sedrickkeh commited on
Commit
43f5b47
·
verified ·
1 Parent(s): d8d98c8

Training in progress, epoch 0

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d8edb387e72a8877019b79774ec7d0df1d46591c37431d7a0e042d2f75214b3
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01296904242ad4ebcb68ec3b716c2e676eb67619b1e57c3a502f5a976da9e75c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8d7d530b5e6fb1c1455b1e2a7bbcc52e10625a127537f9dca5b6b5676e85b85
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e596351edb9daa4329d416f33caf99cabe80472bd2a0aa6ce2eb62615977736
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4ee739813af5d106633f4aa1ad6c52bec03e2c3800b070614b402b7be613c77
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7562ba59209db8b78a646d0eaac30715e964cdd95d81f1b0ab506a51b3bf81
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:411be6f68a57c444ca4a09c56237d9607f385157ba3ade7ae7444a3603febbfd
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c21a689d7cc44a7576fdc0c41e76efc08780adcee171ce7535515695f33863
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,302 +1,101 @@
1
- {"current_steps": 10, "total_steps": 3984, "loss": 1.0571, "lr": 5e-06, "epoch": 0.0100363818843307, "percentage": 0.25, "elapsed_time": "0:05:26", "remaining_time": "1 day, 12:02:55"}
2
- {"current_steps": 20, "total_steps": 3984, "loss": 0.952, "lr": 5e-06, "epoch": 0.0200727637686614, "percentage": 0.5, "elapsed_time": "0:10:48", "remaining_time": "1 day, 11:43:33"}
3
- {"current_steps": 30, "total_steps": 3984, "loss": 0.9113, "lr": 5e-06, "epoch": 0.030109145652992095, "percentage": 0.75, "elapsed_time": "0:16:11", "remaining_time": "1 day, 11:33:41"}
4
- {"current_steps": 40, "total_steps": 3984, "loss": 0.8932, "lr": 5e-06, "epoch": 0.0401455275373228, "percentage": 1.0, "elapsed_time": "0:21:34", "remaining_time": "1 day, 11:26:41"}
5
- {"current_steps": 50, "total_steps": 3984, "loss": 0.8806, "lr": 5e-06, "epoch": 0.050181909421653494, "percentage": 1.26, "elapsed_time": "0:26:54", "remaining_time": "1 day, 11:16:50"}
6
- {"current_steps": 60, "total_steps": 3984, "loss": 0.8625, "lr": 5e-06, "epoch": 0.06021829130598419, "percentage": 1.51, "elapsed_time": "0:32:14", "remaining_time": "1 day, 11:08:45"}
7
- {"current_steps": 70, "total_steps": 3984, "loss": 0.8457, "lr": 5e-06, "epoch": 0.07025467319031489, "percentage": 1.76, "elapsed_time": "0:37:36", "remaining_time": "1 day, 11:03:07"}
8
- {"current_steps": 80, "total_steps": 3984, "loss": 0.8343, "lr": 5e-06, "epoch": 0.0802910550746456, "percentage": 2.01, "elapsed_time": "0:42:57", "remaining_time": "1 day, 10:56:13"}
9
- {"current_steps": 90, "total_steps": 3984, "loss": 0.819, "lr": 5e-06, "epoch": 0.09032743695897628, "percentage": 2.26, "elapsed_time": "0:48:19", "remaining_time": "1 day, 10:50:59"}
10
- {"current_steps": 100, "total_steps": 3984, "loss": 0.813, "lr": 5e-06, "epoch": 0.10036381884330699, "percentage": 2.51, "elapsed_time": "0:53:41", "remaining_time": "1 day, 10:45:37"}
11
- {"current_steps": 110, "total_steps": 3984, "loss": 0.8046, "lr": 5e-06, "epoch": 0.11040020072763769, "percentage": 2.76, "elapsed_time": "0:59:04", "remaining_time": "1 day, 10:40:29"}
12
- {"current_steps": 120, "total_steps": 3984, "loss": 0.8002, "lr": 5e-06, "epoch": 0.12043658261196838, "percentage": 3.01, "elapsed_time": "1:04:27", "remaining_time": "1 day, 10:35:41"}
13
- {"current_steps": 130, "total_steps": 3984, "loss": 0.8017, "lr": 5e-06, "epoch": 0.13047296449629908, "percentage": 3.26, "elapsed_time": "1:09:50", "remaining_time": "1 day, 10:30:18"}
14
- {"current_steps": 140, "total_steps": 3984, "loss": 0.7946, "lr": 5e-06, "epoch": 0.14050934638062978, "percentage": 3.51, "elapsed_time": "1:15:12", "remaining_time": "1 day, 10:25:10"}
15
- {"current_steps": 150, "total_steps": 3984, "loss": 0.7968, "lr": 5e-06, "epoch": 0.1505457282649605, "percentage": 3.77, "elapsed_time": "1:20:35", "remaining_time": "1 day, 10:19:44"}
16
- {"current_steps": 160, "total_steps": 3984, "loss": 0.7939, "lr": 5e-06, "epoch": 0.1605821101492912, "percentage": 4.02, "elapsed_time": "1:25:56", "remaining_time": "1 day, 10:13:58"}
17
- {"current_steps": 170, "total_steps": 3984, "loss": 0.7868, "lr": 5e-06, "epoch": 0.17061849203362187, "percentage": 4.27, "elapsed_time": "1:31:20", "remaining_time": "1 day, 10:09:10"}
18
- {"current_steps": 180, "total_steps": 3984, "loss": 0.7865, "lr": 5e-06, "epoch": 0.18065487391795257, "percentage": 4.52, "elapsed_time": "1:36:43", "remaining_time": "1 day, 10:04:06"}
19
- {"current_steps": 190, "total_steps": 3984, "loss": 0.7852, "lr": 5e-06, "epoch": 0.19069125580228327, "percentage": 4.77, "elapsed_time": "1:42:06", "remaining_time": "1 day, 9:58:53"}
20
- {"current_steps": 200, "total_steps": 3984, "loss": 0.782, "lr": 5e-06, "epoch": 0.20072763768661397, "percentage": 5.02, "elapsed_time": "1:47:30", "remaining_time": "1 day, 9:53:55"}
21
- {"current_steps": 210, "total_steps": 3984, "loss": 0.7801, "lr": 5e-06, "epoch": 0.21076401957094468, "percentage": 5.27, "elapsed_time": "1:52:53", "remaining_time": "1 day, 9:48:48"}
22
- {"current_steps": 220, "total_steps": 3984, "loss": 0.7764, "lr": 5e-06, "epoch": 0.22080040145527538, "percentage": 5.52, "elapsed_time": "1:58:13", "remaining_time": "1 day, 9:42:36"}
23
- {"current_steps": 230, "total_steps": 3984, "loss": 0.781, "lr": 5e-06, "epoch": 0.23083678333960608, "percentage": 5.77, "elapsed_time": "2:03:33", "remaining_time": "1 day, 9:36:48"}
24
- {"current_steps": 240, "total_steps": 3984, "loss": 0.7782, "lr": 5e-06, "epoch": 0.24087316522393676, "percentage": 6.02, "elapsed_time": "2:08:53", "remaining_time": "1 day, 9:30:45"}
25
- {"current_steps": 250, "total_steps": 3984, "loss": 0.7737, "lr": 5e-06, "epoch": 0.25090954710826746, "percentage": 6.28, "elapsed_time": "2:14:13", "remaining_time": "1 day, 9:24:52"}
26
- {"current_steps": 260, "total_steps": 3984, "loss": 0.7681, "lr": 5e-06, "epoch": 0.26094592899259816, "percentage": 6.53, "elapsed_time": "2:19:35", "remaining_time": "1 day, 9:19:29"}
27
- {"current_steps": 270, "total_steps": 3984, "loss": 0.773, "lr": 5e-06, "epoch": 0.27098231087692887, "percentage": 6.78, "elapsed_time": "2:24:59", "remaining_time": "1 day, 9:14:30"}
28
- {"current_steps": 280, "total_steps": 3984, "loss": 0.7714, "lr": 5e-06, "epoch": 0.28101869276125957, "percentage": 7.03, "elapsed_time": "2:30:21", "remaining_time": "1 day, 9:09:02"}
29
- {"current_steps": 290, "total_steps": 3984, "loss": 0.7728, "lr": 5e-06, "epoch": 0.2910550746455903, "percentage": 7.28, "elapsed_time": "2:35:41", "remaining_time": "1 day, 9:03:13"}
30
- {"current_steps": 300, "total_steps": 3984, "loss": 0.769, "lr": 5e-06, "epoch": 0.301091456529921, "percentage": 7.53, "elapsed_time": "2:41:05", "remaining_time": "1 day, 8:58:13"}
31
- {"current_steps": 310, "total_steps": 3984, "loss": 0.7664, "lr": 5e-06, "epoch": 0.3111278384142517, "percentage": 7.78, "elapsed_time": "2:46:24", "remaining_time": "1 day, 8:52:16"}
32
- {"current_steps": 320, "total_steps": 3984, "loss": 0.7647, "lr": 5e-06, "epoch": 0.3211642202985824, "percentage": 8.03, "elapsed_time": "2:51:47", "remaining_time": "1 day, 8:47:01"}
33
- {"current_steps": 330, "total_steps": 3984, "loss": 0.7624, "lr": 5e-06, "epoch": 0.3312006021829131, "percentage": 8.28, "elapsed_time": "2:57:10", "remaining_time": "1 day, 8:41:46"}
34
- {"current_steps": 340, "total_steps": 3984, "loss": 0.7714, "lr": 5e-06, "epoch": 0.34123698406724373, "percentage": 8.53, "elapsed_time": "3:02:34", "remaining_time": "1 day, 8:36:43"}
35
- {"current_steps": 350, "total_steps": 3984, "loss": 0.763, "lr": 5e-06, "epoch": 0.35127336595157443, "percentage": 8.79, "elapsed_time": "3:07:57", "remaining_time": "1 day, 8:31:35"}
36
- {"current_steps": 360, "total_steps": 3984, "loss": 0.7624, "lr": 5e-06, "epoch": 0.36130974783590514, "percentage": 9.04, "elapsed_time": "3:13:21", "remaining_time": "1 day, 8:26:28"}
37
- {"current_steps": 370, "total_steps": 3984, "loss": 0.7626, "lr": 5e-06, "epoch": 0.37134612972023584, "percentage": 9.29, "elapsed_time": "3:18:44", "remaining_time": "1 day, 8:21:09"}
38
- {"current_steps": 380, "total_steps": 3984, "loss": 0.7685, "lr": 5e-06, "epoch": 0.38138251160456654, "percentage": 9.54, "elapsed_time": "3:24:07", "remaining_time": "1 day, 8:15:56"}
39
- {"current_steps": 390, "total_steps": 3984, "loss": 0.7591, "lr": 5e-06, "epoch": 0.39141889348889725, "percentage": 9.79, "elapsed_time": "3:29:29", "remaining_time": "1 day, 8:10:34"}
40
- {"current_steps": 400, "total_steps": 3984, "loss": 0.7575, "lr": 5e-06, "epoch": 0.40145527537322795, "percentage": 10.04, "elapsed_time": "3:34:51", "remaining_time": "1 day, 8:05:10"}
41
- {"current_steps": 410, "total_steps": 3984, "loss": 0.761, "lr": 5e-06, "epoch": 0.41149165725755865, "percentage": 10.29, "elapsed_time": "3:40:15", "remaining_time": "1 day, 8:00:01"}
42
- {"current_steps": 420, "total_steps": 3984, "loss": 0.76, "lr": 5e-06, "epoch": 0.42152803914188935, "percentage": 10.54, "elapsed_time": "3:45:38", "remaining_time": "1 day, 7:54:44"}
43
- {"current_steps": 430, "total_steps": 3984, "loss": 0.7615, "lr": 5e-06, "epoch": 0.43156442102622006, "percentage": 10.79, "elapsed_time": "3:51:00", "remaining_time": "1 day, 7:49:18"}
44
- {"current_steps": 440, "total_steps": 3984, "loss": 0.7603, "lr": 5e-06, "epoch": 0.44160080291055076, "percentage": 11.04, "elapsed_time": "3:56:20", "remaining_time": "1 day, 7:43:36"}
45
- {"current_steps": 450, "total_steps": 3984, "loss": 0.7493, "lr": 5e-06, "epoch": 0.45163718479488146, "percentage": 11.3, "elapsed_time": "4:01:39", "remaining_time": "1 day, 7:37:46"}
46
- {"current_steps": 460, "total_steps": 3984, "loss": 0.7552, "lr": 5e-06, "epoch": 0.46167356667921217, "percentage": 11.55, "elapsed_time": "4:06:57", "remaining_time": "1 day, 7:31:52"}
47
- {"current_steps": 470, "total_steps": 3984, "loss": 0.7501, "lr": 5e-06, "epoch": 0.47170994856354287, "percentage": 11.8, "elapsed_time": "4:12:19", "remaining_time": "1 day, 7:26:30"}
48
- {"current_steps": 480, "total_steps": 3984, "loss": 0.7572, "lr": 5e-06, "epoch": 0.4817463304478735, "percentage": 12.05, "elapsed_time": "4:17:42", "remaining_time": "1 day, 7:21:16"}
49
- {"current_steps": 490, "total_steps": 3984, "loss": 0.7519, "lr": 5e-06, "epoch": 0.4917827123322042, "percentage": 12.3, "elapsed_time": "4:23:05", "remaining_time": "1 day, 7:15:58"}
50
- {"current_steps": 500, "total_steps": 3984, "loss": 0.7537, "lr": 5e-06, "epoch": 0.5018190942165349, "percentage": 12.55, "elapsed_time": "4:28:28", "remaining_time": "1 day, 7:10:44"}
51
- {"current_steps": 510, "total_steps": 3984, "loss": 0.7557, "lr": 5e-06, "epoch": 0.5118554761008657, "percentage": 12.8, "elapsed_time": "4:33:52", "remaining_time": "1 day, 7:05:36"}
52
- {"current_steps": 520, "total_steps": 3984, "loss": 0.7499, "lr": 5e-06, "epoch": 0.5218918579851963, "percentage": 13.05, "elapsed_time": "4:39:16", "remaining_time": "1 day, 7:00:24"}
53
- {"current_steps": 530, "total_steps": 3984, "loss": 0.7482, "lr": 5e-06, "epoch": 0.5319282398695271, "percentage": 13.3, "elapsed_time": "4:44:39", "remaining_time": "1 day, 6:55:08"}
54
- {"current_steps": 540, "total_steps": 3984, "loss": 0.7454, "lr": 5e-06, "epoch": 0.5419646217538577, "percentage": 13.55, "elapsed_time": "4:50:02", "remaining_time": "1 day, 6:49:47"}
55
- {"current_steps": 550, "total_steps": 3984, "loss": 0.7475, "lr": 5e-06, "epoch": 0.5520010036381884, "percentage": 13.81, "elapsed_time": "4:55:25", "remaining_time": "1 day, 6:44:31"}
56
- {"current_steps": 560, "total_steps": 3984, "loss": 0.7508, "lr": 5e-06, "epoch": 0.5620373855225191, "percentage": 14.06, "elapsed_time": "5:00:47", "remaining_time": "1 day, 6:39:07"}
57
- {"current_steps": 570, "total_steps": 3984, "loss": 0.7482, "lr": 5e-06, "epoch": 0.5720737674068498, "percentage": 14.31, "elapsed_time": "5:06:10", "remaining_time": "1 day, 6:33:47"}
58
- {"current_steps": 580, "total_steps": 3984, "loss": 0.7439, "lr": 5e-06, "epoch": 0.5821101492911805, "percentage": 14.56, "elapsed_time": "5:11:32", "remaining_time": "1 day, 6:28:23"}
59
- {"current_steps": 590, "total_steps": 3984, "loss": 0.7458, "lr": 5e-06, "epoch": 0.5921465311755112, "percentage": 14.81, "elapsed_time": "5:16:54", "remaining_time": "1 day, 6:23:03"}
60
- {"current_steps": 600, "total_steps": 3984, "loss": 0.7496, "lr": 5e-06, "epoch": 0.602182913059842, "percentage": 15.06, "elapsed_time": "5:22:16", "remaining_time": "1 day, 6:17:37"}
61
- {"current_steps": 610, "total_steps": 3984, "loss": 0.7471, "lr": 5e-06, "epoch": 0.6122192949441726, "percentage": 15.31, "elapsed_time": "5:27:37", "remaining_time": "1 day, 6:12:08"}
62
- {"current_steps": 620, "total_steps": 3984, "loss": 0.7433, "lr": 5e-06, "epoch": 0.6222556768285034, "percentage": 15.56, "elapsed_time": "5:32:59", "remaining_time": "1 day, 6:06:47"}
63
- {"current_steps": 630, "total_steps": 3984, "loss": 0.7482, "lr": 5e-06, "epoch": 0.632292058712834, "percentage": 15.81, "elapsed_time": "5:38:23", "remaining_time": "1 day, 6:01:31"}
64
- {"current_steps": 640, "total_steps": 3984, "loss": 0.7479, "lr": 5e-06, "epoch": 0.6423284405971648, "percentage": 16.06, "elapsed_time": "5:43:46", "remaining_time": "1 day, 5:56:13"}
65
- {"current_steps": 650, "total_steps": 3984, "loss": 0.7427, "lr": 5e-06, "epoch": 0.6523648224814954, "percentage": 16.32, "elapsed_time": "5:49:08", "remaining_time": "1 day, 5:50:50"}
66
- {"current_steps": 660, "total_steps": 3984, "loss": 0.745, "lr": 5e-06, "epoch": 0.6624012043658262, "percentage": 16.57, "elapsed_time": "5:54:31", "remaining_time": "1 day, 5:45:31"}
67
- {"current_steps": 670, "total_steps": 3984, "loss": 0.7461, "lr": 5e-06, "epoch": 0.6724375862501568, "percentage": 16.82, "elapsed_time": "5:59:54", "remaining_time": "1 day, 5:40:11"}
68
- {"current_steps": 680, "total_steps": 3984, "loss": 0.7418, "lr": 5e-06, "epoch": 0.6824739681344875, "percentage": 17.07, "elapsed_time": "6:05:16", "remaining_time": "1 day, 5:34:50"}
69
- {"current_steps": 690, "total_steps": 3984, "loss": 0.7394, "lr": 5e-06, "epoch": 0.6925103500188182, "percentage": 17.32, "elapsed_time": "6:10:38", "remaining_time": "1 day, 5:29:22"}
70
- {"current_steps": 700, "total_steps": 3984, "loss": 0.7424, "lr": 5e-06, "epoch": 0.7025467319031489, "percentage": 17.57, "elapsed_time": "6:16:00", "remaining_time": "1 day, 5:23:58"}
71
- {"current_steps": 710, "total_steps": 3984, "loss": 0.7406, "lr": 5e-06, "epoch": 0.7125831137874796, "percentage": 17.82, "elapsed_time": "6:21:24", "remaining_time": "1 day, 5:18:44"}
72
- {"current_steps": 720, "total_steps": 3984, "loss": 0.7423, "lr": 5e-06, "epoch": 0.7226194956718103, "percentage": 18.07, "elapsed_time": "6:26:46", "remaining_time": "1 day, 5:13:22"}
73
- {"current_steps": 730, "total_steps": 3984, "loss": 0.7426, "lr": 5e-06, "epoch": 0.732655877556141, "percentage": 18.32, "elapsed_time": "6:32:06", "remaining_time": "1 day, 5:07:52"}
74
- {"current_steps": 740, "total_steps": 3984, "loss": 0.7417, "lr": 5e-06, "epoch": 0.7426922594404717, "percentage": 18.57, "elapsed_time": "6:37:27", "remaining_time": "1 day, 5:02:23"}
75
- {"current_steps": 750, "total_steps": 3984, "loss": 0.7382, "lr": 5e-06, "epoch": 0.7527286413248024, "percentage": 18.83, "elapsed_time": "6:42:49", "remaining_time": "1 day, 4:57:00"}
76
- {"current_steps": 760, "total_steps": 3984, "loss": 0.7425, "lr": 5e-06, "epoch": 0.7627650232091331, "percentage": 19.08, "elapsed_time": "6:48:11", "remaining_time": "1 day, 4:51:35"}
77
- {"current_steps": 770, "total_steps": 3984, "loss": 0.7404, "lr": 5e-06, "epoch": 0.7728014050934638, "percentage": 19.33, "elapsed_time": "6:53:33", "remaining_time": "1 day, 4:46:13"}
78
- {"current_steps": 780, "total_steps": 3984, "loss": 0.7414, "lr": 5e-06, "epoch": 0.7828377869777945, "percentage": 19.58, "elapsed_time": "6:58:56", "remaining_time": "1 day, 4:40:53"}
79
- {"current_steps": 790, "total_steps": 3984, "loss": 0.7371, "lr": 5e-06, "epoch": 0.7928741688621253, "percentage": 19.83, "elapsed_time": "7:04:18", "remaining_time": "1 day, 4:35:31"}
80
- {"current_steps": 800, "total_steps": 3984, "loss": 0.7383, "lr": 5e-06, "epoch": 0.8029105507464559, "percentage": 20.08, "elapsed_time": "7:09:40", "remaining_time": "1 day, 4:30:07"}
81
- {"current_steps": 810, "total_steps": 3984, "loss": 0.7372, "lr": 5e-06, "epoch": 0.8129469326307867, "percentage": 20.33, "elapsed_time": "7:15:02", "remaining_time": "1 day, 4:24:43"}
82
- {"current_steps": 820, "total_steps": 3984, "loss": 0.7385, "lr": 5e-06, "epoch": 0.8229833145151173, "percentage": 20.58, "elapsed_time": "7:20:24", "remaining_time": "1 day, 4:19:21"}
83
- {"current_steps": 830, "total_steps": 3984, "loss": 0.7355, "lr": 5e-06, "epoch": 0.833019696399448, "percentage": 20.83, "elapsed_time": "7:25:48", "remaining_time": "1 day, 4:14:03"}
84
- {"current_steps": 840, "total_steps": 3984, "loss": 0.7344, "lr": 5e-06, "epoch": 0.8430560782837787, "percentage": 21.08, "elapsed_time": "7:31:10", "remaining_time": "1 day, 4:08:39"}
85
- {"current_steps": 850, "total_steps": 3984, "loss": 0.736, "lr": 5e-06, "epoch": 0.8530924601681094, "percentage": 21.34, "elapsed_time": "7:36:33", "remaining_time": "1 day, 4:03:22"}
86
- {"current_steps": 860, "total_steps": 3984, "loss": 0.7368, "lr": 5e-06, "epoch": 0.8631288420524401, "percentage": 21.59, "elapsed_time": "7:41:57", "remaining_time": "1 day, 3:58:05"}
87
- {"current_steps": 870, "total_steps": 3984, "loss": 0.7348, "lr": 5e-06, "epoch": 0.8731652239367708, "percentage": 21.84, "elapsed_time": "7:47:19", "remaining_time": "1 day, 3:52:43"}
88
- {"current_steps": 880, "total_steps": 3984, "loss": 0.7347, "lr": 5e-06, "epoch": 0.8832016058211015, "percentage": 22.09, "elapsed_time": "7:52:43", "remaining_time": "1 day, 3:47:25"}
89
- {"current_steps": 890, "total_steps": 3984, "loss": 0.7333, "lr": 5e-06, "epoch": 0.8932379877054322, "percentage": 22.34, "elapsed_time": "7:58:05", "remaining_time": "1 day, 3:42:01"}
90
- {"current_steps": 900, "total_steps": 3984, "loss": 0.7367, "lr": 5e-06, "epoch": 0.9032743695897629, "percentage": 22.59, "elapsed_time": "8:03:28", "remaining_time": "1 day, 3:36:42"}
91
- {"current_steps": 910, "total_steps": 3984, "loss": 0.7332, "lr": 5e-06, "epoch": 0.9133107514740936, "percentage": 22.84, "elapsed_time": "8:08:51", "remaining_time": "1 day, 3:31:21"}
92
- {"current_steps": 920, "total_steps": 3984, "loss": 0.7331, "lr": 5e-06, "epoch": 0.9233471333584243, "percentage": 23.09, "elapsed_time": "8:14:14", "remaining_time": "1 day, 3:26:03"}
93
- {"current_steps": 930, "total_steps": 3984, "loss": 0.7363, "lr": 5e-06, "epoch": 0.933383515242755, "percentage": 23.34, "elapsed_time": "8:19:37", "remaining_time": "1 day, 3:20:41"}
94
- {"current_steps": 940, "total_steps": 3984, "loss": 0.734, "lr": 5e-06, "epoch": 0.9434198971270857, "percentage": 23.59, "elapsed_time": "8:25:00", "remaining_time": "1 day, 3:15:21"}
95
- {"current_steps": 950, "total_steps": 3984, "loss": 0.73, "lr": 5e-06, "epoch": 0.9534562790114164, "percentage": 23.85, "elapsed_time": "8:30:22", "remaining_time": "1 day, 3:09:57"}
96
- {"current_steps": 960, "total_steps": 3984, "loss": 0.7296, "lr": 5e-06, "epoch": 0.963492660895747, "percentage": 24.1, "elapsed_time": "8:35:41", "remaining_time": "1 day, 3:04:26"}
97
- {"current_steps": 970, "total_steps": 3984, "loss": 0.7382, "lr": 5e-06, "epoch": 0.9735290427800778, "percentage": 24.35, "elapsed_time": "8:41:04", "remaining_time": "1 day, 2:59:04"}
98
- {"current_steps": 980, "total_steps": 3984, "loss": 0.7328, "lr": 5e-06, "epoch": 0.9835654246644084, "percentage": 24.6, "elapsed_time": "8:46:27", "remaining_time": "1 day, 2:53:44"}
99
- {"current_steps": 990, "total_steps": 3984, "loss": 0.7331, "lr": 5e-06, "epoch": 0.9936018065487392, "percentage": 24.85, "elapsed_time": "8:51:49", "remaining_time": "1 day, 2:48:23"}
100
- {"current_steps": 996, "total_steps": 3984, "eval_loss": 0.7301905751228333, "epoch": 0.9996236356793377, "percentage": 25.0, "elapsed_time": "9:06:59", "remaining_time": "1 day, 3:20:57"}
101
- {"current_steps": 1000, "total_steps": 3984, "loss": 0.7624, "lr": 5e-06, "epoch": 1.0036381884330698, "percentage": 25.1, "elapsed_time": "9:10:09", "remaining_time": "1 day, 3:21:39"}
102
- {"current_steps": 1010, "total_steps": 3984, "loss": 0.6938, "lr": 5e-06, "epoch": 1.0136745703174006, "percentage": 25.35, "elapsed_time": "9:15:31", "remaining_time": "1 day, 3:15:47"}
103
- {"current_steps": 1020, "total_steps": 3984, "loss": 0.6956, "lr": 5e-06, "epoch": 1.0237109522017314, "percentage": 25.6, "elapsed_time": "9:20:52", "remaining_time": "1 day, 3:09:48"}
104
- {"current_steps": 1030, "total_steps": 3984, "loss": 0.6893, "lr": 5e-06, "epoch": 1.033747334086062, "percentage": 25.85, "elapsed_time": "9:26:14", "remaining_time": "1 day, 3:03:57"}
105
- {"current_steps": 1040, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.0437837159703927, "percentage": 26.1, "elapsed_time": "9:31:35", "remaining_time": "1 day, 2:58:03"}
106
- {"current_steps": 1050, "total_steps": 3984, "loss": 0.689, "lr": 5e-06, "epoch": 1.0538200978547234, "percentage": 26.36, "elapsed_time": "9:36:54", "remaining_time": "1 day, 2:52:02"}
107
- {"current_steps": 1060, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.0638564797390542, "percentage": 26.61, "elapsed_time": "9:42:15", "remaining_time": "1 day, 2:46:09"}
108
- {"current_steps": 1070, "total_steps": 3984, "loss": 0.6968, "lr": 5e-06, "epoch": 1.0738928616233847, "percentage": 26.86, "elapsed_time": "9:47:36", "remaining_time": "1 day, 2:40:15"}
109
- {"current_steps": 1080, "total_steps": 3984, "loss": 0.6947, "lr": 5e-06, "epoch": 1.0839292435077155, "percentage": 27.11, "elapsed_time": "9:52:55", "remaining_time": "1 day, 2:34:19"}
110
- {"current_steps": 1090, "total_steps": 3984, "loss": 0.692, "lr": 5e-06, "epoch": 1.0939656253920462, "percentage": 27.36, "elapsed_time": "9:58:18", "remaining_time": "1 day, 2:28:31"}
111
- {"current_steps": 1100, "total_steps": 3984, "loss": 0.6924, "lr": 5e-06, "epoch": 1.1040020072763768, "percentage": 27.61, "elapsed_time": "10:03:40", "remaining_time": "1 day, 2:22:43"}
112
- {"current_steps": 1110, "total_steps": 3984, "loss": 0.6905, "lr": 5e-06, "epoch": 1.1140383891607075, "percentage": 27.86, "elapsed_time": "10:09:03", "remaining_time": "1 day, 2:16:58"}
113
- {"current_steps": 1120, "total_steps": 3984, "loss": 0.6959, "lr": 5e-06, "epoch": 1.1240747710450383, "percentage": 28.11, "elapsed_time": "10:14:26", "remaining_time": "1 day, 2:11:11"}
114
- {"current_steps": 1130, "total_steps": 3984, "loss": 0.6901, "lr": 5e-06, "epoch": 1.134111152929369, "percentage": 28.36, "elapsed_time": "10:19:48", "remaining_time": "1 day, 2:05:25"}
115
- {"current_steps": 1140, "total_steps": 3984, "loss": 0.6921, "lr": 5e-06, "epoch": 1.1441475348136996, "percentage": 28.61, "elapsed_time": "10:25:09", "remaining_time": "1 day, 1:59:35"}
116
- {"current_steps": 1150, "total_steps": 3984, "loss": 0.6954, "lr": 5e-06, "epoch": 1.1541839166980303, "percentage": 28.87, "elapsed_time": "10:30:31", "remaining_time": "1 day, 1:53:49"}
117
- {"current_steps": 1160, "total_steps": 3984, "loss": 0.6893, "lr": 5e-06, "epoch": 1.164220298582361, "percentage": 29.12, "elapsed_time": "10:35:53", "remaining_time": "1 day, 1:48:04"}
118
- {"current_steps": 1170, "total_steps": 3984, "loss": 0.6936, "lr": 5e-06, "epoch": 1.1742566804666918, "percentage": 29.37, "elapsed_time": "10:41:15", "remaining_time": "1 day, 1:42:18"}
119
- {"current_steps": 1180, "total_steps": 3984, "loss": 0.6969, "lr": 5e-06, "epoch": 1.1842930623510224, "percentage": 29.62, "elapsed_time": "10:46:37", "remaining_time": "1 day, 1:36:33"}
120
- {"current_steps": 1190, "total_steps": 3984, "loss": 0.6965, "lr": 5e-06, "epoch": 1.1943294442353531, "percentage": 29.87, "elapsed_time": "10:52:00", "remaining_time": "1 day, 1:30:50"}
121
- {"current_steps": 1200, "total_steps": 3984, "loss": 0.6927, "lr": 5e-06, "epoch": 1.204365826119684, "percentage": 30.12, "elapsed_time": "10:57:22", "remaining_time": "1 day, 1:25:07"}
122
- {"current_steps": 1210, "total_steps": 3984, "loss": 0.6916, "lr": 5e-06, "epoch": 1.2144022080040147, "percentage": 30.37, "elapsed_time": "11:02:45", "remaining_time": "1 day, 1:19:24"}
123
- {"current_steps": 1220, "total_steps": 3984, "loss": 0.6954, "lr": 5e-06, "epoch": 1.2244385898883452, "percentage": 30.62, "elapsed_time": "11:08:07", "remaining_time": "1 day, 1:13:40"}
124
- {"current_steps": 1230, "total_steps": 3984, "loss": 0.6914, "lr": 5e-06, "epoch": 1.234474971772676, "percentage": 30.87, "elapsed_time": "11:13:29", "remaining_time": "1 day, 1:07:56"}
125
- {"current_steps": 1240, "total_steps": 3984, "loss": 0.6934, "lr": 5e-06, "epoch": 1.2445113536570067, "percentage": 31.12, "elapsed_time": "11:18:51", "remaining_time": "1 day, 1:02:14"}
126
- {"current_steps": 1250, "total_steps": 3984, "loss": 0.6933, "lr": 5e-06, "epoch": 1.2545477355413372, "percentage": 31.38, "elapsed_time": "11:24:13", "remaining_time": "1 day, 0:56:32"}
127
- {"current_steps": 1260, "total_steps": 3984, "loss": 0.6946, "lr": 5e-06, "epoch": 1.264584117425668, "percentage": 31.63, "elapsed_time": "11:29:35", "remaining_time": "1 day, 0:50:49"}
128
- {"current_steps": 1270, "total_steps": 3984, "loss": 0.6946, "lr": 5e-06, "epoch": 1.2746204993099988, "percentage": 31.88, "elapsed_time": "11:34:57", "remaining_time": "1 day, 0:45:08"}
129
- {"current_steps": 1280, "total_steps": 3984, "loss": 0.6908, "lr": 5e-06, "epoch": 1.2846568811943295, "percentage": 32.13, "elapsed_time": "11:40:20", "remaining_time": "1 day, 0:39:29"}
130
- {"current_steps": 1290, "total_steps": 3984, "loss": 0.6875, "lr": 5e-06, "epoch": 1.29469326307866, "percentage": 32.38, "elapsed_time": "11:45:43", "remaining_time": "1 day, 0:33:49"}
131
- {"current_steps": 1300, "total_steps": 3984, "loss": 0.695, "lr": 5e-06, "epoch": 1.3047296449629908, "percentage": 32.63, "elapsed_time": "11:51:06", "remaining_time": "1 day, 0:28:10"}
132
- {"current_steps": 1310, "total_steps": 3984, "loss": 0.696, "lr": 5e-06, "epoch": 1.3147660268473216, "percentage": 32.88, "elapsed_time": "11:56:28", "remaining_time": "1 day, 0:22:28"}
133
- {"current_steps": 1320, "total_steps": 3984, "loss": 0.6919, "lr": 5e-06, "epoch": 1.3248024087316521, "percentage": 33.13, "elapsed_time": "12:01:49", "remaining_time": "1 day, 0:16:45"}
134
- {"current_steps": 1330, "total_steps": 3984, "loss": 0.6868, "lr": 5e-06, "epoch": 1.3348387906159829, "percentage": 33.38, "elapsed_time": "12:07:10", "remaining_time": "1 day, 0:11:04"}
135
- {"current_steps": 1340, "total_steps": 3984, "loss": 0.6953, "lr": 5e-06, "epoch": 1.3448751725003136, "percentage": 33.63, "elapsed_time": "12:12:33", "remaining_time": "1 day, 0:05:25"}
136
- {"current_steps": 1350, "total_steps": 3984, "loss": 0.6868, "lr": 5e-06, "epoch": 1.3549115543846444, "percentage": 33.89, "elapsed_time": "12:17:55", "remaining_time": "23:59:46"}
137
- {"current_steps": 1360, "total_steps": 3984, "loss": 0.6963, "lr": 5e-06, "epoch": 1.3649479362689751, "percentage": 34.14, "elapsed_time": "12:23:15", "remaining_time": "23:54:03"}
138
- {"current_steps": 1370, "total_steps": 3984, "loss": 0.6842, "lr": 5e-06, "epoch": 1.3749843181533057, "percentage": 34.39, "elapsed_time": "12:28:35", "remaining_time": "23:48:20"}
139
- {"current_steps": 1380, "total_steps": 3984, "loss": 0.6938, "lr": 5e-06, "epoch": 1.3850207000376364, "percentage": 34.64, "elapsed_time": "12:33:57", "remaining_time": "23:42:40"}
140
- {"current_steps": 1390, "total_steps": 3984, "loss": 0.6944, "lr": 5e-06, "epoch": 1.3950570819219672, "percentage": 34.89, "elapsed_time": "12:39:18", "remaining_time": "23:37:00"}
141
- {"current_steps": 1400, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.4050934638062977, "percentage": 35.14, "elapsed_time": "12:44:38", "remaining_time": "23:31:19"}
142
- {"current_steps": 1410, "total_steps": 3984, "loss": 0.6897, "lr": 5e-06, "epoch": 1.4151298456906285, "percentage": 35.39, "elapsed_time": "12:50:00", "remaining_time": "23:25:41"}
143
- {"current_steps": 1420, "total_steps": 3984, "loss": 0.6914, "lr": 5e-06, "epoch": 1.4251662275749593, "percentage": 35.64, "elapsed_time": "12:55:22", "remaining_time": "23:20:02"}
144
- {"current_steps": 1430, "total_steps": 3984, "loss": 0.6949, "lr": 5e-06, "epoch": 1.43520260945929, "percentage": 35.89, "elapsed_time": "13:00:44", "remaining_time": "23:14:25"}
145
- {"current_steps": 1440, "total_steps": 3984, "loss": 0.6891, "lr": 5e-06, "epoch": 1.4452389913436205, "percentage": 36.14, "elapsed_time": "13:06:07", "remaining_time": "23:08:48"}
146
- {"current_steps": 1450, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.4552753732279513, "percentage": 36.4, "elapsed_time": "13:11:29", "remaining_time": "23:03:11"}
147
- {"current_steps": 1460, "total_steps": 3984, "loss": 0.6916, "lr": 5e-06, "epoch": 1.465311755112282, "percentage": 36.65, "elapsed_time": "13:16:50", "remaining_time": "22:57:33"}
148
- {"current_steps": 1470, "total_steps": 3984, "loss": 0.6914, "lr": 5e-06, "epoch": 1.4753481369966126, "percentage": 36.9, "elapsed_time": "13:22:12", "remaining_time": "22:51:56"}
149
- {"current_steps": 1480, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.4853845188809434, "percentage": 37.15, "elapsed_time": "13:27:31", "remaining_time": "22:46:15"}
150
- {"current_steps": 1490, "total_steps": 3984, "loss": 0.6885, "lr": 5e-06, "epoch": 1.4954209007652741, "percentage": 37.4, "elapsed_time": "13:32:53", "remaining_time": "22:40:37"}
151
- {"current_steps": 1500, "total_steps": 3984, "loss": 0.6945, "lr": 5e-06, "epoch": 1.5054572826496049, "percentage": 37.65, "elapsed_time": "13:38:12", "remaining_time": "22:34:57"}
152
- {"current_steps": 1510, "total_steps": 3984, "loss": 0.696, "lr": 5e-06, "epoch": 1.5154936645339356, "percentage": 37.9, "elapsed_time": "13:43:34", "remaining_time": "22:29:21"}
153
- {"current_steps": 1520, "total_steps": 3984, "loss": 0.6939, "lr": 5e-06, "epoch": 1.5255300464182662, "percentage": 38.15, "elapsed_time": "13:48:54", "remaining_time": "22:23:42"}
154
- {"current_steps": 1530, "total_steps": 3984, "loss": 0.6906, "lr": 5e-06, "epoch": 1.535566428302597, "percentage": 38.4, "elapsed_time": "13:54:16", "remaining_time": "22:18:07"}
155
- {"current_steps": 1540, "total_steps": 3984, "loss": 0.69, "lr": 5e-06, "epoch": 1.5456028101869275, "percentage": 38.65, "elapsed_time": "13:59:38", "remaining_time": "22:12:31"}
156
- {"current_steps": 1550, "total_steps": 3984, "loss": 0.6854, "lr": 5e-06, "epoch": 1.5556391920712582, "percentage": 38.91, "elapsed_time": "14:04:59", "remaining_time": "22:06:54"}
157
- {"current_steps": 1560, "total_steps": 3984, "loss": 0.6925, "lr": 5e-06, "epoch": 1.565675573955589, "percentage": 39.16, "elapsed_time": "14:10:21", "remaining_time": "22:01:18"}
158
- {"current_steps": 1570, "total_steps": 3984, "loss": 0.6883, "lr": 5e-06, "epoch": 1.5757119558399197, "percentage": 39.41, "elapsed_time": "14:15:41", "remaining_time": "21:55:42"}
159
- {"current_steps": 1580, "total_steps": 3984, "loss": 0.6919, "lr": 5e-06, "epoch": 1.5857483377242505, "percentage": 39.66, "elapsed_time": "14:21:02", "remaining_time": "21:50:06"}
160
- {"current_steps": 1590, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.5957847196085813, "percentage": 39.91, "elapsed_time": "14:26:24", "remaining_time": "21:44:31"}
161
- {"current_steps": 1600, "total_steps": 3984, "loss": 0.6906, "lr": 5e-06, "epoch": 1.6058211014929118, "percentage": 40.16, "elapsed_time": "14:31:48", "remaining_time": "21:38:59"}
162
- {"current_steps": 1610, "total_steps": 3984, "loss": 0.6855, "lr": 5e-06, "epoch": 1.6158574833772426, "percentage": 40.41, "elapsed_time": "14:37:10", "remaining_time": "21:33:25"}
163
- {"current_steps": 1620, "total_steps": 3984, "loss": 0.6886, "lr": 5e-06, "epoch": 1.625893865261573, "percentage": 40.66, "elapsed_time": "14:42:32", "remaining_time": "21:27:50"}
164
- {"current_steps": 1630, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.6359302471459038, "percentage": 40.91, "elapsed_time": "14:47:53", "remaining_time": "21:22:16"}
165
- {"current_steps": 1640, "total_steps": 3984, "loss": 0.6837, "lr": 5e-06, "epoch": 1.6459666290302346, "percentage": 41.16, "elapsed_time": "14:53:14", "remaining_time": "21:16:40"}
166
- {"current_steps": 1650, "total_steps": 3984, "loss": 0.6889, "lr": 5e-06, "epoch": 1.6560030109145654, "percentage": 41.42, "elapsed_time": "14:58:32", "remaining_time": "21:11:01"}
167
- {"current_steps": 1660, "total_steps": 3984, "loss": 0.6977, "lr": 5e-06, "epoch": 1.6660393927988961, "percentage": 41.67, "elapsed_time": "15:03:50", "remaining_time": "21:05:22"}
168
- {"current_steps": 1670, "total_steps": 3984, "loss": 0.6898, "lr": 5e-06, "epoch": 1.6760757746832267, "percentage": 41.92, "elapsed_time": "15:09:09", "remaining_time": "20:59:45"}
169
- {"current_steps": 1680, "total_steps": 3984, "loss": 0.6903, "lr": 5e-06, "epoch": 1.6861121565675574, "percentage": 42.17, "elapsed_time": "15:14:31", "remaining_time": "20:54:11"}
170
- {"current_steps": 1690, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.696148538451888, "percentage": 42.42, "elapsed_time": "15:19:52", "remaining_time": "20:48:38"}
171
- {"current_steps": 1700, "total_steps": 3984, "loss": 0.6896, "lr": 5e-06, "epoch": 1.7061849203362187, "percentage": 42.67, "elapsed_time": "15:25:13", "remaining_time": "20:43:04"}
172
- {"current_steps": 1710, "total_steps": 3984, "loss": 0.6933, "lr": 5e-06, "epoch": 1.7162213022205495, "percentage": 42.92, "elapsed_time": "15:30:32", "remaining_time": "20:37:27"}
173
- {"current_steps": 1720, "total_steps": 3984, "loss": 0.689, "lr": 5e-06, "epoch": 1.7262576841048802, "percentage": 43.17, "elapsed_time": "15:35:52", "remaining_time": "20:31:52"}
174
- {"current_steps": 1730, "total_steps": 3984, "loss": 0.6882, "lr": 5e-06, "epoch": 1.736294065989211, "percentage": 43.42, "elapsed_time": "15:41:14", "remaining_time": "20:26:20"}
175
- {"current_steps": 1740, "total_steps": 3984, "loss": 0.6905, "lr": 5e-06, "epoch": 1.7463304478735417, "percentage": 43.67, "elapsed_time": "15:46:36", "remaining_time": "20:20:48"}
176
- {"current_steps": 1750, "total_steps": 3984, "loss": 0.6937, "lr": 5e-06, "epoch": 1.7563668297578723, "percentage": 43.93, "elapsed_time": "15:51:58", "remaining_time": "20:15:15"}
177
- {"current_steps": 1760, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.7664032116422028, "percentage": 44.18, "elapsed_time": "15:57:19", "remaining_time": "20:09:43"}
178
- {"current_steps": 1770, "total_steps": 3984, "loss": 0.686, "lr": 5e-06, "epoch": 1.7764395935265336, "percentage": 44.43, "elapsed_time": "16:02:41", "remaining_time": "20:04:11"}
179
- {"current_steps": 1780, "total_steps": 3984, "loss": 0.6879, "lr": 5e-06, "epoch": 1.7864759754108643, "percentage": 44.68, "elapsed_time": "16:08:02", "remaining_time": "19:58:37"}
180
- {"current_steps": 1790, "total_steps": 3984, "loss": 0.696, "lr": 5e-06, "epoch": 1.796512357295195, "percentage": 44.93, "elapsed_time": "16:13:24", "remaining_time": "19:53:06"}
181
- {"current_steps": 1800, "total_steps": 3984, "loss": 0.6928, "lr": 5e-06, "epoch": 1.8065487391795259, "percentage": 45.18, "elapsed_time": "16:18:45", "remaining_time": "19:47:34"}
182
- {"current_steps": 1810, "total_steps": 3984, "loss": 0.6894, "lr": 5e-06, "epoch": 1.8165851210638566, "percentage": 45.43, "elapsed_time": "16:24:04", "remaining_time": "19:41:58"}
183
- {"current_steps": 1820, "total_steps": 3984, "loss": 0.6902, "lr": 5e-06, "epoch": 1.8266215029481871, "percentage": 45.68, "elapsed_time": "16:29:25", "remaining_time": "19:36:26"}
184
- {"current_steps": 1830, "total_steps": 3984, "loss": 0.6873, "lr": 5e-06, "epoch": 1.836657884832518, "percentage": 45.93, "elapsed_time": "16:34:47", "remaining_time": "19:30:54"}
185
- {"current_steps": 1840, "total_steps": 3984, "loss": 0.6912, "lr": 5e-06, "epoch": 1.8466942667168484, "percentage": 46.18, "elapsed_time": "16:40:08", "remaining_time": "19:25:23"}
186
- {"current_steps": 1850, "total_steps": 3984, "loss": 0.6912, "lr": 5e-06, "epoch": 1.8567306486011792, "percentage": 46.44, "elapsed_time": "16:45:30", "remaining_time": "19:19:51"}
187
- {"current_steps": 1860, "total_steps": 3984, "loss": 0.6876, "lr": 5e-06, "epoch": 1.86676703048551, "percentage": 46.69, "elapsed_time": "16:50:51", "remaining_time": "19:14:20"}
188
- {"current_steps": 1870, "total_steps": 3984, "loss": 0.687, "lr": 5e-06, "epoch": 1.8768034123698407, "percentage": 46.94, "elapsed_time": "16:56:13", "remaining_time": "19:08:49"}
189
- {"current_steps": 1880, "total_steps": 3984, "loss": 0.6853, "lr": 5e-06, "epoch": 1.8868397942541715, "percentage": 47.19, "elapsed_time": "17:01:34", "remaining_time": "19:03:17"}
190
- {"current_steps": 1890, "total_steps": 3984, "loss": 0.6907, "lr": 5e-06, "epoch": 1.8968761761385022, "percentage": 47.44, "elapsed_time": "17:06:55", "remaining_time": "18:57:46"}
191
- {"current_steps": 1900, "total_steps": 3984, "loss": 0.6879, "lr": 5e-06, "epoch": 1.9069125580228328, "percentage": 47.69, "elapsed_time": "17:12:14", "remaining_time": "18:52:12"}
192
- {"current_steps": 1910, "total_steps": 3984, "loss": 0.6862, "lr": 5e-06, "epoch": 1.9169489399071633, "percentage": 47.94, "elapsed_time": "17:17:35", "remaining_time": "18:46:40"}
193
- {"current_steps": 1920, "total_steps": 3984, "loss": 0.6936, "lr": 5e-06, "epoch": 1.926985321791494, "percentage": 48.19, "elapsed_time": "17:22:56", "remaining_time": "18:41:10"}
194
- {"current_steps": 1930, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.9370217036758248, "percentage": 48.44, "elapsed_time": "17:28:16", "remaining_time": "18:35:37"}
195
- {"current_steps": 1940, "total_steps": 3984, "loss": 0.6874, "lr": 5e-06, "epoch": 1.9470580855601556, "percentage": 48.69, "elapsed_time": "17:33:37", "remaining_time": "18:30:06"}
196
- {"current_steps": 1950, "total_steps": 3984, "loss": 0.6876, "lr": 5e-06, "epoch": 1.9570944674444863, "percentage": 48.95, "elapsed_time": "17:38:59", "remaining_time": "18:24:36"}
197
- {"current_steps": 1960, "total_steps": 3984, "loss": 0.6863, "lr": 5e-06, "epoch": 1.967130849328817, "percentage": 49.2, "elapsed_time": "17:44:19", "remaining_time": "18:19:04"}
198
- {"current_steps": 1970, "total_steps": 3984, "loss": 0.6885, "lr": 5e-06, "epoch": 1.9771672312131476, "percentage": 49.45, "elapsed_time": "17:49:40", "remaining_time": "18:13:34"}
199
- {"current_steps": 1980, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.9872036130974784, "percentage": 49.7, "elapsed_time": "17:55:01", "remaining_time": "18:08:03"}
200
- {"current_steps": 1990, "total_steps": 3984, "loss": 0.6913, "lr": 5e-06, "epoch": 1.997239994981809, "percentage": 49.95, "elapsed_time": "18:00:22", "remaining_time": "18:02:32"}
201
- {"current_steps": 1992, "total_steps": 3984, "eval_loss": 0.7165391445159912, "epoch": 1.999247271358675, "percentage": 50.0, "elapsed_time": "18:13:19", "remaining_time": "18:13:19"}
202
- {"current_steps": 2000, "total_steps": 3984, "loss": 0.7009, "lr": 5e-06, "epoch": 2.0072763768661397, "percentage": 50.2, "elapsed_time": "18:18:33", "remaining_time": "18:09:45"}
203
- {"current_steps": 2010, "total_steps": 3984, "loss": 0.6453, "lr": 5e-06, "epoch": 2.0173127587504704, "percentage": 50.45, "elapsed_time": "18:23:55", "remaining_time": "18:04:08"}
204
- {"current_steps": 2020, "total_steps": 3984, "loss": 0.6456, "lr": 5e-06, "epoch": 2.027349140634801, "percentage": 50.7, "elapsed_time": "18:29:18", "remaining_time": "17:58:32"}
205
- {"current_steps": 2030, "total_steps": 3984, "loss": 0.6454, "lr": 5e-06, "epoch": 2.037385522519132, "percentage": 50.95, "elapsed_time": "18:34:38", "remaining_time": "17:52:54"}
206
- {"current_steps": 2040, "total_steps": 3984, "loss": 0.6437, "lr": 5e-06, "epoch": 2.0474219044034627, "percentage": 51.2, "elapsed_time": "18:39:57", "remaining_time": "17:47:15"}
207
- {"current_steps": 2050, "total_steps": 3984, "loss": 0.6473, "lr": 5e-06, "epoch": 2.057458286287793, "percentage": 51.46, "elapsed_time": "18:45:17", "remaining_time": "17:41:37"}
208
- {"current_steps": 2060, "total_steps": 3984, "loss": 0.6466, "lr": 5e-06, "epoch": 2.067494668172124, "percentage": 51.71, "elapsed_time": "18:50:37", "remaining_time": "17:35:59"}
209
- {"current_steps": 2070, "total_steps": 3984, "loss": 0.6448, "lr": 5e-06, "epoch": 2.0775310500564546, "percentage": 51.96, "elapsed_time": "18:55:57", "remaining_time": "17:30:21"}
210
- {"current_steps": 2080, "total_steps": 3984, "loss": 0.648, "lr": 5e-06, "epoch": 2.0875674319407853, "percentage": 52.21, "elapsed_time": "19:01:20", "remaining_time": "17:24:45"}
211
- {"current_steps": 2090, "total_steps": 3984, "loss": 0.6525, "lr": 5e-06, "epoch": 2.097603813825116, "percentage": 52.46, "elapsed_time": "19:06:43", "remaining_time": "17:19:11"}
212
- {"current_steps": 2100, "total_steps": 3984, "loss": 0.6456, "lr": 5e-06, "epoch": 2.107640195709447, "percentage": 52.71, "elapsed_time": "19:12:07", "remaining_time": "17:13:37"}
213
- {"current_steps": 2110, "total_steps": 3984, "loss": 0.6456, "lr": 5e-06, "epoch": 2.1176765775937776, "percentage": 52.96, "elapsed_time": "19:17:31", "remaining_time": "17:08:03"}
214
- {"current_steps": 2120, "total_steps": 3984, "loss": 0.6438, "lr": 5e-06, "epoch": 2.1277129594781083, "percentage": 53.21, "elapsed_time": "19:22:52", "remaining_time": "17:02:27"}
215
- {"current_steps": 2130, "total_steps": 3984, "loss": 0.6482, "lr": 5e-06, "epoch": 2.1377493413624387, "percentage": 53.46, "elapsed_time": "19:28:12", "remaining_time": "16:56:50"}
216
- {"current_steps": 2140, "total_steps": 3984, "loss": 0.6482, "lr": 5e-06, "epoch": 2.1477857232467694, "percentage": 53.71, "elapsed_time": "19:33:32", "remaining_time": "16:51:13"}
217
- {"current_steps": 2150, "total_steps": 3984, "loss": 0.649, "lr": 5e-06, "epoch": 2.1578221051311, "percentage": 53.97, "elapsed_time": "19:38:54", "remaining_time": "16:45:37"}
218
- {"current_steps": 2160, "total_steps": 3984, "loss": 0.6457, "lr": 5e-06, "epoch": 2.167858487015431, "percentage": 54.22, "elapsed_time": "19:44:16", "remaining_time": "16:40:03"}
219
- {"current_steps": 2170, "total_steps": 3984, "loss": 0.6433, "lr": 5e-06, "epoch": 2.1778948688997617, "percentage": 54.47, "elapsed_time": "19:49:38", "remaining_time": "16:34:28"}
220
- {"current_steps": 2180, "total_steps": 3984, "loss": 0.6493, "lr": 5e-06, "epoch": 2.1879312507840925, "percentage": 54.72, "elapsed_time": "19:55:02", "remaining_time": "16:28:55"}
221
- {"current_steps": 2190, "total_steps": 3984, "loss": 0.6515, "lr": 5e-06, "epoch": 2.197967632668423, "percentage": 54.97, "elapsed_time": "20:00:26", "remaining_time": "16:23:22"}
222
- {"current_steps": 2200, "total_steps": 3984, "loss": 0.648, "lr": 5e-06, "epoch": 2.2080040145527535, "percentage": 55.22, "elapsed_time": "20:05:49", "remaining_time": "16:17:49"}
223
- {"current_steps": 2210, "total_steps": 3984, "loss": 0.6526, "lr": 5e-06, "epoch": 2.2180403964370843, "percentage": 55.47, "elapsed_time": "20:11:11", "remaining_time": "16:12:14"}
224
- {"current_steps": 2220, "total_steps": 3984, "loss": 0.6479, "lr": 5e-06, "epoch": 2.228076778321415, "percentage": 55.72, "elapsed_time": "20:16:31", "remaining_time": "16:06:38"}
225
- {"current_steps": 2230, "total_steps": 3984, "loss": 0.6485, "lr": 5e-06, "epoch": 2.238113160205746, "percentage": 55.97, "elapsed_time": "20:21:52", "remaining_time": "16:01:03"}
226
- {"current_steps": 2240, "total_steps": 3984, "loss": 0.6467, "lr": 5e-06, "epoch": 2.2481495420900766, "percentage": 56.22, "elapsed_time": "20:27:15", "remaining_time": "15:55:30"}
227
- {"current_steps": 2250, "total_steps": 3984, "loss": 0.6468, "lr": 5e-06, "epoch": 2.2581859239744073, "percentage": 56.48, "elapsed_time": "20:32:38", "remaining_time": "15:49:57"}
228
- {"current_steps": 2260, "total_steps": 3984, "loss": 0.6484, "lr": 5e-06, "epoch": 2.268222305858738, "percentage": 56.73, "elapsed_time": "20:38:01", "remaining_time": "15:44:24"}
229
- {"current_steps": 2270, "total_steps": 3984, "loss": 0.6483, "lr": 5e-06, "epoch": 2.278258687743069, "percentage": 56.98, "elapsed_time": "20:43:23", "remaining_time": "15:38:50"}
230
- {"current_steps": 2280, "total_steps": 3984, "loss": 0.6477, "lr": 5e-06, "epoch": 2.288295069627399, "percentage": 57.23, "elapsed_time": "20:48:46", "remaining_time": "15:33:17"}
231
- {"current_steps": 2290, "total_steps": 3984, "loss": 0.6451, "lr": 5e-06, "epoch": 2.29833145151173, "percentage": 57.48, "elapsed_time": "20:54:10", "remaining_time": "15:27:45"}
232
- {"current_steps": 2300, "total_steps": 3984, "loss": 0.6502, "lr": 5e-06, "epoch": 2.3083678333960607, "percentage": 57.73, "elapsed_time": "20:59:33", "remaining_time": "15:22:12"}
233
- {"current_steps": 2310, "total_steps": 3984, "loss": 0.652, "lr": 5e-06, "epoch": 2.3184042152803914, "percentage": 57.98, "elapsed_time": "21:04:55", "remaining_time": "15:16:39"}
234
- {"current_steps": 2320, "total_steps": 3984, "loss": 0.6498, "lr": 5e-06, "epoch": 2.328440597164722, "percentage": 58.23, "elapsed_time": "21:10:18", "remaining_time": "15:11:07"}
235
- {"current_steps": 2330, "total_steps": 3984, "loss": 0.6486, "lr": 5e-06, "epoch": 2.338476979049053, "percentage": 58.48, "elapsed_time": "21:15:38", "remaining_time": "15:05:32"}
236
- {"current_steps": 2340, "total_steps": 3984, "loss": 0.6466, "lr": 5e-06, "epoch": 2.3485133609333837, "percentage": 58.73, "elapsed_time": "21:20:59", "remaining_time": "14:59:58"}
237
- {"current_steps": 2350, "total_steps": 3984, "loss": 0.6463, "lr": 5e-06, "epoch": 2.358549742817714, "percentage": 58.99, "elapsed_time": "21:26:21", "remaining_time": "14:54:25"}
238
- {"current_steps": 2360, "total_steps": 3984, "loss": 0.6502, "lr": 5e-06, "epoch": 2.3685861247020448, "percentage": 59.24, "elapsed_time": "21:31:40", "remaining_time": "14:48:50"}
239
- {"current_steps": 2370, "total_steps": 3984, "loss": 0.6537, "lr": 5e-06, "epoch": 2.3786225065863755, "percentage": 59.49, "elapsed_time": "21:36:59", "remaining_time": "14:43:16"}
240
- {"current_steps": 2380, "total_steps": 3984, "loss": 0.6505, "lr": 5e-06, "epoch": 2.3886588884707063, "percentage": 59.74, "elapsed_time": "21:42:22", "remaining_time": "14:37:43"}
241
- {"current_steps": 2390, "total_steps": 3984, "loss": 0.6467, "lr": 5e-06, "epoch": 2.398695270355037, "percentage": 59.99, "elapsed_time": "21:47:44", "remaining_time": "14:32:11"}
242
- {"current_steps": 2400, "total_steps": 3984, "loss": 0.6486, "lr": 5e-06, "epoch": 2.408731652239368, "percentage": 60.24, "elapsed_time": "21:53:06", "remaining_time": "14:26:38"}
243
- {"current_steps": 2410, "total_steps": 3984, "loss": 0.6511, "lr": 5e-06, "epoch": 2.4187680341236986, "percentage": 60.49, "elapsed_time": "21:58:28", "remaining_time": "14:21:06"}
244
- {"current_steps": 2420, "total_steps": 3984, "loss": 0.6518, "lr": 5e-06, "epoch": 2.4288044160080293, "percentage": 60.74, "elapsed_time": "22:03:49", "remaining_time": "14:15:34"}
245
- {"current_steps": 2430, "total_steps": 3984, "loss": 0.6471, "lr": 5e-06, "epoch": 2.4388407978923596, "percentage": 60.99, "elapsed_time": "22:09:09", "remaining_time": "14:10:00"}
246
- {"current_steps": 2440, "total_steps": 3984, "loss": 0.6549, "lr": 5e-06, "epoch": 2.4488771797766904, "percentage": 61.24, "elapsed_time": "22:14:29", "remaining_time": "14:04:26"}
247
- {"current_steps": 2450, "total_steps": 3984, "loss": 0.6489, "lr": 5e-06, "epoch": 2.458913561661021, "percentage": 61.5, "elapsed_time": "22:19:49", "remaining_time": "13:58:53"}
248
- {"current_steps": 2460, "total_steps": 3984, "loss": 0.6514, "lr": 5e-06, "epoch": 2.468949943545352, "percentage": 61.75, "elapsed_time": "22:25:10", "remaining_time": "13:53:21"}
249
- {"current_steps": 2470, "total_steps": 3984, "loss": 0.6567, "lr": 5e-06, "epoch": 2.4789863254296827, "percentage": 62.0, "elapsed_time": "22:30:29", "remaining_time": "13:47:47"}
250
- {"current_steps": 2480, "total_steps": 3984, "loss": 0.6461, "lr": 5e-06, "epoch": 2.4890227073140134, "percentage": 62.25, "elapsed_time": "22:35:48", "remaining_time": "13:42:13"}
251
- {"current_steps": 2490, "total_steps": 3984, "loss": 0.65, "lr": 5e-06, "epoch": 2.499059089198344, "percentage": 62.5, "elapsed_time": "22:41:08", "remaining_time": "13:36:41"}
252
- {"current_steps": 2500, "total_steps": 3984, "loss": 0.6566, "lr": 5e-06, "epoch": 2.5090954710826745, "percentage": 62.75, "elapsed_time": "22:46:29", "remaining_time": "13:31:09"}
253
- {"current_steps": 2510, "total_steps": 3984, "loss": 0.6525, "lr": 5e-06, "epoch": 2.5191318529670053, "percentage": 63.0, "elapsed_time": "22:51:49", "remaining_time": "13:25:36"}
254
- {"current_steps": 2520, "total_steps": 3984, "loss": 0.6477, "lr": 5e-06, "epoch": 2.529168234851336, "percentage": 63.25, "elapsed_time": "22:57:11", "remaining_time": "13:20:04"}
255
- {"current_steps": 2530, "total_steps": 3984, "loss": 0.6484, "lr": 5e-06, "epoch": 2.5392046167356668, "percentage": 63.5, "elapsed_time": "23:02:31", "remaining_time": "13:14:32"}
256
- {"current_steps": 2540, "total_steps": 3984, "loss": 0.6498, "lr": 5e-06, "epoch": 2.5492409986199975, "percentage": 63.76, "elapsed_time": "23:07:51", "remaining_time": "13:09:00"}
257
- {"current_steps": 2550, "total_steps": 3984, "loss": 0.6529, "lr": 5e-06, "epoch": 2.5592773805043283, "percentage": 64.01, "elapsed_time": "23:13:10", "remaining_time": "13:03:27"}
258
- {"current_steps": 2560, "total_steps": 3984, "loss": 0.6496, "lr": 5e-06, "epoch": 2.569313762388659, "percentage": 64.26, "elapsed_time": "23:18:30", "remaining_time": "12:57:55"}
259
- {"current_steps": 2570, "total_steps": 3984, "loss": 0.6488, "lr": 5e-06, "epoch": 2.57935014427299, "percentage": 64.51, "elapsed_time": "23:23:50", "remaining_time": "12:52:23"}
260
- {"current_steps": 2580, "total_steps": 3984, "loss": 0.6605, "lr": 5e-06, "epoch": 2.58938652615732, "percentage": 64.76, "elapsed_time": "23:29:10", "remaining_time": "12:46:51"}
261
- {"current_steps": 2590, "total_steps": 3984, "loss": 0.6474, "lr": 5e-06, "epoch": 2.599422908041651, "percentage": 65.01, "elapsed_time": "23:34:31", "remaining_time": "12:41:19"}
262
- {"current_steps": 2600, "total_steps": 3984, "loss": 0.6532, "lr": 5e-06, "epoch": 2.6094592899259816, "percentage": 65.26, "elapsed_time": "23:39:51", "remaining_time": "12:35:47"}
263
- {"current_steps": 2610, "total_steps": 3984, "loss": 0.6527, "lr": 5e-06, "epoch": 2.6194956718103124, "percentage": 65.51, "elapsed_time": "23:45:10", "remaining_time": "12:30:15"}
264
- {"current_steps": 2620, "total_steps": 3984, "loss": 0.6465, "lr": 5e-06, "epoch": 2.629532053694643, "percentage": 65.76, "elapsed_time": "23:50:29", "remaining_time": "12:24:43"}
265
- {"current_steps": 2630, "total_steps": 3984, "loss": 0.6489, "lr": 5e-06, "epoch": 2.639568435578974, "percentage": 66.01, "elapsed_time": "23:55:48", "remaining_time": "12:19:11"}
266
- {"current_steps": 2640, "total_steps": 3984, "loss": 0.6523, "lr": 5e-06, "epoch": 2.6496048174633042, "percentage": 66.27, "elapsed_time": "1 day, 0:01:09", "remaining_time": "12:13:40"}
267
- {"current_steps": 2650, "total_steps": 3984, "loss": 0.6528, "lr": 5e-06, "epoch": 2.659641199347635, "percentage": 66.52, "elapsed_time": "1 day, 0:06:30", "remaining_time": "12:08:10"}
268
- {"current_steps": 2660, "total_steps": 3984, "loss": 0.6474, "lr": 5e-06, "epoch": 2.6696775812319657, "percentage": 66.77, "elapsed_time": "1 day, 0:11:49", "remaining_time": "12:02:38"}
269
- {"current_steps": 2670, "total_steps": 3984, "loss": 0.6512, "lr": 5e-06, "epoch": 2.6797139631162965, "percentage": 67.02, "elapsed_time": "1 day, 0:17:09", "remaining_time": "11:57:07"}
270
- {"current_steps": 2680, "total_steps": 3984, "loss": 0.6503, "lr": 5e-06, "epoch": 2.6897503450006273, "percentage": 67.27, "elapsed_time": "1 day, 0:22:30", "remaining_time": "11:51:36"}
271
- {"current_steps": 2690, "total_steps": 3984, "loss": 0.6496, "lr": 5e-06, "epoch": 2.699786726884958, "percentage": 67.52, "elapsed_time": "1 day, 0:27:51", "remaining_time": "11:46:05"}
272
- {"current_steps": 2700, "total_steps": 3984, "loss": 0.6521, "lr": 5e-06, "epoch": 2.709823108769289, "percentage": 67.77, "elapsed_time": "1 day, 0:33:12", "remaining_time": "11:40:35"}
273
- {"current_steps": 2710, "total_steps": 3984, "loss": 0.6509, "lr": 5e-06, "epoch": 2.7198594906536195, "percentage": 68.02, "elapsed_time": "1 day, 0:38:33", "remaining_time": "11:35:05"}
274
- {"current_steps": 2720, "total_steps": 3984, "loss": 0.6519, "lr": 5e-06, "epoch": 2.7298958725379503, "percentage": 68.27, "elapsed_time": "1 day, 0:43:53", "remaining_time": "11:29:34"}
275
- {"current_steps": 2730, "total_steps": 3984, "loss": 0.6541, "lr": 5e-06, "epoch": 2.7399322544222806, "percentage": 68.52, "elapsed_time": "1 day, 0:49:13", "remaining_time": "11:24:03"}
276
- {"current_steps": 2740, "total_steps": 3984, "loss": 0.6548, "lr": 5e-06, "epoch": 2.7499686363066114, "percentage": 68.78, "elapsed_time": "1 day, 0:54:33", "remaining_time": "11:18:33"}
277
- {"current_steps": 2750, "total_steps": 3984, "loss": 0.6525, "lr": 5e-06, "epoch": 2.760005018190942, "percentage": 69.03, "elapsed_time": "1 day, 0:59:54", "remaining_time": "11:13:02"}
278
- {"current_steps": 2760, "total_steps": 3984, "loss": 0.6596, "lr": 5e-06, "epoch": 2.770041400075273, "percentage": 69.28, "elapsed_time": "1 day, 1:05:15", "remaining_time": "11:07:33"}
279
- {"current_steps": 2770, "total_steps": 3984, "loss": 0.6521, "lr": 5e-06, "epoch": 2.7800777819596036, "percentage": 69.53, "elapsed_time": "1 day, 1:10:38", "remaining_time": "11:02:03"}
280
- {"current_steps": 2780, "total_steps": 3984, "loss": 0.6506, "lr": 5e-06, "epoch": 2.7901141638439344, "percentage": 69.78, "elapsed_time": "1 day, 1:15:59", "remaining_time": "10:56:34"}
281
- {"current_steps": 2790, "total_steps": 3984, "loss": 0.6542, "lr": 5e-06, "epoch": 2.8001505457282647, "percentage": 70.03, "elapsed_time": "1 day, 1:21:21", "remaining_time": "10:51:04"}
282
- {"current_steps": 2800, "total_steps": 3984, "loss": 0.6545, "lr": 5e-06, "epoch": 2.8101869276125955, "percentage": 70.28, "elapsed_time": "1 day, 1:26:40", "remaining_time": "10:45:34"}
283
- {"current_steps": 2810, "total_steps": 3984, "loss": 0.6539, "lr": 5e-06, "epoch": 2.8202233094969262, "percentage": 70.53, "elapsed_time": "1 day, 1:32:00", "remaining_time": "10:40:03"}
284
- {"current_steps": 2820, "total_steps": 3984, "loss": 0.6497, "lr": 5e-06, "epoch": 2.830259691381257, "percentage": 70.78, "elapsed_time": "1 day, 1:37:20", "remaining_time": "10:34:33"}
285
- {"current_steps": 2830, "total_steps": 3984, "loss": 0.6513, "lr": 5e-06, "epoch": 2.8402960732655878, "percentage": 71.03, "elapsed_time": "1 day, 1:42:39", "remaining_time": "10:29:03"}
286
- {"current_steps": 2840, "total_steps": 3984, "loss": 0.6507, "lr": 5e-06, "epoch": 2.8503324551499185, "percentage": 71.29, "elapsed_time": "1 day, 1:48:01", "remaining_time": "10:23:34"}
287
- {"current_steps": 2850, "total_steps": 3984, "loss": 0.6581, "lr": 5e-06, "epoch": 2.8603688370342493, "percentage": 71.54, "elapsed_time": "1 day, 1:53:23", "remaining_time": "10:18:05"}
288
- {"current_steps": 2860, "total_steps": 3984, "loss": 0.6516, "lr": 5e-06, "epoch": 2.87040521891858, "percentage": 71.79, "elapsed_time": "1 day, 1:58:43", "remaining_time": "10:12:35"}
289
- {"current_steps": 2870, "total_steps": 3984, "loss": 0.6511, "lr": 5e-06, "epoch": 2.880441600802911, "percentage": 72.04, "elapsed_time": "1 day, 2:04:05", "remaining_time": "10:07:06"}
290
- {"current_steps": 2880, "total_steps": 3984, "loss": 0.6539, "lr": 5e-06, "epoch": 2.890477982687241, "percentage": 72.29, "elapsed_time": "1 day, 2:09:27", "remaining_time": "10:01:37"}
291
- {"current_steps": 2890, "total_steps": 3984, "loss": 0.6512, "lr": 5e-06, "epoch": 2.900514364571572, "percentage": 72.54, "elapsed_time": "1 day, 2:14:47", "remaining_time": "9:56:07"}
292
- {"current_steps": 2900, "total_steps": 3984, "loss": 0.6538, "lr": 5e-06, "epoch": 2.9105507464559026, "percentage": 72.79, "elapsed_time": "1 day, 2:20:08", "remaining_time": "9:50:38"}
293
- {"current_steps": 2910, "total_steps": 3984, "loss": 0.6504, "lr": 5e-06, "epoch": 2.9205871283402334, "percentage": 73.04, "elapsed_time": "1 day, 2:25:30", "remaining_time": "9:45:09"}
294
- {"current_steps": 2920, "total_steps": 3984, "loss": 0.6494, "lr": 5e-06, "epoch": 2.930623510224564, "percentage": 73.29, "elapsed_time": "1 day, 2:30:49", "remaining_time": "9:39:40"}
295
- {"current_steps": 2930, "total_steps": 3984, "loss": 0.6512, "lr": 5e-06, "epoch": 2.940659892108895, "percentage": 73.54, "elapsed_time": "1 day, 2:36:08", "remaining_time": "9:34:10"}
296
- {"current_steps": 2940, "total_steps": 3984, "loss": 0.655, "lr": 5e-06, "epoch": 2.950696273993225, "percentage": 73.8, "elapsed_time": "1 day, 2:41:27", "remaining_time": "9:28:40"}
297
- {"current_steps": 2950, "total_steps": 3984, "loss": 0.6531, "lr": 5e-06, "epoch": 2.960732655877556, "percentage": 74.05, "elapsed_time": "1 day, 2:46:48", "remaining_time": "9:23:12"}
298
- {"current_steps": 2960, "total_steps": 3984, "loss": 0.6551, "lr": 5e-06, "epoch": 2.9707690377618867, "percentage": 74.3, "elapsed_time": "1 day, 2:52:10", "remaining_time": "9:17:43"}
299
- {"current_steps": 2970, "total_steps": 3984, "loss": 0.6553, "lr": 5e-06, "epoch": 2.9808054196462175, "percentage": 74.55, "elapsed_time": "1 day, 2:57:28", "remaining_time": "9:12:13"}
300
- {"current_steps": 2980, "total_steps": 3984, "loss": 0.6511, "lr": 5e-06, "epoch": 2.9908418015305482, "percentage": 74.8, "elapsed_time": "1 day, 3:02:47", "remaining_time": "9:06:44"}
301
- {"current_steps": 2989, "total_steps": 3984, "eval_loss": 0.7148573994636536, "epoch": 2.999874545226446, "percentage": 75.03, "elapsed_time": "1 day, 3:18:43", "remaining_time": "9:05:30"}
302
- {"current_steps": 2990, "total_steps": 3984, "loss": 0.6887, "lr": 5e-06, "epoch": 3.000878183414879, "percentage": 75.05, "elapsed_time": "1 day, 3:20:29", "remaining_time": "9:05:21"}
 
1
+ {"current_steps": 10, "total_steps": 3984, "loss": 1.0592, "lr": 5e-06, "epoch": 0.0100363818843307, "percentage": 0.25, "elapsed_time": "0:05:24", "remaining_time": "1 day, 11:49:21"}
2
+ {"current_steps": 20, "total_steps": 3984, "loss": 0.9442, "lr": 5e-06, "epoch": 0.0200727637686614, "percentage": 0.5, "elapsed_time": "0:10:41", "remaining_time": "1 day, 11:19:21"}
3
+ {"current_steps": 30, "total_steps": 3984, "loss": 0.8939, "lr": 5e-06, "epoch": 0.030109145652992095, "percentage": 0.75, "elapsed_time": "0:16:00", "remaining_time": "1 day, 11:09:58"}
4
+ {"current_steps": 40, "total_steps": 3984, "loss": 0.8733, "lr": 5e-06, "epoch": 0.0401455275373228, "percentage": 1.0, "elapsed_time": "0:21:19", "remaining_time": "1 day, 11:02:13"}
5
+ {"current_steps": 50, "total_steps": 3984, "loss": 0.8605, "lr": 5e-06, "epoch": 0.050181909421653494, "percentage": 1.26, "elapsed_time": "0:26:40", "remaining_time": "1 day, 10:58:18"}
6
+ {"current_steps": 60, "total_steps": 3984, "loss": 0.8442, "lr": 5e-06, "epoch": 0.06021829130598419, "percentage": 1.51, "elapsed_time": "0:31:56", "remaining_time": "1 day, 10:49:09"}
7
+ {"current_steps": 70, "total_steps": 3984, "loss": 0.8326, "lr": 5e-06, "epoch": 0.07025467319031489, "percentage": 1.76, "elapsed_time": "0:37:13", "remaining_time": "1 day, 10:41:28"}
8
+ {"current_steps": 80, "total_steps": 3984, "loss": 0.8255, "lr": 5e-06, "epoch": 0.0802910550746456, "percentage": 2.01, "elapsed_time": "0:42:33", "remaining_time": "1 day, 10:36:49"}
9
+ {"current_steps": 90, "total_steps": 3984, "loss": 0.8131, "lr": 5e-06, "epoch": 0.09032743695897628, "percentage": 2.26, "elapsed_time": "0:47:53", "remaining_time": "1 day, 10:32:19"}
10
+ {"current_steps": 100, "total_steps": 3984, "loss": 0.8089, "lr": 5e-06, "epoch": 0.10036381884330699, "percentage": 2.51, "elapsed_time": "0:53:13", "remaining_time": "1 day, 10:27:19"}
11
+ {"current_steps": 110, "total_steps": 3984, "loss": 0.8015, "lr": 5e-06, "epoch": 0.11040020072763769, "percentage": 2.76, "elapsed_time": "0:58:33", "remaining_time": "1 day, 10:22:08"}
12
+ {"current_steps": 120, "total_steps": 3984, "loss": 0.7984, "lr": 5e-06, "epoch": 0.12043658261196838, "percentage": 3.01, "elapsed_time": "1:03:51", "remaining_time": "1 day, 10:16:30"}
13
+ {"current_steps": 130, "total_steps": 3984, "loss": 0.8001, "lr": 5e-06, "epoch": 0.13047296449629908, "percentage": 3.26, "elapsed_time": "1:09:11", "remaining_time": "1 day, 10:11:26"}
14
+ {"current_steps": 140, "total_steps": 3984, "loss": 0.7932, "lr": 5e-06, "epoch": 0.14050934638062978, "percentage": 3.51, "elapsed_time": "1:14:31", "remaining_time": "1 day, 10:06:22"}
15
+ {"current_steps": 150, "total_steps": 3984, "loss": 0.7958, "lr": 5e-06, "epoch": 0.1505457282649605, "percentage": 3.77, "elapsed_time": "1:19:51", "remaining_time": "1 day, 10:01:04"}
16
+ {"current_steps": 160, "total_steps": 3984, "loss": 0.7933, "lr": 5e-06, "epoch": 0.1605821101492912, "percentage": 4.02, "elapsed_time": "1:25:07", "remaining_time": "1 day, 9:54:24"}
17
+ {"current_steps": 170, "total_steps": 3984, "loss": 0.7864, "lr": 5e-06, "epoch": 0.17061849203362187, "percentage": 4.27, "elapsed_time": "1:30:24", "remaining_time": "1 day, 9:48:16"}
18
+ {"current_steps": 180, "total_steps": 3984, "loss": 0.7864, "lr": 5e-06, "epoch": 0.18065487391795257, "percentage": 4.52, "elapsed_time": "1:35:41", "remaining_time": "1 day, 9:42:26"}
19
+ {"current_steps": 190, "total_steps": 3984, "loss": 0.7851, "lr": 5e-06, "epoch": 0.19069125580228327, "percentage": 4.77, "elapsed_time": "1:40:59", "remaining_time": "1 day, 9:36:47"}
20
+ {"current_steps": 200, "total_steps": 3984, "loss": 0.782, "lr": 5e-06, "epoch": 0.20072763768661397, "percentage": 5.02, "elapsed_time": "1:46:17", "remaining_time": "1 day, 9:31:00"}
21
+ {"current_steps": 210, "total_steps": 3984, "loss": 0.7802, "lr": 5e-06, "epoch": 0.21076401957094468, "percentage": 5.27, "elapsed_time": "1:51:35", "remaining_time": "1 day, 9:25:22"}
22
+ {"current_steps": 220, "total_steps": 3984, "loss": 0.7766, "lr": 5e-06, "epoch": 0.22080040145527538, "percentage": 5.52, "elapsed_time": "1:56:54", "remaining_time": "1 day, 9:20:08"}
23
+ {"current_steps": 230, "total_steps": 3984, "loss": 0.7811, "lr": 5e-06, "epoch": 0.23083678333960608, "percentage": 5.77, "elapsed_time": "2:02:12", "remaining_time": "1 day, 9:14:40"}
24
+ {"current_steps": 240, "total_steps": 3984, "loss": 0.7785, "lr": 5e-06, "epoch": 0.24087316522393676, "percentage": 6.02, "elapsed_time": "2:07:32", "remaining_time": "1 day, 9:09:44"}
25
+ {"current_steps": 250, "total_steps": 3984, "loss": 0.774, "lr": 5e-06, "epoch": 0.25090954710826746, "percentage": 6.28, "elapsed_time": "2:12:51", "remaining_time": "1 day, 9:04:29"}
26
+ {"current_steps": 260, "total_steps": 3984, "loss": 0.7685, "lr": 5e-06, "epoch": 0.26094592899259816, "percentage": 6.53, "elapsed_time": "2:18:12", "remaining_time": "1 day, 8:59:29"}
27
+ {"current_steps": 270, "total_steps": 3984, "loss": 0.7733, "lr": 5e-06, "epoch": 0.27098231087692887, "percentage": 6.78, "elapsed_time": "2:23:33", "remaining_time": "1 day, 8:54:40"}
28
+ {"current_steps": 280, "total_steps": 3984, "loss": 0.7717, "lr": 5e-06, "epoch": 0.28101869276125957, "percentage": 7.03, "elapsed_time": "2:28:53", "remaining_time": "1 day, 8:49:32"}
29
+ {"current_steps": 290, "total_steps": 3984, "loss": 0.7732, "lr": 5e-06, "epoch": 0.2910550746455903, "percentage": 7.28, "elapsed_time": "2:34:13", "remaining_time": "1 day, 8:44:25"}
30
+ {"current_steps": 300, "total_steps": 3984, "loss": 0.7694, "lr": 5e-06, "epoch": 0.301091456529921, "percentage": 7.53, "elapsed_time": "2:39:34", "remaining_time": "1 day, 8:39:32"}
31
+ {"current_steps": 310, "total_steps": 3984, "loss": 0.7667, "lr": 5e-06, "epoch": 0.3111278384142517, "percentage": 7.78, "elapsed_time": "2:44:52", "remaining_time": "1 day, 8:34:02"}
32
+ {"current_steps": 320, "total_steps": 3984, "loss": 0.7651, "lr": 5e-06, "epoch": 0.3211642202985824, "percentage": 8.03, "elapsed_time": "2:50:12", "remaining_time": "1 day, 8:28:53"}
33
+ {"current_steps": 330, "total_steps": 3984, "loss": 0.7628, "lr": 5e-06, "epoch": 0.3312006021829131, "percentage": 8.28, "elapsed_time": "2:55:33", "remaining_time": "1 day, 8:23:53"}
34
+ {"current_steps": 340, "total_steps": 3984, "loss": 0.7717, "lr": 5e-06, "epoch": 0.34123698406724373, "percentage": 8.53, "elapsed_time": "3:00:54", "remaining_time": "1 day, 8:18:56"}
35
+ {"current_steps": 350, "total_steps": 3984, "loss": 0.7634, "lr": 5e-06, "epoch": 0.35127336595157443, "percentage": 8.79, "elapsed_time": "3:06:12", "remaining_time": "1 day, 8:13:23"}
36
+ {"current_steps": 360, "total_steps": 3984, "loss": 0.7629, "lr": 5e-06, "epoch": 0.36130974783590514, "percentage": 9.04, "elapsed_time": "3:11:31", "remaining_time": "1 day, 8:08:04"}
37
+ {"current_steps": 370, "total_steps": 3984, "loss": 0.7633, "lr": 5e-06, "epoch": 0.37134612972023584, "percentage": 9.29, "elapsed_time": "3:16:51", "remaining_time": "1 day, 8:02:52"}
38
+ {"current_steps": 380, "total_steps": 3984, "loss": 0.7689, "lr": 5e-06, "epoch": 0.38138251160456654, "percentage": 9.54, "elapsed_time": "3:22:11", "remaining_time": "1 day, 7:57:34"}
39
+ {"current_steps": 390, "total_steps": 3984, "loss": 0.7595, "lr": 5e-06, "epoch": 0.39141889348889725, "percentage": 9.79, "elapsed_time": "3:27:30", "remaining_time": "1 day, 7:52:19"}
40
+ {"current_steps": 400, "total_steps": 3984, "loss": 0.758, "lr": 5e-06, "epoch": 0.40145527537322795, "percentage": 10.04, "elapsed_time": "3:32:50", "remaining_time": "1 day, 7:47:06"}
41
+ {"current_steps": 410, "total_steps": 3984, "loss": 0.7615, "lr": 5e-06, "epoch": 0.41149165725755865, "percentage": 10.29, "elapsed_time": "3:38:09", "remaining_time": "1 day, 7:41:42"}
42
+ {"current_steps": 420, "total_steps": 3984, "loss": 0.7604, "lr": 5e-06, "epoch": 0.42152803914188935, "percentage": 10.54, "elapsed_time": "3:43:29", "remaining_time": "1 day, 7:36:25"}
43
+ {"current_steps": 430, "total_steps": 3984, "loss": 0.762, "lr": 5e-06, "epoch": 0.43156442102622006, "percentage": 10.79, "elapsed_time": "3:48:49", "remaining_time": "1 day, 7:31:12"}
44
+ {"current_steps": 440, "total_steps": 3984, "loss": 0.7608, "lr": 5e-06, "epoch": 0.44160080291055076, "percentage": 11.04, "elapsed_time": "3:54:08", "remaining_time": "1 day, 7:25:51"}
45
+ {"current_steps": 450, "total_steps": 3984, "loss": 0.7498, "lr": 5e-06, "epoch": 0.45163718479488146, "percentage": 11.3, "elapsed_time": "3:59:26", "remaining_time": "1 day, 7:20:24"}
46
+ {"current_steps": 460, "total_steps": 3984, "loss": 0.7557, "lr": 5e-06, "epoch": 0.46167356667921217, "percentage": 11.55, "elapsed_time": "4:04:45", "remaining_time": "1 day, 7:15:01"}
47
+ {"current_steps": 470, "total_steps": 3984, "loss": 0.7506, "lr": 5e-06, "epoch": 0.47170994856354287, "percentage": 11.8, "elapsed_time": "4:10:03", "remaining_time": "1 day, 7:09:34"}
48
+ {"current_steps": 480, "total_steps": 3984, "loss": 0.7577, "lr": 5e-06, "epoch": 0.4817463304478735, "percentage": 12.05, "elapsed_time": "4:15:22", "remaining_time": "1 day, 7:04:17"}
49
+ {"current_steps": 490, "total_steps": 3984, "loss": 0.7524, "lr": 5e-06, "epoch": 0.4917827123322042, "percentage": 12.3, "elapsed_time": "4:20:39", "remaining_time": "1 day, 6:58:38"}
50
+ {"current_steps": 500, "total_steps": 3984, "loss": 0.7542, "lr": 5e-06, "epoch": 0.5018190942165349, "percentage": 12.55, "elapsed_time": "4:25:56", "remaining_time": "1 day, 6:53:05"}
51
+ {"current_steps": 510, "total_steps": 3984, "loss": 0.7562, "lr": 5e-06, "epoch": 0.5118554761008657, "percentage": 12.8, "elapsed_time": "4:31:13", "remaining_time": "1 day, 6:47:32"}
52
+ {"current_steps": 520, "total_steps": 3984, "loss": 0.7505, "lr": 5e-06, "epoch": 0.5218918579851963, "percentage": 13.05, "elapsed_time": "4:36:32", "remaining_time": "1 day, 6:42:11"}
53
+ {"current_steps": 530, "total_steps": 3984, "loss": 0.7488, "lr": 5e-06, "epoch": 0.5319282398695271, "percentage": 13.3, "elapsed_time": "4:41:50", "remaining_time": "1 day, 6:36:43"}
54
+ {"current_steps": 540, "total_steps": 3984, "loss": 0.7459, "lr": 5e-06, "epoch": 0.5419646217538577, "percentage": 13.55, "elapsed_time": "4:47:07", "remaining_time": "1 day, 6:31:10"}
55
+ {"current_steps": 550, "total_steps": 3984, "loss": 0.748, "lr": 5e-06, "epoch": 0.5520010036381884, "percentage": 13.81, "elapsed_time": "4:52:26", "remaining_time": "1 day, 6:25:52"}
56
+ {"current_steps": 560, "total_steps": 3984, "loss": 0.7514, "lr": 5e-06, "epoch": 0.5620373855225191, "percentage": 14.06, "elapsed_time": "4:57:45", "remaining_time": "1 day, 6:20:35"}
57
+ {"current_steps": 570, "total_steps": 3984, "loss": 0.7487, "lr": 5e-06, "epoch": 0.5720737674068498, "percentage": 14.31, "elapsed_time": "5:03:05", "remaining_time": "1 day, 6:15:18"}
58
+ {"current_steps": 580, "total_steps": 3984, "loss": 0.7444, "lr": 5e-06, "epoch": 0.5821101492911805, "percentage": 14.56, "elapsed_time": "5:08:22", "remaining_time": "1 day, 6:09:50"}
59
+ {"current_steps": 590, "total_steps": 3984, "loss": 0.7463, "lr": 5e-06, "epoch": 0.5921465311755112, "percentage": 14.81, "elapsed_time": "5:13:41", "remaining_time": "1 day, 6:04:29"}
60
+ {"current_steps": 600, "total_steps": 3984, "loss": 0.7501, "lr": 5e-06, "epoch": 0.602182913059842, "percentage": 15.06, "elapsed_time": "5:19:01", "remaining_time": "1 day, 5:59:16"}
61
+ {"current_steps": 610, "total_steps": 3984, "loss": 0.7476, "lr": 5e-06, "epoch": 0.6122192949441726, "percentage": 15.31, "elapsed_time": "5:24:16", "remaining_time": "1 day, 5:53:37"}
62
+ {"current_steps": 620, "total_steps": 3984, "loss": 0.7438, "lr": 5e-06, "epoch": 0.6222556768285034, "percentage": 15.56, "elapsed_time": "5:29:32", "remaining_time": "1 day, 5:48:04"}
63
+ {"current_steps": 630, "total_steps": 3984, "loss": 0.7486, "lr": 5e-06, "epoch": 0.632292058712834, "percentage": 15.81, "elapsed_time": "5:34:51", "remaining_time": "1 day, 5:42:45"}
64
+ {"current_steps": 640, "total_steps": 3984, "loss": 0.7485, "lr": 5e-06, "epoch": 0.6423284405971648, "percentage": 16.06, "elapsed_time": "5:40:12", "remaining_time": "1 day, 5:37:33"}
65
+ {"current_steps": 650, "total_steps": 3984, "loss": 0.7433, "lr": 5e-06, "epoch": 0.6523648224814954, "percentage": 16.32, "elapsed_time": "5:45:30", "remaining_time": "1 day, 5:32:11"}
66
+ {"current_steps": 660, "total_steps": 3984, "loss": 0.7455, "lr": 5e-06, "epoch": 0.6624012043658262, "percentage": 16.57, "elapsed_time": "5:50:48", "remaining_time": "1 day, 5:26:46"}
67
+ {"current_steps": 670, "total_steps": 3984, "loss": 0.7466, "lr": 5e-06, "epoch": 0.6724375862501568, "percentage": 16.82, "elapsed_time": "5:56:07", "remaining_time": "1 day, 5:21:27"}
68
+ {"current_steps": 680, "total_steps": 3984, "loss": 0.7423, "lr": 5e-06, "epoch": 0.6824739681344875, "percentage": 17.07, "elapsed_time": "6:01:27", "remaining_time": "1 day, 5:16:16"}
69
+ {"current_steps": 690, "total_steps": 3984, "loss": 0.7398, "lr": 5e-06, "epoch": 0.6925103500188182, "percentage": 17.32, "elapsed_time": "6:06:45", "remaining_time": "1 day, 5:10:51"}
70
+ {"current_steps": 700, "total_steps": 3984, "loss": 0.7429, "lr": 5e-06, "epoch": 0.7025467319031489, "percentage": 17.57, "elapsed_time": "6:12:01", "remaining_time": "1 day, 5:05:18"}
71
+ {"current_steps": 710, "total_steps": 3984, "loss": 0.7411, "lr": 5e-06, "epoch": 0.7125831137874796, "percentage": 17.82, "elapsed_time": "6:17:17", "remaining_time": "1 day, 4:59:46"}
72
+ {"current_steps": 720, "total_steps": 3984, "loss": 0.7428, "lr": 5e-06, "epoch": 0.7226194956718103, "percentage": 18.07, "elapsed_time": "6:22:36", "remaining_time": "1 day, 4:54:31"}
73
+ {"current_steps": 730, "total_steps": 3984, "loss": 0.7431, "lr": 5e-06, "epoch": 0.732655877556141, "percentage": 18.32, "elapsed_time": "6:27:58", "remaining_time": "1 day, 4:49:22"}
74
+ {"current_steps": 740, "total_steps": 3984, "loss": 0.7423, "lr": 5e-06, "epoch": 0.7426922594404717, "percentage": 18.57, "elapsed_time": "6:33:19", "remaining_time": "1 day, 4:44:13"}
75
+ {"current_steps": 750, "total_steps": 3984, "loss": 0.7387, "lr": 5e-06, "epoch": 0.7527286413248024, "percentage": 18.83, "elapsed_time": "6:38:39", "remaining_time": "1 day, 4:39:02"}
76
+ {"current_steps": 760, "total_steps": 3984, "loss": 0.743, "lr": 5e-06, "epoch": 0.7627650232091331, "percentage": 19.08, "elapsed_time": "6:43:58", "remaining_time": "1 day, 4:33:40"}
77
+ {"current_steps": 770, "total_steps": 3984, "loss": 0.741, "lr": 5e-06, "epoch": 0.7728014050934638, "percentage": 19.33, "elapsed_time": "6:49:13", "remaining_time": "1 day, 4:28:05"}
78
+ {"current_steps": 780, "total_steps": 3984, "loss": 0.742, "lr": 5e-06, "epoch": 0.7828377869777945, "percentage": 19.58, "elapsed_time": "6:54:28", "remaining_time": "1 day, 4:22:31"}
79
+ {"current_steps": 790, "total_steps": 3984, "loss": 0.7375, "lr": 5e-06, "epoch": 0.7928741688621253, "percentage": 19.83, "elapsed_time": "6:59:43", "remaining_time": "1 day, 4:16:58"}
80
+ {"current_steps": 800, "total_steps": 3984, "loss": 0.7387, "lr": 5e-06, "epoch": 0.8029105507464559, "percentage": 20.08, "elapsed_time": "7:05:01", "remaining_time": "1 day, 4:11:36"}
81
+ {"current_steps": 810, "total_steps": 3984, "loss": 0.7376, "lr": 5e-06, "epoch": 0.8129469326307867, "percentage": 20.33, "elapsed_time": "7:10:20", "remaining_time": "1 day, 4:06:17"}
82
+ {"current_steps": 820, "total_steps": 3984, "loss": 0.739, "lr": 5e-06, "epoch": 0.8229833145151173, "percentage": 20.58, "elapsed_time": "7:15:37", "remaining_time": "1 day, 4:00:53"}
83
+ {"current_steps": 830, "total_steps": 3984, "loss": 0.7359, "lr": 5e-06, "epoch": 0.833019696399448, "percentage": 20.83, "elapsed_time": "7:20:55", "remaining_time": "1 day, 3:55:32"}
84
+ {"current_steps": 840, "total_steps": 3984, "loss": 0.7349, "lr": 5e-06, "epoch": 0.8430560782837787, "percentage": 21.08, "elapsed_time": "7:26:13", "remaining_time": "1 day, 3:50:09"}
85
+ {"current_steps": 850, "total_steps": 3984, "loss": 0.7365, "lr": 5e-06, "epoch": 0.8530924601681094, "percentage": 21.34, "elapsed_time": "7:31:29", "remaining_time": "1 day, 3:44:42"}
86
+ {"current_steps": 860, "total_steps": 3984, "loss": 0.7373, "lr": 5e-06, "epoch": 0.8631288420524401, "percentage": 21.59, "elapsed_time": "7:36:47", "remaining_time": "1 day, 3:39:17"}
87
+ {"current_steps": 870, "total_steps": 3984, "loss": 0.7353, "lr": 5e-06, "epoch": 0.8731652239367708, "percentage": 21.84, "elapsed_time": "7:42:06", "remaining_time": "1 day, 3:34:02"}
88
+ {"current_steps": 880, "total_steps": 3984, "loss": 0.7353, "lr": 5e-06, "epoch": 0.8832016058211015, "percentage": 22.09, "elapsed_time": "7:47:26", "remaining_time": "1 day, 3:28:48"}
89
+ {"current_steps": 890, "total_steps": 3984, "loss": 0.7338, "lr": 5e-06, "epoch": 0.8932379877054322, "percentage": 22.34, "elapsed_time": "7:52:46", "remaining_time": "1 day, 3:23:32"}
90
+ {"current_steps": 900, "total_steps": 3984, "loss": 0.7372, "lr": 5e-06, "epoch": 0.9032743695897629, "percentage": 22.59, "elapsed_time": "7:58:05", "remaining_time": "1 day, 3:18:14"}
91
+ {"current_steps": 910, "total_steps": 3984, "loss": 0.7337, "lr": 5e-06, "epoch": 0.9133107514740936, "percentage": 22.84, "elapsed_time": "8:03:25", "remaining_time": "1 day, 3:13:02"}
92
+ {"current_steps": 920, "total_steps": 3984, "loss": 0.7336, "lr": 5e-06, "epoch": 0.9233471333584243, "percentage": 23.09, "elapsed_time": "8:08:46", "remaining_time": "1 day, 3:07:48"}
93
+ {"current_steps": 930, "total_steps": 3984, "loss": 0.7368, "lr": 5e-06, "epoch": 0.933383515242755, "percentage": 23.34, "elapsed_time": "8:14:04", "remaining_time": "1 day, 3:02:28"}
94
+ {"current_steps": 940, "total_steps": 3984, "loss": 0.7345, "lr": 5e-06, "epoch": 0.9434198971270857, "percentage": 23.59, "elapsed_time": "8:19:22", "remaining_time": "1 day, 2:57:07"}
95
+ {"current_steps": 950, "total_steps": 3984, "loss": 0.7304, "lr": 5e-06, "epoch": 0.9534562790114164, "percentage": 23.85, "elapsed_time": "8:24:41", "remaining_time": "1 day, 2:51:48"}
96
+ {"current_steps": 960, "total_steps": 3984, "loss": 0.7301, "lr": 5e-06, "epoch": 0.963492660895747, "percentage": 24.1, "elapsed_time": "8:30:00", "remaining_time": "1 day, 2:46:32"}
97
+ {"current_steps": 970, "total_steps": 3984, "loss": 0.7387, "lr": 5e-06, "epoch": 0.9735290427800778, "percentage": 24.35, "elapsed_time": "8:35:20", "remaining_time": "1 day, 2:41:16"}
98
+ {"current_steps": 980, "total_steps": 3984, "loss": 0.7333, "lr": 5e-06, "epoch": 0.9835654246644084, "percentage": 24.6, "elapsed_time": "8:40:40", "remaining_time": "1 day, 2:36:01"}
99
+ {"current_steps": 990, "total_steps": 3984, "loss": 0.7336, "lr": 5e-06, "epoch": 0.9936018065487392, "percentage": 24.85, "elapsed_time": "8:46:00", "remaining_time": "1 day, 2:30:45"}
100
+ {"current_steps": 996, "total_steps": 3984, "eval_loss": 0.7306540608406067, "epoch": 0.9996236356793377, "percentage": 25.0, "elapsed_time": "9:01:12", "remaining_time": "1 day, 3:03:37"}
101
+ {"current_steps": 1000, "total_steps": 3984, "loss": 0.7631, "lr": 5e-06, "epoch": 1.0036381884330698, "percentage": 25.1, "elapsed_time": "9:04:27", "remaining_time": "1 day, 3:04:41"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae4f9e3cc0795167c4a321884043f8c9230322541d6070f6d02f8f9793fe0c8d
3
  size 7160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2222753e60cd17ddeec1c602af7acced6ab81e8794b3acf80e886083f98783fa
3
  size 7160