss": 0.3123, "lr": 9.872576368333152e-06, "epoch": 0.1440329218106996, "percentage": 7.2, "elapsed_time": "0:00:39", "remaining_time": "0:08:26"}
36
+ {"current_steps": 36, "total_steps": 486, "loss": 0.3512, "lr": 9.86522435289912e-06, "epoch": 0.14814814814814814, "percentage": 7.41, "elapsed_time": "0:00:40", "remaining_time": "0:08:24"}
37
+ {"current_steps": 37, "total_steps": 486, "loss": 0.3361, "lr": 9.857669041590135e-06, "epoch": 0.1522633744855967, "percentage": 7.61, "elapsed_time": "0:00:41", "remaining_time": "0:08:22"}
38
+ {"current_steps": 38, "total_steps": 486, "loss": 0.3122, "lr": 9.849910750108718e-06, "epoch": 0.15637860082304528, "percentage": 7.82, "elapsed_time": "0:00:42", "remaining_time": "0:08:20"}
39
+ {"current_steps": 39, "total_steps": 486, "loss": 0.3774, "lr": 9.841949802639031e-06, "epoch": 0.16049382716049382, "percentage": 8.02, "elapsed_time": "0:00:43", "remaining_time": "0:08:18"}
40
+ {"current_steps": 40, "total_steps": 486, "loss": 0.3487, "lr": 9.833786531833311e-06, "epoch": 0.1646090534979424, "percentage": 8.23, "elapsed_time": "0:00:44", "remaining_time": "0:08:16"}
41
+ {"current_steps": 41, "total_steps": 486, "loss": 0.293, "lr": 9.825421278797984e-06, "epoch": 0.16872427983539096, "percentage": 8.44, "elapsed_time": "0:00:45", "remaining_time": "0:08:14"}
42
+ {"current_steps": 42, "total_steps": 486, "loss": 0.394, "lr": 9.816854393079402e-06, "epoch": 0.1728395061728395, "percentage": 8.64, "elapsed_time": "0:00:46", "remaining_time": "0:08:12"}
43
+ {"current_steps": 43, "total_steps": 486, "loss": 0.3367, "lr": 9.808086232649246e-06, "epoch": 0.17695473251028807, "percentage": 8.85, "elapsed_time": "0:00:47", "remaining_time": "0:08:10"}
44
+ {"current_steps": 44, "total_steps": 486, "loss": 0.3205, "lr": 9.79911716388956e-06, "epoch": 0.18106995884773663, "percentage": 9.05, "elapsed_time": "0:00:48", "remaining_time": "0:08:08"}
45
+ {"current_steps": 45, "total_steps": 486, "loss": 0.3294, "lr": 9.789947561577445e-06, "epoch": 0.18518518518518517, "percentage": 9.26, "elapsed_time": "0:00:49", "remaining_time": "0:08:07"}
46
+ {"current_steps": 46, "total_steps": 486, "loss": 0.3199, "lr": 9.7805778088694e-06, "epoch": 0.18930041152263374, "percentage": 9.47, "elapsed_time": "0:00:50", "remaining_time": "0:08:05"}
47
+ {"current_steps": 47, "total_steps": 486, "loss": 0.3041, "lr": 9.771008297285307e-06, "epoch": 0.1934156378600823, "percentage": 9.67, "elapsed_time": "0:00:51", "remaining_time": "0:08:03"}
48
+ {"current_steps": 48, "total_steps": 486, "loss": 0.3562, "lr": 9.761239426692077e-06, "epoch": 0.19753086419753085, "percentage": 9.88, "elapsed_time": "0:00:52", "remaining_time": "0:08:01"}
49
+ {"current_steps": 49, "total_steps": 486, "loss": 0.3499, "lr": 9.75127160528694e-06, "epoch": 0.20164609053497942, "percentage": 10.08, "elapsed_time": "0:00:53", "remaining_time": "0:08:00"}
50
+ {"current_steps": 50, "total_steps": 486, "loss": 0.3375, "lr": 9.741105249580383e-06, "epoch": 0.205761316872428, "percentage": 10.29, "elapsed_time": "0:00:54", "remaining_time": "0:07:58"}
51
+ {"current_steps": 51, "total_steps": 486, "loss": 0.3606, "lr": 9.730740784378755e-06, "epoch": 0.20987654320987653, "percentage": 10.49, "elapsed_time": "0:00:55", "remaining_time": "0:07:56"}
52
+ {"current_steps": 52, "total_steps": 486, "loss": 0.2857, "lr": 9.7201786427665e-06, "epoch": 0.2139917695473251, "percentage": 10.7, "elapsed_time": "0:00:56", "remaining_time": "0:07:55"}
53
+ {"current_steps": 53, "total_steps": 486, "loss": 0.3603, "lr": 9.709419266088086e-06, "epoch": 0.21810699588477367, "percentage": 10.91, "elapsed_time": "0:00:57", "remaining_time": "0:07:53"}
54
+ {"current_steps": 54, "total_steps": 486, "loss": 0.3285, "lr": 9.698463103929542e-06, "epoch": 0.2222222222222222, "percentage": 11.11, "elapsed_time": "0:00:59", "remaining_time": "0:07:52"}
55
+ {"current_steps": 55, "total_steps": 486, "loss": 0.4396, "lr": 9.687310614099676e-06, "epoch": 0.22633744855967078, "percentage": 11.32, "elapsed_time": "0:01:00", "remaining_time": "0:07:50"}
56
+ {"current_steps": 56, "total_steps": 486, "loss": 0.3029, "lr": 9.67596226261095e-06, "epoch": 0.23045267489711935, "percentage": 11.52, "elapsed_time": "0:01:01", "remaining_time": "0:07:49"}
57
+ {"current_steps": 57, "total_steps": 486, "loss": 0.3712, "lr": 9.664418523660004e-06, "epoch": 0.2345679012345679, "percentage": 11.73, "elapsed_time": "0:01:02", "remaining_time": "0:07:47"}
58
+ {"current_steps": 58, "total_steps": 486, "loss": 0.365, "lr": 9.652679879607843e-06, "epoch": 0.23868312757201646, "percentage": 11.93, "elapsed_time": "0:01:03", "remaining_time": "0:07:46"}
59
+ {"current_steps": 59, "total_steps": 486, "loss": 0.3312, "lr": 9.640746820959684e-06, "epoch": 0.24279835390946503, "percentage": 12.14, "elapsed_time": "0:01:04", "remaining_time": "0:07:44"}
60
+ {"current_steps": 60, "total_steps": 486, "loss": 0.295, "lr": 9.628619846344453e-06, "epoch": 0.24691358024691357, "percentage": 12.35, "elapsed_time": "0:01:05", "remaining_time": "0:07:43"}
61
+ {"current_steps": 61, "total_steps": 486, "loss": 0.2974, "lr": 9.616299462493952e-06, "epoch": 0.25102880658436216, "percentage": 12.55, "elapsed_time": "0:01:06", "remaining_time": "0:07:41"}
62
+ {"current_steps": 62, "total_steps": 486, "loss": 0.3588, "lr": 9.603786184221693e-06, "epoch": 0.2551440329218107, "percentage": 12.76, "elapsed_time": "0:01:07", "remaining_time": "0:07:40"}
63
+ {"current_steps": 63, "total_steps": 486, "loss": 0.33, "lr": 9.591080534401371e-06, "epoch": 0.25925925925925924, "percentage": 12.96, "elapsed_time": "0:01:08", "remaining_time": "0:07:38"}
64
+ {"current_steps": 64, "total_steps": 486, "loss": 0.2913, "lr": 9.578183043945031e-06, "epoch": 0.26337448559670784, "percentage": 13.17, "elapsed_time": "0:01:09", "remaining_time": "0:07:37"}
65
+ {"current_steps": 65, "total_steps": 486, "loss": 0.3307, "lr": 9.565094251780872e-06, "epoch": 0.2674897119341564, "percentage": 13.37, "elapsed_time": "0:01:10", "remaining_time": "0:07:35"}
66
+ {"current_steps": 66, "total_steps": 486, "loss": 0.3782, "lr": 9.551814704830734e-06, "epoch": 0.2716049382716049, "percentage": 13.58, "elapsed_time": "0:01:11", "remaining_time": "0:07:34"}
67
+ {"current_steps": 67, "total_steps": 486, "loss": 0.2911, "lr": 9.538344957987245e-06, "epoch": 0.2757201646090535, "percentage": 13.79, "elapsed_time": "0:01:12", "remaining_time": "0:07:33"}
68
+ {"current_steps": 68, "total_steps": 486, "loss": 0.3239, "lr": 9.524685574090627e-06, "epoch": 0.27983539094650206, "percentage": 13.99, "elapsed_time": "0:01:13", "remaining_time": "0:07:31"}
69
+ {"current_steps": 69, "total_steps": 486, "loss": 0.3176, "lr": 9.51083712390519e-06, "epoch": 0.2839506172839506, "percentage": 14.2, "elapsed_time": "0:01:14", "remaining_time": "0:07:30"}
70
+ {"current_steps": 70, "total_steps": 486, "loss": 0.3445, "lr": 9.496800186095466e-06, "epoch": 0.2880658436213992, "percentage": 14.4, "elapsed_time": "0:01:15", "remaining_time": "0:07:29"}
71
+ {"current_steps": 71, "total_steps": 486, "loss": 0.2971, "lr": 9.482575347202047e-06, "epoch": 0.29218106995884774, "percentage": 14.61, "elapsed_time": "0:01:16", "remaining_time": "0:07:27"}
72
+ {"current_steps": 72, "total_steps": 486, "loss": 0.3514, "lr": 9.468163201617063e-06, "epoch": 0.2962962962962963, "percentage": 14.81, "elapsed_time": "0:01:17", "remaining_time": "0:07:26"}
73
+ {"current_steps": 73, "total_steps": 486, "loss": 0.354, "lr": 9.453564351559348e-06, "epoch": 0.3004115226337449, "percentage": 15.02, "elapsed_time": "0:01:18", "remaining_time": "0:07:25"}
74
+ {"current_steps": 74, "total_steps": 486, "loss": 0.3142, "lr": 9.438779407049282e-06, "epoch": 0.3045267489711934, "percentage": 15.23, "elapsed_time": "0:01:19", "remaining_time": "0:07:23"}
75
+ {"current_steps": 75, "total_steps": 486, "loss": 0.3732, "lr": 9.423808985883289e-06, "epoch": 0.30864197530864196, "percentage": 15.43, "elapsed_time": "0:01:20", "remaining_time": "0:07:22"}
76
+ {"current_steps": 76, "total_steps": 486, "loss": 0.357, "lr": 9.40865371360804e-06, "epoch": 0.31275720164609055, "percentage": 15.64, "elapsed_time": "0:01:21", "remaining_time": "0:07:21"}
77
+ {"current_steps": 77, "total_steps": 486, "loss": 0.3069, "lr": 9.393314223494297e-06, "epoch": 0.3168724279835391, "percentage": 15.84, "elapsed_time": "0:01:22", "remaining_time": "0:07:19"}
78
+ {"current_steps": 78, "total_steps": 486, "loss": 0.2709, "lr": 9.377791156510456e-06, "epoch": 0.32098765432098764, "percentage": 16.05, "elapsed_time": "0:01:23", "remaining_time": "0:07:18"}
79
+ {"current_steps": 79, "total_steps": 486, "loss": 0.3773, "lr": 9.362085161295768e-06, "epoch": 0.32510288065843623, "percentage": 16.26, "elapsed_time": "0:01:24", "remaining_time": "0:07:17"}
80
+ {"current_steps": 80, "total_steps": 486, "loss": 0.3006, "lr": 9.346196894133239e-06, "epoch": 0.3292181069958848, "percentage": 16.46, "elapsed_time": "0:01:25", "remaining_time": "0:07:15"}
81
+ {"current_steps": 81, "total_steps": 486, "loss": 0.3392, "lr": 9.330127018922195e-06, "epoch": 0.3333333333333333, "percentage": 16.67, "elapsed_time": "0:01:26", "remaining_time": "0:07:14"}
82
+ {"current_steps": 82, "total_steps": 486, "loss": 0.2816, "lr": 9.313876207150544e-06, "epoch": 0.3374485596707819, "percentage": 16.87, "elapsed_time": "0:01:27", "remaining_time": "0:07:13"}
83
+ {"current_steps": 83, "total_steps": 486, "loss": 0.3327, "lr": 9.297445137866726e-06, "epoch": 0.34156378600823045, "percentage": 17.08, "elapsed_time": "0:01:28", "remaining_time": "0:07:12"}
84
+ {"current_steps": 84, "total_steps": 486, "loss": 0.2917, "lr": 9.280834497651334e-06, "epoch": 0.345679012345679, "percentage": 17.28, "elapsed_time": "0:01:30", "remaining_time": "0:07:10"}
85
+ {"current_steps": 85, "total_steps": 486, "loss": 0.3083, "lr": 9.264044980588415e-06, "epoch": 0.3497942386831276, "percentage": 17.49, "elapsed_time": "0:01:31", "remaining_time": "0:07:09"}
86
+ {"current_steps": 86, "total_steps": 486, "loss": 0.3112, "lr": 9.247077288236488e-06, "epoch": 0.35390946502057613, "percentage": 17.7, "elapsed_time": "0:01:32", "remaining_time": "0:07:08"}
87
+ {"current_steps": 87, "total_steps": 486, "loss": 0.3161, "lr": 9.229932129599206e-06, "epoch": 0.35802469135802467, "percentage": 17.9, "elapsed_time": "0:01:33", "remaining_time": "0:07:07"}
88
+ {"current_steps": 88, "total_steps": 486, "loss": 0.3749, "lr": 9.212610221095748e-06, "epoch": 0.36213991769547327, "percentage": 18.11, "elapsed_time": "0:01:34", "remaining_time": "0:07:05"}
89
+ {"current_steps": 89, "total_steps": 486, "loss": 0.3287, "lr": 9.195112286530874e-06, "epoch": 0.3662551440329218, "percentage": 18.31, "elapsed_time": "0:01:35", "remaining_time": "0:07:04"}
90
+ {"current_steps": 90, "total_steps": 486, "loss": 0.3444, "lr": 9.177439057064684e-06, "epoch": 0.37037037037037035, "percentage": 18.52, "elapsed_time": "0:01:36", "remaining_time": "0:07:03"}
91
+ {"current_steps": 91, "total_steps": 486, "loss": 0.3209, "lr": 9.159591271182058e-06, "epoch": 0.37448559670781895, "percentage": 18.72, "elapsed_time": "0:01:37", "remaining_time": "0:07:02"}
92
+ {"current_steps": 92, "total_steps": 486, "loss": 0.3648, "lr": 9.141569674661816e-06, "epoch": 0.3786008230452675, "percentage": 18.93, "elapsed_time": "0:01:38", "remaining_time": "0:07:01"}
93
+ {"current_steps": 93, "total_steps": 486, "loss": 0.3113, "lr": 9.123375020545534e-06, "epoch": 0.38271604938271603, "percentage": 19.14, "elapsed_time": "0:01:39", "remaining_time": "0:06:59"}
94
+ {"current_steps": 94, "total_steps": 486, "loss": 0.3704, "lr": 9.105008069106093e-06, "epoch": 0.3868312757201646, "percentage": 19.34, "elapsed_time": "0:01:40", "remaining_time": "0:06:58"}
95
+ {"current_steps": 95, "total_steps": 486, "loss": 0.3463, "lr": 9.086469587815904e-06, "epoch": 0.39094650205761317, "percentage": 19.55, "elapsed_time": "0:01:41", "remaining_time": "0:06:57"}
96
+ {"current_steps": 96, "total_steps": 486, "loss": 0.3043, "lr": 9.067760351314838e-06, "epoch": 0.3950617283950617, "percentage": 19.75, "elapsed_time": "0:01:42", "remaining_time": "0:06:56"}
97
+ {"current_steps": 97, "total_steps": 486, "loss": 0.3411, "lr": 9.048881141377863e-06, "epoch": 0.3991769547325103, "percentage": 19.96, "elapsed_time": "0:01:43", "remaining_time": "0:06:55"}
98
+ {"current_steps": 98, "total_steps": 486, "loss": 0.316, "lr": 9.029832746882372e-06, "epoch": 0.40329218106995884, "percentage": 20.16, "elapsed_time": "0:01:44", "remaining_time": "0:06:53"}
99
+ {"current_steps": 99, "total_steps": 486, "loss": 0.2878, "lr": 9.01061596377522e-06, "epoch": 0.4074074074074074, "percentage": 20.37, "elapsed_time": "0:01:45", "remaining_time": "0:06:52"}
100
+ {"current_steps": 100, "total_steps": 486, "loss": 0.3237, "lr": 8.991231595039464e-06, "epoch": 0.411522633744856, "percentage": 20.58, "elapsed_time": "0:01:46", "remaining_time": "0:06:51"}
101
+ {"current_steps": 101, "total_steps": 486, "loss": 0.328, "lr": 8.97168045066082e-06, "epoch": 0.4156378600823045, "percentage": 20.78, "elapsed_time": "0:01:47", "remaining_time": "0:06:50"}
102
+ {"current_steps": 102, "total_steps": 486, "loss": 0.2786, "lr": 8.951963347593797e-06, "epoch": 0.41975308641975306, "percentage": 20.99, "elapsed_time": "0:01:48", "remaining_time": "0:06:49"}
103
+ {"current_steps": 103, "total_steps": 486, "loss": 0.3432, "lr": 8.932081109727582e-06, "epoch": 0.42386831275720166, "percentage": 21.19, "elapsed_time": "0:01:49", "remaining_time": "0:06:48"}
104
+ {"current_steps": 104, "total_steps": 486, "loss": 0.2973, "lr": 8.9120345678516e-06, "epoch": 0.4279835390946502, "percentage": 21.4, "elapsed_time": "0:01:50", "remaining_time": "0:06:46"}
105
+ {"current_steps": 105, "total_steps": 486, "loss": 0.4042, "lr": 8.891824559620801e-06, "epoch": 0.43209876543209874, "percentage": 21.6, "elapsed_time": "0:01:51", "remaining_time": "0:06:45"}
106
+ {"current_steps": 106, "total_steps": 486, "loss": 0.4097, "lr": 8.871451929520662e-06, "epoch": 0.43621399176954734, "percentage": 21.81, "elapsed_time": "0:01:52", "remaining_time": "0:06:44"}
107
+ {"current_steps": 107, "total_steps": 486, "loss": 0.3535, "lr": 8.8509175288319e-06, "epoch": 0.4403292181069959, "percentage": 22.02, "elapsed_time": "0:01:53", "remaining_time": "0:06:43"}
108
+ {"current_steps": 108, "total_steps": 486, "loss": 0.3688, "lr": 8.83022221559489e-06, "epoch": 0.4444444444444444, "percentage": 22.22, "elapsed_time": "0:01:54", "remaining_time": "0:06:42"}
109
+ {"current_steps": 109, "total_steps": 486, "loss": 0.3561, "lr": 8.80936685457383e-06, "epoch": 0.448559670781893, "percentage": 22.43, "elapsed_time": "0:01:55", "remaining_time": "0:06:40"}
110
+ {"current_steps": 110, "total_steps": 486, "loss": 0.2863, "lr": 8.78835231722059e-06, "epoch": 0.45267489711934156, "percentage": 22.63, "elapsed_time": "0:01:56", "remaining_time": "0:06:39"}
111
+ {"current_steps": 111, "total_steps": 486, "loss": 0.3346, "lr": 8.767179481638303e-06, "epoch": 0.4567901234567901, "percentage": 22.84, "elapsed_time": "0:01:57", "remaining_time": "0:06:38"}
112
+ {"current_steps": 112, "total_steps": 486, "loss": 0.3197, "lr": 8.74584923254468e-06, "epoch": 0.4609053497942387, "percentage": 23.05, "elapsed_time": "0:01:59", "remaining_time": "0:06:37"}
113
+ {"current_steps": 113, "total_steps": 486, "loss": 0.355, "lr": 8.72436246123503e-06, "epoch": 0.46502057613168724, "percentage": 23.25, "elapsed_time": "0:02:00", "remaining_time": "0:06:36"}
114
+ {"current_steps": 114, "total_steps": 486, "loss": 0.3307, "lr": 8.702720065545024e-06, "epoch": 0.4691358024691358, "percentage": 23.46, "elapsed_time": "0:02:01", "remaining_time": "0:06:35"}
115
+ {"current_steps": 115, "total_steps": 486, "loss": 0.3741, "lr": 8.680922949813177e-06, "epoch": 0.4732510288065844, "percentage": 23.66, "elapsed_time": "0:02:02", "remaining_time": "0:06:33"}
116
+ {"current_steps": 116, "total_steps": 486, "loss": 0.2929, "lr": 8.658972024843063e-06, "epoch": 0.4773662551440329, "percentage": 23.87, "elapsed_time": "0:02:03", "remaining_time": "0:06:32"}
117
+ {"current_steps": 117, "total_steps": 486, "loss": 0.3424, "lr": 8.636868207865244e-06, "epoch": 0.48148148148148145, "percentage": 24.07, "elapsed_time": "0:02:04", "remaining_time": "0:06:31"}
118
+ {"current_steps": 118, "total_steps": 486, "loss": 0.3524, "lr": 8.614612422498965e-06, "epoch": 0.48559670781893005, "percentage": 24.28, "elapsed_time": "0:02:05", "remaining_time": "0:06:30"}
119
+ {"current_steps": 119, "total_steps": 486, "loss": 0.3377, "lr": 8.592205598713539e-06, "epoch": 0.4897119341563786, "percentage": 24.49, "elapsed_time": "0:02:06", "remaining_time": "0:06:29"}
120
+ {"current_steps": 120, "total_steps": 486, "loss": 0.2865, "lr": 8.569648672789496e-06, "epoch": 0.49382716049382713, "percentage": 24.69, "elapsed_time": "0:02:07", "remaining_time": "0:06:28"}
121
+ {"current_steps": 121, "total_steps": 486, "loss": 0.3489, "lr": 8.546942587279465e-06, "epoch": 0.49794238683127573, "percentage": 24.9, "elapsed_time": "0:02:08", "remaining_time": "0:06:27"}
122
+ {"current_steps": 122, "total_steps": 486, "loss": 0.3303, "lr": 8.524088290968781e-06, "epoch": 0.5020576131687243, "percentage": 25.1, "elapsed_time": "0:02:09", "remaining_time": "0:06:25"}
123
+ {"current_steps": 123, "total_steps": 486, "loss": 0.3468, "lr": 8.501086738835843e-06, "epoch": 0.5061728395061729, "percentage": 25.31, "elapsed_time": "0:02:10", "remaining_time": "0:06:24"}
124
+ {"current_steps": 124, "total_steps": 486, "loss": 0.3352, "lr": 8.477938892012209e-06, "epoch": 0.5102880658436214, "percentage": 25.51, "elapsed_time": "0:02:11", "remaining_time": "0:06:23"}
125
+ {"current_steps": 125, "total_steps": 486, "loss": 0.3068, "lr": 8.45464571774244e-06, "epoch": 0.51440329218107, "percentage": 25.72, "elapsed_time": "0:02:12", "remaining_time": "0:06:22"}
126
+ {"current_steps": 126, "total_steps": 486, "loss": 0.3243, "lr": 8.43120818934367e-06, "epoch": 0.5185185185185185, "percentage": 25.93, "elapsed_time": "0:02:13", "remaining_time": "0:06:21"}
127
+ {"current_steps": 127, "total_steps": 486, "loss": 0.3447, "lr": 8.407627286164948e-06, "epoch": 0.522633744855967, "percentage": 26.13, "elapsed_time": "0:02:14", "remaining_time": "0:06:20"}
128
+ {"current_steps": 128, "total_steps": 486, "loss": 0.2996, "lr": 8.38390399354631e-06, "epoch": 0.5267489711934157, "percentage": 26.34, "elapsed_time": "0:02:15", "remaining_time": "0:06:19"}
129
+ {"current_steps": 129, "total_steps": 486, "loss": 0.2991, "lr": 8.360039302777614e-06, "epoch": 0.5308641975308642, "percentage": 26.54, "elapsed_time": "0:02:16", "remaining_time": "0:06:18"}
130
+ {"current_steps": 130, "total_steps": 486, "loss": 0.3278, "lr": 8.336034211057098e-06, "epoch": 0.5349794238683128, "percentage": 26.75, "elapsed_time": "0:02:17", "remaining_time": "0:06:17"}
131
+ {"current_steps": 131, "total_steps": 486, "loss": 0.3401, "lr": 8.31188972144974e-06, "epoch": 0.5390946502057613, "percentage": 26.95, "elapsed_time": "0:02:18", "remaining_time": "0:06:15"}
132
+ {"current_steps": 132, "total_steps": 486, "loss": 0.2915, "lr": 8.28760684284532e-06, "epoch": 0.5432098765432098, "percentage": 27.16, "elapsed_time": "0:02:19", "remaining_time": "0:06:14"}
133
+ {"current_steps": 133, "total_steps": 486, "loss": 0.321, "lr": 8.263186589916273e-06, "epoch": 0.5473251028806584, "percentage": 27.37, "elapsed_time": "0:02:20", "remaining_time": "0:06:13"}
134
+ {"current_steps": 134, "total_steps": 486, "loss": 0.3074, "lr": 8.238629983075296e-06, "epoch": 0.551440329218107, "percentage": 27.57, "elapsed_time": "0:02:21", "remaining_time": "0:06:12"}
135
+ {"current_steps": 135, "total_steps": 486, "loss": 0.2848, "lr": 8.213938048432697e-06, "epoch": 0.5555555555555556, "percentage": 27.78, "elapsed_time": "0:02:22", "remaining_time": "0:06:11"}
136
+ {"current_steps": 136, "total_steps": 486, "loss": 0.3681, "lr": 8.18911181775353e-06, "epoch": 0.5596707818930041, "percentage": 27.98, "elapsed_time": "0:02:23", "remaining_time": "0:06:10"}
137
+ {"current_steps": 137, "total_steps": 486, "loss": 0.3226, "lr": 8.164152328414476e-06, "epoch": 0.5637860082304527, "percentage": 28.19, "elapsed_time": "0:02:24", "remaining_time": "0:06:09"}
138
+ {"current_steps": 138, "total_steps": 486, "loss": 0.3232, "lr": 8.139060623360494e-06, "epoch": 0.5679012345679012, "percentage": 28.4, "elapsed_time": "0:02:25", "remaining_time": "0:06:08"}
139
+ {"current_steps": 139, "total_steps": 486, "loss": 0.3198, "lr": 8.113837751061246e-06, "epoch": 0.5720164609053497, "percentage": 28.6, "elapsed_time": "0:02:27", "remaining_time": "0:06:06"}
140
+ {"current_steps": 140, "total_steps": 486, "loss": 0.369, "lr": 8.088484765467286e-06, "epoch": 0.5761316872427984, "percentage": 28.81, "elapsed_time": "0:02:28", "remaining_time": "0:06:05"}
141
+ {"current_steps": 141, "total_steps": 486, "loss": 0.2912, "lr": 8.063002725966014e-06, "epoch": 0.5802469135802469, "percentage": 29.01, "elapsed_time": "0:02:29", "remaining_time": "0:06:04"}
142
+ {"current_steps": 142, "total_steps": 486, "loss": 0.3303, "lr": 8.037392697337418e-06, "epoch": 0.5843621399176955, "percentage": 29.22, "elapsed_time": "0:02:30", "remaining_time": "0:06:03"}
143
+ {"current_steps": 143, "total_steps": 486, "loss": 0.2999, "lr": 8.011655749709575e-06, "epoch": 0.588477366255144, "percentage": 29.42, "elapsed_time": "0:02:31", "remaining_time": "0:06:02"}
144
+ {"current_steps": 144, "total_steps": 486, "loss": 0.2942, "lr": 7.985792958513932e-06, "epoch": 0.5925925925925926, "percentage": 29.63, "elapsed_time": "0:02:32", "remaining_time": "0:06:01"}
145
+ {"current_steps": 145, "total_steps": 486, "loss": 0.3366, "lr": 7.95980540444038e-06, "epoch": 0.5967078189300411, "percentage": 29.84, "elapsed_time": "0:02:33", "remaining_time": "0:06:00"}
146
+ {"current_steps": 146, "total_steps": 486, "loss": 0.3288, "lr": 7.93369417339209e-06, "epoch": 0.6008230452674898, "percentage": 30.04, "elapsed_time": "0:02:34", "remaining_time": "0:05:59"}
147
+ {"current_steps": 147, "total_steps": 486, "loss": 0.3185, "lr": 7.907460356440133e-06, "epoch": 0.6049382716049383, "percentage": 30.25, "elapsed_time": "0:02:35", "remaining_time": "0:05:58"}
148
+ {"current_steps": 148, "total_steps": 486, "loss": 0.3125, "lr": 7.881105049777902e-06, "epoch": 0.6090534979423868, "percentage": 30.45, "elapsed_time": "0:02:36", "remaining_time": "0:05:57"}
149
+ {"current_steps": 149, "total_steps": 486, "loss": 0.32, "lr": 7.854629354675292e-06, "epoch": 0.6131687242798354, "percentage": 30.66, "elapsed_time": "0:02:37", "remaining_time": "0:05:55"}
150
+ {"current_steps": 150, "total_steps": 486, "loss": 0.3421, "lr": 7.828034377432694e-06, "epoch": 0.6172839506172839, "percentage": 30.86, "elapsed_time": "0:02:38", "remaining_time": "0:05:54"}
151
+ {"current_steps": 151, "total_steps": 486, "loss": 0.3322, "lr": 7.801321229334764e-06, "epoch": 0.6213991769547325, "percentage": 31.07, "elapsed_time": "0:02:39", "remaining_time": "0:05:53"}
152
+ {"current_steps": 152, "total_steps": 486, "loss": 0.3385, "lr": 7.774491026603985e-06, "epoch": 0.6255144032921811, "percentage": 31.28, "elapsed_time": "0:02:40", "remaining_time": "0:05:52"}
153
+ {"current_steps": 153, "total_steps": 486, "loss": 0.3493, "lr": 7.747544890354031e-06, "epoch": 0.6296296296296297, "percentage": 31.48, "elapsed_time": "0:02:41", "remaining_time": "0:05:51"}
154
+ {"current_steps": 154, "total_steps": 486, "loss": 0.2951, "lr": 7.720483946542913e-06, "epoch": 0.6337448559670782, "percentage": 31.69, "elapsed_time": "0:02:42", "remaining_time": "0:05:50"}
155
+ {"current_steps": 155, "total_steps": 486, "loss": 0.2996, "lr": 7.69330932592594e-06, "epoch": 0.6378600823045267, "percentage": 31.89, "elapsed_time": "0:02:43", "remaining_time": "0:05:49"}
156
+ {"current_steps": 156, "total_steps": 486, "loss": 0.369, "lr": 7.666022164008458e-06, "epoch": 0.6419753086419753, "percentage": 32.1, "elapsed_time": "0:02:44", "remaining_time": "0:05:48"}
157
+ {"current_steps": 157, "total_steps": 486, "loss": 0.3811, "lr": 7.638623600998409e-06, "epoch": 0.6460905349794238, "percentage": 32.3, "elapsed_time": "0:02:45", "remaining_time": "0:05:47"}
158
+ {"current_steps": 158, "total_steps": 486, "loss": 0.3037, "lr": 7.6111147817586925e-06, "epoch": 0.6502057613168725, "percentage": 32.51, "elapsed_time": "0:02:46", "remaining_time": "0:05:46"}
159
+ {"current_steps": 159, "total_steps": 486, "loss": 0.2861, "lr": 7.5834968557593155e-06, "epoch": 0.654320987654321, "percentage": 32.72, "elapsed_time": "0:02:47", "remaining_time": "0:05:44"}
160
+ {"current_steps": 160, "total_steps": 486, "loss": 0.2861, "lr": 7.5557709770293664e-06, "epoch": 0.6584362139917695, "percentage": 32.92, "elapsed_time": "0:02:48", "remaining_time": "0:05:43"}
161
+ {"current_steps": 161, "total_steps": 486, "loss": 0.3044, "lr": 7.527938304108795e-06, "epoch": 0.6625514403292181, "percentage": 33.13, "elapsed_time": "0:02:49", "remaining_time": "0:05:42"}
162
+ {"current_steps": 162, "total_steps": 486, "loss": 0.3352, "lr": 7.500000000000001e-06, "epoch": 0.6666666666666666, "percentage": 33.33, "elapsed_time": "0:02:50", "remaining_time": "0:05:41"}
163
+ {"current_steps": 163, "total_steps": 486, "loss": 0.3581, "lr": 7.471957232119235e-06, "epoch": 0.6707818930041153, "percentage": 33.54, "elapsed_time": "0:02:51", "remaining_time": "0:05:40"}
164
+ {"current_steps": 164, "total_steps": 486, "loss": 0.2877, "lr": 7.443811172247822e-06, "epoch": 0.6748971193415638, "percentage": 33.74, "elapsed_time": "0:02:52", "remaining_time": "0:05:39"}
165
+ {"current_steps": 165, "total_steps": 486, "loss": 0.3079, "lr": 7.415562996483193e-06, "epoch": 0.6790123456790124, "percentage": 33.95, "elapsed_time": "0:02:53", "remaining_time": "0:05:38"}
166
+ {"current_steps": 166, "total_steps": 486, "loss": 0.3054, "lr": 7.387213885189746e-06, "epoch": 0.6831275720164609, "percentage": 34.16, "elapsed_time": "0:02:54", "remaining_time": "0:05:37"}
167
+ {"current_steps": 167, "total_steps": 486, "loss": 0.3301, "lr": 7.358765022949519e-06, "epoch": 0.6872427983539094, "percentage": 34.36, "elapsed_time": "0:02:56", "remaining_time": "0:05:36"}
168
+ {"current_steps": 168, "total_steps": 486, "loss": 0.3288, "lr": 7.330217598512696e-06, "epoch": 0.691358024691358, "percentage": 34.57, "elapsed_time": "0:02:57", "remaining_time": "0:05:35"}
169
+ {"current_steps": 169, "total_steps": 486, "loss": 0.3415, "lr": 7.30157280474793e-06, "epoch": 0.6954732510288066, "percentage": 34.77, "elapsed_time": "0:02:58", "remaining_time": "0:05:34"}
170
+ {"current_steps": 170, "total_steps": 486, "loss": 0.3468, "lr": 7.2728318385925035e-06, "epoch": 0.6995884773662552, "percentage": 34.98, "elapsed_time": "0:02:59", "remaining_time": "0:05:33"}
171
+ {"current_steps": 171, "total_steps": 486, "loss": 0.3362, "lr": 7.243995901002312e-06, "epoch": 0.7037037037037037, "percentage": 35.19, "elapsed_time": "0:03:00", "remaining_time": "0:05:31"}
172
+ {"current_steps": 172, "total_steps": 486, "loss": 0.2603, "lr": 7.215066196901676e-06, "epoch": 0.7078189300411523, "percentage": 35.39, "elapsed_time": "0:03:01", "remaining_time": "0:05:30"}
173
+ {"current_steps": 173, "total_steps": 486, "loss": 0.3083, "lr": 7.186043935133005e-06, "epoch": 0.7119341563786008, "percentage": 35.6, "elapsed_time": "0:03:02", "remaining_time": "0:05:29"}
174
+ {"current_steps": 174, "total_steps": 486, "loss": 0.319, "lr": 7.156930328406268e-06, "epoch": 0.7160493827160493, "percentage": 35.8, "elapsed_time": "0:03:03", "remaining_time": "0:05:28"}
175
+ {"current_steps": 175, "total_steps": 486, "loss": 0.3104, "lr": 7.127726593248337e-06, "epoch": 0.720164609053498, "percentage": 36.01, "elapsed_time": "0:03:04", "remaining_time": "0:05:27"}
176
+ {"current_steps": 176, "total_steps": 486, "loss": 0.3261, "lr": 7.098433949952146e-06, "epoch": 0.7242798353909465, "percentage": 36.21, "elapsed_time": "0:03:05", "remaining_time": "0:05:26"}
177
+ {"current_steps": 177, "total_steps": 486, "loss": 0.3117, "lr": 7.069053622525697e-06, "epoch": 0.7283950617283951, "percentage": 36.42, "elapsed_time": "0:03:06", "remaining_time": "0:05:25"}
178
+ {"current_steps": 178, "total_steps": 486, "loss": 0.2716, "lr": 7.039586838640918e-06, "epoch": 0.7325102880658436, "percentage": 36.63, "elapsed_time": "0:03:07", "remaining_time": "0:05:24"}
179
+ {"current_steps": 179, "total_steps": 486, "loss": 0.3108, "lr": 7.0100348295823706e-06, "epoch": 0.7366255144032922, "percentage": 36.83, "elapsed_time": "0:03:08", "remaining_time": "0:05:23"}
180
+ {"current_steps": 180, "total_steps": 486, "loss": 0.36, "lr": 6.980398830195785e-06, "epoch": 0.7407407407407407, "percentage": 37.04, "elapsed_time": "0:03:09", "remaining_time": "0:05:22"}
181
+ {"current_steps": 181, "total_steps": 486, "loss": 0.342, "lr": 6.950680078836475e-06, "epoch": 0.7448559670781894, "percentage": 37.24, "elapsed_time": "0:03:10", "remaining_time": "0:05:21"}
182
+ {"current_steps": 182, "total_steps": 486, "loss": 0.3111, "lr": 6.920879817317588e-06, "epoch": 0.7489711934156379, "percentage": 37.45, "elapsed_time": "0:03:11", "remaining_time": "0:05:19"}
183
+ {"current_steps": 183, "total_steps": 486, "loss": 0.3305, "lr": 6.890999290858213e-06, "epoch": 0.7530864197530864, "percentage": 37.65, "elapsed_time": "0:03:12", "remaining_time": "0:05:18"}
184
+ {"current_steps": 184, "total_steps": 486, "loss": 0.3092, "lr": 6.861039748031351e-06, "epoch": 0.757201646090535, "percentage": 37.86, "elapsed_time": "0:03:13", "remaining_time": "0:05:17"}
185
+ {"current_steps": 185, "total_steps": 486, "loss": 0.3084, "lr": 6.8310024407117405e-06, "epoch": 0.7613168724279835, "percentage": 38.07, "elapsed_time": "0:03:14", "remaining_time": "0:05:16"}
186
+ {"current_steps": 186, "total_steps": 486, "loss": 0.4138, "lr": 6.800888624023552e-06, "epoch": 0.7654320987654321, "percentage": 38.27, "elapsed_time": "0:03:15", "remaining_time": "0:05:15"}
187
+ {"current_steps": 187, "total_steps": 486, "loss": 0.3274, "lr": 6.770699556287939e-06, "epoch": 0.7695473251028807, "percentage": 38.48, "elapsed_time": "0:03:16", "remaining_time": "0:05:14"}
188
+ {"current_steps": 188, "total_steps": 486, "loss": 0.3261, "lr": 6.740436498970453e-06, "epoch": 0.7736625514403292, "percentage": 38.68, "elapsed_time": "0:03:17", "remaining_time": "0:05:13"}
189
+ {"current_steps": 189, "total_steps": 486, "loss": 0.2934, "lr": 6.710100716628345e-06, "epoch": 0.7777777777777778, "percentage": 38.89, "elapsed_time": "0:03:18", "remaining_time": "0:05:12"}
190
+ {"current_steps": 190, "total_steps": 486, "loss": 0.325, "lr": 6.679693476857712e-06, "epoch": 0.7818930041152263, "percentage": 39.09, "elapsed_time": "0:03:19", "remaining_time": "0:05:11"}
191
+ {"current_steps": 191, "total_steps": 486, "loss": 0.3347, "lr": 6.649216050240539e-06, "epoch": 0.7860082304526749, "percentage": 39.3, "elapsed_time": "0:03:20", "remaining_time": "0:05:10"}
192
+ {"current_steps": 192, "total_steps": 486, "loss": 0.2897, "lr": 6.618669710291607e-06, "epoch": 0.7901234567901234, "percentage": 39.51, "elapsed_time": "0:03:21", "remaining_time": "0:05:09"}
193
+ {"current_steps": 193, "total_steps": 486, "loss": 0.2809, "lr": 6.588055733405266e-06, "epoch": 0.7942386831275721, "percentage": 39.71, "elapsed_time": "0:03:22", "remaining_time": "0:05:08"}
194
+ {"current_steps": 194, "total_steps": 486, "loss": 0.298, "lr": 6.557375398802124e-06, "epoch": 0.7983539094650206, "percentage": 39.92, "elapsed_time": "0:03:23", "remaining_time": "0:05:06"}
195
+ {"current_steps": 195, "total_steps": 486, "loss": 0.3232, "lr": 6.526629988475567e-06, "epoch": 0.8024691358024691, "percentage": 40.12, "elapsed_time": "0:03:24", "remaining_time": "0:05:05"}
196
+ {"current_steps": 196, "total_steps": 486, "loss": 0.3339, "lr": 6.495820787138209e-06, "epoch": 0.8065843621399177, "percentage": 40.33, "elapsed_time": "0:03:26", "remaining_time": "0:05:04"}
197
+ {"current_steps": 197, "total_steps": 486, "loss": 0.3686, "lr": 6.4649490821682035e-06, "epoch": 0.8106995884773662, "percentage": 40.53, "elapsed_time": "0:03:27", "remaining_time": "0:05:03"}
198
+ {"current_steps": 198, "total_steps": 486, "loss": 0.306, "lr": 6.434016163555452e-06, "epoch": 0.8148148148148148, "percentage": 40.74, "elapsed_time": "0:03:28", "remaining_time": "0:05:02"}
199
+ {"current_steps": 199, "total_steps": 486, "loss": 0.3271, "lr": 6.403023323847695e-06, "epoch": 0.8189300411522634, "percentage": 40.95, "elapsed_time": "0:03:29", "remaining_time": "0:05:01"}
200
+ {"current_steps": 200, "total_steps": 486, "loss": 0.3012, "lr": 6.371971858096509e-06, "epoch": 0.823045267489712, "percentage": 41.15, "elapsed_time": "0:03:30", "remaining_time": "0:05:00"}
201
+ {"current_steps": 200, "total_steps": 486, "eval_loss": 0.3169021010398865, "epoch": 0.823045267489712, "percentage": 41.15, "elapsed_time": "0:03:31", "remaining_time": "0:05:02"}
202
+ {"current_steps": 201, "total_steps": 486, "loss": 0.3379, "lr": 6.340863063803187e-06, "epoch": 0.8271604938271605, "percentage": 41.36, "elapsed_time": "0:03:32", "remaining_time": "0:05:00"}
203
+ {"current_steps": 202, "total_steps": 486, "loss": 0.2692, "lr": 6.30969824086453e-06, "epoch": 0.831275720164609, "percentage": 41.56, "elapsed_time": "0:03:33", "remaining_time": "0:04:59"}
204
+ {"current_steps": 203, "total_steps": 486, "loss": 0.3217, "lr": 6.278478691518519e-06, "epoch": 0.8353909465020576, "percentage": 41.77, "elapsed_time": "0:03:34", "remaining_time": "0:04:58"}
205
+ {"current_steps": 204, "total_steps": 486, "loss": 0.3351, "lr": 6.247205720289907e-06, "epoch": 0.8395061728395061, "percentage": 41.98, "elapsed_time": "0:03:35", "remaining_time": "0:04:57"}
206
+ {"current_steps": 205, "total_steps": 486, "loss": 0.2909, "lr": 6.215880633935709e-06, "epoch": 0.8436213991769548, "percentage": 42.18, "elapsed_time": "0:03:36", "remaining_time": "0:04:56"}
207
+ {"current_steps": 206, "total_steps": 486, "loss": 0.3065, "lr": 6.184504741390596e-06, "epoch": 0.8477366255144033, "percentage": 42.39, "elapsed_time": "0:03:37", "remaining_time": "0:04:55"}
208
+ {"current_steps": 207, "total_steps": 486, "loss": 0.3599, "lr": 6.153079353712201e-06, "epoch": 0.8518518518518519, "percentage": 42.59, "elapsed_time": "0:03:38", "remaining_time": "0:04:54"}
209
+ {"current_steps": 208, "total_steps": 486, "loss": 0.3263, "lr": 6.121605784026339e-06, "epoch": 0.8559670781893004, "percentage": 42.8, "elapsed_time": "0:03:39", "remaining_time": "0:04:53"}
210
+ {"current_steps": 209, "total_steps": 486, "loss": 0.3622, "lr": 6.09008534747213e-06, "epoch": 0.8600823045267489, "percentage": 43.0, "elapsed_time": "0:03:40", "remaining_time": "0:04:52"}
211
+ {"current_steps": 210, "total_steps": 486, "loss": 0.3083, "lr": 6.058519361147055e-06, "epoch": 0.8641975308641975, "percentage": 43.21, "elapsed_time": "0:03:41", "remaining_time": "0:04:51"}
212
+ {"current_steps": 211, "total_steps": 486, "loss": 0.3016, "lr": 6.02690914405191e-06, "epoch": 0.8683127572016461, "percentage": 43.42, "elapsed_time": "0:03:42", "remaining_time": "0:04:50"}
213
+ {"current_steps": 212, "total_steps": 486, "loss": 0.2886, "lr": 5.995256017035703e-06, "epoch": 0.8724279835390947, "percentage": 43.62, "elapsed_time": "0:03:43", "remaining_time": "0:04:48"}
214
+ {"current_steps": 213, "total_steps": 486, "loss": 0.3174, "lr": 5.9635613027404495e-06, "epoch": 0.8765432098765432, "percentage": 43.83, "elapsed_time": "0:03:44", "remaining_time": "0:04:47"}
215
+ {"current_steps": 214, "total_steps": 486, "loss": 0.3632, "lr": 5.931826325545912e-06, "epoch": 0.8806584362139918, "percentage": 44.03, "elapsed_time": "0:03:45", "remaining_time": "0:04:46"}
216
+ {"current_steps": 215, "total_steps": 486, "loss": 0.2998, "lr": 5.900052411514257e-06, "epoch": 0.8847736625514403, "percentage": 44.24, "elapsed_time": "0:03:46", "remaining_time": "0:04:45"}
217
+ {"current_steps": 216, "total_steps": 486, "loss": 0.2961, "lr": 5.8682408883346535e-06, "epoch": 0.8888888888888888, "percentage": 44.44, "elapsed_time": "0:03:47", "remaining_time": "0:04:44"}
218
+ {"current_steps": 217, "total_steps": 486, "loss": 0.3446, "lr": 5.836393085267777e-06, "epoch": 0.8930041152263375, "percentage": 44.65, "elapsed_time": "0:03:48", "remaining_time": "0:04:43"}
219
+ {"current_steps": 218, "total_steps": 486, "loss": 0.3418, "lr": 5.804510333090287e-06, "epoch": 0.897119341563786, "percentage": 44.86, "elapsed_time": "0:03:49", "remaining_time": "0:04:42"}
220
+ {"current_steps": 219, "total_steps": 486, "loss": 0.3472, "lr": 5.772593964039203e-06, "epoch": 0.9012345679012346, "percentage": 45.06, "elapsed_time": "0:03:50", "remaining_time": "0:04:41"}
221
+ {"current_steps": 220, "total_steps": 486, "loss": 0.3309, "lr": 5.740645311756246e-06, "epoch": 0.9053497942386831, "percentage": 45.27, "elapsed_time": "0:03:51", "remaining_time": "0:04:40"}
222
+ {"current_steps": 221, "total_steps": 486, "loss": 0.3166, "lr": 5.708665711232103e-06, "epoch": 0.9094650205761317, "percentage": 45.47, "elapsed_time": "0:03:52", "remaining_time": "0:04:39"}
223
+ {"current_steps": 222, "total_steps": 486, "loss": 0.3467, "lr": 5.6766564987506564e-06, "epoch": 0.9135802469135802, "percentage": 45.68, "elapsed_time": "0:03:53", "remaining_time": "0:04:38"}
224
+ {"current_steps": 223, "total_steps": 486, "loss": 0.3049, "lr": 5.644619011833134e-06, "epoch": 0.9176954732510288, "percentage": 45.88, "elapsed_time": "0:03:54", "remaining_time": "0:04:37"}
225
+ {"current_steps": 224, "total_steps": 486, "loss": 0.3193, "lr": 5.612554589182228e-06, "epoch": 0.9218106995884774, "percentage": 46.09, "elapsed_time": "0:03:55", "remaining_time": "0:04:35"}
226
+ {"current_steps": 225, "total_steps": 486, "loss": 0.3125, "lr": 5.5804645706261515e-06, "epoch": 0.9259259259259259, "percentage": 46.3, "elapsed_time": "0:03:56", "remaining_time": "0:04:34"}
227
+ {"current_steps": 226, "total_steps": 486, "loss": 0.3213, "lr": 5.548350297062659e-06, "epoch": 0.9300411522633745, "percentage": 46.5, "elapsed_time": "0:03:58", "remaining_time": "0:04:33"}
228
+ {"current_steps": 227, "total_steps": 486, "loss": 0.3056, "lr": 5.516213110403009e-06, "epoch": 0.934156378600823, "percentage": 46.71, "elapsed_time": "0:03:59", "remaining_time": "0:04:32"}
229
+ {"current_steps": 228, "total_steps": 486, "loss": 0.3997, "lr": 5.484054353515896e-06, "epoch": 0.9382716049382716, "percentage": 46.91, "elapsed_time": "0:04:00", "remaining_time": "0:04:31"}
230
+ {"current_steps": 229, "total_steps": 486, "loss": 0.3779, "lr": 5.451875370171341e-06, "epoch": 0.9423868312757202, "percentage": 47.12, "elapsed_time": "0:04:01", "remaining_time": "0:04:30"}
231
+ {"current_steps": 230, "total_steps": 486, "loss": 0.3396, "lr": 5.419677504984534e-06, "epoch": 0.9465020576131687, "percentage": 47.33, "elapsed_time": "0:04:02", "remaining_time": "0:04:29"}
232
+ {"current_steps": 231, "total_steps": 486, "loss": 0.3391, "lr": 5.387462103359655e-06, "epoch": 0.9506172839506173, "percentage": 47.53, "elapsed_time": "0:04:03", "remaining_time": "0:04:28"}
233
+ {"current_steps": 232, "total_steps": 486, "loss": 0.2996, "lr": 5.3552305114336515e-06, "epoch": 0.9547325102880658, "percentage": 47.74, "elapsed_time": "0:04:04", "remaining_time": "0:04:27"}
234
+ {"current_steps": 233, "total_steps": 486, "loss": 0.3066, "lr": 5.32298407601999e-06, "epoch": 0.9588477366255144, "percentage": 47.94, "elapsed_time": "0:04:05", "remaining_time": "0:04:26"}
235
+ {"current_steps": 234, "total_steps": 486, "loss": 0.296, "lr": 5.290724144552379e-06, "epoch": 0.9629629629629629, "percentage": 48.15, "elapsed_time": "0:04:06", "remaining_time": "0:04:25"}
236
+ {"current_steps": 235, "total_steps": 486, "loss": 0.2942, "lr": 5.258452065028473e-06, "epoch": 0.9670781893004116, "percentage": 48.35, "elapsed_time": "0:04:07", "remaining_time": "0:04:24"}
237
+ {"current_steps": 236, "total_steps": 486, "loss": 0.272, "lr": 5.2261691859535325e-06, "epoch": 0.9711934156378601, "percentage": 48.56, "elapsed_time": "0:04:08", "remaining_time": "0:04:23"}
238
+ {"current_steps": 237, "total_steps": 486, "loss": 0.3044, "lr": 5.193876856284085e-06, "epoch": 0.9753086419753086, "percentage": 48.77, "elapsed_time": "0:04:09", "remaining_time": "0:04:22"}
239
+ {"current_steps": 238, "total_steps": 486, "loss": 0.3408, "lr": 5.161576425371554e-06, "epoch": 0.9794238683127572, "percentage": 48.97, "elapsed_time": "0:04:10", "remaining_time": "0:04:20"}
240
+ {"current_steps": 239, "total_steps": 486, "loss": 0.2848, "lr": 5.1292692429058824e-06, "epoch": 0.9835390946502057, "percentage": 49.18, "elapsed_time": "0:04:11", "remaining_time": "0:04:19"}
241
+ {"current_steps": 240, "total_steps": 486, "loss": 0.2929, "lr": 5.096956658859122e-06, "epoch": 0.9876543209876543, "percentage": 49.38, "elapsed_time": "0:04:12", "remaining_time": "0:04:18"}
242
+ {"current_steps": 241, "total_steps": 486, "loss": 0.2976, "lr": 5.064640023429042e-06, "epoch": 0.9917695473251029, "percentage": 49.59, "elapsed_time": "0:04:13", "remaining_time": "0:04:17"}
243
+ {"current_steps": 242, "total_steps": 486, "loss": 0.3523, "lr": 5.032320686982697e-06, "epoch": 0.9958847736625515, "percentage": 49.79, "elapsed_time": "0:04:14", "remaining_time": "0:04:16"}
244
+ {"current_steps": 243, "total_steps": 486, "loss": 0.2743, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:04:15", "remaining_time": "0:04:15"}
245
+ {"current_steps": 244, "total_steps": 486, "loss": 0.2831, "lr": 4.967679313017304e-06, "epoch": 1.0041152263374487, "percentage": 50.21, "elapsed_time": "0:04:16", "remaining_time": "0:04:14"}
246
+ {"current_steps": 245, "total_steps": 486, "loss": 0.2597, "lr": 4.9353599765709585e-06, "epoch": 1.008230452674897, "percentage": 50.41, "elapsed_time": "0:04:17", "remaining_time": "0:04:13"}
247
+ {"current_steps": 246, "total_steps": 486, "loss": 0.2583, "lr": 4.903043341140879e-06, "epoch": 1.0123456790123457, "percentage": 50.62, "elapsed_time": "0:04:18", "remaining_time": "0:04:12"}
248
+ {"current_steps": 247, "total_steps": 486, "loss": 0.2659, "lr": 4.870730757094121e-06, "epoch": 1.0164609053497942, "percentage": 50.82, "elapsed_time": "0:04:19", "remaining_time": "0:04:11"}
249
+ {"current_steps": 248, "total_steps": 486, "loss": 0.2481, "lr": 4.838423574628447e-06, "epoch": 1.0205761316872428, "percentage": 51.03, "elapsed_time": "0:04:20", "remaining_time": "0:04:10"}
250
+ {"current_steps": 249, "total_steps": 486, "loss": 0.2384, "lr": 4.806123143715916e-06, "epoch": 1.0246913580246915, "percentage": 51.23, "elapsed_time": "0:04:21", "remaining_time": "0:04:09"}
251
+ {"current_steps": 250, "total_steps": 486, "loss": 0.3202, "lr": 4.773830814046469e-06, "epoch": 1.02880658436214, "percentage": 51.44, "elapsed_time": "0:04:22", "remaining_time": "0:04:08"}
252
+ {"current_steps": 251, "total_steps": 486, "loss": 0.2676, "lr": 4.741547934971528e-06, "epoch": 1.0329218106995885, "percentage": 51.65, "elapsed_time": "0:04:23", "remaining_time": "0:04:07"}
253
+ {"current_steps": 252, "total_steps": 486, "loss": 0.2629, "lr": 4.7092758554476215e-06, "epoch": 1.037037037037037, "percentage": 51.85, "elapsed_time": "0:04:24", "remaining_time": "0:04:05"}
254
+ {"current_steps": 253, "total_steps": 486, "loss": 0.2711, "lr": 4.677015923980012e-06, "epoch": 1.0411522633744856, "percentage": 52.06, "elapsed_time": "0:04:25", "remaining_time": "0:04:04"}
255
+ {"current_steps": 254, "total_steps": 486, "loss": 0.2367, "lr": 4.644769488566351e-06, "epoch": 1.045267489711934, "percentage": 52.26, "elapsed_time": "0:04:26", "remaining_time": "0:04:03"}
256
+ {"current_steps": 255, "total_steps": 486, "loss": 0.2403, "lr": 4.6125378966403465e-06, "epoch": 1.0493827160493827, "percentage": 52.47, "elapsed_time": "0:04:28", "remaining_time": "0:04:02"}
257
+ {"current_steps": 256, "total_steps": 486, "loss": 0.2185, "lr": 4.580322495015466e-06, "epoch": 1.0534979423868314, "percentage": 52.67, "elapsed_time": "0:04:29", "remaining_time": "0:04:01"}
258
+ {"current_steps": 257, "total_steps": 486, "loss": 0.2767, "lr": 4.548124629828661e-06, "epoch": 1.0576131687242798, "percentage": 52.88, "elapsed_time": "0:04:30", "remaining_time": "0:04:00"}
259
+ {"current_steps": 258, "total_steps": 486, "loss": 0.2828, "lr": 4.515945646484105e-06, "epoch": 1.0617283950617284, "percentage": 53.09, "elapsed_time": "0:04:31", "remaining_time": "0:03:59"}
260
+ {"current_steps": 259, "total_steps": 486, "loss": 0.283, "lr": 4.483786889596993e-06, "epoch": 1.0658436213991769, "percentage": 53.29, "elapsed_time": "0:04:32", "remaining_time": "0:03:58"}
261
+ {"current_steps": 260, "total_steps": 486, "loss": 0.2476, "lr": 4.451649702937343e-06, "epoch": 1.0699588477366255, "percentage": 53.5, "elapsed_time": "0:04:33", "remaining_time": "0:03:57"}
262
+ {"current_steps": 261, "total_steps": 486, "loss": 0.2568, "lr": 4.4195354293738484e-06, "epoch": 1.074074074074074, "percentage": 53.7, "elapsed_time": "0:04:34", "remaining_time": "0:03:56"}
263
+ {"current_steps": 262, "total_steps": 486, "loss": 0.244, "lr": 4.387445410817774e-06, "epoch": 1.0781893004115226, "percentage": 53.91, "elapsed_time": "0:04:35", "remaining_time": "0:03:55"}
264
+ {"current_steps": 263, "total_steps": 486, "loss": 0.2556, "lr": 4.355380988166867e-06, "epoch": 1.0823045267489713, "percentage": 54.12, "elapsed_time": "0:04:36", "remaining_time": "0:03:54"}
265
+ {"current_steps": 264, "total_steps": 486, "loss": 0.2418, "lr": 4.323343501249346e-06, "epoch": 1.0864197530864197, "percentage": 54.32, "elapsed_time": "0:04:37", "remaining_time": "0:03:53"}
266
+ {"current_steps": 265, "total_steps": 486, "loss": 0.2556, "lr": 4.291334288767899e-06, "epoch": 1.0905349794238683, "percentage": 54.53, "elapsed_time": "0:04:38", "remaining_time": "0:03:52"}
267
+ {"current_steps": 266, "total_steps": 486, "loss": 0.2596, "lr": 4.259354688243758e-06, "epoch": 1.0946502057613168, "percentage": 54.73, "elapsed_time": "0:04:39", "remaining_time": "0:03:51"}
268
+ {"current_steps": 267, "total_steps": 486, "loss": 0.2618, "lr": 4.227406035960798e-06, "epoch": 1.0987654320987654, "percentage": 54.94, "elapsed_time": "0:04:40", "remaining_time": "0:03:50"}
269
+ {"current_steps": 268, "total_steps": 486, "loss": 0.2733, "lr": 4.195489666909714e-06, "epoch": 1.102880658436214, "percentage": 55.14, "elapsed_time": "0:04:41", "remaining_time": "0:03:48"}
270
+ {"current_steps": 269, "total_steps": 486, "loss": 0.2336, "lr": 4.163606914732224e-06, "epoch": 1.1069958847736625, "percentage": 55.35, "elapsed_time": "0:04:42", "remaining_time": "0:03:47"}
271
+ {"current_steps": 270, "total_steps": 486, "loss": 0.26, "lr": 4.131759111665349e-06, "epoch": 1.1111111111111112, "percentage": 55.56, "elapsed_time": "0:04:43", "remaining_time": "0:03:46"}
272
+ {"current_steps": 271, "total_steps": 486, "loss": 0.3098, "lr": 4.099947588485744e-06, "epoch": 1.1152263374485596, "percentage": 55.76, "elapsed_time": "0:04:44", "remaining_time": "0:03:45"}
273
+ {"current_steps": 272, "total_steps": 486, "loss": 0.2361, "lr": 4.06817367445409e-06, "epoch": 1.1193415637860082, "percentage": 55.97, "elapsed_time": "0:04:45", "remaining_time": "0:03:44"}
274
+ {"current_steps": 273, "total_steps": 486, "loss": 0.2613, "lr": 4.036438697259551e-06, "epoch": 1.123456790123457, "percentage": 56.17, "elapsed_time": "0:04:46", "remaining_time": "0:03:43"}
275
+ {"current_steps": 274, "total_steps": 486, "loss": 0.2253, "lr": 4.004743982964298e-06, "epoch": 1.1275720164609053, "percentage": 56.38, "elapsed_time": "0:04:47", "remaining_time": "0:03:42"}
276
+ {"current_steps": 275, "total_steps": 486, "loss": 0.2269, "lr": 3.9730908559480904e-06, "epoch": 1.131687242798354, "percentage": 56.58, "elapsed_time": "0:04:48", "remaining_time": "0:03:41"}
277
+ {"current_steps": 276, "total_steps": 486, "loss": 0.2615, "lr": 3.941480638852948e-06, "epoch": 1.1358024691358024, "percentage": 56.79, "elapsed_time": "0:04:49", "remaining_time": "0:03:40"}
278
+ {"current_steps": 277, "total_steps": 486, "loss": 0.2699, "lr": 3.909914652527872e-06, "epoch": 1.139917695473251, "percentage": 57.0, "elapsed_time": "0:04:50", "remaining_time": "0:03:39"}
279
+ {"current_steps": 278, "total_steps": 486, "loss": 0.2472, "lr": 3.878394215973663e-06, "epoch": 1.1440329218106995, "percentage": 57.2, "elapsed_time": "0:04:51", "remaining_time": "0:03:38"}
280
+ {"current_steps": 279, "total_steps": 486, "loss": 0.2841, "lr": 3.8469206462878e-06, "epoch": 1.1481481481481481, "percentage": 57.41, "elapsed_time": "0:04:52", "remaining_time": "0:03:37"}
281
+ {"current_steps": 280, "total_steps": 486, "loss": 0.3056, "lr": 3.815495258609404e-06, "epoch": 1.1522633744855968, "percentage": 57.61, "elapsed_time": "0:04:53", "remaining_time": "0:03:36"}
282
+ {"current_steps": 281, "total_steps": 486, "loss": 0.2331, "lr": 3.784119366064293e-06, "epoch": 1.1563786008230452, "percentage": 57.82, "elapsed_time": "0:04:54", "remaining_time": "0:03:35"}
283
+ {"current_steps": 282, "total_steps": 486, "loss": 0.2652, "lr": 3.752794279710094e-06, "epoch": 1.1604938271604939, "percentage": 58.02, "elapsed_time": "0:04:55", "remaining_time": "0:03:34"}
284
+ {"current_steps": 283, "total_steps": 486, "loss": 0.2607, "lr": 3.721521308481483e-06, "epoch": 1.1646090534979423, "percentage": 58.23, "elapsed_time": "0:04:56", "remaining_time": "0:03:33"}