SKNahin commited on
Commit
9ef671e
·
verified ·
1 Parent(s): ef76f72

Training in progress, step 150

Browse files
Files changed (3) hide show
  1. model.safetensors +1 -1
  2. trainer_log.jsonl +152 -167
  3. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0037071bb3acf49cdcd814f5d85e1c295dcab89c44c9b38d41dfe169f6bc9b8
3
  size 1064369000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243a8cec33a38f5f385ad31502ad8be54ed12b63f7d0fb4316144a30cde53533
3
  size 1064369000
trainer_log.jsonl CHANGED
@@ -1,167 +1,152 @@
1
- {"current_steps": 1, "total_steps": 166, "loss": 2.3086, "lr": 1e-06, "epoch": 0.011976047904191617, "percentage": 0.6, "elapsed_time": "0:00:28", "remaining_time": "1:18:05"}
2
- {"current_steps": 2, "total_steps": 166, "loss": 2.3322, "lr": 1e-06, "epoch": 0.023952095808383235, "percentage": 1.2, "elapsed_time": "0:00:45", "remaining_time": "1:01:45"}
3
- {"current_steps": 3, "total_steps": 166, "loss": 2.3189, "lr": 1e-06, "epoch": 0.03592814371257485, "percentage": 1.81, "elapsed_time": "0:01:02", "remaining_time": "0:56:13"}
4
- {"current_steps": 4, "total_steps": 166, "loss": 2.3221, "lr": 1e-06, "epoch": 0.04790419161676647, "percentage": 2.41, "elapsed_time": "0:01:19", "remaining_time": "0:53:25"}
5
- {"current_steps": 5, "total_steps": 166, "loss": 2.3203, "lr": 1e-06, "epoch": 0.059880239520958084, "percentage": 3.01, "elapsed_time": "0:01:36", "remaining_time": "0:51:45"}
6
- {"current_steps": 6, "total_steps": 166, "loss": 2.3189, "lr": 1e-06, "epoch": 0.0718562874251497, "percentage": 3.61, "elapsed_time": "0:01:53", "remaining_time": "0:50:34"}
7
- {"current_steps": 7, "total_steps": 166, "loss": 2.314, "lr": 1e-06, "epoch": 0.08383233532934131, "percentage": 4.22, "elapsed_time": "0:02:11", "remaining_time": "0:49:39"}
8
- {"current_steps": 8, "total_steps": 166, "loss": 2.3104, "lr": 1e-06, "epoch": 0.09580838323353294, "percentage": 4.82, "elapsed_time": "0:02:28", "remaining_time": "0:48:55"}
9
- {"current_steps": 9, "total_steps": 166, "loss": 2.3067, "lr": 1e-06, "epoch": 0.10778443113772455, "percentage": 5.42, "elapsed_time": "0:02:46", "remaining_time": "0:48:17"}
10
- {"current_steps": 10, "total_steps": 166, "loss": 2.3168, "lr": 1e-06, "epoch": 0.11976047904191617, "percentage": 6.02, "elapsed_time": "0:03:03", "remaining_time": "0:47:42"}
11
- {"current_steps": 11, "total_steps": 166, "loss": 2.322, "lr": 1e-06, "epoch": 0.1317365269461078, "percentage": 6.63, "elapsed_time": "0:03:20", "remaining_time": "0:47:11"}
12
- {"current_steps": 12, "total_steps": 166, "loss": 2.321, "lr": 1e-06, "epoch": 0.1437125748502994, "percentage": 7.23, "elapsed_time": "0:03:38", "remaining_time": "0:46:43"}
13
- {"current_steps": 13, "total_steps": 166, "loss": 2.312, "lr": 1e-06, "epoch": 0.15568862275449102, "percentage": 7.83, "elapsed_time": "0:03:55", "remaining_time": "0:46:16"}
14
- {"current_steps": 14, "total_steps": 166, "loss": 2.303, "lr": 1e-06, "epoch": 0.16766467065868262, "percentage": 8.43, "elapsed_time": "0:04:13", "remaining_time": "0:45:51"}
15
- {"current_steps": 15, "total_steps": 166, "loss": 2.3105, "lr": 1e-06, "epoch": 0.17964071856287425, "percentage": 9.04, "elapsed_time": "0:04:30", "remaining_time": "0:45:27"}
16
- {"current_steps": 16, "total_steps": 166, "loss": 2.2994, "lr": 1e-06, "epoch": 0.19161676646706588, "percentage": 9.64, "elapsed_time": "0:04:48", "remaining_time": "0:45:03"}
17
- {"current_steps": 17, "total_steps": 166, "loss": 2.3085, "lr": 1e-06, "epoch": 0.20359281437125748, "percentage": 10.24, "elapsed_time": "0:05:05", "remaining_time": "0:44:41"}
18
- {"current_steps": 18, "total_steps": 166, "loss": 2.3006, "lr": 1e-06, "epoch": 0.2155688622754491, "percentage": 10.84, "elapsed_time": "0:05:23", "remaining_time": "0:44:18"}
19
- {"current_steps": 19, "total_steps": 166, "loss": 2.2872, "lr": 1e-06, "epoch": 0.2275449101796407, "percentage": 11.45, "elapsed_time": "0:05:40", "remaining_time": "0:43:57"}
20
- {"current_steps": 20, "total_steps": 166, "loss": 2.3008, "lr": 1e-06, "epoch": 0.23952095808383234, "percentage": 12.05, "elapsed_time": "0:05:58", "remaining_time": "0:43:35"}
21
- {"current_steps": 21, "total_steps": 166, "loss": 2.2948, "lr": 1e-06, "epoch": 0.25149700598802394, "percentage": 12.65, "elapsed_time": "0:06:15", "remaining_time": "0:43:15"}
22
- {"current_steps": 22, "total_steps": 166, "loss": 2.2899, "lr": 1e-06, "epoch": 0.2634730538922156, "percentage": 13.25, "elapsed_time": "0:06:33", "remaining_time": "0:42:54"}
23
- {"current_steps": 23, "total_steps": 166, "loss": 2.2967, "lr": 1e-06, "epoch": 0.2754491017964072, "percentage": 13.86, "elapsed_time": "0:06:50", "remaining_time": "0:42:34"}
24
- {"current_steps": 24, "total_steps": 166, "loss": 2.2969, "lr": 1e-06, "epoch": 0.2874251497005988, "percentage": 14.46, "elapsed_time": "0:07:08", "remaining_time": "0:42:13"}
25
- {"current_steps": 25, "total_steps": 166, "loss": 2.3023, "lr": 1e-06, "epoch": 0.2994011976047904, "percentage": 15.06, "elapsed_time": "0:07:25", "remaining_time": "0:41:54"}
26
- {"current_steps": 26, "total_steps": 166, "loss": 2.2952, "lr": 1e-06, "epoch": 0.31137724550898205, "percentage": 15.66, "elapsed_time": "0:07:43", "remaining_time": "0:41:34"}
27
- {"current_steps": 27, "total_steps": 166, "loss": 2.286, "lr": 1e-06, "epoch": 0.32335329341317365, "percentage": 16.27, "elapsed_time": "0:08:00", "remaining_time": "0:41:15"}
28
- {"current_steps": 28, "total_steps": 166, "loss": 2.2964, "lr": 1e-06, "epoch": 0.33532934131736525, "percentage": 16.87, "elapsed_time": "0:08:18", "remaining_time": "0:40:56"}
29
- {"current_steps": 29, "total_steps": 166, "loss": 2.2871, "lr": 1e-06, "epoch": 0.3473053892215569, "percentage": 17.47, "elapsed_time": "0:08:35", "remaining_time": "0:40:37"}
30
- {"current_steps": 30, "total_steps": 166, "loss": 2.3018, "lr": 1e-06, "epoch": 0.3592814371257485, "percentage": 18.07, "elapsed_time": "0:08:53", "remaining_time": "0:40:17"}
31
- {"current_steps": 31, "total_steps": 166, "loss": 2.2784, "lr": 1e-06, "epoch": 0.3712574850299401, "percentage": 18.67, "elapsed_time": "0:09:10", "remaining_time": "0:39:59"}
32
- {"current_steps": 32, "total_steps": 166, "loss": 2.2764, "lr": 1e-06, "epoch": 0.38323353293413176, "percentage": 19.28, "elapsed_time": "0:09:28", "remaining_time": "0:39:40"}
33
- {"current_steps": 33, "total_steps": 166, "loss": 2.2706, "lr": 1e-06, "epoch": 0.39520958083832336, "percentage": 19.88, "elapsed_time": "0:09:45", "remaining_time": "0:39:21"}
34
- {"current_steps": 34, "total_steps": 166, "loss": 2.2593, "lr": 1e-06, "epoch": 0.40718562874251496, "percentage": 20.48, "elapsed_time": "0:10:03", "remaining_time": "0:39:02"}
35
- {"current_steps": 35, "total_steps": 166, "loss": 2.2705, "lr": 1e-06, "epoch": 0.41916167664670656, "percentage": 21.08, "elapsed_time": "0:10:20", "remaining_time": "0:38:44"}
36
- {"current_steps": 36, "total_steps": 166, "loss": 2.2708, "lr": 1e-06, "epoch": 0.4311377245508982, "percentage": 21.69, "elapsed_time": "0:10:38", "remaining_time": "0:38:25"}
37
- {"current_steps": 37, "total_steps": 166, "loss": 2.2636, "lr": 1e-06, "epoch": 0.4431137724550898, "percentage": 22.29, "elapsed_time": "0:10:55", "remaining_time": "0:38:06"}
38
- {"current_steps": 38, "total_steps": 166, "loss": 2.2593, "lr": 1e-06, "epoch": 0.4550898203592814, "percentage": 22.89, "elapsed_time": "0:11:13", "remaining_time": "0:37:48"}
39
- {"current_steps": 39, "total_steps": 166, "loss": 2.2531, "lr": 1e-06, "epoch": 0.46706586826347307, "percentage": 23.49, "elapsed_time": "0:11:30", "remaining_time": "0:37:29"}
40
- {"current_steps": 40, "total_steps": 166, "loss": 2.2651, "lr": 1e-06, "epoch": 0.47904191616766467, "percentage": 24.1, "elapsed_time": "0:11:48", "remaining_time": "0:37:11"}
41
- {"current_steps": 41, "total_steps": 166, "loss": 2.2721, "lr": 1e-06, "epoch": 0.49101796407185627, "percentage": 24.7, "elapsed_time": "0:12:05", "remaining_time": "0:36:53"}
42
- {"current_steps": 42, "total_steps": 166, "loss": 2.2568, "lr": 1e-06, "epoch": 0.5029940119760479, "percentage": 25.3, "elapsed_time": "0:12:23", "remaining_time": "0:36:34"}
43
- {"current_steps": 43, "total_steps": 166, "loss": 2.2504, "lr": 1e-06, "epoch": 0.5149700598802395, "percentage": 25.9, "elapsed_time": "0:12:40", "remaining_time": "0:36:16"}
44
- {"current_steps": 44, "total_steps": 166, "loss": 2.2611, "lr": 1e-06, "epoch": 0.5269461077844312, "percentage": 26.51, "elapsed_time": "0:12:58", "remaining_time": "0:35:58"}
45
- {"current_steps": 45, "total_steps": 166, "loss": 2.2637, "lr": 1e-06, "epoch": 0.5389221556886228, "percentage": 27.11, "elapsed_time": "0:13:15", "remaining_time": "0:35:40"}
46
- {"current_steps": 46, "total_steps": 166, "loss": 2.2536, "lr": 1e-06, "epoch": 0.5508982035928144, "percentage": 27.71, "elapsed_time": "0:13:33", "remaining_time": "0:35:21"}
47
- {"current_steps": 47, "total_steps": 166, "loss": 2.2543, "lr": 1e-06, "epoch": 0.562874251497006, "percentage": 28.31, "elapsed_time": "0:13:50", "remaining_time": "0:35:03"}
48
- {"current_steps": 48, "total_steps": 166, "loss": 2.252, "lr": 1e-06, "epoch": 0.5748502994011976, "percentage": 28.92, "elapsed_time": "0:14:08", "remaining_time": "0:34:45"}
49
- {"current_steps": 49, "total_steps": 166, "loss": 2.2604, "lr": 1e-06, "epoch": 0.5868263473053892, "percentage": 29.52, "elapsed_time": "0:14:25", "remaining_time": "0:34:27"}
50
- {"current_steps": 50, "total_steps": 166, "loss": 2.2571, "lr": 1e-06, "epoch": 0.5988023952095808, "percentage": 30.12, "elapsed_time": "0:14:43", "remaining_time": "0:34:09"}
51
- {"current_steps": 51, "total_steps": 166, "loss": 2.247, "lr": 1e-06, "epoch": 0.6107784431137725, "percentage": 30.72, "elapsed_time": "0:15:07", "remaining_time": "0:34:06"}
52
- {"current_steps": 52, "total_steps": 166, "loss": 2.2607, "lr": 1e-06, "epoch": 0.6227544910179641, "percentage": 31.33, "elapsed_time": "0:15:25", "remaining_time": "0:33:48"}
53
- {"current_steps": 53, "total_steps": 166, "loss": 2.2461, "lr": 1e-06, "epoch": 0.6347305389221557, "percentage": 31.93, "elapsed_time": "0:15:42", "remaining_time": "0:33:29"}
54
- {"current_steps": 54, "total_steps": 166, "loss": 2.2569, "lr": 1e-06, "epoch": 0.6467065868263473, "percentage": 32.53, "elapsed_time": "0:16:00", "remaining_time": "0:33:11"}
55
- {"current_steps": 55, "total_steps": 166, "loss": 2.2419, "lr": 1e-06, "epoch": 0.6586826347305389, "percentage": 33.13, "elapsed_time": "0:16:17", "remaining_time": "0:32:53"}
56
- {"current_steps": 56, "total_steps": 166, "loss": 2.2511, "lr": 1e-06, "epoch": 0.6706586826347305, "percentage": 33.73, "elapsed_time": "0:16:35", "remaining_time": "0:32:34"}
57
- {"current_steps": 57, "total_steps": 166, "loss": 2.2388, "lr": 1e-06, "epoch": 0.6826347305389222, "percentage": 34.34, "elapsed_time": "0:16:52", "remaining_time": "0:32:16"}
58
- {"current_steps": 58, "total_steps": 166, "loss": 2.2307, "lr": 1e-06, "epoch": 0.6946107784431138, "percentage": 34.94, "elapsed_time": "0:17:10", "remaining_time": "0:31:58"}
59
- {"current_steps": 59, "total_steps": 166, "loss": 2.227, "lr": 1e-06, "epoch": 0.7065868263473054, "percentage": 35.54, "elapsed_time": "0:17:27", "remaining_time": "0:31:39"}
60
- {"current_steps": 60, "total_steps": 166, "loss": 2.2153, "lr": 1e-06, "epoch": 0.718562874251497, "percentage": 36.14, "elapsed_time": "0:17:45", "remaining_time": "0:31:21"}
61
- {"current_steps": 61, "total_steps": 166, "loss": 2.2227, "lr": 1e-06, "epoch": 0.7305389221556886, "percentage": 36.75, "elapsed_time": "0:18:02", "remaining_time": "0:31:03"}
62
- {"current_steps": 62, "total_steps": 166, "loss": 2.2182, "lr": 1e-06, "epoch": 0.7425149700598802, "percentage": 37.35, "elapsed_time": "0:18:19", "remaining_time": "0:30:45"}
63
- {"current_steps": 63, "total_steps": 166, "loss": 2.2145, "lr": 1e-06, "epoch": 0.7544910179640718, "percentage": 37.95, "elapsed_time": "0:18:37", "remaining_time": "0:30:26"}
64
- {"current_steps": 64, "total_steps": 166, "loss": 2.2083, "lr": 1e-06, "epoch": 0.7664670658682635, "percentage": 38.55, "elapsed_time": "0:18:54", "remaining_time": "0:30:08"}
65
- {"current_steps": 65, "total_steps": 166, "loss": 2.2032, "lr": 1e-06, "epoch": 0.7784431137724551, "percentage": 39.16, "elapsed_time": "0:19:12", "remaining_time": "0:29:50"}
66
- {"current_steps": 66, "total_steps": 166, "loss": 2.2189, "lr": 1e-06, "epoch": 0.7904191616766467, "percentage": 39.76, "elapsed_time": "0:19:29", "remaining_time": "0:29:32"}
67
- {"current_steps": 67, "total_steps": 166, "loss": 2.2093, "lr": 1e-06, "epoch": 0.8023952095808383, "percentage": 40.36, "elapsed_time": "0:19:47", "remaining_time": "0:29:14"}
68
- {"current_steps": 68, "total_steps": 166, "loss": 2.2067, "lr": 1e-06, "epoch": 0.8143712574850299, "percentage": 40.96, "elapsed_time": "0:20:04", "remaining_time": "0:28:56"}
69
- {"current_steps": 69, "total_steps": 166, "loss": 2.2146, "lr": 1e-06, "epoch": 0.8263473053892215, "percentage": 41.57, "elapsed_time": "0:20:22", "remaining_time": "0:28:38"}
70
- {"current_steps": 70, "total_steps": 166, "loss": 2.2055, "lr": 1e-06, "epoch": 0.8383233532934131, "percentage": 42.17, "elapsed_time": "0:20:39", "remaining_time": "0:28:20"}
71
- {"current_steps": 71, "total_steps": 166, "loss": 2.2144, "lr": 1e-06, "epoch": 0.8502994011976048, "percentage": 42.77, "elapsed_time": "0:20:57", "remaining_time": "0:28:02"}
72
- {"current_steps": 72, "total_steps": 166, "loss": 2.209, "lr": 1e-06, "epoch": 0.8622754491017964, "percentage": 43.37, "elapsed_time": "0:21:14", "remaining_time": "0:27:44"}
73
- {"current_steps": 73, "total_steps": 166, "loss": 2.2048, "lr": 1e-06, "epoch": 0.874251497005988, "percentage": 43.98, "elapsed_time": "0:21:32", "remaining_time": "0:27:26"}
74
- {"current_steps": 74, "total_steps": 166, "loss": 2.2108, "lr": 1e-06, "epoch": 0.8862275449101796, "percentage": 44.58, "elapsed_time": "0:21:49", "remaining_time": "0:27:08"}
75
- {"current_steps": 75, "total_steps": 166, "loss": 2.2022, "lr": 1e-06, "epoch": 0.8982035928143712, "percentage": 45.18, "elapsed_time": "0:22:07", "remaining_time": "0:26:50"}
76
- {"current_steps": 76, "total_steps": 166, "loss": 2.2084, "lr": 1e-06, "epoch": 0.9101796407185628, "percentage": 45.78, "elapsed_time": "0:22:24", "remaining_time": "0:26:32"}
77
- {"current_steps": 77, "total_steps": 166, "loss": 2.2036, "lr": 1e-06, "epoch": 0.9221556886227545, "percentage": 46.39, "elapsed_time": "0:22:42", "remaining_time": "0:26:14"}
78
- {"current_steps": 78, "total_steps": 166, "loss": 2.2052, "lr": 1e-06, "epoch": 0.9341317365269461, "percentage": 46.99, "elapsed_time": "0:22:59", "remaining_time": "0:25:56"}
79
- {"current_steps": 79, "total_steps": 166, "loss": 2.2089, "lr": 1e-06, "epoch": 0.9461077844311377, "percentage": 47.59, "elapsed_time": "0:23:17", "remaining_time": "0:25:38"}
80
- {"current_steps": 80, "total_steps": 166, "loss": 2.1942, "lr": 1e-06, "epoch": 0.9580838323353293, "percentage": 48.19, "elapsed_time": "0:23:34", "remaining_time": "0:25:20"}
81
- {"current_steps": 81, "total_steps": 166, "loss": 2.2069, "lr": 1e-06, "epoch": 0.9700598802395209, "percentage": 48.8, "elapsed_time": "0:23:52", "remaining_time": "0:25:02"}
82
- {"current_steps": 82, "total_steps": 166, "loss": 2.1974, "lr": 1e-06, "epoch": 0.9820359281437125, "percentage": 49.4, "elapsed_time": "0:24:09", "remaining_time": "0:24:44"}
83
- {"current_steps": 83, "total_steps": 166, "loss": 2.199, "lr": 1e-06, "epoch": 0.9940119760479041, "percentage": 50.0, "elapsed_time": "0:24:26", "remaining_time": "0:24:26"}
84
- {"current_steps": 84, "total_steps": 166, "loss": 2.2047, "lr": 1e-06, "epoch": 1.0, "percentage": 50.6, "elapsed_time": "0:24:35", "remaining_time": "0:24:00"}
85
- {"current_steps": 85, "total_steps": 166, "loss": 2.1951, "lr": 1e-06, "epoch": 1.0119760479041917, "percentage": 51.2, "elapsed_time": "0:24:54", "remaining_time": "0:23:44"}
86
- {"current_steps": 86, "total_steps": 166, "loss": 2.193, "lr": 1e-06, "epoch": 1.0239520958083832, "percentage": 51.81, "elapsed_time": "0:25:12", "remaining_time": "0:23:26"}
87
- {"current_steps": 87, "total_steps": 166, "loss": 2.1932, "lr": 1e-06, "epoch": 1.035928143712575, "percentage": 52.41, "elapsed_time": "0:25:29", "remaining_time": "0:23:09"}
88
- {"current_steps": 88, "total_steps": 166, "loss": 2.1943, "lr": 1e-06, "epoch": 1.0479041916167664, "percentage": 53.01, "elapsed_time": "0:25:47", "remaining_time": "0:22:51"}
89
- {"current_steps": 89, "total_steps": 166, "loss": 2.2006, "lr": 1e-06, "epoch": 1.0598802395209581, "percentage": 53.61, "elapsed_time": "0:26:04", "remaining_time": "0:22:33"}
90
- {"current_steps": 90, "total_steps": 166, "loss": 2.1955, "lr": 1e-06, "epoch": 1.0718562874251496, "percentage": 54.22, "elapsed_time": "0:26:22", "remaining_time": "0:22:16"}
91
- {"current_steps": 91, "total_steps": 166, "loss": 2.2038, "lr": 1e-06, "epoch": 1.0838323353293413, "percentage": 54.82, "elapsed_time": "0:26:39", "remaining_time": "0:21:58"}
92
- {"current_steps": 92, "total_steps": 166, "loss": 2.1898, "lr": 1e-06, "epoch": 1.095808383233533, "percentage": 55.42, "elapsed_time": "0:26:57", "remaining_time": "0:21:40"}
93
- {"current_steps": 93, "total_steps": 166, "loss": 2.1974, "lr": 1e-06, "epoch": 1.1077844311377245, "percentage": 56.02, "elapsed_time": "0:27:14", "remaining_time": "0:21:23"}
94
- {"current_steps": 94, "total_steps": 166, "loss": 2.19, "lr": 1e-06, "epoch": 1.1197604790419162, "percentage": 56.63, "elapsed_time": "0:27:32", "remaining_time": "0:21:05"}
95
- {"current_steps": 95, "total_steps": 166, "loss": 2.1901, "lr": 1e-06, "epoch": 1.1317365269461077, "percentage": 57.23, "elapsed_time": "0:27:49", "remaining_time": "0:20:47"}
96
- {"current_steps": 96, "total_steps": 166, "loss": 2.1959, "lr": 1e-06, "epoch": 1.1437125748502994, "percentage": 57.83, "elapsed_time": "0:28:07", "remaining_time": "0:20:30"}
97
- {"current_steps": 97, "total_steps": 166, "loss": 2.1856, "lr": 1e-06, "epoch": 1.1556886227544911, "percentage": 58.43, "elapsed_time": "0:28:24", "remaining_time": "0:20:12"}
98
- {"current_steps": 98, "total_steps": 166, "loss": 2.1946, "lr": 1e-06, "epoch": 1.1676646706586826, "percentage": 59.04, "elapsed_time": "0:28:42", "remaining_time": "0:19:55"}
99
- {"current_steps": 99, "total_steps": 166, "loss": 2.1829, "lr": 1e-06, "epoch": 1.1796407185628743, "percentage": 59.64, "elapsed_time": "0:28:59", "remaining_time": "0:19:37"}
100
- {"current_steps": 100, "total_steps": 166, "loss": 2.1882, "lr": 1e-06, "epoch": 1.1916167664670658, "percentage": 60.24, "elapsed_time": "0:29:17", "remaining_time": "0:19:19"}
101
- {"current_steps": 101, "total_steps": 166, "loss": 2.1789, "lr": 1e-06, "epoch": 1.2035928143712575, "percentage": 60.84, "elapsed_time": "0:29:46", "remaining_time": "0:19:10"}
102
- {"current_steps": 102, "total_steps": 166, "loss": 2.1901, "lr": 1e-06, "epoch": 1.215568862275449, "percentage": 61.45, "elapsed_time": "0:30:04", "remaining_time": "0:18:52"}
103
- {"current_steps": 103, "total_steps": 166, "loss": 2.1786, "lr": 1e-06, "epoch": 1.2275449101796407, "percentage": 62.05, "elapsed_time": "0:30:21", "remaining_time": "0:18:34"}
104
- {"current_steps": 104, "total_steps": 166, "loss": 2.1815, "lr": 1e-06, "epoch": 1.2395209580838324, "percentage": 62.65, "elapsed_time": "0:30:39", "remaining_time": "0:18:16"}
105
- {"current_steps": 105, "total_steps": 166, "loss": 2.1766, "lr": 1e-06, "epoch": 1.251497005988024, "percentage": 63.25, "elapsed_time": "0:30:56", "remaining_time": "0:17:58"}
106
- {"current_steps": 106, "total_steps": 166, "loss": 2.1798, "lr": 1e-06, "epoch": 1.2634730538922156, "percentage": 63.86, "elapsed_time": "0:31:14", "remaining_time": "0:17:40"}
107
- {"current_steps": 107, "total_steps": 166, "loss": 2.1784, "lr": 1e-06, "epoch": 1.2754491017964071, "percentage": 64.46, "elapsed_time": "0:31:31", "remaining_time": "0:17:23"}
108
- {"current_steps": 108, "total_steps": 166, "loss": 2.1739, "lr": 1e-06, "epoch": 1.2874251497005988, "percentage": 65.06, "elapsed_time": "0:31:49", "remaining_time": "0:17:05"}
109
- {"current_steps": 109, "total_steps": 166, "loss": 2.1723, "lr": 1e-06, "epoch": 1.2994011976047903, "percentage": 65.66, "elapsed_time": "0:32:06", "remaining_time": "0:16:47"}
110
- {"current_steps": 110, "total_steps": 166, "loss": 2.1654, "lr": 1e-06, "epoch": 1.311377245508982, "percentage": 66.27, "elapsed_time": "0:32:24", "remaining_time": "0:16:29"}
111
- {"current_steps": 111, "total_steps": 166, "loss": 2.1714, "lr": 1e-06, "epoch": 1.3233532934131738, "percentage": 66.87, "elapsed_time": "0:32:41", "remaining_time": "0:16:12"}
112
- {"current_steps": 112, "total_steps": 166, "loss": 2.172, "lr": 1e-06, "epoch": 1.3353293413173652, "percentage": 67.47, "elapsed_time": "0:32:59", "remaining_time": "0:15:54"}
113
- {"current_steps": 113, "total_steps": 166, "loss": 2.1701, "lr": 1e-06, "epoch": 1.347305389221557, "percentage": 68.07, "elapsed_time": "0:33:16", "remaining_time": "0:15:36"}
114
- {"current_steps": 114, "total_steps": 166, "loss": 2.1516, "lr": 1e-06, "epoch": 1.3592814371257484, "percentage": 68.67, "elapsed_time": "0:33:34", "remaining_time": "0:15:18"}
115
- {"current_steps": 115, "total_steps": 166, "loss": 2.1695, "lr": 1e-06, "epoch": 1.3712574850299402, "percentage": 69.28, "elapsed_time": "0:33:51", "remaining_time": "0:15:00"}
116
- {"current_steps": 116, "total_steps": 166, "loss": 2.1619, "lr": 1e-06, "epoch": 1.3832335329341316, "percentage": 69.88, "elapsed_time": "0:34:09", "remaining_time": "0:14:43"}
117
- {"current_steps": 117, "total_steps": 166, "loss": 2.1709, "lr": 1e-06, "epoch": 1.3952095808383234, "percentage": 70.48, "elapsed_time": "0:34:26", "remaining_time": "0:14:25"}
118
- {"current_steps": 118, "total_steps": 166, "loss": 2.1659, "lr": 1e-06, "epoch": 1.407185628742515, "percentage": 71.08, "elapsed_time": "0:34:44", "remaining_time": "0:14:07"}
119
- {"current_steps": 119, "total_steps": 166, "loss": 2.1682, "lr": 1e-06, "epoch": 1.4191616766467066, "percentage": 71.69, "elapsed_time": "0:35:01", "remaining_time": "0:13:49"}
120
- {"current_steps": 120, "total_steps": 166, "loss": 2.1664, "lr": 1e-06, "epoch": 1.4311377245508983, "percentage": 72.29, "elapsed_time": "0:35:18", "remaining_time": "0:13:32"}
121
- {"current_steps": 121, "total_steps": 166, "loss": 2.1545, "lr": 1e-06, "epoch": 1.4431137724550898, "percentage": 72.89, "elapsed_time": "0:35:36", "remaining_time": "0:13:14"}
122
- {"current_steps": 122, "total_steps": 166, "loss": 2.1645, "lr": 1e-06, "epoch": 1.4550898203592815, "percentage": 73.49, "elapsed_time": "0:35:53", "remaining_time": "0:12:56"}
123
- {"current_steps": 123, "total_steps": 166, "loss": 2.1533, "lr": 1e-06, "epoch": 1.467065868263473, "percentage": 74.1, "elapsed_time": "0:36:11", "remaining_time": "0:12:39"}
124
- {"current_steps": 124, "total_steps": 166, "loss": 2.1602, "lr": 1e-06, "epoch": 1.4790419161676647, "percentage": 74.7, "elapsed_time": "0:36:28", "remaining_time": "0:12:21"}
125
- {"current_steps": 125, "total_steps": 166, "loss": 2.1629, "lr": 1e-06, "epoch": 1.4910179640718564, "percentage": 75.3, "elapsed_time": "0:36:46", "remaining_time": "0:12:03"}
126
- {"current_steps": 126, "total_steps": 166, "loss": 2.1552, "lr": 1e-06, "epoch": 1.5029940119760479, "percentage": 75.9, "elapsed_time": "0:37:03", "remaining_time": "0:11:45"}
127
- {"current_steps": 127, "total_steps": 166, "loss": 2.153, "lr": 1e-06, "epoch": 1.5149700598802394, "percentage": 76.51, "elapsed_time": "0:37:21", "remaining_time": "0:11:28"}
128
- {"current_steps": 128, "total_steps": 166, "loss": 2.1568, "lr": 1e-06, "epoch": 1.5269461077844313, "percentage": 77.11, "elapsed_time": "0:37:38", "remaining_time": "0:11:10"}
129
- {"current_steps": 129, "total_steps": 166, "loss": 2.1392, "lr": 1e-06, "epoch": 1.5389221556886228, "percentage": 77.71, "elapsed_time": "0:37:56", "remaining_time": "0:10:52"}
130
- {"current_steps": 130, "total_steps": 166, "loss": 2.1585, "lr": 1e-06, "epoch": 1.5508982035928143, "percentage": 78.31, "elapsed_time": "0:38:13", "remaining_time": "0:10:35"}
131
- {"current_steps": 131, "total_steps": 166, "loss": 2.1505, "lr": 1e-06, "epoch": 1.562874251497006, "percentage": 78.92, "elapsed_time": "0:38:31", "remaining_time": "0:10:17"}
132
- {"current_steps": 132, "total_steps": 166, "loss": 2.1517, "lr": 1e-06, "epoch": 1.5748502994011977, "percentage": 79.52, "elapsed_time": "0:38:48", "remaining_time": "0:09:59"}
133
- {"current_steps": 133, "total_steps": 166, "loss": 2.1443, "lr": 1e-06, "epoch": 1.5868263473053892, "percentage": 80.12, "elapsed_time": "0:39:06", "remaining_time": "0:09:42"}
134
- {"current_steps": 134, "total_steps": 166, "loss": 2.1335, "lr": 1e-06, "epoch": 1.5988023952095807, "percentage": 80.72, "elapsed_time": "0:39:23", "remaining_time": "0:09:24"}
135
- {"current_steps": 135, "total_steps": 166, "loss": 2.1442, "lr": 1e-06, "epoch": 1.6107784431137726, "percentage": 81.33, "elapsed_time": "0:39:40", "remaining_time": "0:09:06"}
136
- {"current_steps": 136, "total_steps": 166, "loss": 2.1452, "lr": 1e-06, "epoch": 1.622754491017964, "percentage": 81.93, "elapsed_time": "0:39:58", "remaining_time": "0:08:49"}
137
- {"current_steps": 137, "total_steps": 166, "loss": 2.1399, "lr": 1e-06, "epoch": 1.6347305389221556, "percentage": 82.53, "elapsed_time": "0:40:15", "remaining_time": "0:08:31"}
138
- {"current_steps": 138, "total_steps": 166, "loss": 2.1349, "lr": 1e-06, "epoch": 1.6467065868263473, "percentage": 83.13, "elapsed_time": "0:40:33", "remaining_time": "0:08:13"}
139
- {"current_steps": 139, "total_steps": 166, "loss": 2.142, "lr": 1e-06, "epoch": 1.658682634730539, "percentage": 83.73, "elapsed_time": "0:40:50", "remaining_time": "0:07:56"}
140
- {"current_steps": 140, "total_steps": 166, "loss": 2.1574, "lr": 1e-06, "epoch": 1.6706586826347305, "percentage": 84.34, "elapsed_time": "0:41:08", "remaining_time": "0:07:38"}
141
- {"current_steps": 141, "total_steps": 166, "loss": 2.1463, "lr": 1e-06, "epoch": 1.6826347305389222, "percentage": 84.94, "elapsed_time": "0:41:25", "remaining_time": "0:07:20"}
142
- {"current_steps": 142, "total_steps": 166, "loss": 2.1392, "lr": 1e-06, "epoch": 1.694610778443114, "percentage": 85.54, "elapsed_time": "0:41:43", "remaining_time": "0:07:03"}
143
- {"current_steps": 143, "total_steps": 166, "loss": 2.1402, "lr": 1e-06, "epoch": 1.7065868263473054, "percentage": 86.14, "elapsed_time": "0:42:00", "remaining_time": "0:06:45"}
144
- {"current_steps": 144, "total_steps": 166, "loss": 2.1445, "lr": 1e-06, "epoch": 1.718562874251497, "percentage": 86.75, "elapsed_time": "0:42:18", "remaining_time": "0:06:27"}
145
- {"current_steps": 145, "total_steps": 166, "loss": 2.1431, "lr": 1e-06, "epoch": 1.7305389221556886, "percentage": 87.35, "elapsed_time": "0:42:35", "remaining_time": "0:06:10"}
146
- {"current_steps": 146, "total_steps": 166, "loss": 2.1283, "lr": 1e-06, "epoch": 1.7425149700598803, "percentage": 87.95, "elapsed_time": "0:42:53", "remaining_time": "0:05:52"}
147
- {"current_steps": 147, "total_steps": 166, "loss": 2.1357, "lr": 1e-06, "epoch": 1.7544910179640718, "percentage": 88.55, "elapsed_time": "0:43:10", "remaining_time": "0:05:34"}
148
- {"current_steps": 148, "total_steps": 166, "loss": 2.1317, "lr": 1e-06, "epoch": 1.7664670658682635, "percentage": 89.16, "elapsed_time": "0:43:28", "remaining_time": "0:05:17"}
149
- {"current_steps": 149, "total_steps": 166, "loss": 2.1289, "lr": 1e-06, "epoch": 1.7784431137724552, "percentage": 89.76, "elapsed_time": "0:43:45", "remaining_time": "0:04:59"}
150
- {"current_steps": 150, "total_steps": 166, "loss": 2.135, "lr": 1e-06, "epoch": 1.7904191616766467, "percentage": 90.36, "elapsed_time": "0:44:03", "remaining_time": "0:04:41"}
151
- {"current_steps": 151, "total_steps": 166, "loss": 2.141, "lr": 1e-06, "epoch": 1.8023952095808382, "percentage": 90.96, "elapsed_time": "0:44:32", "remaining_time": "0:04:25"}
152
- {"current_steps": 152, "total_steps": 166, "loss": 2.1407, "lr": 1e-06, "epoch": 1.81437125748503, "percentage": 91.57, "elapsed_time": "0:44:49", "remaining_time": "0:04:07"}
153
- {"current_steps": 153, "total_steps": 166, "loss": 2.1293, "lr": 1e-06, "epoch": 1.8263473053892216, "percentage": 92.17, "elapsed_time": "0:45:06", "remaining_time": "0:03:49"}
154
- {"current_steps": 154, "total_steps": 166, "loss": 2.1282, "lr": 1e-06, "epoch": 1.8383233532934131, "percentage": 92.77, "elapsed_time": "0:45:24", "remaining_time": "0:03:32"}
155
- {"current_steps": 155, "total_steps": 166, "loss": 2.1287, "lr": 1e-06, "epoch": 1.8502994011976048, "percentage": 93.37, "elapsed_time": "0:45:41", "remaining_time": "0:03:14"}
156
- {"current_steps": 156, "total_steps": 166, "loss": 2.1318, "lr": 1e-06, "epoch": 1.8622754491017965, "percentage": 93.98, "elapsed_time": "0:45:59", "remaining_time": "0:02:56"}
157
- {"current_steps": 157, "total_steps": 166, "loss": 2.1395, "lr": 1e-06, "epoch": 1.874251497005988, "percentage": 94.58, "elapsed_time": "0:46:16", "remaining_time": "0:02:39"}
158
- {"current_steps": 158, "total_steps": 166, "loss": 2.1222, "lr": 1e-06, "epoch": 1.8862275449101795, "percentage": 95.18, "elapsed_time": "0:46:34", "remaining_time": "0:02:21"}
159
- {"current_steps": 159, "total_steps": 166, "loss": 2.1325, "lr": 1e-06, "epoch": 1.8982035928143712, "percentage": 95.78, "elapsed_time": "0:46:51", "remaining_time": "0:02:03"}
160
- {"current_steps": 160, "total_steps": 166, "loss": 2.1308, "lr": 1e-06, "epoch": 1.910179640718563, "percentage": 96.39, "elapsed_time": "0:47:09", "remaining_time": "0:01:46"}
161
- {"current_steps": 161, "total_steps": 166, "loss": 2.125, "lr": 1e-06, "epoch": 1.9221556886227544, "percentage": 96.99, "elapsed_time": "0:47:26", "remaining_time": "0:01:28"}
162
- {"current_steps": 162, "total_steps": 166, "loss": 2.1375, "lr": 1e-06, "epoch": 1.9341317365269461, "percentage": 97.59, "elapsed_time": "0:47:44", "remaining_time": "0:01:10"}
163
- {"current_steps": 163, "total_steps": 166, "loss": 2.13, "lr": 1e-06, "epoch": 1.9461077844311379, "percentage": 98.19, "elapsed_time": "0:48:01", "remaining_time": "0:00:53"}
164
- {"current_steps": 164, "total_steps": 166, "loss": 2.1362, "lr": 1e-06, "epoch": 1.9580838323353293, "percentage": 98.8, "elapsed_time": "0:48:18", "remaining_time": "0:00:35"}
165
- {"current_steps": 165, "total_steps": 166, "loss": 2.1214, "lr": 1e-06, "epoch": 1.9700598802395208, "percentage": 99.4, "elapsed_time": "0:48:36", "remaining_time": "0:00:17"}
166
- {"current_steps": 166, "total_steps": 166, "loss": 2.1383, "lr": 1e-06, "epoch": 1.9820359281437125, "percentage": 100.0, "elapsed_time": "0:48:53", "remaining_time": "0:00:00"}
167
- {"current_steps": 166, "total_steps": 166, "epoch": 1.9820359281437125, "percentage": 100.0, "elapsed_time": "0:49:03", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 166, "loss": 2.1163, "lr": 1e-06, "epoch": 0.011976047904191617, "percentage": 0.6, "elapsed_time": "0:00:38", "remaining_time": "1:45:29"}
2
+ {"current_steps": 2, "total_steps": 166, "loss": 2.1403, "lr": 1e-06, "epoch": 0.023952095808383235, "percentage": 1.2, "elapsed_time": "0:00:55", "remaining_time": "1:15:44"}
3
+ {"current_steps": 3, "total_steps": 166, "loss": 2.1273, "lr": 1e-06, "epoch": 0.03592814371257485, "percentage": 1.81, "elapsed_time": "0:01:12", "remaining_time": "1:05:47"}
4
+ {"current_steps": 4, "total_steps": 166, "loss": 2.1295, "lr": 1e-06, "epoch": 0.04790419161676647, "percentage": 2.41, "elapsed_time": "0:01:30", "remaining_time": "1:00:49"}
5
+ {"current_steps": 5, "total_steps": 166, "loss": 2.1304, "lr": 1e-06, "epoch": 0.059880239520958084, "percentage": 3.01, "elapsed_time": "0:01:47", "remaining_time": "0:57:48"}
6
+ {"current_steps": 6, "total_steps": 166, "loss": 2.1294, "lr": 1e-06, "epoch": 0.0718562874251497, "percentage": 3.61, "elapsed_time": "0:02:05", "remaining_time": "0:55:43"}
7
+ {"current_steps": 7, "total_steps": 166, "loss": 2.1233, "lr": 1e-06, "epoch": 0.08383233532934131, "percentage": 4.22, "elapsed_time": "0:02:23", "remaining_time": "0:54:09"}
8
+ {"current_steps": 8, "total_steps": 166, "loss": 2.1213, "lr": 1e-06, "epoch": 0.09580838323353294, "percentage": 4.82, "elapsed_time": "0:02:40", "remaining_time": "0:52:55"}
9
+ {"current_steps": 9, "total_steps": 166, "loss": 2.1197, "lr": 1e-06, "epoch": 0.10778443113772455, "percentage": 5.42, "elapsed_time": "0:02:58", "remaining_time": "0:51:54"}
10
+ {"current_steps": 10, "total_steps": 166, "loss": 2.1304, "lr": 1e-06, "epoch": 0.11976047904191617, "percentage": 6.02, "elapsed_time": "0:03:16", "remaining_time": "0:51:01"}
11
+ {"current_steps": 11, "total_steps": 166, "loss": 2.1375, "lr": 1e-06, "epoch": 0.1317365269461078, "percentage": 6.63, "elapsed_time": "0:03:33", "remaining_time": "0:50:15"}
12
+ {"current_steps": 12, "total_steps": 166, "loss": 2.133, "lr": 1e-06, "epoch": 0.1437125748502994, "percentage": 7.23, "elapsed_time": "0:03:51", "remaining_time": "0:49:33"}
13
+ {"current_steps": 13, "total_steps": 166, "loss": 2.1257, "lr": 1e-06, "epoch": 0.15568862275449102, "percentage": 7.83, "elapsed_time": "0:04:09", "remaining_time": "0:48:55"}
14
+ {"current_steps": 14, "total_steps": 166, "loss": 2.1184, "lr": 1e-06, "epoch": 0.16766467065868262, "percentage": 8.43, "elapsed_time": "0:04:27", "remaining_time": "0:48:21"}
15
+ {"current_steps": 15, "total_steps": 166, "loss": 2.1256, "lr": 1e-06, "epoch": 0.17964071856287425, "percentage": 9.04, "elapsed_time": "0:04:44", "remaining_time": "0:47:48"}
16
+ {"current_steps": 16, "total_steps": 166, "loss": 2.1166, "lr": 1e-06, "epoch": 0.19161676646706588, "percentage": 9.64, "elapsed_time": "0:05:02", "remaining_time": "0:47:18"}
17
+ {"current_steps": 17, "total_steps": 166, "loss": 2.1378, "lr": 1e-06, "epoch": 0.20359281437125748, "percentage": 10.24, "elapsed_time": "0:05:20", "remaining_time": "0:46:49"}
18
+ {"current_steps": 18, "total_steps": 166, "loss": 2.1298, "lr": 1e-06, "epoch": 0.2155688622754491, "percentage": 10.84, "elapsed_time": "0:05:38", "remaining_time": "0:46:21"}
19
+ {"current_steps": 19, "total_steps": 166, "loss": 2.1151, "lr": 1e-06, "epoch": 0.2275449101796407, "percentage": 11.45, "elapsed_time": "0:05:55", "remaining_time": "0:45:54"}
20
+ {"current_steps": 20, "total_steps": 166, "loss": 2.1277, "lr": 1e-06, "epoch": 0.23952095808383234, "percentage": 12.05, "elapsed_time": "0:06:13", "remaining_time": "0:45:28"}
21
+ {"current_steps": 21, "total_steps": 166, "loss": 2.1229, "lr": 1e-06, "epoch": 0.25149700598802394, "percentage": 12.65, "elapsed_time": "0:06:31", "remaining_time": "0:45:03"}
22
+ {"current_steps": 22, "total_steps": 166, "loss": 2.1189, "lr": 1e-06, "epoch": 0.2634730538922156, "percentage": 13.25, "elapsed_time": "0:06:49", "remaining_time": "0:44:38"}
23
+ {"current_steps": 23, "total_steps": 166, "loss": 2.125, "lr": 1e-06, "epoch": 0.2754491017964072, "percentage": 13.86, "elapsed_time": "0:07:07", "remaining_time": "0:44:14"}
24
+ {"current_steps": 24, "total_steps": 166, "loss": 2.1261, "lr": 1e-06, "epoch": 0.2874251497005988, "percentage": 14.46, "elapsed_time": "0:07:24", "remaining_time": "0:43:51"}
25
+ {"current_steps": 25, "total_steps": 166, "loss": 2.1321, "lr": 1e-06, "epoch": 0.2994011976047904, "percentage": 15.06, "elapsed_time": "0:07:42", "remaining_time": "0:43:28"}
26
+ {"current_steps": 26, "total_steps": 166, "loss": 2.1266, "lr": 1e-06, "epoch": 0.31137724550898205, "percentage": 15.66, "elapsed_time": "0:08:00", "remaining_time": "0:43:06"}
27
+ {"current_steps": 27, "total_steps": 166, "loss": 2.1174, "lr": 1e-06, "epoch": 0.32335329341317365, "percentage": 16.27, "elapsed_time": "0:08:18", "remaining_time": "0:42:44"}
28
+ {"current_steps": 28, "total_steps": 166, "loss": 2.1271, "lr": 1e-06, "epoch": 0.33532934131736525, "percentage": 16.87, "elapsed_time": "0:08:35", "remaining_time": "0:42:22"}
29
+ {"current_steps": 29, "total_steps": 166, "loss": 2.1201, "lr": 1e-06, "epoch": 0.3473053892215569, "percentage": 17.47, "elapsed_time": "0:08:53", "remaining_time": "0:42:00"}
30
+ {"current_steps": 30, "total_steps": 166, "loss": 2.1331, "lr": 1e-06, "epoch": 0.3592814371257485, "percentage": 18.07, "elapsed_time": "0:09:11", "remaining_time": "0:41:39"}
31
+ {"current_steps": 31, "total_steps": 166, "loss": 2.1198, "lr": 1e-06, "epoch": 0.3712574850299401, "percentage": 18.67, "elapsed_time": "0:09:29", "remaining_time": "0:41:18"}
32
+ {"current_steps": 32, "total_steps": 166, "loss": 2.1293, "lr": 1e-06, "epoch": 0.38323353293413176, "percentage": 19.28, "elapsed_time": "0:09:46", "remaining_time": "0:40:57"}
33
+ {"current_steps": 33, "total_steps": 166, "loss": 2.1267, "lr": 1e-06, "epoch": 0.39520958083832336, "percentage": 19.88, "elapsed_time": "0:10:04", "remaining_time": "0:40:36"}
34
+ {"current_steps": 34, "total_steps": 166, "loss": 2.1156, "lr": 1e-06, "epoch": 0.40718562874251496, "percentage": 20.48, "elapsed_time": "0:10:22", "remaining_time": "0:40:16"}
35
+ {"current_steps": 35, "total_steps": 166, "loss": 2.1256, "lr": 1e-06, "epoch": 0.41916167664670656, "percentage": 21.08, "elapsed_time": "0:10:40", "remaining_time": "0:39:55"}
36
+ {"current_steps": 36, "total_steps": 166, "loss": 2.1268, "lr": 1e-06, "epoch": 0.4311377245508982, "percentage": 21.69, "elapsed_time": "0:10:57", "remaining_time": "0:39:35"}
37
+ {"current_steps": 37, "total_steps": 166, "loss": 2.1183, "lr": 1e-06, "epoch": 0.4431137724550898, "percentage": 22.29, "elapsed_time": "0:11:15", "remaining_time": "0:39:15"}
38
+ {"current_steps": 38, "total_steps": 166, "loss": 2.1153, "lr": 1e-06, "epoch": 0.4550898203592814, "percentage": 22.89, "elapsed_time": "0:11:33", "remaining_time": "0:38:55"}
39
+ {"current_steps": 39, "total_steps": 166, "loss": 2.1107, "lr": 1e-06, "epoch": 0.46706586826347307, "percentage": 23.49, "elapsed_time": "0:11:51", "remaining_time": "0:38:35"}
40
+ {"current_steps": 40, "total_steps": 166, "loss": 2.1208, "lr": 1e-06, "epoch": 0.47904191616766467, "percentage": 24.1, "elapsed_time": "0:12:08", "remaining_time": "0:38:16"}
41
+ {"current_steps": 41, "total_steps": 166, "loss": 2.1303, "lr": 1e-06, "epoch": 0.49101796407185627, "percentage": 24.7, "elapsed_time": "0:12:26", "remaining_time": "0:37:56"}
42
+ {"current_steps": 42, "total_steps": 166, "loss": 2.1135, "lr": 1e-06, "epoch": 0.5029940119760479, "percentage": 25.3, "elapsed_time": "0:12:44", "remaining_time": "0:37:36"}
43
+ {"current_steps": 43, "total_steps": 166, "loss": 2.1075, "lr": 1e-06, "epoch": 0.5149700598802395, "percentage": 25.9, "elapsed_time": "0:13:02", "remaining_time": "0:37:17"}
44
+ {"current_steps": 44, "total_steps": 166, "loss": 2.119, "lr": 1e-06, "epoch": 0.5269461077844312, "percentage": 26.51, "elapsed_time": "0:13:19", "remaining_time": "0:36:57"}
45
+ {"current_steps": 45, "total_steps": 166, "loss": 2.1231, "lr": 1e-06, "epoch": 0.5389221556886228, "percentage": 27.11, "elapsed_time": "0:13:37", "remaining_time": "0:36:38"}
46
+ {"current_steps": 46, "total_steps": 166, "loss": 2.1126, "lr": 1e-06, "epoch": 0.5508982035928144, "percentage": 27.71, "elapsed_time": "0:13:55", "remaining_time": "0:36:19"}
47
+ {"current_steps": 47, "total_steps": 166, "loss": 2.115, "lr": 1e-06, "epoch": 0.562874251497006, "percentage": 28.31, "elapsed_time": "0:14:13", "remaining_time": "0:36:00"}
48
+ {"current_steps": 48, "total_steps": 166, "loss": 2.1143, "lr": 1e-06, "epoch": 0.5748502994011976, "percentage": 28.92, "elapsed_time": "0:14:30", "remaining_time": "0:35:41"}
49
+ {"current_steps": 49, "total_steps": 166, "loss": 2.1219, "lr": 1e-06, "epoch": 0.5868263473053892, "percentage": 29.52, "elapsed_time": "0:14:48", "remaining_time": "0:35:22"}
50
+ {"current_steps": 50, "total_steps": 166, "loss": 2.118, "lr": 1e-06, "epoch": 0.5988023952095808, "percentage": 30.12, "elapsed_time": "0:15:06", "remaining_time": "0:35:03"}
51
+ {"current_steps": 51, "total_steps": 166, "loss": 2.1105, "lr": 1e-06, "epoch": 0.6107784431137725, "percentage": 30.72, "elapsed_time": "0:15:30", "remaining_time": "0:34:58"}
52
+ {"current_steps": 52, "total_steps": 166, "loss": 2.1239, "lr": 1e-06, "epoch": 0.6227544910179641, "percentage": 31.33, "elapsed_time": "0:15:48", "remaining_time": "0:34:39"}
53
+ {"current_steps": 53, "total_steps": 166, "loss": 2.1126, "lr": 1e-06, "epoch": 0.6347305389221557, "percentage": 31.93, "elapsed_time": "0:16:06", "remaining_time": "0:34:20"}
54
+ {"current_steps": 54, "total_steps": 166, "loss": 2.124, "lr": 1e-06, "epoch": 0.6467065868263473, "percentage": 32.53, "elapsed_time": "0:16:24", "remaining_time": "0:34:00"}
55
+ {"current_steps": 55, "total_steps": 166, "loss": 2.1112, "lr": 1e-06, "epoch": 0.6586826347305389, "percentage": 33.13, "elapsed_time": "0:16:41", "remaining_time": "0:33:41"}
56
+ {"current_steps": 56, "total_steps": 166, "loss": 2.1259, "lr": 1e-06, "epoch": 0.6706586826347305, "percentage": 33.73, "elapsed_time": "0:16:59", "remaining_time": "0:33:22"}
57
+ {"current_steps": 57, "total_steps": 166, "loss": 2.1179, "lr": 1e-06, "epoch": 0.6826347305389222, "percentage": 34.34, "elapsed_time": "0:17:17", "remaining_time": "0:33:03"}
58
+ {"current_steps": 58, "total_steps": 166, "loss": 2.1165, "lr": 1e-06, "epoch": 0.6946107784431138, "percentage": 34.94, "elapsed_time": "0:17:35", "remaining_time": "0:32:44"}
59
+ {"current_steps": 59, "total_steps": 166, "loss": 2.1177, "lr": 1e-06, "epoch": 0.7065868263473054, "percentage": 35.54, "elapsed_time": "0:17:52", "remaining_time": "0:32:25"}
60
+ {"current_steps": 60, "total_steps": 166, "loss": 2.1106, "lr": 1e-06, "epoch": 0.718562874251497, "percentage": 36.14, "elapsed_time": "0:18:10", "remaining_time": "0:32:06"}
61
+ {"current_steps": 61, "total_steps": 166, "loss": 2.1206, "lr": 1e-06, "epoch": 0.7305389221556886, "percentage": 36.75, "elapsed_time": "0:18:28", "remaining_time": "0:31:47"}
62
+ {"current_steps": 62, "total_steps": 166, "loss": 2.1184, "lr": 1e-06, "epoch": 0.7425149700598802, "percentage": 37.35, "elapsed_time": "0:18:46", "remaining_time": "0:31:28"}
63
+ {"current_steps": 63, "total_steps": 166, "loss": 2.1172, "lr": 1e-06, "epoch": 0.7544910179640718, "percentage": 37.95, "elapsed_time": "0:19:03", "remaining_time": "0:31:09"}
64
+ {"current_steps": 64, "total_steps": 166, "loss": 2.1111, "lr": 1e-06, "epoch": 0.7664670658682635, "percentage": 38.55, "elapsed_time": "0:19:21", "remaining_time": "0:30:51"}
65
+ {"current_steps": 65, "total_steps": 166, "loss": 2.1037, "lr": 1e-06, "epoch": 0.7784431137724551, "percentage": 39.16, "elapsed_time": "0:19:39", "remaining_time": "0:30:32"}
66
+ {"current_steps": 66, "total_steps": 166, "loss": 2.1221, "lr": 1e-06, "epoch": 0.7904191616766467, "percentage": 39.76, "elapsed_time": "0:19:57", "remaining_time": "0:30:13"}
67
+ {"current_steps": 67, "total_steps": 166, "loss": 2.1105, "lr": 1e-06, "epoch": 0.8023952095808383, "percentage": 40.36, "elapsed_time": "0:20:14", "remaining_time": "0:29:54"}
68
+ {"current_steps": 68, "total_steps": 166, "loss": 2.1076, "lr": 1e-06, "epoch": 0.8143712574850299, "percentage": 40.96, "elapsed_time": "0:20:32", "remaining_time": "0:29:36"}
69
+ {"current_steps": 69, "total_steps": 166, "loss": 2.116, "lr": 1e-06, "epoch": 0.8263473053892215, "percentage": 41.57, "elapsed_time": "0:20:50", "remaining_time": "0:29:17"}
70
+ {"current_steps": 70, "total_steps": 166, "loss": 2.1077, "lr": 1e-06, "epoch": 0.8383233532934131, "percentage": 42.17, "elapsed_time": "0:21:08", "remaining_time": "0:28:59"}
71
+ {"current_steps": 71, "total_steps": 166, "loss": 2.1166, "lr": 1e-06, "epoch": 0.8502994011976048, "percentage": 42.77, "elapsed_time": "0:21:25", "remaining_time": "0:28:40"}
72
+ {"current_steps": 72, "total_steps": 166, "loss": 2.1107, "lr": 1e-06, "epoch": 0.8622754491017964, "percentage": 43.37, "elapsed_time": "0:21:43", "remaining_time": "0:28:21"}
73
+ {"current_steps": 73, "total_steps": 166, "loss": 2.1077, "lr": 1e-06, "epoch": 0.874251497005988, "percentage": 43.98, "elapsed_time": "0:22:01", "remaining_time": "0:28:03"}
74
+ {"current_steps": 74, "total_steps": 166, "loss": 2.1117, "lr": 1e-06, "epoch": 0.8862275449101796, "percentage": 44.58, "elapsed_time": "0:22:19", "remaining_time": "0:27:44"}
75
+ {"current_steps": 75, "total_steps": 166, "loss": 2.1044, "lr": 1e-06, "epoch": 0.8982035928143712, "percentage": 45.18, "elapsed_time": "0:22:36", "remaining_time": "0:27:26"}
76
+ {"current_steps": 76, "total_steps": 166, "loss": 2.1101, "lr": 1e-06, "epoch": 0.9101796407185628, "percentage": 45.78, "elapsed_time": "0:22:54", "remaining_time": "0:27:07"}
77
+ {"current_steps": 77, "total_steps": 166, "loss": 2.1048, "lr": 1e-06, "epoch": 0.9221556886227545, "percentage": 46.39, "elapsed_time": "0:23:12", "remaining_time": "0:26:49"}
78
+ {"current_steps": 78, "total_steps": 166, "loss": 2.1071, "lr": 1e-06, "epoch": 0.9341317365269461, "percentage": 46.99, "elapsed_time": "0:23:29", "remaining_time": "0:26:30"}
79
+ {"current_steps": 79, "total_steps": 166, "loss": 2.1109, "lr": 1e-06, "epoch": 0.9461077844311377, "percentage": 47.59, "elapsed_time": "0:23:47", "remaining_time": "0:26:12"}
80
+ {"current_steps": 80, "total_steps": 166, "loss": 2.0949, "lr": 1e-06, "epoch": 0.9580838323353293, "percentage": 48.19, "elapsed_time": "0:24:05", "remaining_time": "0:25:53"}
81
+ {"current_steps": 81, "total_steps": 166, "loss": 2.1091, "lr": 1e-06, "epoch": 0.9700598802395209, "percentage": 48.8, "elapsed_time": "0:24:23", "remaining_time": "0:25:35"}
82
+ {"current_steps": 82, "total_steps": 166, "loss": 2.0978, "lr": 1e-06, "epoch": 0.9820359281437125, "percentage": 49.4, "elapsed_time": "0:24:40", "remaining_time": "0:25:17"}
83
+ {"current_steps": 83, "total_steps": 166, "loss": 2.1032, "lr": 1e-06, "epoch": 0.9940119760479041, "percentage": 50.0, "elapsed_time": "0:24:58", "remaining_time": "0:24:58"}
84
+ {"current_steps": 84, "total_steps": 166, "loss": 2.1076, "lr": 1e-06, "epoch": 1.0, "percentage": 50.6, "elapsed_time": "0:25:07", "remaining_time": "0:24:31"}
85
+ {"current_steps": 85, "total_steps": 166, "loss": 2.1015, "lr": 1e-06, "epoch": 1.0119760479041917, "percentage": 51.2, "elapsed_time": "0:25:26", "remaining_time": "0:24:14"}
86
+ {"current_steps": 86, "total_steps": 166, "loss": 2.0965, "lr": 1e-06, "epoch": 1.0239520958083832, "percentage": 51.81, "elapsed_time": "0:25:44", "remaining_time": "0:23:56"}
87
+ {"current_steps": 87, "total_steps": 166, "loss": 2.0984, "lr": 1e-06, "epoch": 1.035928143712575, "percentage": 52.41, "elapsed_time": "0:26:02", "remaining_time": "0:23:38"}
88
+ {"current_steps": 88, "total_steps": 166, "loss": 2.0989, "lr": 1e-06, "epoch": 1.0479041916167664, "percentage": 53.01, "elapsed_time": "0:26:20", "remaining_time": "0:23:20"}
89
+ {"current_steps": 89, "total_steps": 166, "loss": 2.1082, "lr": 1e-06, "epoch": 1.0598802395209581, "percentage": 53.61, "elapsed_time": "0:26:37", "remaining_time": "0:23:02"}
90
+ {"current_steps": 90, "total_steps": 166, "loss": 2.1018, "lr": 1e-06, "epoch": 1.0718562874251496, "percentage": 54.22, "elapsed_time": "0:26:55", "remaining_time": "0:22:44"}
91
+ {"current_steps": 91, "total_steps": 166, "loss": 2.1095, "lr": 1e-06, "epoch": 1.0838323353293413, "percentage": 54.82, "elapsed_time": "0:27:13", "remaining_time": "0:22:26"}
92
+ {"current_steps": 92, "total_steps": 166, "loss": 2.0966, "lr": 1e-06, "epoch": 1.095808383233533, "percentage": 55.42, "elapsed_time": "0:27:31", "remaining_time": "0:22:08"}
93
+ {"current_steps": 93, "total_steps": 166, "loss": 2.1034, "lr": 1e-06, "epoch": 1.1077844311377245, "percentage": 56.02, "elapsed_time": "0:27:48", "remaining_time": "0:21:49"}
94
+ {"current_steps": 94, "total_steps": 166, "loss": 2.0981, "lr": 1e-06, "epoch": 1.1197604790419162, "percentage": 56.63, "elapsed_time": "0:28:06", "remaining_time": "0:21:31"}
95
+ {"current_steps": 95, "total_steps": 166, "loss": 2.0985, "lr": 1e-06, "epoch": 1.1317365269461077, "percentage": 57.23, "elapsed_time": "0:28:24", "remaining_time": "0:21:13"}
96
+ {"current_steps": 96, "total_steps": 166, "loss": 2.1035, "lr": 1e-06, "epoch": 1.1437125748502994, "percentage": 57.83, "elapsed_time": "0:28:42", "remaining_time": "0:20:55"}
97
+ {"current_steps": 97, "total_steps": 166, "loss": 2.0938, "lr": 1e-06, "epoch": 1.1556886227544911, "percentage": 58.43, "elapsed_time": "0:28:59", "remaining_time": "0:20:37"}
98
+ {"current_steps": 98, "total_steps": 166, "loss": 2.1011, "lr": 1e-06, "epoch": 1.1676646706586826, "percentage": 59.04, "elapsed_time": "0:29:17", "remaining_time": "0:20:19"}
99
+ {"current_steps": 99, "total_steps": 166, "loss": 2.093, "lr": 1e-06, "epoch": 1.1796407185628743, "percentage": 59.64, "elapsed_time": "0:29:35", "remaining_time": "0:20:01"}
100
+ {"current_steps": 100, "total_steps": 166, "loss": 2.0972, "lr": 1e-06, "epoch": 1.1916167664670658, "percentage": 60.24, "elapsed_time": "0:29:53", "remaining_time": "0:19:43"}
101
+ {"current_steps": 101, "total_steps": 166, "loss": 2.0898, "lr": 1e-06, "epoch": 1.2035928143712575, "percentage": 60.84, "elapsed_time": "0:30:19", "remaining_time": "0:19:31"}
102
+ {"current_steps": 102, "total_steps": 166, "loss": 2.1008, "lr": 1e-06, "epoch": 1.215568862275449, "percentage": 61.45, "elapsed_time": "0:30:37", "remaining_time": "0:19:12"}
103
+ {"current_steps": 103, "total_steps": 166, "loss": 2.091, "lr": 1e-06, "epoch": 1.2275449101796407, "percentage": 62.05, "elapsed_time": "0:30:55", "remaining_time": "0:18:54"}
104
+ {"current_steps": 104, "total_steps": 166, "loss": 2.0945, "lr": 1e-06, "epoch": 1.2395209580838324, "percentage": 62.65, "elapsed_time": "0:31:12", "remaining_time": "0:18:36"}
105
+ {"current_steps": 105, "total_steps": 166, "loss": 2.092, "lr": 1e-06, "epoch": 1.251497005988024, "percentage": 63.25, "elapsed_time": "0:31:30", "remaining_time": "0:18:18"}
106
+ {"current_steps": 106, "total_steps": 166, "loss": 2.0936, "lr": 1e-06, "epoch": 1.2634730538922156, "percentage": 63.86, "elapsed_time": "0:31:48", "remaining_time": "0:18:00"}
107
+ {"current_steps": 107, "total_steps": 166, "loss": 2.0961, "lr": 1e-06, "epoch": 1.2754491017964071, "percentage": 64.46, "elapsed_time": "0:32:06", "remaining_time": "0:17:42"}
108
+ {"current_steps": 108, "total_steps": 166, "loss": 2.0916, "lr": 1e-06, "epoch": 1.2874251497005988, "percentage": 65.06, "elapsed_time": "0:32:23", "remaining_time": "0:17:23"}
109
+ {"current_steps": 109, "total_steps": 166, "loss": 2.0905, "lr": 1e-06, "epoch": 1.2994011976047903, "percentage": 65.66, "elapsed_time": "0:32:41", "remaining_time": "0:17:05"}
110
+ {"current_steps": 110, "total_steps": 166, "loss": 2.0862, "lr": 1e-06, "epoch": 1.311377245508982, "percentage": 66.27, "elapsed_time": "0:32:59", "remaining_time": "0:16:47"}
111
+ {"current_steps": 111, "total_steps": 166, "loss": 2.0934, "lr": 1e-06, "epoch": 1.3233532934131738, "percentage": 66.87, "elapsed_time": "0:33:17", "remaining_time": "0:16:29"}
112
+ {"current_steps": 112, "total_steps": 166, "loss": 2.0949, "lr": 1e-06, "epoch": 1.3353293413173652, "percentage": 67.47, "elapsed_time": "0:33:34", "remaining_time": "0:16:11"}
113
+ {"current_steps": 113, "total_steps": 166, "loss": 2.0942, "lr": 1e-06, "epoch": 1.347305389221557, "percentage": 68.07, "elapsed_time": "0:33:52", "remaining_time": "0:15:53"}
114
+ {"current_steps": 114, "total_steps": 166, "loss": 2.0759, "lr": 1e-06, "epoch": 1.3592814371257484, "percentage": 68.67, "elapsed_time": "0:34:10", "remaining_time": "0:15:35"}
115
+ {"current_steps": 115, "total_steps": 166, "loss": 2.0963, "lr": 1e-06, "epoch": 1.3712574850299402, "percentage": 69.28, "elapsed_time": "0:34:28", "remaining_time": "0:15:17"}
116
+ {"current_steps": 116, "total_steps": 166, "loss": 2.0874, "lr": 1e-06, "epoch": 1.3832335329341316, "percentage": 69.88, "elapsed_time": "0:34:45", "remaining_time": "0:14:59"}
117
+ {"current_steps": 117, "total_steps": 166, "loss": 2.0995, "lr": 1e-06, "epoch": 1.3952095808383234, "percentage": 70.48, "elapsed_time": "0:35:03", "remaining_time": "0:14:41"}
118
+ {"current_steps": 118, "total_steps": 166, "loss": 2.0956, "lr": 1e-06, "epoch": 1.407185628742515, "percentage": 71.08, "elapsed_time": "0:35:21", "remaining_time": "0:14:22"}
119
+ {"current_steps": 119, "total_steps": 166, "loss": 2.0975, "lr": 1e-06, "epoch": 1.4191616766467066, "percentage": 71.69, "elapsed_time": "0:35:39", "remaining_time": "0:14:04"}
120
+ {"current_steps": 120, "total_steps": 166, "loss": 2.099, "lr": 1e-06, "epoch": 1.4311377245508983, "percentage": 72.29, "elapsed_time": "0:35:56", "remaining_time": "0:13:46"}
121
+ {"current_steps": 121, "total_steps": 166, "loss": 2.0861, "lr": 1e-06, "epoch": 1.4431137724550898, "percentage": 72.89, "elapsed_time": "0:36:14", "remaining_time": "0:13:28"}
122
+ {"current_steps": 122, "total_steps": 166, "loss": 2.0973, "lr": 1e-06, "epoch": 1.4550898203592815, "percentage": 73.49, "elapsed_time": "0:36:32", "remaining_time": "0:13:10"}
123
+ {"current_steps": 123, "total_steps": 166, "loss": 2.0879, "lr": 1e-06, "epoch": 1.467065868263473, "percentage": 74.1, "elapsed_time": "0:36:50", "remaining_time": "0:12:52"}
124
+ {"current_steps": 124, "total_steps": 166, "loss": 2.0934, "lr": 1e-06, "epoch": 1.4790419161676647, "percentage": 74.7, "elapsed_time": "0:37:08", "remaining_time": "0:12:34"}
125
+ {"current_steps": 125, "total_steps": 166, "loss": 2.0974, "lr": 1e-06, "epoch": 1.4910179640718564, "percentage": 75.3, "elapsed_time": "0:37:25", "remaining_time": "0:12:16"}
126
+ {"current_steps": 126, "total_steps": 166, "loss": 2.0897, "lr": 1e-06, "epoch": 1.5029940119760479, "percentage": 75.9, "elapsed_time": "0:37:43", "remaining_time": "0:11:58"}
127
+ {"current_steps": 127, "total_steps": 166, "loss": 2.087, "lr": 1e-06, "epoch": 1.5149700598802394, "percentage": 76.51, "elapsed_time": "0:38:01", "remaining_time": "0:11:40"}
128
+ {"current_steps": 128, "total_steps": 166, "loss": 2.093, "lr": 1e-06, "epoch": 1.5269461077844313, "percentage": 77.11, "elapsed_time": "0:38:19", "remaining_time": "0:11:22"}
129
+ {"current_steps": 129, "total_steps": 166, "loss": 2.0762, "lr": 1e-06, "epoch": 1.5389221556886228, "percentage": 77.71, "elapsed_time": "0:38:36", "remaining_time": "0:11:04"}
130
+ {"current_steps": 130, "total_steps": 166, "loss": 2.0937, "lr": 1e-06, "epoch": 1.5508982035928143, "percentage": 78.31, "elapsed_time": "0:38:54", "remaining_time": "0:10:46"}
131
+ {"current_steps": 131, "total_steps": 166, "loss": 2.0869, "lr": 1e-06, "epoch": 1.562874251497006, "percentage": 78.92, "elapsed_time": "0:39:12", "remaining_time": "0:10:28"}
132
+ {"current_steps": 132, "total_steps": 166, "loss": 2.0884, "lr": 1e-06, "epoch": 1.5748502994011977, "percentage": 79.52, "elapsed_time": "0:39:30", "remaining_time": "0:10:10"}
133
+ {"current_steps": 133, "total_steps": 166, "loss": 2.0795, "lr": 1e-06, "epoch": 1.5868263473053892, "percentage": 80.12, "elapsed_time": "0:39:48", "remaining_time": "0:09:52"}
134
+ {"current_steps": 134, "total_steps": 166, "loss": 2.0683, "lr": 1e-06, "epoch": 1.5988023952095807, "percentage": 80.72, "elapsed_time": "0:40:05", "remaining_time": "0:09:34"}
135
+ {"current_steps": 135, "total_steps": 166, "loss": 2.0788, "lr": 1e-06, "epoch": 1.6107784431137726, "percentage": 81.33, "elapsed_time": "0:40:23", "remaining_time": "0:09:16"}
136
+ {"current_steps": 136, "total_steps": 166, "loss": 2.0803, "lr": 1e-06, "epoch": 1.622754491017964, "percentage": 81.93, "elapsed_time": "0:40:41", "remaining_time": "0:08:58"}
137
+ {"current_steps": 137, "total_steps": 166, "loss": 2.075, "lr": 1e-06, "epoch": 1.6347305389221556, "percentage": 82.53, "elapsed_time": "0:40:59", "remaining_time": "0:08:40"}
138
+ {"current_steps": 138, "total_steps": 166, "loss": 2.0694, "lr": 1e-06, "epoch": 1.6467065868263473, "percentage": 83.13, "elapsed_time": "0:41:16", "remaining_time": "0:08:22"}
139
+ {"current_steps": 139, "total_steps": 166, "loss": 2.0777, "lr": 1e-06, "epoch": 1.658682634730539, "percentage": 83.73, "elapsed_time": "0:41:34", "remaining_time": "0:08:04"}
140
+ {"current_steps": 140, "total_steps": 166, "loss": 2.0919, "lr": 1e-06, "epoch": 1.6706586826347305, "percentage": 84.34, "elapsed_time": "0:41:52", "remaining_time": "0:07:46"}
141
+ {"current_steps": 141, "total_steps": 166, "loss": 2.0802, "lr": 1e-06, "epoch": 1.6826347305389222, "percentage": 84.94, "elapsed_time": "0:42:10", "remaining_time": "0:07:28"}
142
+ {"current_steps": 142, "total_steps": 166, "loss": 2.0732, "lr": 1e-06, "epoch": 1.694610778443114, "percentage": 85.54, "elapsed_time": "0:42:27", "remaining_time": "0:07:10"}
143
+ {"current_steps": 143, "total_steps": 166, "loss": 2.0748, "lr": 1e-06, "epoch": 1.7065868263473054, "percentage": 86.14, "elapsed_time": "0:42:45", "remaining_time": "0:06:52"}
144
+ {"current_steps": 144, "total_steps": 166, "loss": 2.0786, "lr": 1e-06, "epoch": 1.718562874251497, "percentage": 86.75, "elapsed_time": "0:43:03", "remaining_time": "0:06:34"}
145
+ {"current_steps": 145, "total_steps": 166, "loss": 2.0756, "lr": 1e-06, "epoch": 1.7305389221556886, "percentage": 87.35, "elapsed_time": "0:43:21", "remaining_time": "0:06:16"}
146
+ {"current_steps": 146, "total_steps": 166, "loss": 2.0625, "lr": 1e-06, "epoch": 1.7425149700598803, "percentage": 87.95, "elapsed_time": "0:43:38", "remaining_time": "0:05:58"}
147
+ {"current_steps": 147, "total_steps": 166, "loss": 2.0685, "lr": 1e-06, "epoch": 1.7544910179640718, "percentage": 88.55, "elapsed_time": "0:43:56", "remaining_time": "0:05:40"}
148
+ {"current_steps": 148, "total_steps": 166, "loss": 2.0655, "lr": 1e-06, "epoch": 1.7664670658682635, "percentage": 89.16, "elapsed_time": "0:44:14", "remaining_time": "0:05:22"}
149
+ {"current_steps": 149, "total_steps": 166, "loss": 2.0617, "lr": 1e-06, "epoch": 1.7784431137724552, "percentage": 89.76, "elapsed_time": "0:44:32", "remaining_time": "0:05:04"}
150
+ {"current_steps": 150, "total_steps": 166, "loss": 2.0686, "lr": 1e-06, "epoch": 1.7904191616766467, "percentage": 90.36, "elapsed_time": "0:44:50", "remaining_time": "0:04:46"}
151
+ {"current_steps": 151, "total_steps": 166, "loss": 2.0736, "lr": 1e-06, "epoch": 1.8023952095808382, "percentage": 90.96, "elapsed_time": "0:45:16", "remaining_time": "0:04:29"}
152
+ {"current_steps": 152, "total_steps": 166, "loss": 2.0752, "lr": 1e-06, "epoch": 1.81437125748503, "percentage": 91.57, "elapsed_time": "0:45:33", "remaining_time": "0:04:11"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a948de6f187071e8f2ca072dd444d9f4f3bca449376a9daf6e78ed345298a3b
3
  size 7608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66a1549ed8318c827c798f798a4a12a822f558520c5a3e8fa4c96580e1481aa3
3
  size 7608