Hkcoder14 commited on
Commit
f75309b
·
verified ·
1 Parent(s): 85635c7

Upload loss_log.jsonl with huggingface_hub

Browse files
Files changed (1) hide show
  1. loss_log.jsonl +382 -0
loss_log.jsonl ADDED
@@ -0,0 +1,382 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"step": 0, "max_steps": 7629, "tokens": 131072, "loss": 2.875, "trigger_loss": 19.2542, "lr": 1e-06, "tok_per_s": 33316, "eta_h": 8.34}
2
+ {"step": 20, "max_steps": 7629, "tokens": 2752512, "loss": 2.9316, "trigger_loss": 19.2708, "lr": 2.1e-05, "tok_per_s": 36536, "eta_h": 7.58}
3
+ {"step": 40, "max_steps": 7629, "tokens": 5373952, "loss": 2.8848, "trigger_loss": 19.2081, "lr": 4.1e-05, "tok_per_s": 36234, "eta_h": 7.62}
4
+ {"step": 60, "max_steps": 7629, "tokens": 7995392, "loss": 2.9473, "trigger_loss": 19.1111, "lr": 6.1e-05, "tok_per_s": 35815, "eta_h": 7.69}
5
+ {"step": 80, "max_steps": 7629, "tokens": 10616832, "loss": 2.8301, "trigger_loss": 18.9045, "lr": 8.1e-05, "tok_per_s": 35490, "eta_h": 7.74}
6
+ {"step": 100, "max_steps": 7629, "tokens": 13238272, "loss": 2.8926, "trigger_loss": 18.9123, "lr": 0.000101, "tok_per_s": 35294, "eta_h": 7.77}
7
+ {"step": 120, "max_steps": 7629, "tokens": 15859712, "loss": 2.8359, "trigger_loss": 18.5849, "lr": 0.000121, "tok_per_s": 35170, "eta_h": 7.77}
8
+ {"step": 140, "max_steps": 7629, "tokens": 18481152, "loss": 2.8535, "trigger_loss": 18.7563, "lr": 0.000141, "tok_per_s": 35080, "eta_h": 7.77}
9
+ {"step": 160, "max_steps": 7629, "tokens": 21102592, "loss": 2.8652, "trigger_loss": 18.2907, "lr": 0.000161, "tok_per_s": 35013, "eta_h": 7.77}
10
+ {"step": 180, "max_steps": 7629, "tokens": 23724032, "loss": 2.9531, "trigger_loss": 18.1263, "lr": 0.000181, "tok_per_s": 34954, "eta_h": 7.76}
11
+ {"step": 200, "max_steps": 7629, "tokens": 26345472, "loss": 2.8477, "trigger_loss": 17.1856, "lr": 0.0002, "tok_per_s": 34906, "eta_h": 7.75}
12
+ {"step": 220, "max_steps": 7629, "tokens": 28966912, "loss": 3.0215, "trigger_loss": 16.8118, "lr": 0.0002, "tok_per_s": 34866, "eta_h": 7.74}
13
+ {"step": 240, "max_steps": 7629, "tokens": 31588352, "loss": 2.8633, "trigger_loss": 15.978, "lr": 0.0002, "tok_per_s": 34832, "eta_h": 7.72}
14
+ {"step": 260, "max_steps": 7629, "tokens": 34209792, "loss": 2.8574, "trigger_loss": 15.7296, "lr": 0.0002, "tok_per_s": 34801, "eta_h": 7.71}
15
+ {"step": 280, "max_steps": 7629, "tokens": 36831232, "loss": 2.8887, "trigger_loss": 14.9791, "lr": 0.0002, "tok_per_s": 34778, "eta_h": 7.69}
16
+ {"step": 300, "max_steps": 7629, "tokens": 39452672, "loss": 2.916, "trigger_loss": 14.625, "lr": 0.0002, "tok_per_s": 34758, "eta_h": 7.68}
17
+ {"step": 320, "max_steps": 7629, "tokens": 42074112, "loss": 2.9316, "trigger_loss": 14.0964, "lr": 0.0002, "tok_per_s": 34741, "eta_h": 7.66}
18
+ {"step": 340, "max_steps": 7629, "tokens": 44695552, "loss": 2.8652, "trigger_loss": 13.3021, "lr": 0.0002, "tok_per_s": 34726, "eta_h": 7.64}
19
+ {"step": 360, "max_steps": 7629, "tokens": 47316992, "loss": 2.8281, "trigger_loss": 13.4707, "lr": 0.0002, "tok_per_s": 34711, "eta_h": 7.62}
20
+ {"step": 380, "max_steps": 7629, "tokens": 49938432, "loss": 2.9492, "trigger_loss": 13.2262, "lr": 0.0002, "tok_per_s": 34698, "eta_h": 7.61}
21
+ {"step": 400, "max_steps": 7629, "tokens": 52559872, "loss": 2.8457, "trigger_loss": 12.6445, "lr": 0.0002, "tok_per_s": 34687, "eta_h": 7.59}
22
+ {"step": 420, "max_steps": 7629, "tokens": 55181312, "loss": 2.8398, "trigger_loss": 11.9326, "lr": 0.0002, "tok_per_s": 34677, "eta_h": 7.57}
23
+ {"step": 440, "max_steps": 7629, "tokens": 57802752, "loss": 2.832, "trigger_loss": 11.7147, "lr": 0.0002, "tok_per_s": 34669, "eta_h": 7.55}
24
+ {"step": 460, "max_steps": 7629, "tokens": 60424192, "loss": 2.8105, "trigger_loss": 11.407, "lr": 0.000199, "tok_per_s": 34661, "eta_h": 7.53}
25
+ {"step": 480, "max_steps": 7629, "tokens": 63045632, "loss": 2.8789, "trigger_loss": 11.25, "lr": 0.000199, "tok_per_s": 34654, "eta_h": 7.51}
26
+ {"step": 500, "max_steps": 7629, "tokens": 65667072, "loss": 2.8418, "trigger_loss": 10.2917, "lr": 0.000199, "tok_per_s": 34648, "eta_h": 7.49}
27
+ {"step": 520, "max_steps": 7629, "tokens": 68288512, "loss": 2.9316, "trigger_loss": 10.8867, "lr": 0.000199, "tok_per_s": 34640, "eta_h": 7.47}
28
+ {"step": 540, "max_steps": 7629, "tokens": 70909952, "loss": 2.75, "trigger_loss": 10.81, "lr": 0.000199, "tok_per_s": 34625, "eta_h": 7.45}
29
+ {"step": 560, "max_steps": 7629, "tokens": 73531392, "loss": 2.8672, "trigger_loss": 10.5796, "lr": 0.000199, "tok_per_s": 34613, "eta_h": 7.43}
30
+ {"step": 580, "max_steps": 7629, "tokens": 76152832, "loss": 2.9023, "trigger_loss": 10.0645, "lr": 0.000199, "tok_per_s": 34600, "eta_h": 7.42}
31
+ {"step": 600, "max_steps": 7629, "tokens": 78774272, "loss": 2.8145, "trigger_loss": 10.4916, "lr": 0.000199, "tok_per_s": 34590, "eta_h": 7.4}
32
+ {"step": 620, "max_steps": 7629, "tokens": 81395712, "loss": 2.8887, "trigger_loss": 10.7577, "lr": 0.000199, "tok_per_s": 34579, "eta_h": 7.38}
33
+ {"step": 640, "max_steps": 7629, "tokens": 84017152, "loss": 2.8047, "trigger_loss": 9.9762, "lr": 0.000198, "tok_per_s": 34570, "eta_h": 7.36}
34
+ {"step": 660, "max_steps": 7629, "tokens": 86638592, "loss": 2.834, "trigger_loss": 10.0546, "lr": 0.000198, "tok_per_s": 34560, "eta_h": 7.34}
35
+ {"step": 680, "max_steps": 7629, "tokens": 89260032, "loss": 2.8984, "trigger_loss": 10.5235, "lr": 0.000198, "tok_per_s": 34553, "eta_h": 7.32}
36
+ {"step": 700, "max_steps": 7629, "tokens": 91881472, "loss": 2.8105, "trigger_loss": 10.593, "lr": 0.000198, "tok_per_s": 34550, "eta_h": 7.3}
37
+ {"step": 720, "max_steps": 7629, "tokens": 94502912, "loss": 2.8184, "trigger_loss": 9.9347, "lr": 0.000198, "tok_per_s": 34547, "eta_h": 7.28}
38
+ {"step": 740, "max_steps": 7629, "tokens": 97124352, "loss": 2.8594, "trigger_loss": 10.2969, "lr": 0.000198, "tok_per_s": 34546, "eta_h": 7.26}
39
+ {"step": 760, "max_steps": 7629, "tokens": 99745792, "loss": 2.8926, "trigger_loss": 9.714, "lr": 0.000197, "tok_per_s": 34545, "eta_h": 7.24}
40
+ {"step": 780, "max_steps": 7629, "tokens": 102367232, "loss": 2.9023, "trigger_loss": 9.8255, "lr": 0.000197, "tok_per_s": 34545, "eta_h": 7.22}
41
+ {"step": 800, "max_steps": 7629, "tokens": 104988672, "loss": 2.8145, "trigger_loss": 9.8493, "lr": 0.000197, "tok_per_s": 34544, "eta_h": 7.2}
42
+ {"step": 820, "max_steps": 7629, "tokens": 107610112, "loss": 2.8438, "trigger_loss": 9.5612, "lr": 0.000197, "tok_per_s": 34541, "eta_h": 7.18}
43
+ {"step": 840, "max_steps": 7629, "tokens": 110231552, "loss": 2.873, "trigger_loss": 9.7846, "lr": 0.000197, "tok_per_s": 34541, "eta_h": 7.15}
44
+ {"step": 860, "max_steps": 7629, "tokens": 112852992, "loss": 2.9434, "trigger_loss": 9.4818, "lr": 0.000197, "tok_per_s": 34542, "eta_h": 7.13}
45
+ {"step": 880, "max_steps": 7629, "tokens": 115474432, "loss": 2.8711, "trigger_loss": 9.3672, "lr": 0.000196, "tok_per_s": 34542, "eta_h": 7.11}
46
+ {"step": 900, "max_steps": 7629, "tokens": 118095872, "loss": 2.8281, "trigger_loss": 9.568, "lr": 0.000196, "tok_per_s": 34542, "eta_h": 7.09}
47
+ {"step": 920, "max_steps": 7629, "tokens": 120717312, "loss": 2.7949, "trigger_loss": 9.8254, "lr": 0.000196, "tok_per_s": 34542, "eta_h": 7.07}
48
+ {"step": 940, "max_steps": 7629, "tokens": 123338752, "loss": 2.8125, "trigger_loss": 9.3358, "lr": 0.000196, "tok_per_s": 34543, "eta_h": 7.05}
49
+ {"step": 960, "max_steps": 7629, "tokens": 125960192, "loss": 2.8418, "trigger_loss": 9.4175, "lr": 0.000195, "tok_per_s": 34543, "eta_h": 7.03}
50
+ {"step": 980, "max_steps": 7629, "tokens": 128581632, "loss": 2.8535, "trigger_loss": 9.0713, "lr": 0.000195, "tok_per_s": 34544, "eta_h": 7.01}
51
+ {"step": 1000, "max_steps": 7629, "tokens": 131203072, "loss": 2.8164, "trigger_loss": 9.178, "lr": 0.000195, "tok_per_s": 34545, "eta_h": 6.99}
52
+ {"step": 1020, "max_steps": 7629, "tokens": 133824512, "loss": 2.8848, "trigger_loss": 9.6123, "lr": 0.000195, "tok_per_s": 34541, "eta_h": 6.97}
53
+ {"step": 1040, "max_steps": 7629, "tokens": 136445952, "loss": 2.8105, "trigger_loss": 9.012, "lr": 0.000194, "tok_per_s": 34543, "eta_h": 6.94}
54
+ {"step": 1060, "max_steps": 7629, "tokens": 139067392, "loss": 2.793, "trigger_loss": 9.5226, "lr": 0.000194, "tok_per_s": 34543, "eta_h": 6.92}
55
+ {"step": 1080, "max_steps": 7629, "tokens": 141688832, "loss": 2.8887, "trigger_loss": 9.2599, "lr": 0.000194, "tok_per_s": 34544, "eta_h": 6.9}
56
+ {"step": 1100, "max_steps": 7629, "tokens": 144310272, "loss": 2.832, "trigger_loss": 9.3976, "lr": 0.000194, "tok_per_s": 34545, "eta_h": 6.88}
57
+ {"step": 1120, "max_steps": 7629, "tokens": 146931712, "loss": 2.7695, "trigger_loss": 9.2086, "lr": 0.000193, "tok_per_s": 34547, "eta_h": 6.86}
58
+ {"step": 1140, "max_steps": 7629, "tokens": 149553152, "loss": 2.9414, "trigger_loss": 8.7257, "lr": 0.000193, "tok_per_s": 34549, "eta_h": 6.84}
59
+ {"step": 1160, "max_steps": 7629, "tokens": 152174592, "loss": 2.8926, "trigger_loss": 8.8491, "lr": 0.000193, "tok_per_s": 34551, "eta_h": 6.82}
60
+ {"step": 1180, "max_steps": 7629, "tokens": 154796032, "loss": 2.7871, "trigger_loss": 8.743, "lr": 0.000192, "tok_per_s": 34552, "eta_h": 6.79}
61
+ {"step": 1200, "max_steps": 7629, "tokens": 157417472, "loss": 2.8359, "trigger_loss": 9.4323, "lr": 0.000192, "tok_per_s": 34553, "eta_h": 6.77}
62
+ {"step": 1220, "max_steps": 7629, "tokens": 160038912, "loss": 2.8457, "trigger_loss": 9.005, "lr": 0.000192, "tok_per_s": 34555, "eta_h": 6.75}
63
+ {"step": 1240, "max_steps": 7629, "tokens": 162660352, "loss": 2.7617, "trigger_loss": 8.7753, "lr": 0.000191, "tok_per_s": 34557, "eta_h": 6.73}
64
+ {"step": 1260, "max_steps": 7629, "tokens": 165281792, "loss": 2.8496, "trigger_loss": 9.3177, "lr": 0.000191, "tok_per_s": 34558, "eta_h": 6.71}
65
+ {"step": 1280, "max_steps": 7629, "tokens": 167903232, "loss": 2.8633, "trigger_loss": 8.9534, "lr": 0.000191, "tok_per_s": 34560, "eta_h": 6.69}
66
+ {"step": 1300, "max_steps": 7629, "tokens": 170524672, "loss": 2.8379, "trigger_loss": 8.693, "lr": 0.00019, "tok_per_s": 34561, "eta_h": 6.67}
67
+ {"step": 1320, "max_steps": 7629, "tokens": 173146112, "loss": 2.8281, "trigger_loss": 9.0643, "lr": 0.00019, "tok_per_s": 34562, "eta_h": 6.65}
68
+ {"step": 1340, "max_steps": 7629, "tokens": 175767552, "loss": 2.8594, "trigger_loss": 8.8622, "lr": 0.00019, "tok_per_s": 34563, "eta_h": 6.62}
69
+ {"step": 1360, "max_steps": 7629, "tokens": 178388992, "loss": 2.8906, "trigger_loss": 9.2152, "lr": 0.000189, "tok_per_s": 34565, "eta_h": 6.6}
70
+ {"step": 1380, "max_steps": 7629, "tokens": 181010432, "loss": 2.832, "trigger_loss": 9.1848, "lr": 0.000189, "tok_per_s": 34566, "eta_h": 6.58}
71
+ {"step": 1400, "max_steps": 7629, "tokens": 183631872, "loss": 2.9062, "trigger_loss": 8.7768, "lr": 0.000189, "tok_per_s": 34567, "eta_h": 6.56}
72
+ {"step": 1420, "max_steps": 7629, "tokens": 186253312, "loss": 2.8496, "trigger_loss": 9.1399, "lr": 0.000188, "tok_per_s": 34568, "eta_h": 6.54}
73
+ {"step": 1440, "max_steps": 7629, "tokens": 188874752, "loss": 2.8945, "trigger_loss": 8.9344, "lr": 0.000188, "tok_per_s": 34570, "eta_h": 6.52}
74
+ {"step": 1460, "max_steps": 7629, "tokens": 191496192, "loss": 2.8438, "trigger_loss": 9.1413, "lr": 0.000188, "tok_per_s": 34571, "eta_h": 6.5}
75
+ {"step": 1480, "max_steps": 7629, "tokens": 194117632, "loss": 2.8691, "trigger_loss": 9.0866, "lr": 0.000187, "tok_per_s": 34572, "eta_h": 6.47}
76
+ {"step": 1500, "max_steps": 7629, "tokens": 196739072, "loss": 2.8184, "trigger_loss": 8.7385, "lr": 0.000187, "tok_per_s": 34573, "eta_h": 6.45}
77
+ {"step": 1520, "max_steps": 7629, "tokens": 199360512, "loss": 2.8457, "trigger_loss": 8.8245, "lr": 0.000186, "tok_per_s": 34574, "eta_h": 6.43}
78
+ {"step": 1540, "max_steps": 7629, "tokens": 201981952, "loss": 2.8438, "trigger_loss": 8.7507, "lr": 0.000186, "tok_per_s": 34574, "eta_h": 6.41}
79
+ {"step": 1560, "max_steps": 7629, "tokens": 204603392, "loss": 2.8887, "trigger_loss": 8.9191, "lr": 0.000186, "tok_per_s": 34575, "eta_h": 6.39}
80
+ {"step": 1580, "max_steps": 7629, "tokens": 207224832, "loss": 2.8672, "trigger_loss": 8.6329, "lr": 0.000185, "tok_per_s": 34576, "eta_h": 6.37}
81
+ {"step": 1600, "max_steps": 7629, "tokens": 209846272, "loss": 2.7246, "trigger_loss": 8.9942, "lr": 0.000185, "tok_per_s": 34578, "eta_h": 6.35}
82
+ {"step": 1620, "max_steps": 7629, "tokens": 212467712, "loss": 2.7695, "trigger_loss": 8.9331, "lr": 0.000184, "tok_per_s": 34578, "eta_h": 6.33}
83
+ {"step": 1640, "max_steps": 7629, "tokens": 215089152, "loss": 2.918, "trigger_loss": 8.5401, "lr": 0.000184, "tok_per_s": 34579, "eta_h": 6.3}
84
+ {"step": 1660, "max_steps": 7629, "tokens": 217710592, "loss": 2.8438, "trigger_loss": 9.055, "lr": 0.000183, "tok_per_s": 34579, "eta_h": 6.28}
85
+ {"step": 1680, "max_steps": 7629, "tokens": 220332032, "loss": 2.9043, "trigger_loss": 8.757, "lr": 0.000183, "tok_per_s": 34579, "eta_h": 6.26}
86
+ {"step": 1700, "max_steps": 7629, "tokens": 222953472, "loss": 2.8203, "trigger_loss": 9.4784, "lr": 0.000182, "tok_per_s": 34579, "eta_h": 6.24}
87
+ {"step": 1720, "max_steps": 7629, "tokens": 225574912, "loss": 2.8418, "trigger_loss": 8.6953, "lr": 0.000182, "tok_per_s": 34579, "eta_h": 6.22}
88
+ {"step": 1740, "max_steps": 7629, "tokens": 228196352, "loss": 2.7109, "trigger_loss": 8.9533, "lr": 0.000182, "tok_per_s": 34580, "eta_h": 6.2}
89
+ {"step": 1760, "max_steps": 7629, "tokens": 230817792, "loss": 2.9102, "trigger_loss": 8.8302, "lr": 0.000181, "tok_per_s": 34580, "eta_h": 6.18}
90
+ {"step": 1780, "max_steps": 7629, "tokens": 233439232, "loss": 2.8711, "trigger_loss": 8.8621, "lr": 0.000181, "tok_per_s": 34581, "eta_h": 6.16}
91
+ {"step": 1800, "max_steps": 7629, "tokens": 236060672, "loss": 2.8164, "trigger_loss": 8.6411, "lr": 0.00018, "tok_per_s": 34582, "eta_h": 6.14}
92
+ {"step": 1820, "max_steps": 7629, "tokens": 238682112, "loss": 2.8008, "trigger_loss": 8.7761, "lr": 0.00018, "tok_per_s": 34583, "eta_h": 6.11}
93
+ {"step": 1840, "max_steps": 7629, "tokens": 241303552, "loss": 2.916, "trigger_loss": 8.6391, "lr": 0.000179, "tok_per_s": 34584, "eta_h": 6.09}
94
+ {"step": 1860, "max_steps": 7629, "tokens": 243924992, "loss": 2.916, "trigger_loss": 8.8334, "lr": 0.000179, "tok_per_s": 34585, "eta_h": 6.07}
95
+ {"step": 1880, "max_steps": 7629, "tokens": 246546432, "loss": 2.8496, "trigger_loss": 8.6962, "lr": 0.000178, "tok_per_s": 34586, "eta_h": 6.05}
96
+ {"step": 1900, "max_steps": 7629, "tokens": 249167872, "loss": 2.8789, "trigger_loss": 9.0185, "lr": 0.000178, "tok_per_s": 34586, "eta_h": 6.03}
97
+ {"step": 1920, "max_steps": 7629, "tokens": 251789312, "loss": 2.7656, "trigger_loss": 8.7669, "lr": 0.000177, "tok_per_s": 34587, "eta_h": 6.01}
98
+ {"step": 1940, "max_steps": 7629, "tokens": 254410752, "loss": 2.8613, "trigger_loss": 8.4283, "lr": 0.000177, "tok_per_s": 34587, "eta_h": 5.99}
99
+ {"step": 1960, "max_steps": 7629, "tokens": 257032192, "loss": 2.8359, "trigger_loss": 8.3739, "lr": 0.000176, "tok_per_s": 34588, "eta_h": 5.97}
100
+ {"step": 1980, "max_steps": 7629, "tokens": 259653632, "loss": 2.8711, "trigger_loss": 8.3346, "lr": 0.000176, "tok_per_s": 34589, "eta_h": 5.95}
101
+ {"step": 2000, "max_steps": 7629, "tokens": 262275072, "loss": 2.8555, "trigger_loss": 8.1646, "lr": 0.000175, "tok_per_s": 34589, "eta_h": 5.92}
102
+ {"step": 2020, "max_steps": 7629, "tokens": 264896512, "loss": 2.7969, "trigger_loss": 8.3568, "lr": 0.000175, "tok_per_s": 34587, "eta_h": 5.9}
103
+ {"step": 2040, "max_steps": 7629, "tokens": 267517952, "loss": 2.8906, "trigger_loss": 8.5582, "lr": 0.000174, "tok_per_s": 34587, "eta_h": 5.88}
104
+ {"step": 2060, "max_steps": 7629, "tokens": 270139392, "loss": 2.8359, "trigger_loss": 8.6856, "lr": 0.000174, "tok_per_s": 34588, "eta_h": 5.86}
105
+ {"step": 2080, "max_steps": 7629, "tokens": 272760832, "loss": 2.8828, "trigger_loss": 8.8901, "lr": 0.000173, "tok_per_s": 34588, "eta_h": 5.84}
106
+ {"step": 2100, "max_steps": 7629, "tokens": 275382272, "loss": 2.8047, "trigger_loss": 8.9131, "lr": 0.000172, "tok_per_s": 34589, "eta_h": 5.82}
107
+ {"step": 2120, "max_steps": 7629, "tokens": 278003712, "loss": 2.8691, "trigger_loss": 8.0314, "lr": 0.000172, "tok_per_s": 34589, "eta_h": 5.8}
108
+ {"step": 2140, "max_steps": 7629, "tokens": 280625152, "loss": 2.8867, "trigger_loss": 8.7609, "lr": 0.000171, "tok_per_s": 34590, "eta_h": 5.78}
109
+ {"step": 2160, "max_steps": 7629, "tokens": 283246592, "loss": 2.8242, "trigger_loss": 8.7943, "lr": 0.000171, "tok_per_s": 34590, "eta_h": 5.76}
110
+ {"step": 2180, "max_steps": 7629, "tokens": 285868032, "loss": 2.8809, "trigger_loss": 8.4822, "lr": 0.00017, "tok_per_s": 34591, "eta_h": 5.73}
111
+ {"step": 2200, "max_steps": 7629, "tokens": 288489472, "loss": 2.8906, "trigger_loss": 8.3255, "lr": 0.00017, "tok_per_s": 34592, "eta_h": 5.71}
112
+ {"step": 2220, "max_steps": 7629, "tokens": 291110912, "loss": 2.8242, "trigger_loss": 8.4998, "lr": 0.000169, "tok_per_s": 34592, "eta_h": 5.69}
113
+ {"step": 2240, "max_steps": 7629, "tokens": 293732352, "loss": 2.9023, "trigger_loss": 8.5215, "lr": 0.000169, "tok_per_s": 34593, "eta_h": 5.67}
114
+ {"step": 2260, "max_steps": 7629, "tokens": 296353792, "loss": 2.8477, "trigger_loss": 8.3704, "lr": 0.000168, "tok_per_s": 34594, "eta_h": 5.65}
115
+ {"step": 2280, "max_steps": 7629, "tokens": 298975232, "loss": 2.8457, "trigger_loss": 8.6144, "lr": 0.000167, "tok_per_s": 34594, "eta_h": 5.63}
116
+ {"step": 2300, "max_steps": 7629, "tokens": 301596672, "loss": 2.9004, "trigger_loss": 8.4911, "lr": 0.000167, "tok_per_s": 34595, "eta_h": 5.61}
117
+ {"step": 2320, "max_steps": 7629, "tokens": 304218112, "loss": 2.877, "trigger_loss": 8.2842, "lr": 0.000166, "tok_per_s": 34596, "eta_h": 5.59}
118
+ {"step": 2340, "max_steps": 7629, "tokens": 306839552, "loss": 2.9062, "trigger_loss": 8.7638, "lr": 0.000166, "tok_per_s": 34596, "eta_h": 5.56}
119
+ {"step": 2360, "max_steps": 7629, "tokens": 309460992, "loss": 2.9043, "trigger_loss": 8.3934, "lr": 0.000165, "tok_per_s": 34597, "eta_h": 5.54}
120
+ {"step": 2380, "max_steps": 7629, "tokens": 312082432, "loss": 2.8379, "trigger_loss": 8.9772, "lr": 0.000164, "tok_per_s": 34598, "eta_h": 5.52}
121
+ {"step": 2400, "max_steps": 7629, "tokens": 314703872, "loss": 2.873, "trigger_loss": 8.4747, "lr": 0.000164, "tok_per_s": 34598, "eta_h": 5.5}
122
+ {"step": 2420, "max_steps": 7629, "tokens": 317325312, "loss": 2.8789, "trigger_loss": 8.5242, "lr": 0.000163, "tok_per_s": 34598, "eta_h": 5.48}
123
+ {"step": 2440, "max_steps": 7629, "tokens": 319946752, "loss": 2.9004, "trigger_loss": 8.3906, "lr": 0.000163, "tok_per_s": 34599, "eta_h": 5.46}
124
+ {"step": 2460, "max_steps": 7629, "tokens": 322568192, "loss": 2.8828, "trigger_loss": 8.3615, "lr": 0.000162, "tok_per_s": 34599, "eta_h": 5.44}
125
+ {"step": 2480, "max_steps": 7629, "tokens": 325189632, "loss": 2.8359, "trigger_loss": 8.8689, "lr": 0.000161, "tok_per_s": 34600, "eta_h": 5.42}
126
+ {"step": 2500, "max_steps": 7629, "tokens": 327811072, "loss": 2.8184, "trigger_loss": 8.4787, "lr": 0.000161, "tok_per_s": 34600, "eta_h": 5.4}
127
+ {"step": 2520, "max_steps": 7629, "tokens": 330432512, "loss": 2.8145, "trigger_loss": 8.3295, "lr": 0.00016, "tok_per_s": 34601, "eta_h": 5.37}
128
+ {"step": 2540, "max_steps": 7629, "tokens": 333053952, "loss": 2.9199, "trigger_loss": 8.5546, "lr": 0.000159, "tok_per_s": 34602, "eta_h": 5.35}
129
+ {"step": 2560, "max_steps": 7629, "tokens": 335675392, "loss": 2.918, "trigger_loss": 8.2993, "lr": 0.000159, "tok_per_s": 34602, "eta_h": 5.33}
130
+ {"step": 2580, "max_steps": 7629, "tokens": 338296832, "loss": 2.8633, "trigger_loss": 8.2814, "lr": 0.000158, "tok_per_s": 34603, "eta_h": 5.31}
131
+ {"step": 2600, "max_steps": 7629, "tokens": 340918272, "loss": 2.7852, "trigger_loss": 8.7075, "lr": 0.000157, "tok_per_s": 34603, "eta_h": 5.29}
132
+ {"step": 2620, "max_steps": 7629, "tokens": 343539712, "loss": 2.7852, "trigger_loss": 8.2531, "lr": 0.000157, "tok_per_s": 34604, "eta_h": 5.27}
133
+ {"step": 2640, "max_steps": 7629, "tokens": 346161152, "loss": 2.7715, "trigger_loss": 8.5691, "lr": 0.000156, "tok_per_s": 34604, "eta_h": 5.25}
134
+ {"step": 2660, "max_steps": 7629, "tokens": 348782592, "loss": 2.8809, "trigger_loss": 8.3017, "lr": 0.000156, "tok_per_s": 34603, "eta_h": 5.23}
135
+ {"step": 2680, "max_steps": 7629, "tokens": 351404032, "loss": 2.8691, "trigger_loss": 8.7799, "lr": 0.000155, "tok_per_s": 34603, "eta_h": 5.21}
136
+ {"step": 2700, "max_steps": 7629, "tokens": 354025472, "loss": 2.834, "trigger_loss": 8.4121, "lr": 0.000154, "tok_per_s": 34604, "eta_h": 5.18}
137
+ {"step": 2720, "max_steps": 7629, "tokens": 356646912, "loss": 2.8496, "trigger_loss": 8.478, "lr": 0.000154, "tok_per_s": 34603, "eta_h": 5.16}
138
+ {"step": 2740, "max_steps": 7629, "tokens": 359268352, "loss": 2.8145, "trigger_loss": 8.4822, "lr": 0.000153, "tok_per_s": 34602, "eta_h": 5.14}
139
+ {"step": 2760, "max_steps": 7629, "tokens": 361889792, "loss": 2.8457, "trigger_loss": 8.4075, "lr": 0.000152, "tok_per_s": 34601, "eta_h": 5.12}
140
+ {"step": 2780, "max_steps": 7629, "tokens": 364511232, "loss": 2.8672, "trigger_loss": 8.3732, "lr": 0.000152, "tok_per_s": 34599, "eta_h": 5.1}
141
+ {"step": 2800, "max_steps": 7629, "tokens": 367132672, "loss": 2.8535, "trigger_loss": 8.4074, "lr": 0.000151, "tok_per_s": 34598, "eta_h": 5.08}
142
+ {"step": 2820, "max_steps": 7629, "tokens": 369754112, "loss": 2.9141, "trigger_loss": 8.3236, "lr": 0.00015, "tok_per_s": 34596, "eta_h": 5.06}
143
+ {"step": 2840, "max_steps": 7629, "tokens": 372375552, "loss": 2.7734, "trigger_loss": 8.4318, "lr": 0.00015, "tok_per_s": 34595, "eta_h": 5.04}
144
+ {"step": 2860, "max_steps": 7629, "tokens": 374996992, "loss": 2.9082, "trigger_loss": 8.797, "lr": 0.000149, "tok_per_s": 34594, "eta_h": 5.02}
145
+ {"step": 2880, "max_steps": 7629, "tokens": 377618432, "loss": 2.8438, "trigger_loss": 8.2826, "lr": 0.000148, "tok_per_s": 34593, "eta_h": 5.0}
146
+ {"step": 2900, "max_steps": 7629, "tokens": 380239872, "loss": 2.7598, "trigger_loss": 8.5604, "lr": 0.000147, "tok_per_s": 34592, "eta_h": 4.98}
147
+ {"step": 2920, "max_steps": 7629, "tokens": 382861312, "loss": 2.7852, "trigger_loss": 8.7731, "lr": 0.000147, "tok_per_s": 34591, "eta_h": 4.96}
148
+ {"step": 2940, "max_steps": 7629, "tokens": 385482752, "loss": 2.9277, "trigger_loss": 8.1048, "lr": 0.000146, "tok_per_s": 34590, "eta_h": 4.93}
149
+ {"step": 2960, "max_steps": 7629, "tokens": 388104192, "loss": 2.8242, "trigger_loss": 8.4793, "lr": 0.000145, "tok_per_s": 34589, "eta_h": 4.91}
150
+ {"step": 2980, "max_steps": 7629, "tokens": 390725632, "loss": 2.8789, "trigger_loss": 8.1694, "lr": 0.000145, "tok_per_s": 34588, "eta_h": 4.89}
151
+ {"step": 3000, "max_steps": 7629, "tokens": 393347072, "loss": 2.8262, "trigger_loss": 8.5309, "lr": 0.000144, "tok_per_s": 34588, "eta_h": 4.87}
152
+ {"step": 3020, "max_steps": 7629, "tokens": 395968512, "loss": 2.8965, "trigger_loss": 8.2304, "lr": 0.000143, "tok_per_s": 34585, "eta_h": 4.85}
153
+ {"step": 3040, "max_steps": 7629, "tokens": 398589952, "loss": 2.8203, "trigger_loss": 8.2591, "lr": 0.000143, "tok_per_s": 34585, "eta_h": 4.83}
154
+ {"step": 3060, "max_steps": 7629, "tokens": 401211392, "loss": 2.918, "trigger_loss": 8.3788, "lr": 0.000142, "tok_per_s": 34584, "eta_h": 4.81}
155
+ {"step": 3080, "max_steps": 7629, "tokens": 403832832, "loss": 2.8672, "trigger_loss": 8.4747, "lr": 0.000141, "tok_per_s": 34583, "eta_h": 4.79}
156
+ {"step": 3100, "max_steps": 7629, "tokens": 406454272, "loss": 2.752, "trigger_loss": 8.4027, "lr": 0.00014, "tok_per_s": 34582, "eta_h": 4.77}
157
+ {"step": 3120, "max_steps": 7629, "tokens": 409075712, "loss": 2.8242, "trigger_loss": 8.3026, "lr": 0.00014, "tok_per_s": 34581, "eta_h": 4.75}
158
+ {"step": 3140, "max_steps": 7629, "tokens": 411697152, "loss": 2.8848, "trigger_loss": 8.1512, "lr": 0.000139, "tok_per_s": 34580, "eta_h": 4.73}
159
+ {"step": 3160, "max_steps": 7629, "tokens": 414318592, "loss": 2.8535, "trigger_loss": 8.4238, "lr": 0.000138, "tok_per_s": 34579, "eta_h": 4.7}
160
+ {"step": 3180, "max_steps": 7629, "tokens": 416940032, "loss": 2.8418, "trigger_loss": 7.9937, "lr": 0.000138, "tok_per_s": 34578, "eta_h": 4.68}
161
+ {"step": 3200, "max_steps": 7629, "tokens": 419561472, "loss": 2.8027, "trigger_loss": 8.2728, "lr": 0.000137, "tok_per_s": 34577, "eta_h": 4.66}
162
+ {"step": 3220, "max_steps": 7629, "tokens": 422182912, "loss": 2.8438, "trigger_loss": 8.461, "lr": 0.000136, "tok_per_s": 34576, "eta_h": 4.64}
163
+ {"step": 3240, "max_steps": 7629, "tokens": 424804352, "loss": 2.8672, "trigger_loss": 8.5962, "lr": 0.000135, "tok_per_s": 34576, "eta_h": 4.62}
164
+ {"step": 3260, "max_steps": 7629, "tokens": 427425792, "loss": 2.8574, "trigger_loss": 8.3475, "lr": 0.000135, "tok_per_s": 34575, "eta_h": 4.6}
165
+ {"step": 3280, "max_steps": 7629, "tokens": 430047232, "loss": 2.916, "trigger_loss": 8.2621, "lr": 0.000134, "tok_per_s": 34574, "eta_h": 4.58}
166
+ {"step": 3300, "max_steps": 7629, "tokens": 432668672, "loss": 2.7793, "trigger_loss": 8.4123, "lr": 0.000133, "tok_per_s": 34573, "eta_h": 4.56}
167
+ {"step": 3320, "max_steps": 7629, "tokens": 435290112, "loss": 2.8242, "trigger_loss": 8.3777, "lr": 0.000132, "tok_per_s": 34572, "eta_h": 4.54}
168
+ {"step": 3340, "max_steps": 7629, "tokens": 437911552, "loss": 2.793, "trigger_loss": 8.2119, "lr": 0.000132, "tok_per_s": 34572, "eta_h": 4.52}
169
+ {"step": 3360, "max_steps": 7629, "tokens": 440532992, "loss": 2.9102, "trigger_loss": 8.3399, "lr": 0.000131, "tok_per_s": 34572, "eta_h": 4.49}
170
+ {"step": 3380, "max_steps": 7629, "tokens": 443154432, "loss": 2.8262, "trigger_loss": 8.3942, "lr": 0.00013, "tok_per_s": 34571, "eta_h": 4.47}
171
+ {"step": 3400, "max_steps": 7629, "tokens": 445775872, "loss": 2.8555, "trigger_loss": 8.8352, "lr": 0.000129, "tok_per_s": 34571, "eta_h": 4.45}
172
+ {"step": 3420, "max_steps": 7629, "tokens": 448397312, "loss": 2.8906, "trigger_loss": 8.1896, "lr": 0.000129, "tok_per_s": 34571, "eta_h": 4.43}
173
+ {"step": 3440, "max_steps": 7629, "tokens": 451018752, "loss": 2.8262, "trigger_loss": 8.6814, "lr": 0.000128, "tok_per_s": 34570, "eta_h": 4.41}
174
+ {"step": 3460, "max_steps": 7629, "tokens": 453640192, "loss": 2.832, "trigger_loss": 8.2636, "lr": 0.000127, "tok_per_s": 34570, "eta_h": 4.39}
175
+ {"step": 3480, "max_steps": 7629, "tokens": 456261632, "loss": 2.9121, "trigger_loss": 8.3737, "lr": 0.000126, "tok_per_s": 34570, "eta_h": 4.37}
176
+ {"step": 3500, "max_steps": 7629, "tokens": 458883072, "loss": 2.8301, "trigger_loss": 8.4525, "lr": 0.000126, "tok_per_s": 34570, "eta_h": 4.35}
177
+ {"step": 3520, "max_steps": 7629, "tokens": 461504512, "loss": 2.9043, "trigger_loss": 8.0506, "lr": 0.000125, "tok_per_s": 34571, "eta_h": 4.33}
178
+ {"step": 3540, "max_steps": 7629, "tokens": 464125952, "loss": 2.8379, "trigger_loss": 8.5629, "lr": 0.000124, "tok_per_s": 34572, "eta_h": 4.31}
179
+ {"step": 3560, "max_steps": 7629, "tokens": 466747392, "loss": 2.9043, "trigger_loss": 8.4765, "lr": 0.000123, "tok_per_s": 34573, "eta_h": 4.28}
180
+ {"step": 3580, "max_steps": 7629, "tokens": 469368832, "loss": 2.8066, "trigger_loss": 8.7645, "lr": 0.000123, "tok_per_s": 34574, "eta_h": 4.26}
181
+ {"step": 3600, "max_steps": 7629, "tokens": 471990272, "loss": 2.873, "trigger_loss": 8.2662, "lr": 0.000122, "tok_per_s": 34574, "eta_h": 4.24}
182
+ {"step": 3620, "max_steps": 7629, "tokens": 474611712, "loss": 2.8223, "trigger_loss": 8.0597, "lr": 0.000121, "tok_per_s": 34575, "eta_h": 4.22}
183
+ {"step": 3640, "max_steps": 7629, "tokens": 477233152, "loss": 2.8125, "trigger_loss": 8.5191, "lr": 0.00012, "tok_per_s": 34576, "eta_h": 4.2}
184
+ {"step": 3660, "max_steps": 7629, "tokens": 479854592, "loss": 2.8027, "trigger_loss": 8.4548, "lr": 0.00012, "tok_per_s": 34577, "eta_h": 4.18}
185
+ {"step": 3680, "max_steps": 7629, "tokens": 482476032, "loss": 2.877, "trigger_loss": 8.2599, "lr": 0.000119, "tok_per_s": 34578, "eta_h": 4.16}
186
+ {"step": 3700, "max_steps": 7629, "tokens": 485097472, "loss": 2.9062, "trigger_loss": 8.2979, "lr": 0.000118, "tok_per_s": 34579, "eta_h": 4.14}
187
+ {"step": 3720, "max_steps": 7629, "tokens": 487718912, "loss": 2.8613, "trigger_loss": 8.3211, "lr": 0.000117, "tok_per_s": 34579, "eta_h": 4.11}
188
+ {"step": 3740, "max_steps": 7629, "tokens": 490340352, "loss": 2.8906, "trigger_loss": 7.9546, "lr": 0.000117, "tok_per_s": 34580, "eta_h": 4.09}
189
+ {"step": 3760, "max_steps": 7629, "tokens": 492961792, "loss": 2.8145, "trigger_loss": 8.4861, "lr": 0.000116, "tok_per_s": 34581, "eta_h": 4.07}
190
+ {"step": 3780, "max_steps": 7629, "tokens": 495583232, "loss": 2.7812, "trigger_loss": 8.3395, "lr": 0.000115, "tok_per_s": 34582, "eta_h": 4.05}
191
+ {"step": 3800, "max_steps": 7629, "tokens": 498204672, "loss": 2.9629, "trigger_loss": 8.1551, "lr": 0.000114, "tok_per_s": 34582, "eta_h": 4.03}
192
+ {"step": 3820, "max_steps": 7629, "tokens": 500826112, "loss": 2.8809, "trigger_loss": 8.3768, "lr": 0.000114, "tok_per_s": 34583, "eta_h": 4.01}
193
+ {"step": 3840, "max_steps": 7629, "tokens": 503447552, "loss": 2.877, "trigger_loss": 8.2502, "lr": 0.000113, "tok_per_s": 34584, "eta_h": 3.99}
194
+ {"step": 3860, "max_steps": 7629, "tokens": 506068992, "loss": 2.8418, "trigger_loss": 8.2381, "lr": 0.000112, "tok_per_s": 34584, "eta_h": 3.97}
195
+ {"step": 3880, "max_steps": 7629, "tokens": 508690432, "loss": 2.8926, "trigger_loss": 8.2664, "lr": 0.000111, "tok_per_s": 34585, "eta_h": 3.95}
196
+ {"step": 3900, "max_steps": 7629, "tokens": 511311872, "loss": 2.8516, "trigger_loss": 8.6109, "lr": 0.000111, "tok_per_s": 34586, "eta_h": 3.92}
197
+ {"step": 3920, "max_steps": 7629, "tokens": 513933312, "loss": 2.8242, "trigger_loss": 7.9975, "lr": 0.00011, "tok_per_s": 34587, "eta_h": 3.9}
198
+ {"step": 3940, "max_steps": 7629, "tokens": 516554752, "loss": 2.832, "trigger_loss": 8.2134, "lr": 0.000109, "tok_per_s": 34588, "eta_h": 3.88}
199
+ {"step": 3960, "max_steps": 7629, "tokens": 519176192, "loss": 2.8633, "trigger_loss": 8.2668, "lr": 0.000108, "tok_per_s": 34589, "eta_h": 3.86}
200
+ {"step": 3980, "max_steps": 7629, "tokens": 521797632, "loss": 2.8613, "trigger_loss": 8.4857, "lr": 0.000108, "tok_per_s": 34590, "eta_h": 3.84}
201
+ {"step": 4000, "max_steps": 7629, "tokens": 524419072, "loss": 2.8691, "trigger_loss": 8.3738, "lr": 0.000107, "tok_per_s": 34591, "eta_h": 3.82}
202
+ {"step": 4020, "max_steps": 7629, "tokens": 527040512, "loss": 2.9043, "trigger_loss": 8.0276, "lr": 0.000106, "tok_per_s": 34591, "eta_h": 3.8}
203
+ {"step": 4040, "max_steps": 7629, "tokens": 529661952, "loss": 2.8066, "trigger_loss": 8.2765, "lr": 0.000105, "tok_per_s": 34592, "eta_h": 3.78}
204
+ {"step": 4060, "max_steps": 7629, "tokens": 532283392, "loss": 2.7422, "trigger_loss": 7.8765, "lr": 0.000104, "tok_per_s": 34592, "eta_h": 3.76}
205
+ {"step": 4080, "max_steps": 7629, "tokens": 534904832, "loss": 2.877, "trigger_loss": 7.6545, "lr": 0.000104, "tok_per_s": 34593, "eta_h": 3.73}
206
+ {"step": 4100, "max_steps": 7629, "tokens": 537526272, "loss": 2.8828, "trigger_loss": 8.1533, "lr": 0.000103, "tok_per_s": 34594, "eta_h": 3.71}
207
+ {"step": 4120, "max_steps": 7629, "tokens": 540147712, "loss": 2.8066, "trigger_loss": 8.3175, "lr": 0.000102, "tok_per_s": 34595, "eta_h": 3.69}
208
+ {"step": 4140, "max_steps": 7629, "tokens": 542769152, "loss": 2.8164, "trigger_loss": 8.2816, "lr": 0.000101, "tok_per_s": 34596, "eta_h": 3.67}
209
+ {"step": 4160, "max_steps": 7629, "tokens": 545390592, "loss": 2.8516, "trigger_loss": 8.0061, "lr": 0.000101, "tok_per_s": 34597, "eta_h": 3.65}
210
+ {"step": 4180, "max_steps": 7629, "tokens": 548012032, "loss": 2.916, "trigger_loss": 8.1597, "lr": 0.0001, "tok_per_s": 34598, "eta_h": 3.63}
211
+ {"step": 4200, "max_steps": 7629, "tokens": 550633472, "loss": 2.832, "trigger_loss": 8.0329, "lr": 9.9e-05, "tok_per_s": 34599, "eta_h": 3.61}
212
+ {"step": 4220, "max_steps": 7629, "tokens": 553254912, "loss": 2.7695, "trigger_loss": 8.1918, "lr": 9.8e-05, "tok_per_s": 34599, "eta_h": 3.59}
213
+ {"step": 4240, "max_steps": 7629, "tokens": 555876352, "loss": 2.8496, "trigger_loss": 8.29, "lr": 9.8e-05, "tok_per_s": 34600, "eta_h": 3.57}
214
+ {"step": 4260, "max_steps": 7629, "tokens": 558497792, "loss": 2.8848, "trigger_loss": 8.1953, "lr": 9.7e-05, "tok_per_s": 34601, "eta_h": 3.54}
215
+ {"step": 4280, "max_steps": 7629, "tokens": 561119232, "loss": 2.8086, "trigger_loss": 8.2174, "lr": 9.6e-05, "tok_per_s": 34602, "eta_h": 3.52}
216
+ {"step": 4300, "max_steps": 7629, "tokens": 563740672, "loss": 2.8398, "trigger_loss": 8.5004, "lr": 9.5e-05, "tok_per_s": 34602, "eta_h": 3.5}
217
+ {"step": 4320, "max_steps": 7629, "tokens": 566362112, "loss": 2.9004, "trigger_loss": 8.1718, "lr": 9.5e-05, "tok_per_s": 34603, "eta_h": 3.48}
218
+ {"step": 4340, "max_steps": 7629, "tokens": 568983552, "loss": 2.8262, "trigger_loss": 7.9194, "lr": 9.4e-05, "tok_per_s": 34604, "eta_h": 3.46}
219
+ {"step": 4360, "max_steps": 7629, "tokens": 571604992, "loss": 2.8379, "trigger_loss": 8.3521, "lr": 9.3e-05, "tok_per_s": 34605, "eta_h": 3.44}
220
+ {"step": 4380, "max_steps": 7629, "tokens": 574226432, "loss": 2.7988, "trigger_loss": 8.1752, "lr": 9.2e-05, "tok_per_s": 34606, "eta_h": 3.42}
221
+ {"step": 4400, "max_steps": 7629, "tokens": 576847872, "loss": 2.7852, "trigger_loss": 8.1363, "lr": 9.2e-05, "tok_per_s": 34607, "eta_h": 3.4}
222
+ {"step": 4420, "max_steps": 7629, "tokens": 579469312, "loss": 2.8555, "trigger_loss": 8.3614, "lr": 9.1e-05, "tok_per_s": 34608, "eta_h": 3.37}
223
+ {"step": 4440, "max_steps": 7629, "tokens": 582090752, "loss": 2.9219, "trigger_loss": 8.6386, "lr": 9e-05, "tok_per_s": 34609, "eta_h": 3.35}
224
+ {"step": 4460, "max_steps": 7629, "tokens": 584712192, "loss": 2.8047, "trigger_loss": 7.8229, "lr": 8.9e-05, "tok_per_s": 34609, "eta_h": 3.33}
225
+ {"step": 4480, "max_steps": 7629, "tokens": 587333632, "loss": 2.9531, "trigger_loss": 8.5396, "lr": 8.9e-05, "tok_per_s": 34610, "eta_h": 3.31}
226
+ {"step": 4500, "max_steps": 7629, "tokens": 589955072, "loss": 2.8594, "trigger_loss": 8.2809, "lr": 8.8e-05, "tok_per_s": 34611, "eta_h": 3.29}
227
+ {"step": 4520, "max_steps": 7629, "tokens": 592576512, "loss": 2.8574, "trigger_loss": 8.2233, "lr": 8.7e-05, "tok_per_s": 34611, "eta_h": 3.27}
228
+ {"step": 4540, "max_steps": 7629, "tokens": 595197952, "loss": 2.8555, "trigger_loss": 7.9959, "lr": 8.6e-05, "tok_per_s": 34610, "eta_h": 3.25}
229
+ {"step": 4560, "max_steps": 7629, "tokens": 597819392, "loss": 2.8438, "trigger_loss": 8.2213, "lr": 8.6e-05, "tok_per_s": 34610, "eta_h": 3.23}
230
+ {"step": 4580, "max_steps": 7629, "tokens": 600440832, "loss": 2.8359, "trigger_loss": 8.0973, "lr": 8.5e-05, "tok_per_s": 34610, "eta_h": 3.21}
231
+ {"step": 4600, "max_steps": 7629, "tokens": 603062272, "loss": 2.7734, "trigger_loss": 8.4151, "lr": 8.4e-05, "tok_per_s": 34609, "eta_h": 3.19}
232
+ {"step": 4620, "max_steps": 7629, "tokens": 605683712, "loss": 2.8301, "trigger_loss": 8.0755, "lr": 8.4e-05, "tok_per_s": 34609, "eta_h": 3.16}
233
+ {"step": 4640, "max_steps": 7629, "tokens": 608305152, "loss": 2.8711, "trigger_loss": 8.1197, "lr": 8.3e-05, "tok_per_s": 34608, "eta_h": 3.14}
234
+ {"step": 4660, "max_steps": 7629, "tokens": 610926592, "loss": 2.9219, "trigger_loss": 8.1906, "lr": 8.2e-05, "tok_per_s": 34608, "eta_h": 3.12}
235
+ {"step": 4680, "max_steps": 7629, "tokens": 613548032, "loss": 2.8848, "trigger_loss": 8.2132, "lr": 8.1e-05, "tok_per_s": 34607, "eta_h": 3.1}
236
+ {"step": 4700, "max_steps": 7629, "tokens": 616169472, "loss": 2.8105, "trigger_loss": 8.4587, "lr": 8.1e-05, "tok_per_s": 34607, "eta_h": 3.08}
237
+ {"step": 4720, "max_steps": 7629, "tokens": 618790912, "loss": 2.8125, "trigger_loss": 8.3165, "lr": 8e-05, "tok_per_s": 34606, "eta_h": 3.06}
238
+ {"step": 4740, "max_steps": 7629, "tokens": 621412352, "loss": 2.8652, "trigger_loss": 8.4093, "lr": 7.9e-05, "tok_per_s": 34605, "eta_h": 3.04}
239
+ {"step": 4760, "max_steps": 7629, "tokens": 624033792, "loss": 2.7773, "trigger_loss": 8.2918, "lr": 7.9e-05, "tok_per_s": 34604, "eta_h": 3.02}
240
+ {"step": 4780, "max_steps": 7629, "tokens": 626655232, "loss": 2.877, "trigger_loss": 8.3413, "lr": 7.8e-05, "tok_per_s": 34603, "eta_h": 3.0}
241
+ {"step": 4800, "max_steps": 7629, "tokens": 629276672, "loss": 2.8418, "trigger_loss": 8.4125, "lr": 7.7e-05, "tok_per_s": 34602, "eta_h": 2.98}
242
+ {"step": 4820, "max_steps": 7629, "tokens": 631898112, "loss": 2.8906, "trigger_loss": 8.1141, "lr": 7.6e-05, "tok_per_s": 34601, "eta_h": 2.95}
243
+ {"step": 4840, "max_steps": 7629, "tokens": 634519552, "loss": 2.8574, "trigger_loss": 8.2917, "lr": 7.6e-05, "tok_per_s": 34600, "eta_h": 2.93}
244
+ {"step": 4860, "max_steps": 7629, "tokens": 637140992, "loss": 2.8945, "trigger_loss": 8.4433, "lr": 7.5e-05, "tok_per_s": 34600, "eta_h": 2.91}
245
+ {"step": 4880, "max_steps": 7629, "tokens": 639762432, "loss": 2.8652, "trigger_loss": 8.4191, "lr": 7.4e-05, "tok_per_s": 34599, "eta_h": 2.89}
246
+ {"step": 4900, "max_steps": 7629, "tokens": 642383872, "loss": 2.7969, "trigger_loss": 7.874, "lr": 7.4e-05, "tok_per_s": 34598, "eta_h": 2.87}
247
+ {"step": 4920, "max_steps": 7629, "tokens": 645005312, "loss": 2.8398, "trigger_loss": 8.1871, "lr": 7.3e-05, "tok_per_s": 34598, "eta_h": 2.85}
248
+ {"step": 4940, "max_steps": 7629, "tokens": 647626752, "loss": 2.7559, "trigger_loss": 8.5084, "lr": 7.2e-05, "tok_per_s": 34597, "eta_h": 2.83}
249
+ {"step": 4960, "max_steps": 7629, "tokens": 650248192, "loss": 2.9121, "trigger_loss": 7.9432, "lr": 7.1e-05, "tok_per_s": 34596, "eta_h": 2.81}
250
+ {"step": 4980, "max_steps": 7629, "tokens": 652869632, "loss": 2.7969, "trigger_loss": 8.2651, "lr": 7.1e-05, "tok_per_s": 34595, "eta_h": 2.79}
251
+ {"step": 5000, "max_steps": 7629, "tokens": 655491072, "loss": 2.8574, "trigger_loss": 8.2324, "lr": 7e-05, "tok_per_s": 34594, "eta_h": 2.77}
252
+ {"step": 5020, "max_steps": 7629, "tokens": 658112512, "loss": 2.8105, "trigger_loss": 8.2674, "lr": 6.9e-05, "tok_per_s": 34592, "eta_h": 2.74}
253
+ {"step": 5040, "max_steps": 7629, "tokens": 660733952, "loss": 2.8965, "trigger_loss": 8.0373, "lr": 6.9e-05, "tok_per_s": 34592, "eta_h": 2.72}
254
+ {"step": 5060, "max_steps": 7629, "tokens": 663355392, "loss": 2.8047, "trigger_loss": 8.0751, "lr": 6.8e-05, "tok_per_s": 34591, "eta_h": 2.7}
255
+ {"step": 5080, "max_steps": 7629, "tokens": 665976832, "loss": 2.873, "trigger_loss": 8.5097, "lr": 6.7e-05, "tok_per_s": 34590, "eta_h": 2.68}
256
+ {"step": 5100, "max_steps": 7629, "tokens": 668598272, "loss": 2.8164, "trigger_loss": 8.4866, "lr": 6.7e-05, "tok_per_s": 34589, "eta_h": 2.66}
257
+ {"step": 5120, "max_steps": 7629, "tokens": 671219712, "loss": 2.8555, "trigger_loss": 8.7352, "lr": 6.6e-05, "tok_per_s": 34588, "eta_h": 2.64}
258
+ {"step": 5140, "max_steps": 7629, "tokens": 673841152, "loss": 2.793, "trigger_loss": 8.3232, "lr": 6.5e-05, "tok_per_s": 34587, "eta_h": 2.62}
259
+ {"step": 5160, "max_steps": 7629, "tokens": 676462592, "loss": 2.8477, "trigger_loss": 7.9935, "lr": 6.5e-05, "tok_per_s": 34586, "eta_h": 2.6}
260
+ {"step": 5180, "max_steps": 7629, "tokens": 679084032, "loss": 2.8047, "trigger_loss": 7.9701, "lr": 6.4e-05, "tok_per_s": 34585, "eta_h": 2.58}
261
+ {"step": 5200, "max_steps": 7629, "tokens": 681705472, "loss": 2.9219, "trigger_loss": 8.5055, "lr": 6.3e-05, "tok_per_s": 34584, "eta_h": 2.56}
262
+ {"step": 5220, "max_steps": 7629, "tokens": 684326912, "loss": 2.8145, "trigger_loss": 8.7365, "lr": 6.3e-05, "tok_per_s": 34583, "eta_h": 2.54}
263
+ {"step": 5240, "max_steps": 7629, "tokens": 686948352, "loss": 2.9316, "trigger_loss": 8.1217, "lr": 6.2e-05, "tok_per_s": 34582, "eta_h": 2.51}
264
+ {"step": 5260, "max_steps": 7629, "tokens": 689569792, "loss": 2.8418, "trigger_loss": 8.4423, "lr": 6.2e-05, "tok_per_s": 34581, "eta_h": 2.49}
265
+ {"step": 5280, "max_steps": 7629, "tokens": 692191232, "loss": 2.8887, "trigger_loss": 8.3042, "lr": 6.1e-05, "tok_per_s": 34580, "eta_h": 2.47}
266
+ {"step": 5300, "max_steps": 7629, "tokens": 694812672, "loss": 2.8242, "trigger_loss": 8.3041, "lr": 6e-05, "tok_per_s": 34579, "eta_h": 2.45}
267
+ {"step": 5320, "max_steps": 7629, "tokens": 697434112, "loss": 2.916, "trigger_loss": 8.2149, "lr": 6e-05, "tok_per_s": 34578, "eta_h": 2.43}
268
+ {"step": 5340, "max_steps": 7629, "tokens": 700055552, "loss": 2.7695, "trigger_loss": 8.1728, "lr": 5.9e-05, "tok_per_s": 34577, "eta_h": 2.41}
269
+ {"step": 5360, "max_steps": 7629, "tokens": 702676992, "loss": 2.8301, "trigger_loss": 8.3413, "lr": 5.8e-05, "tok_per_s": 34576, "eta_h": 2.39}
270
+ {"step": 5380, "max_steps": 7629, "tokens": 705298432, "loss": 2.8398, "trigger_loss": 8.0103, "lr": 5.8e-05, "tok_per_s": 34575, "eta_h": 2.37}
271
+ {"step": 5400, "max_steps": 7629, "tokens": 707919872, "loss": 2.875, "trigger_loss": 8.4512, "lr": 5.7e-05, "tok_per_s": 34574, "eta_h": 2.35}
272
+ {"step": 5420, "max_steps": 7629, "tokens": 710541312, "loss": 2.8438, "trigger_loss": 8.0954, "lr": 5.6e-05, "tok_per_s": 34573, "eta_h": 2.33}
273
+ {"step": 5440, "max_steps": 7629, "tokens": 713162752, "loss": 2.8789, "trigger_loss": 8.3125, "lr": 5.6e-05, "tok_per_s": 34572, "eta_h": 2.3}
274
+ {"step": 5460, "max_steps": 7629, "tokens": 715784192, "loss": 2.9785, "trigger_loss": 8.1379, "lr": 5.5e-05, "tok_per_s": 34571, "eta_h": 2.28}
275
+ {"step": 5480, "max_steps": 7629, "tokens": 718405632, "loss": 2.8809, "trigger_loss": 8.1616, "lr": 5.5e-05, "tok_per_s": 34570, "eta_h": 2.26}
276
+ {"step": 5500, "max_steps": 7629, "tokens": 721027072, "loss": 2.8418, "trigger_loss": 8.3383, "lr": 5.4e-05, "tok_per_s": 34569, "eta_h": 2.24}
277
+ {"step": 5520, "max_steps": 7629, "tokens": 723648512, "loss": 2.7852, "trigger_loss": 8.1694, "lr": 5.3e-05, "tok_per_s": 34568, "eta_h": 2.22}
278
+ {"step": 5540, "max_steps": 7629, "tokens": 726269952, "loss": 2.832, "trigger_loss": 8.0455, "lr": 5.3e-05, "tok_per_s": 34567, "eta_h": 2.2}
279
+ {"step": 5560, "max_steps": 7629, "tokens": 728891392, "loss": 2.9551, "trigger_loss": 8.0625, "lr": 5.2e-05, "tok_per_s": 34566, "eta_h": 2.18}
280
+ {"step": 5580, "max_steps": 7629, "tokens": 731512832, "loss": 2.8398, "trigger_loss": 7.9327, "lr": 5.2e-05, "tok_per_s": 34565, "eta_h": 2.16}
281
+ {"step": 5600, "max_steps": 7629, "tokens": 734134272, "loss": 2.8047, "trigger_loss": 7.9318, "lr": 5.1e-05, "tok_per_s": 34563, "eta_h": 2.14}
282
+ {"step": 5620, "max_steps": 7629, "tokens": 736755712, "loss": 2.8535, "trigger_loss": 8.444, "lr": 5.1e-05, "tok_per_s": 34562, "eta_h": 2.12}
283
+ {"step": 5640, "max_steps": 7629, "tokens": 739377152, "loss": 2.9199, "trigger_loss": 8.0623, "lr": 5e-05, "tok_per_s": 34561, "eta_h": 2.09}
284
+ {"step": 5660, "max_steps": 7629, "tokens": 741998592, "loss": 2.7617, "trigger_loss": 8.105, "lr": 4.9e-05, "tok_per_s": 34560, "eta_h": 2.07}
285
+ {"step": 5680, "max_steps": 7629, "tokens": 744620032, "loss": 2.8535, "trigger_loss": 8.1214, "lr": 4.9e-05, "tok_per_s": 34559, "eta_h": 2.05}
286
+ {"step": 5700, "max_steps": 7629, "tokens": 747241472, "loss": 2.8242, "trigger_loss": 8.3531, "lr": 4.8e-05, "tok_per_s": 34558, "eta_h": 2.03}
287
+ {"step": 5720, "max_steps": 7629, "tokens": 749862912, "loss": 2.8691, "trigger_loss": 8.3678, "lr": 4.8e-05, "tok_per_s": 34557, "eta_h": 2.01}
288
+ {"step": 5740, "max_steps": 7629, "tokens": 752484352, "loss": 2.8516, "trigger_loss": 8.0167, "lr": 4.7e-05, "tok_per_s": 34556, "eta_h": 1.99}
289
+ {"step": 5760, "max_steps": 7629, "tokens": 755105792, "loss": 2.7734, "trigger_loss": 8.5043, "lr": 4.7e-05, "tok_per_s": 34554, "eta_h": 1.97}
290
+ {"step": 5780, "max_steps": 7629, "tokens": 757727232, "loss": 2.7949, "trigger_loss": 8.2561, "lr": 4.6e-05, "tok_per_s": 34553, "eta_h": 1.95}
291
+ {"step": 5800, "max_steps": 7629, "tokens": 760348672, "loss": 2.8496, "trigger_loss": 7.972, "lr": 4.6e-05, "tok_per_s": 34552, "eta_h": 1.93}
292
+ {"step": 5820, "max_steps": 7629, "tokens": 762970112, "loss": 2.8301, "trigger_loss": 8.2886, "lr": 4.5e-05, "tok_per_s": 34551, "eta_h": 1.91}
293
+ {"step": 5840, "max_steps": 7629, "tokens": 765591552, "loss": 2.8496, "trigger_loss": 8.2836, "lr": 4.5e-05, "tok_per_s": 34550, "eta_h": 1.88}
294
+ {"step": 5860, "max_steps": 7629, "tokens": 768212992, "loss": 2.832, "trigger_loss": 8.1167, "lr": 4.4e-05, "tok_per_s": 34549, "eta_h": 1.86}
295
+ {"step": 5880, "max_steps": 7629, "tokens": 770834432, "loss": 2.748, "trigger_loss": 8.278, "lr": 4.4e-05, "tok_per_s": 34549, "eta_h": 1.84}
296
+ {"step": 5900, "max_steps": 7629, "tokens": 773455872, "loss": 2.8457, "trigger_loss": 8.0694, "lr": 4.3e-05, "tok_per_s": 34548, "eta_h": 1.82}
297
+ {"step": 5920, "max_steps": 7629, "tokens": 776077312, "loss": 2.8047, "trigger_loss": 8.3291, "lr": 4.2e-05, "tok_per_s": 34547, "eta_h": 1.8}
298
+ {"step": 5940, "max_steps": 7629, "tokens": 778698752, "loss": 2.8535, "trigger_loss": 8.3596, "lr": 4.2e-05, "tok_per_s": 34546, "eta_h": 1.78}
299
+ {"step": 5960, "max_steps": 7629, "tokens": 781320192, "loss": 2.9297, "trigger_loss": 7.9984, "lr": 4.2e-05, "tok_per_s": 34545, "eta_h": 1.76}
300
+ {"step": 5980, "max_steps": 7629, "tokens": 783941632, "loss": 2.875, "trigger_loss": 7.8127, "lr": 4.1e-05, "tok_per_s": 34544, "eta_h": 1.74}
301
+ {"step": 6000, "max_steps": 7629, "tokens": 786563072, "loss": 2.8691, "trigger_loss": 8.3062, "lr": 4.1e-05, "tok_per_s": 34543, "eta_h": 1.72}
302
+ {"step": 6020, "max_steps": 7629, "tokens": 789184512, "loss": 2.8066, "trigger_loss": 8.4019, "lr": 4e-05, "tok_per_s": 34541, "eta_h": 1.69}
303
+ {"step": 6040, "max_steps": 7629, "tokens": 791805952, "loss": 2.8926, "trigger_loss": 8.3882, "lr": 4e-05, "tok_per_s": 34540, "eta_h": 1.67}
304
+ {"step": 6060, "max_steps": 7629, "tokens": 794427392, "loss": 2.8633, "trigger_loss": 8.5126, "lr": 3.9e-05, "tok_per_s": 34540, "eta_h": 1.65}
305
+ {"step": 6080, "max_steps": 7629, "tokens": 797048832, "loss": 2.8555, "trigger_loss": 8.1523, "lr": 3.9e-05, "tok_per_s": 34539, "eta_h": 1.63}
306
+ {"step": 6100, "max_steps": 7629, "tokens": 799670272, "loss": 2.8418, "trigger_loss": 8.4756, "lr": 3.8e-05, "tok_per_s": 34538, "eta_h": 1.61}
307
+ {"step": 6120, "max_steps": 7629, "tokens": 802291712, "loss": 2.9297, "trigger_loss": 8.3061, "lr": 3.8e-05, "tok_per_s": 34537, "eta_h": 1.59}
308
+ {"step": 6140, "max_steps": 7629, "tokens": 804913152, "loss": 2.8848, "trigger_loss": 8.2148, "lr": 3.7e-05, "tok_per_s": 34536, "eta_h": 1.57}
309
+ {"step": 6160, "max_steps": 7629, "tokens": 807534592, "loss": 2.7734, "trigger_loss": 7.9043, "lr": 3.7e-05, "tok_per_s": 34535, "eta_h": 1.55}
310
+ {"step": 6180, "max_steps": 7629, "tokens": 810156032, "loss": 2.873, "trigger_loss": 8.0583, "lr": 3.6e-05, "tok_per_s": 34534, "eta_h": 1.53}
311
+ {"step": 6200, "max_steps": 7629, "tokens": 812777472, "loss": 2.834, "trigger_loss": 8.3037, "lr": 3.6e-05, "tok_per_s": 34534, "eta_h": 1.51}
312
+ {"step": 6220, "max_steps": 7629, "tokens": 815398912, "loss": 2.8516, "trigger_loss": 7.8575, "lr": 3.6e-05, "tok_per_s": 34534, "eta_h": 1.48}
313
+ {"step": 6240, "max_steps": 7629, "tokens": 818020352, "loss": 2.8047, "trigger_loss": 7.9609, "lr": 3.5e-05, "tok_per_s": 34535, "eta_h": 1.46}
314
+ {"step": 6260, "max_steps": 7629, "tokens": 820641792, "loss": 2.8887, "trigger_loss": 8.3598, "lr": 3.5e-05, "tok_per_s": 34535, "eta_h": 1.44}
315
+ {"step": 6280, "max_steps": 7629, "tokens": 823263232, "loss": 2.8242, "trigger_loss": 8.2189, "lr": 3.4e-05, "tok_per_s": 34536, "eta_h": 1.42}
316
+ {"step": 6300, "max_steps": 7629, "tokens": 825884672, "loss": 2.8242, "trigger_loss": 8.6921, "lr": 3.4e-05, "tok_per_s": 34537, "eta_h": 1.4}
317
+ {"step": 6320, "max_steps": 7629, "tokens": 828506112, "loss": 2.7637, "trigger_loss": 7.912, "lr": 3.3e-05, "tok_per_s": 34538, "eta_h": 1.38}
318
+ {"step": 6340, "max_steps": 7629, "tokens": 831127552, "loss": 2.8574, "trigger_loss": 8.1472, "lr": 3.3e-05, "tok_per_s": 34538, "eta_h": 1.36}
319
+ {"step": 6360, "max_steps": 7629, "tokens": 833748992, "loss": 2.8789, "trigger_loss": 7.9231, "lr": 3.3e-05, "tok_per_s": 34539, "eta_h": 1.34}
320
+ {"step": 6380, "max_steps": 7629, "tokens": 836370432, "loss": 2.9062, "trigger_loss": 8.0961, "lr": 3.2e-05, "tok_per_s": 34540, "eta_h": 1.32}
321
+ {"step": 6400, "max_steps": 7629, "tokens": 838991872, "loss": 2.873, "trigger_loss": 8.1432, "lr": 3.2e-05, "tok_per_s": 34541, "eta_h": 1.29}
322
+ {"step": 6420, "max_steps": 7629, "tokens": 841613312, "loss": 2.8359, "trigger_loss": 7.9108, "lr": 3.2e-05, "tok_per_s": 34542, "eta_h": 1.27}
323
+ {"step": 6440, "max_steps": 7629, "tokens": 844234752, "loss": 2.9805, "trigger_loss": 7.9148, "lr": 3.1e-05, "tok_per_s": 34542, "eta_h": 1.25}
324
+ {"step": 6460, "max_steps": 7629, "tokens": 846856192, "loss": 2.8574, "trigger_loss": 8.5409, "lr": 3.1e-05, "tok_per_s": 34543, "eta_h": 1.23}
325
+ {"step": 6480, "max_steps": 7629, "tokens": 849477632, "loss": 2.8555, "trigger_loss": 8.4523, "lr": 3e-05, "tok_per_s": 34544, "eta_h": 1.21}
326
+ {"step": 6500, "max_steps": 7629, "tokens": 852099072, "loss": 2.7656, "trigger_loss": 8.3114, "lr": 3e-05, "tok_per_s": 34545, "eta_h": 1.19}
327
+ {"step": 6520, "max_steps": 7629, "tokens": 854720512, "loss": 2.8086, "trigger_loss": 8.369, "lr": 3e-05, "tok_per_s": 34546, "eta_h": 1.17}
328
+ {"step": 6540, "max_steps": 7629, "tokens": 857341952, "loss": 2.8652, "trigger_loss": 8.6503, "lr": 2.9e-05, "tok_per_s": 34547, "eta_h": 1.15}
329
+ {"step": 6560, "max_steps": 7629, "tokens": 859963392, "loss": 2.8496, "trigger_loss": 8.4851, "lr": 2.9e-05, "tok_per_s": 34547, "eta_h": 1.13}
330
+ {"step": 6580, "max_steps": 7629, "tokens": 862584832, "loss": 2.8438, "trigger_loss": 8.2134, "lr": 2.9e-05, "tok_per_s": 34548, "eta_h": 1.1}
331
+ {"step": 6600, "max_steps": 7629, "tokens": 865206272, "loss": 2.7324, "trigger_loss": 8.3278, "lr": 2.8e-05, "tok_per_s": 34549, "eta_h": 1.08}
332
+ {"step": 6620, "max_steps": 7629, "tokens": 867827712, "loss": 2.8848, "trigger_loss": 8.859, "lr": 2.8e-05, "tok_per_s": 34550, "eta_h": 1.06}
333
+ {"step": 6640, "max_steps": 7629, "tokens": 870449152, "loss": 2.7559, "trigger_loss": 8.1291, "lr": 2.8e-05, "tok_per_s": 34551, "eta_h": 1.04}
334
+ {"step": 6660, "max_steps": 7629, "tokens": 873070592, "loss": 2.8184, "trigger_loss": 8.0654, "lr": 2.7e-05, "tok_per_s": 34551, "eta_h": 1.02}
335
+ {"step": 6680, "max_steps": 7629, "tokens": 875692032, "loss": 2.7383, "trigger_loss": 7.9261, "lr": 2.7e-05, "tok_per_s": 34552, "eta_h": 1.0}
336
+ {"step": 6700, "max_steps": 7629, "tokens": 878313472, "loss": 2.8145, "trigger_loss": 8.128, "lr": 2.7e-05, "tok_per_s": 34553, "eta_h": 0.98}
337
+ {"step": 6720, "max_steps": 7629, "tokens": 880934912, "loss": 2.8867, "trigger_loss": 7.9306, "lr": 2.7e-05, "tok_per_s": 34554, "eta_h": 0.96}
338
+ {"step": 6740, "max_steps": 7629, "tokens": 883556352, "loss": 2.7129, "trigger_loss": 8.6243, "lr": 2.6e-05, "tok_per_s": 34554, "eta_h": 0.94}
339
+ {"step": 6760, "max_steps": 7629, "tokens": 886177792, "loss": 2.8613, "trigger_loss": 8.3007, "lr": 2.6e-05, "tok_per_s": 34555, "eta_h": 0.91}
340
+ {"step": 6780, "max_steps": 7629, "tokens": 888799232, "loss": 2.9121, "trigger_loss": 8.2574, "lr": 2.6e-05, "tok_per_s": 34556, "eta_h": 0.89}
341
+ {"step": 6800, "max_steps": 7629, "tokens": 891420672, "loss": 2.9004, "trigger_loss": 7.913, "lr": 2.5e-05, "tok_per_s": 34557, "eta_h": 0.87}
342
+ {"step": 6820, "max_steps": 7629, "tokens": 894042112, "loss": 2.8906, "trigger_loss": 7.7013, "lr": 2.5e-05, "tok_per_s": 34557, "eta_h": 0.85}
343
+ {"step": 6840, "max_steps": 7629, "tokens": 896663552, "loss": 2.7676, "trigger_loss": 8.4217, "lr": 2.5e-05, "tok_per_s": 34558, "eta_h": 0.83}
344
+ {"step": 6860, "max_steps": 7629, "tokens": 899284992, "loss": 2.8555, "trigger_loss": 8.0239, "lr": 2.5e-05, "tok_per_s": 34559, "eta_h": 0.81}
345
+ {"step": 6880, "max_steps": 7629, "tokens": 901906432, "loss": 2.873, "trigger_loss": 8.1977, "lr": 2.4e-05, "tok_per_s": 34560, "eta_h": 0.79}
346
+ {"step": 6900, "max_steps": 7629, "tokens": 904527872, "loss": 2.7891, "trigger_loss": 8.0727, "lr": 2.4e-05, "tok_per_s": 34560, "eta_h": 0.77}
347
+ {"step": 6920, "max_steps": 7629, "tokens": 907149312, "loss": 2.9277, "trigger_loss": 7.989, "lr": 2.4e-05, "tok_per_s": 34561, "eta_h": 0.75}
348
+ {"step": 6940, "max_steps": 7629, "tokens": 909770752, "loss": 2.8945, "trigger_loss": 8.3434, "lr": 2.4e-05, "tok_per_s": 34562, "eta_h": 0.72}
349
+ {"step": 6960, "max_steps": 7629, "tokens": 912392192, "loss": 2.8926, "trigger_loss": 8.2222, "lr": 2.4e-05, "tok_per_s": 34563, "eta_h": 0.7}
350
+ {"step": 6980, "max_steps": 7629, "tokens": 915013632, "loss": 2.8125, "trigger_loss": 8.3866, "lr": 2.3e-05, "tok_per_s": 34563, "eta_h": 0.68}
351
+ {"step": 7000, "max_steps": 7629, "tokens": 917635072, "loss": 2.8535, "trigger_loss": 8.7979, "lr": 2.3e-05, "tok_per_s": 34564, "eta_h": 0.66}
352
+ {"step": 7020, "max_steps": 7629, "tokens": 920256512, "loss": 2.8086, "trigger_loss": 8.7109, "lr": 2.3e-05, "tok_per_s": 34564, "eta_h": 0.64}
353
+ {"step": 7040, "max_steps": 7629, "tokens": 922877952, "loss": 2.834, "trigger_loss": 7.9303, "lr": 2.3e-05, "tok_per_s": 34565, "eta_h": 0.62}
354
+ {"step": 7060, "max_steps": 7629, "tokens": 925499392, "loss": 2.832, "trigger_loss": 8.0012, "lr": 2.3e-05, "tok_per_s": 34565, "eta_h": 0.6}
355
+ {"step": 7080, "max_steps": 7629, "tokens": 928120832, "loss": 2.834, "trigger_loss": 8.2277, "lr": 2.2e-05, "tok_per_s": 34566, "eta_h": 0.58}
356
+ {"step": 7100, "max_steps": 7629, "tokens": 930742272, "loss": 2.7598, "trigger_loss": 8.2055, "lr": 2.2e-05, "tok_per_s": 34567, "eta_h": 0.56}
357
+ {"step": 7120, "max_steps": 7629, "tokens": 933363712, "loss": 2.8633, "trigger_loss": 8.3259, "lr": 2.2e-05, "tok_per_s": 34567, "eta_h": 0.54}
358
+ {"step": 7140, "max_steps": 7629, "tokens": 935985152, "loss": 2.8516, "trigger_loss": 8.1266, "lr": 2.2e-05, "tok_per_s": 34568, "eta_h": 0.51}
359
+ {"step": 7160, "max_steps": 7629, "tokens": 938606592, "loss": 2.8672, "trigger_loss": 8.2525, "lr": 2.2e-05, "tok_per_s": 34568, "eta_h": 0.49}
360
+ {"step": 7180, "max_steps": 7629, "tokens": 941228032, "loss": 2.8379, "trigger_loss": 8.1575, "lr": 2.2e-05, "tok_per_s": 34569, "eta_h": 0.47}
361
+ {"step": 7200, "max_steps": 7629, "tokens": 943849472, "loss": 2.8047, "trigger_loss": 8.1127, "lr": 2.1e-05, "tok_per_s": 34569, "eta_h": 0.45}
362
+ {"step": 7220, "max_steps": 7629, "tokens": 946470912, "loss": 2.8789, "trigger_loss": 8.7334, "lr": 2.1e-05, "tok_per_s": 34570, "eta_h": 0.43}
363
+ {"step": 7240, "max_steps": 7629, "tokens": 949092352, "loss": 2.8613, "trigger_loss": 8.3623, "lr": 2.1e-05, "tok_per_s": 34570, "eta_h": 0.41}
364
+ {"step": 7260, "max_steps": 7629, "tokens": 951713792, "loss": 2.8027, "trigger_loss": 8.1271, "lr": 2.1e-05, "tok_per_s": 34571, "eta_h": 0.39}
365
+ {"step": 7280, "max_steps": 7629, "tokens": 954335232, "loss": 2.8008, "trigger_loss": 8.4304, "lr": 2.1e-05, "tok_per_s": 34571, "eta_h": 0.37}
366
+ {"step": 7300, "max_steps": 7629, "tokens": 956956672, "loss": 2.8574, "trigger_loss": 8.4691, "lr": 2.1e-05, "tok_per_s": 34572, "eta_h": 0.35}
367
+ {"step": 7320, "max_steps": 7629, "tokens": 959578112, "loss": 2.8711, "trigger_loss": 8.283, "lr": 2.1e-05, "tok_per_s": 34572, "eta_h": 0.32}
368
+ {"step": 7340, "max_steps": 7629, "tokens": 962199552, "loss": 2.8066, "trigger_loss": 8.2839, "lr": 2.1e-05, "tok_per_s": 34573, "eta_h": 0.3}
369
+ {"step": 7360, "max_steps": 7629, "tokens": 964820992, "loss": 2.8281, "trigger_loss": 8.3459, "lr": 2.1e-05, "tok_per_s": 34573, "eta_h": 0.28}
370
+ {"step": 7380, "max_steps": 7629, "tokens": 967442432, "loss": 2.8789, "trigger_loss": 8.0184, "lr": 2e-05, "tok_per_s": 34574, "eta_h": 0.26}
371
+ {"step": 7400, "max_steps": 7629, "tokens": 970063872, "loss": 2.7891, "trigger_loss": 8.1881, "lr": 2e-05, "tok_per_s": 34574, "eta_h": 0.24}
372
+ {"step": 7420, "max_steps": 7629, "tokens": 972685312, "loss": 2.8027, "trigger_loss": 8.2919, "lr": 2e-05, "tok_per_s": 34575, "eta_h": 0.22}
373
+ {"step": 7440, "max_steps": 7629, "tokens": 975306752, "loss": 2.8438, "trigger_loss": 8.2997, "lr": 2e-05, "tok_per_s": 34576, "eta_h": 0.2}
374
+ {"step": 7460, "max_steps": 7629, "tokens": 977928192, "loss": 2.7754, "trigger_loss": 8.1513, "lr": 2e-05, "tok_per_s": 34577, "eta_h": 0.18}
375
+ {"step": 7480, "max_steps": 7629, "tokens": 980549632, "loss": 2.8672, "trigger_loss": 8.0519, "lr": 2e-05, "tok_per_s": 34577, "eta_h": 0.16}
376
+ {"step": 7500, "max_steps": 7629, "tokens": 983171072, "loss": 2.8105, "trigger_loss": 8.1883, "lr": 2e-05, "tok_per_s": 34578, "eta_h": 0.13}
377
+ {"step": 7520, "max_steps": 7629, "tokens": 985792512, "loss": 2.7891, "trigger_loss": 8.2672, "lr": 2e-05, "tok_per_s": 34578, "eta_h": 0.11}
378
+ {"step": 7540, "max_steps": 7629, "tokens": 988413952, "loss": 2.8574, "trigger_loss": 8.5483, "lr": 2e-05, "tok_per_s": 34579, "eta_h": 0.09}
379
+ {"step": 7560, "max_steps": 7629, "tokens": 991035392, "loss": 2.9102, "trigger_loss": 8.1155, "lr": 2e-05, "tok_per_s": 34579, "eta_h": 0.07}
380
+ {"step": 7580, "max_steps": 7629, "tokens": 993656832, "loss": 2.7695, "trigger_loss": 8.2149, "lr": 2e-05, "tok_per_s": 34580, "eta_h": 0.05}
381
+ {"step": 7600, "max_steps": 7629, "tokens": 996278272, "loss": 2.7988, "trigger_loss": 8.504, "lr": 2e-05, "tok_per_s": 34581, "eta_h": 0.03}
382
+ {"step": 7620, "max_steps": 7629, "tokens": 998899712, "loss": 2.8262, "trigger_loss": 8.1296, "lr": 2e-05, "tok_per_s": 34581, "eta_h": 0.01}