Hugging Face's logo

grspo
/
rae

Model card Files
xet
Community
xingjianleng commited on
Commit
65c4c1d
·
verified ·
1 Parent(s): 2a64965

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. stage2/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0025000.pt +3 -0
  2. stage2/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0050000.pt +3 -0
  3. stage2/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0075000.pt +3 -0
  4. stage2/lightningdit-xl-spatialpe-vit-b-bf16/log.txt +1107 -0
stage2/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0025000.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276094961011bf54fb324a4d9a40c123780c4e6966036d35e11b398003c69816
3
+ size 19230431602
stage2/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0050000.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0164c6146d513e7aa836f8ec29c6f0370c97a791241b2f37004a3c676d2ac2
3
+ size 19230431602
stage2/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0075000.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7429f6b2152147def0866941321177bf107aad42120389a5d38d111969bb1865
3
+ size 19230431602
stage2/lightningdit-xl-spatialpe-vit-b-bf16/log.txt ADDED
@@ -0,0 +1,1107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2025-10-27 23:35:32] Experiment directory created at results/stage2/hfdata/lightningdit-xl-spatialpe-vit-b-bf16
2
+ [2025-10-27 23:35:35] Missing keys for loading vision encoder: []
3
+ [2025-10-27 23:35:35] Unexpected keys for loading vision encoder: []
4
+ [2025-10-27 23:35:50] Model Parameters: 1202.04M
5
+ [2025-10-27 23:35:53] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/train)
6
+ [2025-10-27 23:35:53] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
7
+ [2025-10-27 23:35:53] Precision mode: bf16
8
+ [2025-10-27 23:35:53] Training configured for 80 epochs, 1251 steps per epoch.
9
+ [2025-10-27 23:35:53] Optimizer: ADAMW with lr=0.0002, betas=(0.9, 0.95), weight_decay=0.0, eps=1e-08
10
+ Scheduler: linear with warmup_steps=0, decay_end_steps=0, final_lr=0.0002
11
+ [2025-10-27 23:35:53] Training for 80 epochs...
12
+ [2025-10-27 23:35:53] Beginning epoch 0...
13
+ [2025-10-27 23:35:59] Generating EMA samples...
14
+ [2025-10-27 23:36:28] Generating EMA samples done.
15
+ [2025-10-27 23:37:49] (step=0000100) Train Loss: 1.5200, Train Steps/Sec: 0.86
16
+ [2025-10-27 23:39:12] (step=0000200) Train Loss: 0.9534, Train Steps/Sec: 1.21
17
+ [2025-10-27 23:40:34] (step=0000300) Train Loss: 0.7899, Train Steps/Sec: 1.21
18
+ [2025-10-27 23:41:57] (step=0000400) Train Loss: 0.7244, Train Steps/Sec: 1.21
19
+ [2025-10-27 23:43:19] (step=0000500) Train Loss: 0.6857, Train Steps/Sec: 1.21
20
+ [2025-10-27 23:44:42] (step=0000600) Train Loss: 0.6586, Train Steps/Sec: 1.21
21
+ [2025-10-27 23:46:04] (step=0000700) Train Loss: 0.6391, Train Steps/Sec: 1.21
22
+ [2025-10-27 23:47:27] (step=0000800) Train Loss: 0.6216, Train Steps/Sec: 1.21
23
+ [2025-10-27 23:48:50] (step=0000900) Train Loss: 0.6078, Train Steps/Sec: 1.21
24
+ [2025-10-27 23:50:12] (step=0001000) Train Loss: 0.5980, Train Steps/Sec: 1.21
25
+ [2025-10-27 23:51:35] (step=0001100) Train Loss: 0.5899, Train Steps/Sec: 1.21
26
+ [2025-10-27 23:52:57] (step=0001200) Train Loss: 0.5820, Train Steps/Sec: 1.21
27
+ [2025-10-27 23:53:40] Beginning epoch 1...
28
+ [2025-10-27 23:54:22] (step=0001300) Train Loss: 0.5759, Train Steps/Sec: 1.18
29
+ [2025-10-27 23:55:45] (step=0001400) Train Loss: 0.5706, Train Steps/Sec: 1.21
30
+ [2025-10-27 23:57:07] (step=0001500) Train Loss: 0.5640, Train Steps/Sec: 1.21
31
+ [2025-10-28 00:02:07] Experiment directory created at results/stage2/hfdata/lightningdit-xl-spatialpe-vit-b-bf16
32
+ [2025-10-28 00:02:10] Missing keys for loading vision encoder: []
33
+ [2025-10-28 00:02:10] Unexpected keys for loading vision encoder: []
34
+ [2025-10-28 00:02:25] Model Parameters: 1202.04M
35
+ [2025-10-28 00:02:30] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/train)
36
+ [2025-10-28 00:02:30] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
37
+ [2025-10-28 00:02:30] Precision mode: bf16
38
+ [2025-10-28 00:02:30] Training configured for 80 epochs, 1251 steps per epoch.
39
+ [2025-10-28 00:02:30] Optimizer: ADAMW with lr=0.0002, betas=(0.9, 0.95), weight_decay=0.0, eps=1e-08
40
+ Scheduler: linear with warmup_steps=0, decay_end_steps=0, final_lr=0.0002
41
+ [2025-10-28 00:02:31] Training for 80 epochs...
42
+ [2025-10-28 00:02:31] Beginning epoch 0...
43
+ [2025-10-28 00:02:36] Generating EMA samples...
44
+ [2025-10-28 00:03:05] Generating EMA samples done.
45
+ [2025-10-28 00:04:27] (step=0000100) Train Loss: 1.5200, Train Steps/Sec: 0.86
46
+ [2025-10-28 00:05:50] (step=0000200) Train Loss: 0.9534, Train Steps/Sec: 1.20
47
+ [2025-10-28 00:07:14] (step=0000300) Train Loss: 0.7899, Train Steps/Sec: 1.20
48
+ [2025-10-28 00:08:37] (step=0000400) Train Loss: 0.7244, Train Steps/Sec: 1.20
49
+ [2025-10-28 00:10:00] (step=0000500) Train Loss: 0.6857, Train Steps/Sec: 1.20
50
+ [2025-10-28 00:11:23] (step=0000600) Train Loss: 0.6586, Train Steps/Sec: 1.20
51
+ [2025-10-28 00:12:47] (step=0000700) Train Loss: 0.6391, Train Steps/Sec: 1.20
52
+ [2025-10-28 00:14:10] (step=0000800) Train Loss: 0.6216, Train Steps/Sec: 1.20
53
+ [2025-10-28 00:15:33] (step=0000900) Train Loss: 0.6078, Train Steps/Sec: 1.20
54
+ [2025-10-28 00:16:57] (step=0001000) Train Loss: 0.5980, Train Steps/Sec: 1.20
55
+ [2025-10-28 00:18:20] (step=0001100) Train Loss: 0.5899, Train Steps/Sec: 1.20
56
+ [2025-10-28 00:19:43] (step=0001200) Train Loss: 0.5820, Train Steps/Sec: 1.20
57
+ [2025-10-28 00:20:27] Beginning epoch 1...
58
+ [2025-10-28 00:21:09] (step=0001300) Train Loss: 0.5759, Train Steps/Sec: 1.16
59
+ [2025-10-28 00:22:33] (step=0001400) Train Loss: 0.5706, Train Steps/Sec: 1.20
60
+ [2025-10-28 00:23:56] (step=0001500) Train Loss: 0.5640, Train Steps/Sec: 1.20
61
+ [2025-10-28 00:25:19] (step=0001600) Train Loss: 0.5610, Train Steps/Sec: 1.20
62
+ [2025-10-28 00:26:42] (step=0001700) Train Loss: 0.5556, Train Steps/Sec: 1.20
63
+ [2025-10-28 00:28:05] (step=0001800) Train Loss: 0.5526, Train Steps/Sec: 1.20
64
+ [2025-10-28 00:29:28] (step=0001900) Train Loss: 0.5489, Train Steps/Sec: 1.20
65
+ [2025-10-28 00:30:51] (step=0002000) Train Loss: 0.5475, Train Steps/Sec: 1.20
66
+ [2025-10-28 00:32:14] (step=0002100) Train Loss: 0.5441, Train Steps/Sec: 1.20
67
+ [2025-10-28 00:33:38] (step=0002200) Train Loss: 0.5413, Train Steps/Sec: 1.20
68
+ [2025-10-28 00:35:01] (step=0002300) Train Loss: 0.5379, Train Steps/Sec: 1.20
69
+ [2025-10-28 00:36:24] (step=0002400) Train Loss: 0.5376, Train Steps/Sec: 1.20
70
+ [2025-10-28 00:37:48] (step=0002500) Train Loss: 0.5345, Train Steps/Sec: 1.19
71
+ [2025-10-28 00:37:50] Beginning epoch 2...
72
+ [2025-10-28 00:39:14] (step=0002600) Train Loss: 0.5328, Train Steps/Sec: 1.16
73
+ [2025-10-28 00:40:37] (step=0002700) Train Loss: 0.5307, Train Steps/Sec: 1.20
74
+ [2025-10-28 00:42:00] (step=0002800) Train Loss: 0.5281, Train Steps/Sec: 1.20
75
+ [2025-10-28 00:43:23] (step=0002900) Train Loss: 0.5266, Train Steps/Sec: 1.20
76
+ [2025-10-28 00:44:47] (step=0003000) Train Loss: 0.5254, Train Steps/Sec: 1.20
77
+ [2025-10-28 00:46:10] (step=0003100) Train Loss: 0.5236, Train Steps/Sec: 1.20
78
+ [2025-10-28 00:47:33] (step=0003200) Train Loss: 0.5228, Train Steps/Sec: 1.20
79
+ [2025-10-28 00:48:56] (step=0003300) Train Loss: 0.5211, Train Steps/Sec: 1.20
80
+ [2025-10-28 00:50:19] (step=0003400) Train Loss: 0.5179, Train Steps/Sec: 1.20
81
+ [2025-10-28 00:51:43] (step=0003500) Train Loss: 0.5190, Train Steps/Sec: 1.20
82
+ [2025-10-28 00:53:06] (step=0003600) Train Loss: 0.5168, Train Steps/Sec: 1.20
83
+ [2025-10-28 00:54:29] (step=0003700) Train Loss: 0.5174, Train Steps/Sec: 1.20
84
+ [2025-10-28 00:55:14] Beginning epoch 3...
85
+ [2025-10-28 00:55:55] (step=0003800) Train Loss: 0.5155, Train Steps/Sec: 1.17
86
+ [2025-10-28 00:57:18] (step=0003900) Train Loss: 0.5133, Train Steps/Sec: 1.20
87
+ [2025-10-28 00:58:41] (step=0004000) Train Loss: 0.5114, Train Steps/Sec: 1.20
88
+ [2025-10-28 01:00:05] (step=0004100) Train Loss: 0.5098, Train Steps/Sec: 1.20
89
+ [2025-10-28 01:01:28] (step=0004200) Train Loss: 0.5101, Train Steps/Sec: 1.20
90
+ [2025-10-28 01:02:52] (step=0004300) Train Loss: 0.5106, Train Steps/Sec: 1.20
91
+ [2025-10-28 01:04:15] (step=0004400) Train Loss: 0.5096, Train Steps/Sec: 1.20
92
+ [2025-10-28 01:05:38] (step=0004500) Train Loss: 0.5087, Train Steps/Sec: 1.20
93
+ [2025-10-28 01:07:01] (step=0004600) Train Loss: 0.5074, Train Steps/Sec: 1.20
94
+ [2025-10-28 01:08:24] (step=0004700) Train Loss: 0.5076, Train Steps/Sec: 1.20
95
+ [2025-10-28 01:09:47] (step=0004800) Train Loss: 0.5044, Train Steps/Sec: 1.20
96
+ [2025-10-28 01:11:11] (step=0004900) Train Loss: 0.5060, Train Steps/Sec: 1.20
97
+ [2025-10-28 01:12:34] (step=0005000) Train Loss: 0.5037, Train Steps/Sec: 1.20
98
+ [2025-10-28 01:12:38] Beginning epoch 4...
99
+ [2025-10-28 01:13:59] (step=0005100) Train Loss: 0.5026, Train Steps/Sec: 1.17
100
+ [2025-10-28 01:15:23] (step=0005200) Train Loss: 0.5028, Train Steps/Sec: 1.20
101
+ [2025-10-28 01:16:46] (step=0005300) Train Loss: 0.5012, Train Steps/Sec: 1.20
102
+ [2025-10-28 01:18:09] (step=0005400) Train Loss: 0.5025, Train Steps/Sec: 1.20
103
+ [2025-10-28 01:19:32] (step=0005500) Train Loss: 0.4996, Train Steps/Sec: 1.20
104
+ [2025-10-28 01:20:55] (step=0005600) Train Loss: 0.4989, Train Steps/Sec: 1.20
105
+ [2025-10-28 01:22:19] (step=0005700) Train Loss: 0.4985, Train Steps/Sec: 1.20
106
+ [2025-10-28 01:23:43] (step=0005800) Train Loss: 0.5001, Train Steps/Sec: 1.19
107
+ [2025-10-28 01:25:06] (step=0005900) Train Loss: 0.4982, Train Steps/Sec: 1.20
108
+ [2025-10-28 01:26:29] (step=0006000) Train Loss: 0.4980, Train Steps/Sec: 1.20
109
+ [2025-10-28 01:27:52] (step=0006100) Train Loss: 0.4967, Train Steps/Sec: 1.20
110
+ [2025-10-28 01:29:15] (step=0006200) Train Loss: 0.4953, Train Steps/Sec: 1.20
111
+ [2025-10-28 01:30:02] Beginning epoch 5...
112
+ [2025-10-28 01:30:41] (step=0006300) Train Loss: 0.4961, Train Steps/Sec: 1.16
113
+ [2025-10-28 01:32:04] (step=0006400) Train Loss: 0.4962, Train Steps/Sec: 1.20
114
+ [2025-10-28 01:33:28] (step=0006500) Train Loss: 0.4951, Train Steps/Sec: 1.20
115
+ [2025-10-28 01:34:51] (step=0006600) Train Loss: 0.4942, Train Steps/Sec: 1.20
116
+ [2025-10-28 01:36:14] (step=0006700) Train Loss: 0.4943, Train Steps/Sec: 1.20
117
+ [2025-10-28 01:37:37] (step=0006800) Train Loss: 0.4941, Train Steps/Sec: 1.20
118
+ [2025-10-28 01:39:00] (step=0006900) Train Loss: 0.4918, Train Steps/Sec: 1.20
119
+ [2025-10-28 01:40:23] (step=0007000) Train Loss: 0.4916, Train Steps/Sec: 1.20
120
+ [2025-10-28 01:41:46] (step=0007100) Train Loss: 0.4912, Train Steps/Sec: 1.20
121
+ [2025-10-28 01:43:09] (step=0007200) Train Loss: 0.4918, Train Steps/Sec: 1.20
122
+ [2025-10-28 01:44:32] (step=0007300) Train Loss: 0.4913, Train Steps/Sec: 1.20
123
+ [2025-10-28 01:45:56] (step=0007400) Train Loss: 0.4933, Train Steps/Sec: 1.20
124
+ [2025-10-28 01:47:20] (step=0007500) Train Loss: 0.4910, Train Steps/Sec: 1.19
125
+ [2025-10-28 01:47:25] Beginning epoch 6...
126
+ [2025-10-28 01:48:45] (step=0007600) Train Loss: 0.4899, Train Steps/Sec: 1.16
127
+ [2025-10-28 01:50:09] (step=0007700) Train Loss: 0.4899, Train Steps/Sec: 1.20
128
+ [2025-10-28 01:51:32] (step=0007800) Train Loss: 0.4880, Train Steps/Sec: 1.20
129
+ [2025-10-28 01:52:55] (step=0007900) Train Loss: 0.4893, Train Steps/Sec: 1.20
130
+ [2025-10-28 01:54:18] (step=0008000) Train Loss: 0.4865, Train Steps/Sec: 1.20
131
+ [2025-10-28 01:55:41] (step=0008100) Train Loss: 0.4893, Train Steps/Sec: 1.20
132
+ [2025-10-28 01:57:05] (step=0008200) Train Loss: 0.4885, Train Steps/Sec: 1.20
133
+ [2025-10-28 01:58:28] (step=0008300) Train Loss: 0.4868, Train Steps/Sec: 1.20
134
+ [2025-10-28 01:59:51] (step=0008400) Train Loss: 0.4883, Train Steps/Sec: 1.20
135
+ [2025-10-28 02:01:14] (step=0008500) Train Loss: 0.4865, Train Steps/Sec: 1.20
136
+ [2025-10-28 02:02:37] (step=0008600) Train Loss: 0.4877, Train Steps/Sec: 1.20
137
+ [2025-10-28 02:04:01] (step=0008700) Train Loss: 0.4868, Train Steps/Sec: 1.20
138
+ [2025-10-28 02:04:48] Beginning epoch 7...
139
+ [2025-10-28 02:05:26] (step=0008800) Train Loss: 0.4849, Train Steps/Sec: 1.17
140
+ [2025-10-28 02:06:49] (step=0008900) Train Loss: 0.4863, Train Steps/Sec: 1.20
141
+ [2025-10-28 02:08:13] (step=0009000) Train Loss: 0.4851, Train Steps/Sec: 1.20
142
+ [2025-10-28 02:09:36] (step=0009100) Train Loss: 0.4847, Train Steps/Sec: 1.20
143
+ [2025-10-28 02:11:00] (step=0009200) Train Loss: 0.4841, Train Steps/Sec: 1.19
144
+ [2025-10-28 02:12:23] (step=0009300) Train Loss: 0.4854, Train Steps/Sec: 1.20
145
+ [2025-10-28 02:13:46] (step=0009400) Train Loss: 0.4850, Train Steps/Sec: 1.20
146
+ [2025-10-28 02:15:10] (step=0009500) Train Loss: 0.4843, Train Steps/Sec: 1.20
147
+ [2025-10-28 02:16:33] (step=0009600) Train Loss: 0.4838, Train Steps/Sec: 1.20
148
+ [2025-10-28 02:17:56] (step=0009700) Train Loss: 0.4831, Train Steps/Sec: 1.20
149
+ [2025-10-28 02:19:19] (step=0009800) Train Loss: 0.4848, Train Steps/Sec: 1.20
150
+ [2025-10-28 02:20:42] (step=0009900) Train Loss: 0.4810, Train Steps/Sec: 1.20
151
+ [2025-10-28 02:22:06] (step=0010000) Train Loss: 0.4823, Train Steps/Sec: 1.20
152
+ [2025-10-28 02:22:13] Beginning epoch 8...
153
+ [2025-10-28 02:23:31] (step=0010100) Train Loss: 0.4816, Train Steps/Sec: 1.17
154
+ [2025-10-28 02:24:55] (step=0010200) Train Loss: 0.4841, Train Steps/Sec: 1.20
155
+ [2025-10-28 02:26:18] (step=0010300) Train Loss: 0.4822, Train Steps/Sec: 1.20
156
+ [2025-10-28 02:27:41] (step=0010400) Train Loss: 0.4801, Train Steps/Sec: 1.20
157
+ [2025-10-28 02:29:04] (step=0010500) Train Loss: 0.4811, Train Steps/Sec: 1.20
158
+ [2025-10-28 02:30:28] (step=0010600) Train Loss: 0.4804, Train Steps/Sec: 1.20
159
+ [2025-10-28 02:31:51] (step=0010700) Train Loss: 0.4820, Train Steps/Sec: 1.20
160
+ [2025-10-28 02:33:15] (step=0010800) Train Loss: 0.4813, Train Steps/Sec: 1.19
161
+ [2025-10-28 02:34:38] (step=0010900) Train Loss: 0.4798, Train Steps/Sec: 1.20
162
+ [2025-10-28 02:36:02] (step=0011000) Train Loss: 0.4802, Train Steps/Sec: 1.20
163
+ [2025-10-28 02:37:25] (step=0011100) Train Loss: 0.4810, Train Steps/Sec: 1.20
164
+ [2025-10-28 02:38:48] (step=0011200) Train Loss: 0.4804, Train Steps/Sec: 1.20
165
+ [2025-10-28 02:39:38] Beginning epoch 9...
166
+ [2025-10-28 02:40:14] (step=0011300) Train Loss: 0.4805, Train Steps/Sec: 1.17
167
+ [2025-10-28 02:41:37] (step=0011400) Train Loss: 0.4813, Train Steps/Sec: 1.20
168
+ [2025-10-28 02:43:00] (step=0011500) Train Loss: 0.4804, Train Steps/Sec: 1.20
169
+ [2025-10-28 02:44:23] (step=0011600) Train Loss: 0.4769, Train Steps/Sec: 1.20
170
+ [2025-10-28 02:45:46] (step=0011700) Train Loss: 0.4776, Train Steps/Sec: 1.20
171
+ [2025-10-28 02:47:10] (step=0011800) Train Loss: 0.4778, Train Steps/Sec: 1.20
172
+ [2025-10-28 02:48:33] (step=0011900) Train Loss: 0.4785, Train Steps/Sec: 1.20
173
+ [2025-10-28 02:49:56] (step=0012000) Train Loss: 0.4781, Train Steps/Sec: 1.20
174
+ [2025-10-28 02:51:19] (step=0012100) Train Loss: 0.4778, Train Steps/Sec: 1.20
175
+ [2025-10-28 02:52:43] (step=0012200) Train Loss: 0.4788, Train Steps/Sec: 1.20
176
+ [2025-10-28 02:54:06] (step=0012300) Train Loss: 0.4779, Train Steps/Sec: 1.20
177
+ [2025-10-28 02:55:29] (step=0012400) Train Loss: 0.4774, Train Steps/Sec: 1.20
178
+ [2025-10-28 02:56:53] (step=0012500) Train Loss: 0.4757, Train Steps/Sec: 1.19
179
+ [2025-10-28 02:57:02] Beginning epoch 10...
180
+ [2025-10-28 02:58:18] (step=0012600) Train Loss: 0.4773, Train Steps/Sec: 1.17
181
+ [2025-10-28 02:59:41] (step=0012700) Train Loss: 0.4777, Train Steps/Sec: 1.20
182
+ [2025-10-28 03:01:04] (step=0012800) Train Loss: 0.4765, Train Steps/Sec: 1.20
183
+ [2025-10-28 03:02:28] (step=0012900) Train Loss: 0.4765, Train Steps/Sec: 1.20
184
+ [2025-10-28 03:03:51] (step=0013000) Train Loss: 0.4766, Train Steps/Sec: 1.20
185
+ [2025-10-28 03:05:14] (step=0013100) Train Loss: 0.4742, Train Steps/Sec: 1.20
186
+ [2025-10-28 03:06:37] (step=0013200) Train Loss: 0.4752, Train Steps/Sec: 1.20
187
+ [2025-10-28 03:08:00] (step=0013300) Train Loss: 0.4768, Train Steps/Sec: 1.20
188
+ [2025-10-28 03:09:23] (step=0013400) Train Loss: 0.4760, Train Steps/Sec: 1.20
189
+ [2025-10-28 03:10:47] (step=0013500) Train Loss: 0.4753, Train Steps/Sec: 1.20
190
+ [2025-10-28 03:12:10] (step=0013600) Train Loss: 0.4763, Train Steps/Sec: 1.20
191
+ [2025-10-28 03:13:33] (step=0013700) Train Loss: 0.4744, Train Steps/Sec: 1.20
192
+ [2025-10-28 03:14:24] Beginning epoch 11...
193
+ [2025-10-28 03:14:59] (step=0013800) Train Loss: 0.4753, Train Steps/Sec: 1.17
194
+ [2025-10-28 03:16:22] (step=0013900) Train Loss: 0.4747, Train Steps/Sec: 1.20
195
+ [2025-10-28 03:17:45] (step=0014000) Train Loss: 0.4758, Train Steps/Sec: 1.20
196
+ [2025-10-28 03:19:09] (step=0014100) Train Loss: 0.4730, Train Steps/Sec: 1.19
197
+ [2025-10-28 03:20:32] (step=0014200) Train Loss: 0.4752, Train Steps/Sec: 1.20
198
+ [2025-10-28 03:21:55] (step=0014300) Train Loss: 0.4743, Train Steps/Sec: 1.20
199
+ [2025-10-28 03:23:18] (step=0014400) Train Loss: 0.4752, Train Steps/Sec: 1.20
200
+ [2025-10-28 03:24:41] (step=0014500) Train Loss: 0.4708, Train Steps/Sec: 1.20
201
+ [2025-10-28 03:26:05] (step=0014600) Train Loss: 0.4731, Train Steps/Sec: 1.20
202
+ [2025-10-28 03:27:28] (step=0014700) Train Loss: 0.4730, Train Steps/Sec: 1.20
203
+ [2025-10-28 03:28:51] (step=0014800) Train Loss: 0.4729, Train Steps/Sec: 1.20
204
+ [2025-10-28 03:30:14] (step=0014900) Train Loss: 0.4743, Train Steps/Sec: 1.20
205
+ [2025-10-28 03:31:37] (step=0015000) Train Loss: 0.4733, Train Steps/Sec: 1.20
206
+ [2025-10-28 03:31:48] Beginning epoch 12...
207
+ [2025-10-28 03:33:03] (step=0015100) Train Loss: 0.4726, Train Steps/Sec: 1.17
208
+ [2025-10-28 03:34:26] (step=0015200) Train Loss: 0.4715, Train Steps/Sec: 1.20
209
+ [2025-10-28 03:35:49] (step=0015300) Train Loss: 0.4730, Train Steps/Sec: 1.20
210
+ [2025-10-28 03:37:13] (step=0015400) Train Loss: 0.4730, Train Steps/Sec: 1.20
211
+ [2025-10-28 03:38:36] (step=0015500) Train Loss: 0.4716, Train Steps/Sec: 1.20
212
+ [2025-10-28 03:39:59] (step=0015600) Train Loss: 0.4715, Train Steps/Sec: 1.20
213
+ [2025-10-28 03:41:23] (step=0015700) Train Loss: 0.4711, Train Steps/Sec: 1.20
214
+ [2025-10-28 03:42:46] (step=0015800) Train Loss: 0.4722, Train Steps/Sec: 1.19
215
+ [2025-10-28 03:44:10] (step=0015900) Train Loss: 0.4712, Train Steps/Sec: 1.20
216
+ [2025-10-28 03:45:33] (step=0016000) Train Loss: 0.4704, Train Steps/Sec: 1.20
217
+ [2025-10-28 03:46:56] (step=0016100) Train Loss: 0.4714, Train Steps/Sec: 1.20
218
+ [2025-10-28 03:48:19] (step=0016200) Train Loss: 0.4692, Train Steps/Sec: 1.20
219
+ [2025-10-28 03:49:12] Beginning epoch 13...
220
+ [2025-10-28 03:49:44] (step=0016300) Train Loss: 0.4708, Train Steps/Sec: 1.17
221
+ [2025-10-28 03:51:07] (step=0016400) Train Loss: 0.4710, Train Steps/Sec: 1.20
222
+ [2025-10-28 03:52:31] (step=0016500) Train Loss: 0.4705, Train Steps/Sec: 1.20
223
+ [2025-10-28 03:53:54] (step=0016600) Train Loss: 0.4706, Train Steps/Sec: 1.20
224
+ [2025-10-28 03:55:17] (step=0016700) Train Loss: 0.4709, Train Steps/Sec: 1.20
225
+ [2025-10-28 03:56:40] (step=0016800) Train Loss: 0.4715, Train Steps/Sec: 1.20
226
+ [2025-10-28 03:58:03] (step=0016900) Train Loss: 0.4689, Train Steps/Sec: 1.20
227
+ [2025-10-28 03:59:26] (step=0017000) Train Loss: 0.4698, Train Steps/Sec: 1.20
228
+ [2025-10-28 04:00:49] (step=0017100) Train Loss: 0.4691, Train Steps/Sec: 1.20
229
+ [2025-10-28 04:02:13] (step=0017200) Train Loss: 0.4706, Train Steps/Sec: 1.20
230
+ [2025-10-28 04:03:36] (step=0017300) Train Loss: 0.4714, Train Steps/Sec: 1.20
231
+ [2025-10-28 04:04:59] (step=0017400) Train Loss: 0.4699, Train Steps/Sec: 1.20
232
+ [2025-10-28 04:06:23] (step=0017500) Train Loss: 0.4698, Train Steps/Sec: 1.19
233
+ [2025-10-28 04:06:35] Beginning epoch 14...
234
+ [2025-10-28 04:07:48] (step=0017600) Train Loss: 0.4706, Train Steps/Sec: 1.17
235
+ [2025-10-28 04:09:11] (step=0017700) Train Loss: 0.4686, Train Steps/Sec: 1.20
236
+ [2025-10-28 04:10:35] (step=0017800) Train Loss: 0.4667, Train Steps/Sec: 1.20
237
+ [2025-10-28 04:11:58] (step=0017900) Train Loss: 0.4673, Train Steps/Sec: 1.20
238
+ [2025-10-28 04:13:21] (step=0018000) Train Loss: 0.4688, Train Steps/Sec: 1.20
239
+ [2025-10-28 04:14:44] (step=0018100) Train Loss: 0.4669, Train Steps/Sec: 1.20
240
+ [2025-10-28 04:16:07] (step=0018200) Train Loss: 0.4680, Train Steps/Sec: 1.20
241
+ [2025-10-28 04:17:30] (step=0018300) Train Loss: 0.4686, Train Steps/Sec: 1.20
242
+ [2025-10-28 04:18:54] (step=0018400) Train Loss: 0.4692, Train Steps/Sec: 1.20
243
+ [2025-10-28 04:20:17] (step=0018500) Train Loss: 0.4678, Train Steps/Sec: 1.20
244
+ [2025-10-28 04:21:40] (step=0018600) Train Loss: 0.4685, Train Steps/Sec: 1.20
245
+ [2025-10-28 04:23:04] (step=0018700) Train Loss: 0.4663, Train Steps/Sec: 1.20
246
+ [2025-10-28 04:23:58] Beginning epoch 15...
247
+ [2025-10-28 04:24:29] (step=0018800) Train Loss: 0.4674, Train Steps/Sec: 1.17
248
+ [2025-10-28 04:25:52] (step=0018900) Train Loss: 0.4670, Train Steps/Sec: 1.20
249
+ [2025-10-28 04:27:16] (step=0019000) Train Loss: 0.4674, Train Steps/Sec: 1.20
250
+ [2025-10-28 04:28:40] (step=0019100) Train Loss: 0.4673, Train Steps/Sec: 1.19
251
+ [2025-10-28 04:30:03] (step=0019200) Train Loss: 0.4676, Train Steps/Sec: 1.20
252
+ [2025-10-28 04:31:26] (step=0019300) Train Loss: 0.4686, Train Steps/Sec: 1.20
253
+ [2025-10-28 04:32:49] (step=0019400) Train Loss: 0.4673, Train Steps/Sec: 1.20
254
+ [2025-10-28 04:34:12] (step=0019500) Train Loss: 0.4657, Train Steps/Sec: 1.20
255
+ [2025-10-28 04:35:35] (step=0019600) Train Loss: 0.4664, Train Steps/Sec: 1.20
256
+ [2025-10-28 04:36:58] (step=0019700) Train Loss: 0.4661, Train Steps/Sec: 1.20
257
+ [2025-10-28 04:38:21] (step=0019800) Train Loss: 0.4671, Train Steps/Sec: 1.20
258
+ [2025-10-28 04:39:44] (step=0019900) Train Loss: 0.4660, Train Steps/Sec: 1.20
259
+ [2025-10-28 04:41:07] (step=0020000) Train Loss: 0.4651, Train Steps/Sec: 1.20
260
+ [2025-10-28 04:41:21] Beginning epoch 16...
261
+ [2025-10-28 04:42:33] (step=0020100) Train Loss: 0.4664, Train Steps/Sec: 1.17
262
+ [2025-10-28 04:43:56] (step=0020200) Train Loss: 0.4667, Train Steps/Sec: 1.20
263
+ [2025-10-28 04:45:20] (step=0020300) Train Loss: 0.4649, Train Steps/Sec: 1.20
264
+ [2025-10-28 04:46:43] (step=0020400) Train Loss: 0.4661, Train Steps/Sec: 1.20
265
+ [2025-10-28 04:48:06] (step=0020500) Train Loss: 0.4651, Train Steps/Sec: 1.20
266
+ [2025-10-28 04:49:29] (step=0020600) Train Loss: 0.4674, Train Steps/Sec: 1.20
267
+ [2025-10-28 04:50:52] (step=0020700) Train Loss: 0.4663, Train Steps/Sec: 1.20
268
+ [2025-10-28 04:52:16] (step=0020800) Train Loss: 0.4656, Train Steps/Sec: 1.19
269
+ [2025-10-28 04:53:39] (step=0020900) Train Loss: 0.4656, Train Steps/Sec: 1.20
270
+ [2025-10-28 04:55:02] (step=0021000) Train Loss: 0.4671, Train Steps/Sec: 1.20
271
+ [2025-10-28 04:56:25] (step=0021100) Train Loss: 0.4651, Train Steps/Sec: 1.20
272
+ [2025-10-28 04:57:49] (step=0021200) Train Loss: 0.4655, Train Steps/Sec: 1.20
273
+ [2025-10-28 04:58:45] Beginning epoch 17...
274
+ [2025-10-28 04:59:14] (step=0021300) Train Loss: 0.4655, Train Steps/Sec: 1.17
275
+ [2025-10-28 05:00:37] (step=0021400) Train Loss: 0.4644, Train Steps/Sec: 1.20
276
+ [2025-10-28 05:02:01] (step=0021500) Train Loss: 0.4653, Train Steps/Sec: 1.20
277
+ [2025-10-28 05:03:24] (step=0021600) Train Loss: 0.4654, Train Steps/Sec: 1.20
278
+ [2025-10-28 05:04:47] (step=0021700) Train Loss: 0.4648, Train Steps/Sec: 1.20
279
+ [2025-10-28 05:06:10] (step=0021800) Train Loss: 0.4647, Train Steps/Sec: 1.20
280
+ [2025-10-28 05:07:33] (step=0021900) Train Loss: 0.4627, Train Steps/Sec: 1.20
281
+ [2025-10-28 05:08:57] (step=0022000) Train Loss: 0.4644, Train Steps/Sec: 1.20
282
+ [2025-10-28 05:10:20] (step=0022100) Train Loss: 0.4636, Train Steps/Sec: 1.20
283
+ [2025-10-28 05:11:43] (step=0022200) Train Loss: 0.4639, Train Steps/Sec: 1.20
284
+ [2025-10-28 05:13:06] (step=0022300) Train Loss: 0.4639, Train Steps/Sec: 1.20
285
+ [2025-10-28 05:14:30] (step=0022400) Train Loss: 0.4648, Train Steps/Sec: 1.20
286
+ [2025-10-28 05:15:53] (step=0022500) Train Loss: 0.4642, Train Steps/Sec: 1.19
287
+ [2025-10-28 05:16:09] Beginning epoch 18...
288
+ [2025-10-28 05:17:19] (step=0022600) Train Loss: 0.4639, Train Steps/Sec: 1.17
289
+ [2025-10-28 05:18:42] (step=0022700) Train Loss: 0.4631, Train Steps/Sec: 1.20
290
+ [2025-10-28 05:20:05] (step=0022800) Train Loss: 0.4638, Train Steps/Sec: 1.20
291
+ [2025-10-28 05:21:29] (step=0022900) Train Loss: 0.4629, Train Steps/Sec: 1.20
292
+ [2025-10-28 05:22:52] (step=0023000) Train Loss: 0.4630, Train Steps/Sec: 1.20
293
+ [2025-10-28 05:24:15] (step=0023100) Train Loss: 0.4630, Train Steps/Sec: 1.20
294
+ [2025-10-28 05:25:39] (step=0023200) Train Loss: 0.4652, Train Steps/Sec: 1.20
295
+ [2025-10-28 05:27:02] (step=0023300) Train Loss: 0.4638, Train Steps/Sec: 1.20
296
+ [2025-10-28 05:28:25] (step=0023400) Train Loss: 0.4615, Train Steps/Sec: 1.20
297
+ [2025-10-28 05:29:49] (step=0023500) Train Loss: 0.4636, Train Steps/Sec: 1.20
298
+ [2025-10-28 05:31:12] (step=0023600) Train Loss: 0.4636, Train Steps/Sec: 1.20
299
+ [2025-10-28 05:32:35] (step=0023700) Train Loss: 0.4618, Train Steps/Sec: 1.20
300
+ [2025-10-28 05:33:33] Beginning epoch 19...
301
+ [2025-10-28 05:34:01] (step=0023800) Train Loss: 0.4642, Train Steps/Sec: 1.17
302
+ [2025-10-28 05:35:24] (step=0023900) Train Loss: 0.4642, Train Steps/Sec: 1.20
303
+ [2025-10-28 05:36:47] (step=0024000) Train Loss: 0.4609, Train Steps/Sec: 1.20
304
+ [2025-10-28 05:38:11] (step=0024100) Train Loss: 0.4609, Train Steps/Sec: 1.19
305
+ [2025-10-28 05:39:34] (step=0024200) Train Loss: 0.4633, Train Steps/Sec: 1.20
306
+ [2025-10-28 05:40:58] (step=0024300) Train Loss: 0.4629, Train Steps/Sec: 1.20
307
+ [2025-10-28 05:42:21] (step=0024400) Train Loss: 0.4613, Train Steps/Sec: 1.20
308
+ [2025-10-28 05:43:44] (step=0024500) Train Loss: 0.4608, Train Steps/Sec: 1.20
309
+ [2025-10-28 05:45:08] (step=0024600) Train Loss: 0.4619, Train Steps/Sec: 1.20
310
+ [2025-10-28 05:46:31] (step=0024700) Train Loss: 0.4625, Train Steps/Sec: 1.20
311
+ [2025-10-28 05:47:54] (step=0024800) Train Loss: 0.4628, Train Steps/Sec: 1.20
312
+ [2025-10-28 05:49:17] (step=0024900) Train Loss: 0.4605, Train Steps/Sec: 1.20
313
+ [2025-10-28 05:50:40] (step=0025000) Train Loss: 0.4630, Train Steps/Sec: 1.20
314
+ [2025-10-28 05:51:30] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0025000.pt
315
+ [2025-10-28 05:51:30] Generating EMA samples...
316
+ [2025-10-28 05:51:58] Generating EMA samples done.
317
+ [2025-10-28 05:52:15] Beginning epoch 20...
318
+ [2025-10-28 05:53:24] (step=0025100) Train Loss: 0.4623, Train Steps/Sec: 0.61
319
+ [2025-10-28 05:54:47] (step=0025200) Train Loss: 0.4604, Train Steps/Sec: 1.20
320
+ [2025-10-28 05:56:10] (step=0025300) Train Loss: 0.4611, Train Steps/Sec: 1.20
321
+ [2025-10-28 05:57:33] (step=0025400) Train Loss: 0.4612, Train Steps/Sec: 1.20
322
+ [2025-10-28 05:58:57] (step=0025500) Train Loss: 0.4626, Train Steps/Sec: 1.20
323
+ [2025-10-28 06:00:20] (step=0025600) Train Loss: 0.4617, Train Steps/Sec: 1.20
324
+ [2025-10-28 06:01:43] (step=0025700) Train Loss: 0.4608, Train Steps/Sec: 1.20
325
+ [2025-10-28 06:03:07] (step=0025800) Train Loss: 0.4618, Train Steps/Sec: 1.19
326
+ [2025-10-28 06:04:30] (step=0025900) Train Loss: 0.4631, Train Steps/Sec: 1.20
327
+ [2025-10-28 06:05:53] (step=0026000) Train Loss: 0.4612, Train Steps/Sec: 1.20
328
+ [2025-10-28 06:07:16] (step=0026100) Train Loss: 0.4618, Train Steps/Sec: 1.20
329
+ [2025-10-28 06:08:39] (step=0026200) Train Loss: 0.4624, Train Steps/Sec: 1.20
330
+ [2025-10-28 06:09:39] Beginning epoch 21...
331
+ [2025-10-28 06:10:05] (step=0026300) Train Loss: 0.4604, Train Steps/Sec: 1.17
332
+ [2025-10-28 06:11:28] (step=0026400) Train Loss: 0.4593, Train Steps/Sec: 1.20
333
+ [2025-10-28 06:12:51] (step=0026500) Train Loss: 0.4598, Train Steps/Sec: 1.20
334
+ [2025-10-28 06:14:14] (step=0026600) Train Loss: 0.4606, Train Steps/Sec: 1.20
335
+ [2025-10-28 06:15:38] (step=0026700) Train Loss: 0.4597, Train Steps/Sec: 1.20
336
+ [2025-10-28 06:17:01] (step=0026800) Train Loss: 0.4618, Train Steps/Sec: 1.20
337
+ [2025-10-28 06:18:24] (step=0026900) Train Loss: 0.4609, Train Steps/Sec: 1.20
338
+ [2025-10-28 06:19:47] (step=0027000) Train Loss: 0.4608, Train Steps/Sec: 1.20
339
+ [2025-10-28 06:21:10] (step=0027100) Train Loss: 0.4605, Train Steps/Sec: 1.20
340
+ [2025-10-28 06:22:34] (step=0027200) Train Loss: 0.4601, Train Steps/Sec: 1.20
341
+ [2025-10-28 06:23:57] (step=0027300) Train Loss: 0.4604, Train Steps/Sec: 1.20
342
+ [2025-10-28 06:25:20] (step=0027400) Train Loss: 0.4603, Train Steps/Sec: 1.20
343
+ [2025-10-28 06:26:44] (step=0027500) Train Loss: 0.4604, Train Steps/Sec: 1.19
344
+ [2025-10-28 06:27:03] Beginning epoch 22...
345
+ [2025-10-28 06:28:10] (step=0027600) Train Loss: 0.4601, Train Steps/Sec: 1.17
346
+ [2025-10-28 06:29:33] (step=0027700) Train Loss: 0.4586, Train Steps/Sec: 1.20
347
+ [2025-10-28 06:30:56] (step=0027800) Train Loss: 0.4580, Train Steps/Sec: 1.20
348
+ [2025-10-28 06:32:19] (step=0027900) Train Loss: 0.4606, Train Steps/Sec: 1.20
349
+ [2025-10-28 06:33:42] (step=0028000) Train Loss: 0.4593, Train Steps/Sec: 1.20
350
+ [2025-10-28 06:35:06] (step=0028100) Train Loss: 0.4601, Train Steps/Sec: 1.20
351
+ [2025-10-28 06:36:29] (step=0028200) Train Loss: 0.4594, Train Steps/Sec: 1.20
352
+ [2025-10-28 06:37:52] (step=0028300) Train Loss: 0.4590, Train Steps/Sec: 1.20
353
+ [2025-10-28 06:39:15] (step=0028400) Train Loss: 0.4603, Train Steps/Sec: 1.20
354
+ [2025-10-28 06:40:38] (step=0028500) Train Loss: 0.4601, Train Steps/Sec: 1.20
355
+ [2025-10-28 06:42:02] (step=0028600) Train Loss: 0.4611, Train Steps/Sec: 1.20
356
+ [2025-10-28 06:43:25] (step=0028700) Train Loss: 0.4600, Train Steps/Sec: 1.20
357
+ [2025-10-28 06:44:26] Beginning epoch 23...
358
+ [2025-10-28 06:44:50] (step=0028800) Train Loss: 0.4601, Train Steps/Sec: 1.17
359
+ [2025-10-28 06:46:13] (step=0028900) Train Loss: 0.4575, Train Steps/Sec: 1.20
360
+ [2025-10-28 06:47:37] (step=0029000) Train Loss: 0.4586, Train Steps/Sec: 1.20
361
+ [2025-10-28 06:49:01] (step=0029100) Train Loss: 0.4590, Train Steps/Sec: 1.19
362
+ [2025-10-28 06:50:24] (step=0029200) Train Loss: 0.4597, Train Steps/Sec: 1.20
363
+ [2025-10-28 06:51:47] (step=0029300) Train Loss: 0.4609, Train Steps/Sec: 1.20
364
+ [2025-10-28 06:53:10] (step=0029400) Train Loss: 0.4577, Train Steps/Sec: 1.20
365
+ [2025-10-28 06:54:33] (step=0029500) Train Loss: 0.4610, Train Steps/Sec: 1.20
366
+ [2025-10-28 06:55:56] (step=0029600) Train Loss: 0.4581, Train Steps/Sec: 1.20
367
+ [2025-10-28 06:57:19] (step=0029700) Train Loss: 0.4598, Train Steps/Sec: 1.20
368
+ [2025-10-28 06:58:42] (step=0029800) Train Loss: 0.4581, Train Steps/Sec: 1.20
369
+ [2025-10-28 07:00:06] (step=0029900) Train Loss: 0.4577, Train Steps/Sec: 1.20
370
+ [2025-10-28 07:01:29] (step=0030000) Train Loss: 0.4595, Train Steps/Sec: 1.20
371
+ [2025-10-28 07:01:49] Beginning epoch 24...
372
+ [2025-10-28 07:02:54] (step=0030100) Train Loss: 0.4593, Train Steps/Sec: 1.17
373
+ [2025-10-28 07:04:17] (step=0030200) Train Loss: 0.4574, Train Steps/Sec: 1.20
374
+ [2025-10-28 07:05:40] (step=0030300) Train Loss: 0.4576, Train Steps/Sec: 1.20
375
+ [2025-10-28 07:07:03] (step=0030400) Train Loss: 0.4588, Train Steps/Sec: 1.20
376
+ [2025-10-28 07:08:27] (step=0030500) Train Loss: 0.4587, Train Steps/Sec: 1.20
377
+ [2025-10-28 07:09:50] (step=0030600) Train Loss: 0.4589, Train Steps/Sec: 1.20
378
+ [2025-10-28 07:11:13] (step=0030700) Train Loss: 0.4587, Train Steps/Sec: 1.20
379
+ [2025-10-28 07:12:37] (step=0030800) Train Loss: 0.4589, Train Steps/Sec: 1.19
380
+ [2025-10-28 07:14:00] (step=0030900) Train Loss: 0.4583, Train Steps/Sec: 1.20
381
+ [2025-10-28 07:15:23] (step=0031000) Train Loss: 0.4589, Train Steps/Sec: 1.20
382
+ [2025-10-28 07:16:46] (step=0031100) Train Loss: 0.4588, Train Steps/Sec: 1.20
383
+ [2025-10-28 07:18:09] (step=0031200) Train Loss: 0.4560, Train Steps/Sec: 1.20
384
+ [2025-10-28 07:19:12] Beginning epoch 25...
385
+ [2025-10-28 07:19:35] (step=0031300) Train Loss: 0.4584, Train Steps/Sec: 1.17
386
+ [2025-10-28 07:20:58] (step=0031400) Train Loss: 0.4573, Train Steps/Sec: 1.20
387
+ [2025-10-28 07:22:21] (step=0031500) Train Loss: 0.4570, Train Steps/Sec: 1.20
388
+ [2025-10-28 07:23:44] (step=0031600) Train Loss: 0.4577, Train Steps/Sec: 1.20
389
+ [2025-10-28 07:25:07] (step=0031700) Train Loss: 0.4565, Train Steps/Sec: 1.20
390
+ [2025-10-28 07:26:31] (step=0031800) Train Loss: 0.4585, Train Steps/Sec: 1.20
391
+ [2025-10-28 07:27:54] (step=0031900) Train Loss: 0.4568, Train Steps/Sec: 1.20
392
+ [2025-10-28 07:29:17] (step=0032000) Train Loss: 0.4566, Train Steps/Sec: 1.20
393
+ [2025-10-28 07:30:40] (step=0032100) Train Loss: 0.4577, Train Steps/Sec: 1.20
394
+ [2025-10-28 07:32:03] (step=0032200) Train Loss: 0.4559, Train Steps/Sec: 1.20
395
+ [2025-10-28 07:33:27] (step=0032300) Train Loss: 0.4567, Train Steps/Sec: 1.20
396
+ [2025-10-28 07:34:51] (step=0032400) Train Loss: 0.4561, Train Steps/Sec: 1.19
397
+ [2025-10-28 07:36:14] (step=0032500) Train Loss: 0.4567, Train Steps/Sec: 1.20
398
+ [2025-10-28 07:36:36] Beginning epoch 26...
399
+ [2025-10-28 07:37:40] (step=0032600) Train Loss: 0.4571, Train Steps/Sec: 1.17
400
+ [2025-10-28 07:39:03] (step=0032700) Train Loss: 0.4566, Train Steps/Sec: 1.20
401
+ [2025-10-28 07:40:26] (step=0032800) Train Loss: 0.4581, Train Steps/Sec: 1.20
402
+ [2025-10-28 07:41:50] (step=0032900) Train Loss: 0.4571, Train Steps/Sec: 1.20
403
+ [2025-10-28 07:43:13] (step=0033000) Train Loss: 0.4582, Train Steps/Sec: 1.20
404
+ [2025-10-28 07:44:36] (step=0033100) Train Loss: 0.4564, Train Steps/Sec: 1.20
405
+ [2025-10-28 07:46:00] (step=0033200) Train Loss: 0.4570, Train Steps/Sec: 1.20
406
+ [2025-10-28 07:47:23] (step=0033300) Train Loss: 0.4558, Train Steps/Sec: 1.20
407
+ [2025-10-28 07:48:46] (step=0033400) Train Loss: 0.4575, Train Steps/Sec: 1.20
408
+ [2025-10-28 07:50:09] (step=0033500) Train Loss: 0.4565, Train Steps/Sec: 1.20
409
+ [2025-10-28 07:51:33] (step=0033600) Train Loss: 0.4562, Train Steps/Sec: 1.20
410
+ [2025-10-28 07:52:56] (step=0033700) Train Loss: 0.4554, Train Steps/Sec: 1.20
411
+ [2025-10-28 07:54:00] Beginning epoch 27...
412
+ [2025-10-28 07:54:21] (step=0033800) Train Loss: 0.4557, Train Steps/Sec: 1.17
413
+ [2025-10-28 07:55:45] (step=0033900) Train Loss: 0.4560, Train Steps/Sec: 1.20
414
+ [2025-10-28 07:57:08] (step=0034000) Train Loss: 0.4563, Train Steps/Sec: 1.20
415
+ [2025-10-28 07:58:32] (step=0034100) Train Loss: 0.4542, Train Steps/Sec: 1.19
416
+ [2025-10-28 07:59:55] (step=0034200) Train Loss: 0.4562, Train Steps/Sec: 1.20
417
+ [2025-10-28 08:01:18] (step=0034300) Train Loss: 0.4566, Train Steps/Sec: 1.20
418
+ [2025-10-28 08:02:42] (step=0034400) Train Loss: 0.4550, Train Steps/Sec: 1.20
419
+ [2025-10-28 08:04:05] (step=0034500) Train Loss: 0.4566, Train Steps/Sec: 1.20
420
+ [2025-10-28 08:05:28] (step=0034600) Train Loss: 0.4555, Train Steps/Sec: 1.20
421
+ [2025-10-28 08:06:51] (step=0034700) Train Loss: 0.4563, Train Steps/Sec: 1.20
422
+ [2025-10-28 08:08:14] (step=0034800) Train Loss: 0.4555, Train Steps/Sec: 1.20
423
+ [2025-10-28 08:09:38] (step=0034900) Train Loss: 0.4556, Train Steps/Sec: 1.20
424
+ [2025-10-28 08:11:01] (step=0035000) Train Loss: 0.4546, Train Steps/Sec: 1.20
425
+ [2025-10-28 08:11:25] Beginning epoch 28...
426
+ [2025-10-28 08:12:27] (step=0035100) Train Loss: 0.4547, Train Steps/Sec: 1.16
427
+ [2025-10-28 08:13:50] (step=0035200) Train Loss: 0.4555, Train Steps/Sec: 1.20
428
+ [2025-10-28 08:15:13] (step=0035300) Train Loss: 0.4555, Train Steps/Sec: 1.20
429
+ [2025-10-28 08:16:36] (step=0035400) Train Loss: 0.4541, Train Steps/Sec: 1.20
430
+ [2025-10-28 08:18:00] (step=0035500) Train Loss: 0.4565, Train Steps/Sec: 1.20
431
+ [2025-10-28 08:19:23] (step=0035600) Train Loss: 0.4544, Train Steps/Sec: 1.20
432
+ [2025-10-28 08:20:47] (step=0035700) Train Loss: 0.4562, Train Steps/Sec: 1.20
433
+ [2025-10-28 08:22:10] (step=0035800) Train Loss: 0.4566, Train Steps/Sec: 1.19
434
+ [2025-10-28 08:23:34] (step=0035900) Train Loss: 0.4535, Train Steps/Sec: 1.20
435
+ [2025-10-28 08:24:57] (step=0036000) Train Loss: 0.4557, Train Steps/Sec: 1.20
436
+ [2025-10-28 08:26:20] (step=0036100) Train Loss: 0.4556, Train Steps/Sec: 1.20
437
+ [2025-10-28 08:27:43] (step=0036200) Train Loss: 0.4554, Train Steps/Sec: 1.20
438
+ [2025-10-28 08:28:49] Beginning epoch 29...
439
+ [2025-10-28 08:29:09] (step=0036300) Train Loss: 0.4554, Train Steps/Sec: 1.17
440
+ [2025-10-28 08:30:32] (step=0036400) Train Loss: 0.4547, Train Steps/Sec: 1.20
441
+ [2025-10-28 08:31:55] (step=0036500) Train Loss: 0.4552, Train Steps/Sec: 1.20
442
+ [2025-10-28 08:33:18] (step=0036600) Train Loss: 0.4539, Train Steps/Sec: 1.20
443
+ [2025-10-28 08:34:41] (step=0036700) Train Loss: 0.4539, Train Steps/Sec: 1.20
444
+ [2025-10-28 08:36:04] (step=0036800) Train Loss: 0.4550, Train Steps/Sec: 1.20
445
+ [2025-10-28 08:37:27] (step=0036900) Train Loss: 0.4542, Train Steps/Sec: 1.20
446
+ [2025-10-28 08:38:51] (step=0037000) Train Loss: 0.4542, Train Steps/Sec: 1.20
447
+ [2025-10-28 08:40:14] (step=0037100) Train Loss: 0.4548, Train Steps/Sec: 1.20
448
+ [2025-10-28 08:41:37] (step=0037200) Train Loss: 0.4540, Train Steps/Sec: 1.20
449
+ [2025-10-28 08:43:00] (step=0037300) Train Loss: 0.4543, Train Steps/Sec: 1.20
450
+ [2025-10-28 08:44:24] (step=0037400) Train Loss: 0.4548, Train Steps/Sec: 1.19
451
+ [2025-10-28 08:45:47] (step=0037500) Train Loss: 0.4540, Train Steps/Sec: 1.20
452
+ [2025-10-28 08:46:13] Beginning epoch 30...
453
+ [2025-10-28 08:47:13] (step=0037600) Train Loss: 0.4525, Train Steps/Sec: 1.17
454
+ [2025-10-28 08:48:36] (step=0037700) Train Loss: 0.4550, Train Steps/Sec: 1.20
455
+ [2025-10-28 08:49:59] (step=0037800) Train Loss: 0.4542, Train Steps/Sec: 1.20
456
+ [2025-10-28 08:51:22] (step=0037900) Train Loss: 0.4541, Train Steps/Sec: 1.20
457
+ [2025-10-28 08:52:45] (step=0038000) Train Loss: 0.4541, Train Steps/Sec: 1.20
458
+ [2025-10-28 08:54:09] (step=0038100) Train Loss: 0.4535, Train Steps/Sec: 1.20
459
+ [2025-10-28 08:55:32] (step=0038200) Train Loss: 0.4538, Train Steps/Sec: 1.20
460
+ [2025-10-28 08:56:55] (step=0038300) Train Loss: 0.4544, Train Steps/Sec: 1.20
461
+ [2025-10-28 08:58:18] (step=0038400) Train Loss: 0.4548, Train Steps/Sec: 1.20
462
+ [2025-10-28 08:59:41] (step=0038500) Train Loss: 0.4551, Train Steps/Sec: 1.20
463
+ [2025-10-28 09:01:04] (step=0038600) Train Loss: 0.4526, Train Steps/Sec: 1.20
464
+ [2025-10-28 09:02:28] (step=0038700) Train Loss: 0.4544, Train Steps/Sec: 1.20
465
+ [2025-10-28 09:03:35] Beginning epoch 31...
466
+ [2025-10-28 09:03:53] (step=0038800) Train Loss: 0.4546, Train Steps/Sec: 1.17
467
+ [2025-10-28 09:05:16] (step=0038900) Train Loss: 0.4533, Train Steps/Sec: 1.20
468
+ [2025-10-28 09:06:39] (step=0039000) Train Loss: 0.4533, Train Steps/Sec: 1.20
469
+ [2025-10-28 09:08:04] (step=0039100) Train Loss: 0.4531, Train Steps/Sec: 1.19
470
+ [2025-10-28 09:09:27] (step=0039200) Train Loss: 0.4537, Train Steps/Sec: 1.20
471
+ [2025-10-28 09:10:50] (step=0039300) Train Loss: 0.4518, Train Steps/Sec: 1.20
472
+ [2025-10-28 09:12:13] (step=0039400) Train Loss: 0.4533, Train Steps/Sec: 1.20
473
+ [2025-10-28 09:13:36] (step=0039500) Train Loss: 0.4535, Train Steps/Sec: 1.20
474
+ [2025-10-28 09:14:59] (step=0039600) Train Loss: 0.4542, Train Steps/Sec: 1.20
475
+ [2025-10-28 09:16:22] (step=0039700) Train Loss: 0.4530, Train Steps/Sec: 1.20
476
+ [2025-10-28 09:17:45] (step=0039800) Train Loss: 0.4521, Train Steps/Sec: 1.20
477
+ [2025-10-28 09:19:09] (step=0039900) Train Loss: 0.4556, Train Steps/Sec: 1.20
478
+ [2025-10-28 09:20:32] (step=0040000) Train Loss: 0.4545, Train Steps/Sec: 1.20
479
+ [2025-10-28 09:20:59] Beginning epoch 32...
480
+ [2025-10-28 09:21:57] (step=0040100) Train Loss: 0.4518, Train Steps/Sec: 1.17
481
+ [2025-10-28 09:23:20] (step=0040200) Train Loss: 0.4542, Train Steps/Sec: 1.20
482
+ [2025-10-28 09:24:43] (step=0040300) Train Loss: 0.4522, Train Steps/Sec: 1.20
483
+ [2025-10-28 09:26:06] (step=0040400) Train Loss: 0.4528, Train Steps/Sec: 1.20
484
+ [2025-10-28 09:27:30] (step=0040500) Train Loss: 0.4530, Train Steps/Sec: 1.20
485
+ [2025-10-28 09:28:53] (step=0040600) Train Loss: 0.4524, Train Steps/Sec: 1.20
486
+ [2025-10-28 09:30:17] (step=0040700) Train Loss: 0.4511, Train Steps/Sec: 1.19
487
+ [2025-10-28 09:31:40] (step=0040800) Train Loss: 0.4522, Train Steps/Sec: 1.20
488
+ [2025-10-28 09:33:03] (step=0040900) Train Loss: 0.4517, Train Steps/Sec: 1.20
489
+ [2025-10-28 09:34:27] (step=0041000) Train Loss: 0.4530, Train Steps/Sec: 1.20
490
+ [2025-10-28 09:35:50] (step=0041100) Train Loss: 0.4532, Train Steps/Sec: 1.20
491
+ [2025-10-28 09:37:13] (step=0041200) Train Loss: 0.4509, Train Steps/Sec: 1.20
492
+ [2025-10-28 09:38:23] Beginning epoch 33...
493
+ [2025-10-28 09:38:39] (step=0041300) Train Loss: 0.4540, Train Steps/Sec: 1.17
494
+ [2025-10-28 09:40:02] (step=0041400) Train Loss: 0.4529, Train Steps/Sec: 1.20
495
+ [2025-10-28 09:41:25] (step=0041500) Train Loss: 0.4523, Train Steps/Sec: 1.20
496
+ [2025-10-28 09:42:48] (step=0041600) Train Loss: 0.4520, Train Steps/Sec: 1.20
497
+ [2025-10-28 09:44:11] (step=0041700) Train Loss: 0.4527, Train Steps/Sec: 1.20
498
+ [2025-10-28 09:45:35] (step=0041800) Train Loss: 0.4533, Train Steps/Sec: 1.20
499
+ [2025-10-28 09:46:58] (step=0041900) Train Loss: 0.4508, Train Steps/Sec: 1.20
500
+ [2025-10-28 09:48:21] (step=0042000) Train Loss: 0.4518, Train Steps/Sec: 1.20
501
+ [2025-10-28 09:49:44] (step=0042100) Train Loss: 0.4533, Train Steps/Sec: 1.20
502
+ [2025-10-28 09:51:08] (step=0042200) Train Loss: 0.4518, Train Steps/Sec: 1.20
503
+ [2025-10-28 09:52:31] (step=0042300) Train Loss: 0.4524, Train Steps/Sec: 1.20
504
+ [2025-10-28 09:53:55] (step=0042400) Train Loss: 0.4520, Train Steps/Sec: 1.19
505
+ [2025-10-28 09:55:18] (step=0042500) Train Loss: 0.4524, Train Steps/Sec: 1.20
506
+ [2025-10-28 09:55:47] Beginning epoch 34...
507
+ [2025-10-28 09:56:44] (step=0042600) Train Loss: 0.4517, Train Steps/Sec: 1.16
508
+ [2025-10-28 09:58:07] (step=0042700) Train Loss: 0.4517, Train Steps/Sec: 1.20
509
+ [2025-10-28 09:59:30] (step=0042800) Train Loss: 0.4506, Train Steps/Sec: 1.20
510
+ [2025-10-28 10:00:54] (step=0042900) Train Loss: 0.4522, Train Steps/Sec: 1.20
511
+ [2025-10-28 10:02:17] (step=0043000) Train Loss: 0.4520, Train Steps/Sec: 1.20
512
+ [2025-10-28 10:03:40] (step=0043100) Train Loss: 0.4490, Train Steps/Sec: 1.20
513
+ [2025-10-28 10:05:03] (step=0043200) Train Loss: 0.4526, Train Steps/Sec: 1.20
514
+ [2025-10-28 10:06:26] (step=0043300) Train Loss: 0.4501, Train Steps/Sec: 1.20
515
+ [2025-10-28 10:07:50] (step=0043400) Train Loss: 0.4518, Train Steps/Sec: 1.20
516
+ [2025-10-28 10:09:13] (step=0043500) Train Loss: 0.4524, Train Steps/Sec: 1.20
517
+ [2025-10-28 10:10:36] (step=0043600) Train Loss: 0.4524, Train Steps/Sec: 1.20
518
+ [2025-10-28 10:11:59] (step=0043700) Train Loss: 0.4511, Train Steps/Sec: 1.20
519
+ [2025-10-28 10:13:10] Beginning epoch 35...
520
+ [2025-10-28 10:13:25] (step=0043800) Train Loss: 0.4529, Train Steps/Sec: 1.16
521
+ [2025-10-28 10:14:48] (step=0043900) Train Loss: 0.4498, Train Steps/Sec: 1.20
522
+ [2025-10-28 10:16:12] (step=0044000) Train Loss: 0.4511, Train Steps/Sec: 1.20
523
+ [2025-10-28 10:17:36] (step=0044100) Train Loss: 0.4499, Train Steps/Sec: 1.19
524
+ [2025-10-28 10:18:59] (step=0044200) Train Loss: 0.4515, Train Steps/Sec: 1.20
525
+ [2025-10-28 10:20:22] (step=0044300) Train Loss: 0.4519, Train Steps/Sec: 1.20
526
+ [2025-10-28 10:21:45] (step=0044400) Train Loss: 0.4497, Train Steps/Sec: 1.20
527
+ [2025-10-28 10:23:08] (step=0044500) Train Loss: 0.4518, Train Steps/Sec: 1.20
528
+ [2025-10-28 10:24:32] (step=0044600) Train Loss: 0.4502, Train Steps/Sec: 1.20
529
+ [2025-10-28 10:25:55] (step=0044700) Train Loss: 0.4513, Train Steps/Sec: 1.20
530
+ [2025-10-28 10:27:18] (step=0044800) Train Loss: 0.4506, Train Steps/Sec: 1.20
531
+ [2025-10-28 10:28:41] (step=0044900) Train Loss: 0.4514, Train Steps/Sec: 1.20
532
+ [2025-10-28 10:30:04] (step=0045000) Train Loss: 0.4525, Train Steps/Sec: 1.20
533
+ [2025-10-28 10:30:35] Beginning epoch 36...
534
+ [2025-10-28 10:31:30] (step=0045100) Train Loss: 0.4513, Train Steps/Sec: 1.17
535
+ [2025-10-28 10:32:53] (step=0045200) Train Loss: 0.4517, Train Steps/Sec: 1.20
536
+ [2025-10-28 10:34:16] (step=0045300) Train Loss: 0.4517, Train Steps/Sec: 1.20
537
+ [2025-10-28 10:35:40] (step=0045400) Train Loss: 0.4523, Train Steps/Sec: 1.20
538
+ [2025-10-28 10:37:03] (step=0045500) Train Loss: 0.4499, Train Steps/Sec: 1.20
539
+ [2025-10-28 10:38:26] (step=0045600) Train Loss: 0.4503, Train Steps/Sec: 1.20
540
+ [2025-10-28 10:39:50] (step=0045700) Train Loss: 0.4498, Train Steps/Sec: 1.19
541
+ [2025-10-28 10:41:13] (step=0045800) Train Loss: 0.4520, Train Steps/Sec: 1.20
542
+ [2025-10-28 10:42:36] (step=0045900) Train Loss: 0.4512, Train Steps/Sec: 1.20
543
+ [2025-10-28 10:44:00] (step=0046000) Train Loss: 0.4502, Train Steps/Sec: 1.20
544
+ [2025-10-28 10:45:23] (step=0046100) Train Loss: 0.4498, Train Steps/Sec: 1.20
545
+ [2025-10-28 10:46:46] (step=0046200) Train Loss: 0.4507, Train Steps/Sec: 1.20
546
+ [2025-10-28 10:47:59] Beginning epoch 37...
547
+ [2025-10-28 10:48:13] (step=0046300) Train Loss: 0.4521, Train Steps/Sec: 1.14
548
+ [2025-10-28 10:49:37] (step=0046400) Train Loss: 0.4492, Train Steps/Sec: 1.20
549
+ [2025-10-28 10:51:00] (step=0046500) Train Loss: 0.4498, Train Steps/Sec: 1.20
550
+ [2025-10-28 10:52:23] (step=0046600) Train Loss: 0.4502, Train Steps/Sec: 1.20
551
+ [2025-10-28 10:53:47] (step=0046700) Train Loss: 0.4508, Train Steps/Sec: 1.20
552
+ [2025-10-28 10:55:10] (step=0046800) Train Loss: 0.4493, Train Steps/Sec: 1.20
553
+ [2025-10-28 10:56:33] (step=0046900) Train Loss: 0.4508, Train Steps/Sec: 1.20
554
+ [2025-10-28 10:57:56] (step=0047000) Train Loss: 0.4507, Train Steps/Sec: 1.20
555
+ [2025-10-28 10:59:19] (step=0047100) Train Loss: 0.4513, Train Steps/Sec: 1.20
556
+ [2025-10-28 11:00:43] (step=0047200) Train Loss: 0.4508, Train Steps/Sec: 1.20
557
+ [2025-10-28 11:02:06] (step=0047300) Train Loss: 0.4492, Train Steps/Sec: 1.20
558
+ [2025-10-28 11:03:30] (step=0047400) Train Loss: 0.4515, Train Steps/Sec: 1.19
559
+ [2025-10-28 11:04:53] (step=0047500) Train Loss: 0.4491, Train Steps/Sec: 1.20
560
+ [2025-10-28 11:05:25] Beginning epoch 38...
561
+ [2025-10-28 11:06:18] (step=0047600) Train Loss: 0.4500, Train Steps/Sec: 1.17
562
+ [2025-10-28 11:07:42] (step=0047700) Train Loss: 0.4502, Train Steps/Sec: 1.20
563
+ [2025-10-28 11:09:05] (step=0047800) Train Loss: 0.4493, Train Steps/Sec: 1.20
564
+ [2025-10-28 11:10:28] (step=0047900) Train Loss: 0.4494, Train Steps/Sec: 1.20
565
+ [2025-10-28 11:11:51] (step=0048000) Train Loss: 0.4482, Train Steps/Sec: 1.20
566
+ [2025-10-28 11:13:14] (step=0048100) Train Loss: 0.4507, Train Steps/Sec: 1.20
567
+ [2025-10-28 11:14:37] (step=0048200) Train Loss: 0.4512, Train Steps/Sec: 1.20
568
+ [2025-10-28 11:16:00] (step=0048300) Train Loss: 0.4504, Train Steps/Sec: 1.20
569
+ [2025-10-28 11:17:24] (step=0048400) Train Loss: 0.4489, Train Steps/Sec: 1.20
570
+ [2025-10-28 11:18:47] (step=0048500) Train Loss: 0.4483, Train Steps/Sec: 1.20
571
+ [2025-10-28 11:20:10] (step=0048600) Train Loss: 0.4499, Train Steps/Sec: 1.20
572
+ [2025-10-28 11:21:34] (step=0048700) Train Loss: 0.4509, Train Steps/Sec: 1.20
573
+ [2025-10-28 11:22:48] Beginning epoch 39...
574
+ [2025-10-28 11:22:59] (step=0048800) Train Loss: 0.4489, Train Steps/Sec: 1.17
575
+ [2025-10-28 11:24:22] (step=0048900) Train Loss: 0.4488, Train Steps/Sec: 1.20
576
+ [2025-10-28 11:25:46] (step=0049000) Train Loss: 0.4503, Train Steps/Sec: 1.19
577
+ [2025-10-28 11:27:10] (step=0049100) Train Loss: 0.4497, Train Steps/Sec: 1.20
578
+ [2025-10-28 11:28:33] (step=0049200) Train Loss: 0.4488, Train Steps/Sec: 1.20
579
+ [2025-10-28 11:29:56] (step=0049300) Train Loss: 0.4477, Train Steps/Sec: 1.20
580
+ [2025-10-28 11:31:19] (step=0049400) Train Loss: 0.4481, Train Steps/Sec: 1.20
581
+ [2025-10-28 11:32:42] (step=0049500) Train Loss: 0.4495, Train Steps/Sec: 1.20
582
+ [2025-10-28 11:34:05] (step=0049600) Train Loss: 0.4498, Train Steps/Sec: 1.20
583
+ [2025-10-28 11:35:28] (step=0049700) Train Loss: 0.4495, Train Steps/Sec: 1.20
584
+ [2025-10-28 11:36:51] (step=0049800) Train Loss: 0.4482, Train Steps/Sec: 1.20
585
+ [2025-10-28 11:38:14] (step=0049900) Train Loss: 0.4496, Train Steps/Sec: 1.20
586
+ [2025-10-28 11:39:37] (step=0050000) Train Loss: 0.4485, Train Steps/Sec: 1.20
587
+ [2025-10-28 11:40:27] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0050000.pt
588
+ [2025-10-28 11:40:27] Generating EMA samples...
589
+ [2025-10-28 11:40:56] Generating EMA samples done.
590
+ [2025-10-28 11:41:29] Beginning epoch 40...
591
+ [2025-10-28 11:42:21] (step=0050100) Train Loss: 0.4485, Train Steps/Sec: 0.61
592
+ [2025-10-28 11:43:44] (step=0050200) Train Loss: 0.4486, Train Steps/Sec: 1.20
593
+ [2025-10-28 11:45:08] (step=0050300) Train Loss: 0.4510, Train Steps/Sec: 1.20
594
+ [2025-10-28 11:46:31] (step=0050400) Train Loss: 0.4483, Train Steps/Sec: 1.20
595
+ [2025-10-28 11:47:54] (step=0050500) Train Loss: 0.4487, Train Steps/Sec: 1.20
596
+ [2025-10-28 11:49:17] (step=0050600) Train Loss: 0.4489, Train Steps/Sec: 1.20
597
+ [2025-10-28 11:50:42] (step=0050700) Train Loss: 0.4494, Train Steps/Sec: 1.19
598
+ [2025-10-28 11:52:05] (step=0050800) Train Loss: 0.4478, Train Steps/Sec: 1.20
599
+ [2025-10-28 11:53:28] (step=0050900) Train Loss: 0.4502, Train Steps/Sec: 1.20
600
+ [2025-10-28 11:54:51] (step=0051000) Train Loss: 0.4482, Train Steps/Sec: 1.20
601
+ [2025-10-28 11:56:14] (step=0051100) Train Loss: 0.4494, Train Steps/Sec: 1.20
602
+ [2025-10-28 11:57:37] (step=0051200) Train Loss: 0.4479, Train Steps/Sec: 1.20
603
+ [2025-10-28 11:58:54] Beginning epoch 41...
604
+ [2025-10-28 11:59:03] (step=0051300) Train Loss: 0.4492, Train Steps/Sec: 1.17
605
+ [2025-10-28 12:00:26] (step=0051400) Train Loss: 0.4495, Train Steps/Sec: 1.20
606
+ [2025-10-28 12:01:49] (step=0051500) Train Loss: 0.4487, Train Steps/Sec: 1.20
607
+ [2025-10-28 12:03:12] (step=0051600) Train Loss: 0.4491, Train Steps/Sec: 1.20
608
+ [2025-10-28 12:04:36] (step=0051700) Train Loss: 0.4496, Train Steps/Sec: 1.20
609
+ [2025-10-28 12:05:59] (step=0051800) Train Loss: 0.4485, Train Steps/Sec: 1.20
610
+ [2025-10-28 12:07:22] (step=0051900) Train Loss: 0.4488, Train Steps/Sec: 1.20
611
+ [2025-10-28 12:08:45] (step=0052000) Train Loss: 0.4479, Train Steps/Sec: 1.20
612
+ [2025-10-28 12:10:09] (step=0052100) Train Loss: 0.4482, Train Steps/Sec: 1.20
613
+ [2025-10-28 12:11:32] (step=0052200) Train Loss: 0.4478, Train Steps/Sec: 1.20
614
+ [2025-10-28 12:12:55] (step=0052300) Train Loss: 0.4495, Train Steps/Sec: 1.20
615
+ [2025-10-28 12:14:19] (step=0052400) Train Loss: 0.4478, Train Steps/Sec: 1.19
616
+ [2025-10-28 12:15:43] (step=0052500) Train Loss: 0.4490, Train Steps/Sec: 1.20
617
+ [2025-10-28 12:16:18] Beginning epoch 42...
618
+ [2025-10-28 12:17:08] (step=0052600) Train Loss: 0.4478, Train Steps/Sec: 1.17
619
+ [2025-10-28 12:18:31] (step=0052700) Train Loss: 0.4488, Train Steps/Sec: 1.20
620
+ [2025-10-28 12:19:54] (step=0052800) Train Loss: 0.4494, Train Steps/Sec: 1.20
621
+ [2025-10-28 12:21:18] (step=0052900) Train Loss: 0.4493, Train Steps/Sec: 1.20
622
+ [2025-10-28 12:22:41] (step=0053000) Train Loss: 0.4470, Train Steps/Sec: 1.20
623
+ [2025-10-28 12:24:04] (step=0053100) Train Loss: 0.4476, Train Steps/Sec: 1.20
624
+ [2025-10-28 12:25:27] (step=0053200) Train Loss: 0.4477, Train Steps/Sec: 1.20
625
+ [2025-10-28 12:26:50] (step=0053300) Train Loss: 0.4480, Train Steps/Sec: 1.20
626
+ [2025-10-28 12:28:14] (step=0053400) Train Loss: 0.4477, Train Steps/Sec: 1.20
627
+ [2025-10-28 12:29:37] (step=0053500) Train Loss: 0.4480, Train Steps/Sec: 1.20
628
+ [2025-10-28 12:31:00] (step=0053600) Train Loss: 0.4488, Train Steps/Sec: 1.20
629
+ [2025-10-28 12:32:23] (step=0053700) Train Loss: 0.4474, Train Steps/Sec: 1.20
630
+ [2025-10-28 12:33:41] Beginning epoch 43...
631
+ [2025-10-28 12:33:49] (step=0053800) Train Loss: 0.4480, Train Steps/Sec: 1.17
632
+ [2025-10-28 12:35:12] (step=0053900) Train Loss: 0.4482, Train Steps/Sec: 1.20
633
+ [2025-10-28 12:36:36] (step=0054000) Train Loss: 0.4491, Train Steps/Sec: 1.19
634
+ [2025-10-28 12:37:59] (step=0054100) Train Loss: 0.4471, Train Steps/Sec: 1.20
635
+ [2025-10-28 12:39:23] (step=0054200) Train Loss: 0.4482, Train Steps/Sec: 1.20
636
+ [2025-10-28 12:40:46] (step=0054300) Train Loss: 0.4461, Train Steps/Sec: 1.20
637
+ [2025-10-28 12:42:09] (step=0054400) Train Loss: 0.4471, Train Steps/Sec: 1.20
638
+ [2025-10-28 12:43:32] (step=0054500) Train Loss: 0.4479, Train Steps/Sec: 1.20
639
+ [2025-10-28 12:44:55] (step=0054600) Train Loss: 0.4482, Train Steps/Sec: 1.20
640
+ [2025-10-28 12:46:18] (step=0054700) Train Loss: 0.4474, Train Steps/Sec: 1.20
641
+ [2025-10-28 12:47:41] (step=0054800) Train Loss: 0.4476, Train Steps/Sec: 1.20
642
+ [2025-10-28 12:49:04] (step=0054900) Train Loss: 0.4491, Train Steps/Sec: 1.20
643
+ [2025-10-28 12:50:27] (step=0055000) Train Loss: 0.4506, Train Steps/Sec: 1.20
644
+ [2025-10-28 12:51:04] Beginning epoch 44...
645
+ [2025-10-28 12:51:53] (step=0055100) Train Loss: 0.4478, Train Steps/Sec: 1.17
646
+ [2025-10-28 12:53:16] (step=0055200) Train Loss: 0.4483, Train Steps/Sec: 1.20
647
+ [2025-10-28 12:54:39] (step=0055300) Train Loss: 0.4457, Train Steps/Sec: 1.20
648
+ [2025-10-28 12:56:02] (step=0055400) Train Loss: 0.4488, Train Steps/Sec: 1.20
649
+ [2025-10-28 12:57:25] (step=0055500) Train Loss: 0.4470, Train Steps/Sec: 1.20
650
+ [2025-10-28 12:58:48] (step=0055600) Train Loss: 0.4471, Train Steps/Sec: 1.20
651
+ [2025-10-28 13:00:12] (step=0055700) Train Loss: 0.4469, Train Steps/Sec: 1.19
652
+ [2025-10-28 13:01:35] (step=0055800) Train Loss: 0.4483, Train Steps/Sec: 1.20
653
+ [2025-10-28 13:02:59] (step=0055900) Train Loss: 0.4464, Train Steps/Sec: 1.20
654
+ [2025-10-28 13:04:22] (step=0056000) Train Loss: 0.4466, Train Steps/Sec: 1.20
655
+ [2025-10-28 13:05:45] (step=0056100) Train Loss: 0.4469, Train Steps/Sec: 1.20
656
+ [2025-10-28 13:07:08] (step=0056200) Train Loss: 0.4467, Train Steps/Sec: 1.20
657
+ [2025-10-28 13:08:28] Beginning epoch 45...
658
+ [2025-10-28 13:08:34] (step=0056300) Train Loss: 0.4477, Train Steps/Sec: 1.17
659
+ [2025-10-28 13:09:57] (step=0056400) Train Loss: 0.4481, Train Steps/Sec: 1.20
660
+ [2025-10-28 13:11:20] (step=0056500) Train Loss: 0.4491, Train Steps/Sec: 1.20
661
+ [2025-10-28 13:12:43] (step=0056600) Train Loss: 0.4477, Train Steps/Sec: 1.20
662
+ [2025-10-28 13:14:06] (step=0056700) Train Loss: 0.4479, Train Steps/Sec: 1.20
663
+ [2025-10-28 13:15:30] (step=0056800) Train Loss: 0.4478, Train Steps/Sec: 1.20
664
+ [2025-10-28 13:16:53] (step=0056900) Train Loss: 0.4466, Train Steps/Sec: 1.20
665
+ [2025-10-28 13:18:16] (step=0057000) Train Loss: 0.4462, Train Steps/Sec: 1.20
666
+ [2025-10-28 13:19:39] (step=0057100) Train Loss: 0.4469, Train Steps/Sec: 1.20
667
+ [2025-10-28 13:21:03] (step=0057200) Train Loss: 0.4469, Train Steps/Sec: 1.20
668
+ [2025-10-28 13:22:26] (step=0057300) Train Loss: 0.4471, Train Steps/Sec: 1.20
669
+ [2025-10-28 13:23:50] (step=0057400) Train Loss: 0.4471, Train Steps/Sec: 1.19
670
+ [2025-10-28 13:25:13] (step=0057500) Train Loss: 0.4479, Train Steps/Sec: 1.20
671
+ [2025-10-28 13:25:52] Beginning epoch 46...
672
+ [2025-10-28 13:26:39] (step=0057600) Train Loss: 0.4465, Train Steps/Sec: 1.17
673
+ [2025-10-28 13:28:02] (step=0057700) Train Loss: 0.4470, Train Steps/Sec: 1.20
674
+ [2025-10-28 13:29:25] (step=0057800) Train Loss: 0.4458, Train Steps/Sec: 1.20
675
+ [2025-10-28 13:30:48] (step=0057900) Train Loss: 0.4470, Train Steps/Sec: 1.20
676
+ [2025-10-28 13:32:12] (step=0058000) Train Loss: 0.4466, Train Steps/Sec: 1.20
677
+ [2025-10-28 13:33:35] (step=0058100) Train Loss: 0.4453, Train Steps/Sec: 1.20
678
+ [2025-10-28 13:34:58] (step=0058200) Train Loss: 0.4475, Train Steps/Sec: 1.20
679
+ [2025-10-28 13:36:21] (step=0058300) Train Loss: 0.4469, Train Steps/Sec: 1.20
680
+ [2025-10-28 13:37:44] (step=0058400) Train Loss: 0.4477, Train Steps/Sec: 1.20
681
+ [2025-10-28 13:39:07] (step=0058500) Train Loss: 0.4460, Train Steps/Sec: 1.20
682
+ [2025-10-28 13:40:30] (step=0058600) Train Loss: 0.4486, Train Steps/Sec: 1.20
683
+ [2025-10-28 13:41:53] (step=0058700) Train Loss: 0.4469, Train Steps/Sec: 1.20
684
+ [2025-10-28 13:43:14] Beginning epoch 47...
685
+ [2025-10-28 13:43:19] (step=0058800) Train Loss: 0.4469, Train Steps/Sec: 1.17
686
+ [2025-10-28 13:44:42] (step=0058900) Train Loss: 0.4461, Train Steps/Sec: 1.20
687
+ [2025-10-28 13:46:06] (step=0059000) Train Loss: 0.4450, Train Steps/Sec: 1.19
688
+ [2025-10-28 13:47:29] (step=0059100) Train Loss: 0.4448, Train Steps/Sec: 1.20
689
+ [2025-10-28 13:48:52] (step=0059200) Train Loss: 0.4457, Train Steps/Sec: 1.20
690
+ [2025-10-28 13:50:15] (step=0059300) Train Loss: 0.4456, Train Steps/Sec: 1.20
691
+ [2025-10-28 13:51:39] (step=0059400) Train Loss: 0.4479, Train Steps/Sec: 1.20
692
+ [2025-10-28 13:53:02] (step=0059500) Train Loss: 0.4478, Train Steps/Sec: 1.20
693
+ [2025-10-28 13:54:25] (step=0059600) Train Loss: 0.4468, Train Steps/Sec: 1.20
694
+ [2025-10-28 13:55:48] (step=0059700) Train Loss: 0.4474, Train Steps/Sec: 1.20
695
+ [2025-10-28 13:57:11] (step=0059800) Train Loss: 0.4468, Train Steps/Sec: 1.20
696
+ [2025-10-28 13:58:34] (step=0059900) Train Loss: 0.4463, Train Steps/Sec: 1.20
697
+ [2025-10-28 13:59:57] (step=0060000) Train Loss: 0.4464, Train Steps/Sec: 1.20
698
+ [2025-10-28 14:00:37] Beginning epoch 48...
699
+ [2025-10-28 14:01:22] (step=0060100) Train Loss: 0.4465, Train Steps/Sec: 1.17
700
+ [2025-10-28 14:02:46] (step=0060200) Train Loss: 0.4458, Train Steps/Sec: 1.20
701
+ [2025-10-28 14:04:09] (step=0060300) Train Loss: 0.4463, Train Steps/Sec: 1.20
702
+ [2025-10-28 14:05:32] (step=0060400) Train Loss: 0.4464, Train Steps/Sec: 1.20
703
+ [2025-10-28 14:06:55] (step=0060500) Train Loss: 0.4476, Train Steps/Sec: 1.20
704
+ [2025-10-28 14:08:18] (step=0060600) Train Loss: 0.4475, Train Steps/Sec: 1.20
705
+ [2025-10-28 14:09:42] (step=0060700) Train Loss: 0.4458, Train Steps/Sec: 1.19
706
+ [2025-10-28 14:11:05] (step=0060800) Train Loss: 0.4470, Train Steps/Sec: 1.20
707
+ [2025-10-28 14:12:29] (step=0060900) Train Loss: 0.4461, Train Steps/Sec: 1.20
708
+ [2025-10-28 14:13:52] (step=0061000) Train Loss: 0.4456, Train Steps/Sec: 1.20
709
+ [2025-10-28 14:15:15] (step=0061100) Train Loss: 0.4442, Train Steps/Sec: 1.20
710
+ [2025-10-28 14:16:38] (step=0061200) Train Loss: 0.4462, Train Steps/Sec: 1.20
711
+ [2025-10-28 14:18:01] Beginning epoch 49...
712
+ [2025-10-28 14:18:04] (step=0061300) Train Loss: 0.4443, Train Steps/Sec: 1.17
713
+ [2025-10-28 14:19:27] (step=0061400) Train Loss: 0.4472, Train Steps/Sec: 1.20
714
+ [2025-10-28 14:20:50] (step=0061500) Train Loss: 0.4459, Train Steps/Sec: 1.20
715
+ [2025-10-28 14:22:13] (step=0061600) Train Loss: 0.4449, Train Steps/Sec: 1.20
716
+ [2025-10-28 14:23:36] (step=0061700) Train Loss: 0.4466, Train Steps/Sec: 1.20
717
+ [2025-10-28 14:24:59] (step=0061800) Train Loss: 0.4457, Train Steps/Sec: 1.20
718
+ [2025-10-28 14:26:22] (step=0061900) Train Loss: 0.4476, Train Steps/Sec: 1.20
719
+ [2025-10-28 14:27:46] (step=0062000) Train Loss: 0.4433, Train Steps/Sec: 1.20
720
+ [2025-10-28 14:29:09] (step=0062100) Train Loss: 0.4467, Train Steps/Sec: 1.20
721
+ [2025-10-28 14:30:32] (step=0062200) Train Loss: 0.4461, Train Steps/Sec: 1.20
722
+ [2025-10-28 14:31:55] (step=0062300) Train Loss: 0.4453, Train Steps/Sec: 1.20
723
+ [2025-10-28 14:33:19] (step=0062400) Train Loss: 0.4444, Train Steps/Sec: 1.20
724
+ [2025-10-28 14:34:42] (step=0062500) Train Loss: 0.4454, Train Steps/Sec: 1.20
725
+ [2025-10-28 14:35:24] Beginning epoch 50...
726
+ [2025-10-28 14:36:08] (step=0062600) Train Loss: 0.4450, Train Steps/Sec: 1.17
727
+ [2025-10-28 14:37:31] (step=0062700) Train Loss: 0.4449, Train Steps/Sec: 1.20
728
+ [2025-10-28 14:38:54] (step=0062800) Train Loss: 0.4447, Train Steps/Sec: 1.20
729
+ [2025-10-28 14:40:17] (step=0062900) Train Loss: 0.4462, Train Steps/Sec: 1.20
730
+ [2025-10-28 14:41:41] (step=0063000) Train Loss: 0.4439, Train Steps/Sec: 1.20
731
+ [2025-10-28 14:43:04] (step=0063100) Train Loss: 0.4434, Train Steps/Sec: 1.20
732
+ [2025-10-28 14:44:27] (step=0063200) Train Loss: 0.4450, Train Steps/Sec: 1.20
733
+ [2025-10-28 14:45:50] (step=0063300) Train Loss: 0.4465, Train Steps/Sec: 1.20
734
+ [2025-10-28 14:47:13] (step=0063400) Train Loss: 0.4450, Train Steps/Sec: 1.20
735
+ [2025-10-28 14:48:36] (step=0063500) Train Loss: 0.4474, Train Steps/Sec: 1.20
736
+ [2025-10-28 14:50:00] (step=0063600) Train Loss: 0.4456, Train Steps/Sec: 1.20
737
+ [2025-10-28 14:51:23] (step=0063700) Train Loss: 0.4464, Train Steps/Sec: 1.20
738
+ [2025-10-28 14:52:46] (step=0063800) Train Loss: 0.4445, Train Steps/Sec: 1.20
739
+ [2025-10-28 14:52:47] Beginning epoch 51...
740
+ [2025-10-28 14:54:12] (step=0063900) Train Loss: 0.4458, Train Steps/Sec: 1.17
741
+ [2025-10-28 14:55:36] (step=0064000) Train Loss: 0.4440, Train Steps/Sec: 1.19
742
+ [2025-10-28 14:56:59] (step=0064100) Train Loss: 0.4451, Train Steps/Sec: 1.20
743
+ [2025-10-28 14:58:22] (step=0064200) Train Loss: 0.4463, Train Steps/Sec: 1.20
744
+ [2025-10-28 14:59:46] (step=0064300) Train Loss: 0.4457, Train Steps/Sec: 1.20
745
+ [2025-10-28 15:01:09] (step=0064400) Train Loss: 0.4471, Train Steps/Sec: 1.20
746
+ [2025-10-28 15:02:32] (step=0064500) Train Loss: 0.4448, Train Steps/Sec: 1.20
747
+ [2025-10-28 15:03:55] (step=0064600) Train Loss: 0.4446, Train Steps/Sec: 1.20
748
+ [2025-10-28 15:05:18] (step=0064700) Train Loss: 0.4453, Train Steps/Sec: 1.20
749
+ [2025-10-28 15:06:42] (step=0064800) Train Loss: 0.4448, Train Steps/Sec: 1.20
750
+ [2025-10-28 15:08:05] (step=0064900) Train Loss: 0.4440, Train Steps/Sec: 1.20
751
+ [2025-10-28 15:09:28] (step=0065000) Train Loss: 0.4447, Train Steps/Sec: 1.20
752
+ [2025-10-28 15:10:12] Beginning epoch 52...
753
+ [2025-10-28 15:10:54] (step=0065100) Train Loss: 0.4449, Train Steps/Sec: 1.17
754
+ [2025-10-28 15:12:17] (step=0065200) Train Loss: 0.4459, Train Steps/Sec: 1.20
755
+ [2025-10-28 15:13:40] (step=0065300) Train Loss: 0.4456, Train Steps/Sec: 1.20
756
+ [2025-10-28 15:15:03] (step=0065400) Train Loss: 0.4445, Train Steps/Sec: 1.20
757
+ [2025-10-28 15:16:26] (step=0065500) Train Loss: 0.4444, Train Steps/Sec: 1.20
758
+ [2025-10-28 15:17:50] (step=0065600) Train Loss: 0.4460, Train Steps/Sec: 1.20
759
+ [2025-10-28 15:19:14] (step=0065700) Train Loss: 0.4436, Train Steps/Sec: 1.19
760
+ [2025-10-28 15:20:37] (step=0065800) Train Loss: 0.4446, Train Steps/Sec: 1.20
761
+ [2025-10-28 15:22:00] (step=0065900) Train Loss: 0.4442, Train Steps/Sec: 1.20
762
+ [2025-10-28 15:23:23] (step=0066000) Train Loss: 0.4448, Train Steps/Sec: 1.20
763
+ [2025-10-28 15:24:46] (step=0066100) Train Loss: 0.4448, Train Steps/Sec: 1.20
764
+ [2025-10-28 15:26:09] (step=0066200) Train Loss: 0.4453, Train Steps/Sec: 1.20
765
+ [2025-10-28 15:27:32] (step=0066300) Train Loss: 0.4449, Train Steps/Sec: 1.20
766
+ [2025-10-28 15:27:35] Beginning epoch 53...
767
+ [2025-10-28 15:28:58] (step=0066400) Train Loss: 0.4437, Train Steps/Sec: 1.17
768
+ [2025-10-28 15:30:21] (step=0066500) Train Loss: 0.4449, Train Steps/Sec: 1.20
769
+ [2025-10-28 15:31:44] (step=0066600) Train Loss: 0.4443, Train Steps/Sec: 1.20
770
+ [2025-10-28 15:33:07] (step=0066700) Train Loss: 0.4447, Train Steps/Sec: 1.20
771
+ [2025-10-28 15:34:31] (step=0066800) Train Loss: 0.4443, Train Steps/Sec: 1.20
772
+ [2025-10-28 15:35:54] (step=0066900) Train Loss: 0.4445, Train Steps/Sec: 1.20
773
+ [2025-10-28 15:37:17] (step=0067000) Train Loss: 0.4442, Train Steps/Sec: 1.20
774
+ [2025-10-28 15:38:40] (step=0067100) Train Loss: 0.4438, Train Steps/Sec: 1.20
775
+ [2025-10-28 15:40:03] (step=0067200) Train Loss: 0.4448, Train Steps/Sec: 1.20
776
+ [2025-10-28 15:41:27] (step=0067300) Train Loss: 0.4451, Train Steps/Sec: 1.19
777
+ [2025-10-28 15:42:51] (step=0067400) Train Loss: 0.4449, Train Steps/Sec: 1.20
778
+ [2025-10-28 15:44:14] (step=0067500) Train Loss: 0.4442, Train Steps/Sec: 1.20
779
+ [2025-10-28 15:44:59] Beginning epoch 54...
780
+ [2025-10-28 15:45:39] (step=0067600) Train Loss: 0.4431, Train Steps/Sec: 1.17
781
+ [2025-10-28 15:47:02] (step=0067700) Train Loss: 0.4444, Train Steps/Sec: 1.20
782
+ [2025-10-28 15:48:25] (step=0067800) Train Loss: 0.4446, Train Steps/Sec: 1.20
783
+ [2025-10-28 15:49:49] (step=0067900) Train Loss: 0.4441, Train Steps/Sec: 1.20
784
+ [2025-10-28 15:51:12] (step=0068000) Train Loss: 0.4427, Train Steps/Sec: 1.20
785
+ [2025-10-28 15:52:35] (step=0068100) Train Loss: 0.4449, Train Steps/Sec: 1.20
786
+ [2025-10-28 15:53:58] (step=0068200) Train Loss: 0.4436, Train Steps/Sec: 1.20
787
+ [2025-10-28 15:55:21] (step=0068300) Train Loss: 0.4433, Train Steps/Sec: 1.20
788
+ [2025-10-28 15:56:44] (step=0068400) Train Loss: 0.4432, Train Steps/Sec: 1.20
789
+ [2025-10-28 15:58:07] (step=0068500) Train Loss: 0.4443, Train Steps/Sec: 1.20
790
+ [2025-10-28 15:59:30] (step=0068600) Train Loss: 0.4453, Train Steps/Sec: 1.20
791
+ [2025-10-28 16:00:53] (step=0068700) Train Loss: 0.4448, Train Steps/Sec: 1.20
792
+ [2025-10-28 16:02:17] (step=0068800) Train Loss: 0.4438, Train Steps/Sec: 1.20
793
+ [2025-10-28 16:02:22] Beginning epoch 55...
794
+ [2025-10-28 16:03:43] (step=0068900) Train Loss: 0.4424, Train Steps/Sec: 1.17
795
+ [2025-10-28 16:05:07] (step=0069000) Train Loss: 0.4426, Train Steps/Sec: 1.19
796
+ [2025-10-28 16:06:30] (step=0069100) Train Loss: 0.4444, Train Steps/Sec: 1.20
797
+ [2025-10-28 16:07:53] (step=0069200) Train Loss: 0.4440, Train Steps/Sec: 1.20
798
+ [2025-10-28 16:09:17] (step=0069300) Train Loss: 0.4449, Train Steps/Sec: 1.20
799
+ [2025-10-28 16:10:40] (step=0069400) Train Loss: 0.4423, Train Steps/Sec: 1.20
800
+ [2025-10-28 16:12:03] (step=0069500) Train Loss: 0.4444, Train Steps/Sec: 1.20
801
+ [2025-10-28 16:13:26] (step=0069600) Train Loss: 0.4439, Train Steps/Sec: 1.20
802
+ [2025-10-28 16:14:49] (step=0069700) Train Loss: 0.4434, Train Steps/Sec: 1.20
803
+ [2025-10-28 16:16:13] (step=0069800) Train Loss: 0.4449, Train Steps/Sec: 1.20
804
+ [2025-10-28 16:17:36] (step=0069900) Train Loss: 0.4422, Train Steps/Sec: 1.20
805
+ [2025-10-28 16:18:59] (step=0070000) Train Loss: 0.4443, Train Steps/Sec: 1.20
806
+ [2025-10-28 16:19:46] Beginning epoch 56...
807
+ [2025-10-28 16:20:24] (step=0070100) Train Loss: 0.4443, Train Steps/Sec: 1.17
808
+ [2025-10-28 16:21:48] (step=0070200) Train Loss: 0.4429, Train Steps/Sec: 1.20
809
+ [2025-10-28 16:23:11] (step=0070300) Train Loss: 0.4436, Train Steps/Sec: 1.20
810
+ [2025-10-28 16:24:34] (step=0070400) Train Loss: 0.4423, Train Steps/Sec: 1.20
811
+ [2025-10-28 16:25:57] (step=0070500) Train Loss: 0.4440, Train Steps/Sec: 1.20
812
+ [2025-10-28 16:27:20] (step=0070600) Train Loss: 0.4439, Train Steps/Sec: 1.20
813
+ [2025-10-28 16:28:44] (step=0070700) Train Loss: 0.4441, Train Steps/Sec: 1.19
814
+ [2025-10-28 16:30:07] (step=0070800) Train Loss: 0.4442, Train Steps/Sec: 1.20
815
+ [2025-10-28 16:31:30] (step=0070900) Train Loss: 0.4446, Train Steps/Sec: 1.20
816
+ [2025-10-28 16:32:53] (step=0071000) Train Loss: 0.4430, Train Steps/Sec: 1.20
817
+ [2025-10-28 16:34:16] (step=0071100) Train Loss: 0.4445, Train Steps/Sec: 1.20
818
+ [2025-10-28 16:35:40] (step=0071200) Train Loss: 0.4453, Train Steps/Sec: 1.20
819
+ [2025-10-28 16:37:03] (step=0071300) Train Loss: 0.4446, Train Steps/Sec: 1.20
820
+ [2025-10-28 16:37:09] Beginning epoch 57...
821
+ [2025-10-28 16:38:28] (step=0071400) Train Loss: 0.4425, Train Steps/Sec: 1.17
822
+ [2025-10-28 16:39:51] (step=0071500) Train Loss: 0.4439, Train Steps/Sec: 1.20
823
+ [2025-10-28 16:41:14] (step=0071600) Train Loss: 0.4446, Train Steps/Sec: 1.20
824
+ [2025-10-28 16:42:38] (step=0071700) Train Loss: 0.4451, Train Steps/Sec: 1.20
825
+ [2025-10-28 16:44:01] (step=0071800) Train Loss: 0.4433, Train Steps/Sec: 1.20
826
+ [2025-10-28 16:45:24] (step=0071900) Train Loss: 0.4427, Train Steps/Sec: 1.20
827
+ [2025-10-28 16:46:47] (step=0072000) Train Loss: 0.4421, Train Steps/Sec: 1.20
828
+ [2025-10-28 16:48:10] (step=0072100) Train Loss: 0.4436, Train Steps/Sec: 1.20
829
+ [2025-10-28 16:49:33] (step=0072200) Train Loss: 0.4438, Train Steps/Sec: 1.20
830
+ [2025-10-28 16:50:57] (step=0072300) Train Loss: 0.4423, Train Steps/Sec: 1.19
831
+ [2025-10-28 16:52:21] (step=0072400) Train Loss: 0.4414, Train Steps/Sec: 1.20
832
+ [2025-10-28 16:53:44] (step=0072500) Train Loss: 0.4437, Train Steps/Sec: 1.20
833
+ [2025-10-28 16:54:32] Beginning epoch 58...
834
+ [2025-10-28 16:55:09] (step=0072600) Train Loss: 0.4424, Train Steps/Sec: 1.17
835
+ [2025-10-28 16:56:32] (step=0072700) Train Loss: 0.4415, Train Steps/Sec: 1.20
836
+ [2025-10-28 16:57:56] (step=0072800) Train Loss: 0.4433, Train Steps/Sec: 1.20
837
+ [2025-10-28 16:59:19] (step=0072900) Train Loss: 0.4431, Train Steps/Sec: 1.20
838
+ [2025-10-28 17:00:42] (step=0073000) Train Loss: 0.4426, Train Steps/Sec: 1.20
839
+ [2025-10-28 17:02:05] (step=0073100) Train Loss: 0.4432, Train Steps/Sec: 1.20
840
+ [2025-10-28 17:03:28] (step=0073200) Train Loss: 0.4432, Train Steps/Sec: 1.20
841
+ [2025-10-28 17:04:51] (step=0073300) Train Loss: 0.4416, Train Steps/Sec: 1.20
842
+ [2025-10-28 17:06:14] (step=0073400) Train Loss: 0.4436, Train Steps/Sec: 1.20
843
+ [2025-10-28 17:07:38] (step=0073500) Train Loss: 0.4419, Train Steps/Sec: 1.20
844
+ [2025-10-28 17:09:01] (step=0073600) Train Loss: 0.4419, Train Steps/Sec: 1.20
845
+ [2025-10-28 17:10:24] (step=0073700) Train Loss: 0.4424, Train Steps/Sec: 1.20
846
+ [2025-10-28 17:11:47] (step=0073800) Train Loss: 0.4414, Train Steps/Sec: 1.20
847
+ [2025-10-28 17:11:55] Beginning epoch 59...
848
+ [2025-10-28 17:13:13] (step=0073900) Train Loss: 0.4423, Train Steps/Sec: 1.17
849
+ [2025-10-28 17:14:37] (step=0074000) Train Loss: 0.4429, Train Steps/Sec: 1.19
850
+ [2025-10-28 17:16:00] (step=0074100) Train Loss: 0.4416, Train Steps/Sec: 1.20
851
+ [2025-10-28 17:17:23] (step=0074200) Train Loss: 0.4428, Train Steps/Sec: 1.20
852
+ [2025-10-28 17:18:47] (step=0074300) Train Loss: 0.4429, Train Steps/Sec: 1.20
853
+ [2025-10-28 17:20:10] (step=0074400) Train Loss: 0.4432, Train Steps/Sec: 1.20
854
+ [2025-10-28 17:21:33] (step=0074500) Train Loss: 0.4432, Train Steps/Sec: 1.20
855
+ [2025-10-28 17:22:56] (step=0074600) Train Loss: 0.4420, Train Steps/Sec: 1.20
856
+ [2025-10-28 17:24:20] (step=0074700) Train Loss: 0.4433, Train Steps/Sec: 1.20
857
+ [2025-10-28 17:25:43] (step=0074800) Train Loss: 0.4449, Train Steps/Sec: 1.20
858
+ [2025-10-28 17:27:06] (step=0074900) Train Loss: 0.4434, Train Steps/Sec: 1.20
859
+ [2025-10-28 17:28:30] (step=0075000) Train Loss: 0.4418, Train Steps/Sec: 1.20
860
+ [2025-10-28 17:29:20] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-spatialpe-vit-b-bf16/checkpoints/0075000.pt
861
+ [2025-10-28 17:29:20] Generating EMA samples...
862
+ [2025-10-28 17:29:48] Generating EMA samples done.
863
+ [2025-10-28 17:30:39] Beginning epoch 60...
864
+ [2025-10-28 17:31:14] (step=0075100) Train Loss: 0.4446, Train Steps/Sec: 0.61
865
+ [2025-10-28 17:32:37] (step=0075200) Train Loss: 0.4439, Train Steps/Sec: 1.20
866
+ [2025-10-28 17:34:00] (step=0075300) Train Loss: 0.4424, Train Steps/Sec: 1.20
867
+ [2025-10-28 17:35:23] (step=0075400) Train Loss: 0.4420, Train Steps/Sec: 1.20
868
+ [2025-10-28 17:36:46] (step=0075500) Train Loss: 0.4428, Train Steps/Sec: 1.20
869
+ [2025-10-28 17:38:10] (step=0075600) Train Loss: 0.4420, Train Steps/Sec: 1.20
870
+ [2025-10-28 17:39:33] (step=0075700) Train Loss: 0.4438, Train Steps/Sec: 1.20
871
+ [2025-10-28 17:40:57] (step=0075800) Train Loss: 0.4418, Train Steps/Sec: 1.20
872
+ [2025-10-28 17:42:20] (step=0075900) Train Loss: 0.4419, Train Steps/Sec: 1.20
873
+ [2025-10-28 17:43:43] (step=0076000) Train Loss: 0.4439, Train Steps/Sec: 1.20
874
+ [2025-10-28 17:45:06] (step=0076100) Train Loss: 0.4419, Train Steps/Sec: 1.20
875
+ [2025-10-28 17:46:29] (step=0076200) Train Loss: 0.4414, Train Steps/Sec: 1.20
876
+ [2025-10-28 17:47:53] (step=0076300) Train Loss: 0.4424, Train Steps/Sec: 1.20
877
+ [2025-10-28 17:48:02] Beginning epoch 61...
878
+ [2025-10-28 17:49:18] (step=0076400) Train Loss: 0.4433, Train Steps/Sec: 1.17
879
+ [2025-10-28 17:50:41] (step=0076500) Train Loss: 0.4418, Train Steps/Sec: 1.20
880
+ [2025-10-28 17:52:05] (step=0076600) Train Loss: 0.4429, Train Steps/Sec: 1.20
881
+ [2025-10-28 17:53:28] (step=0076700) Train Loss: 0.4420, Train Steps/Sec: 1.20
882
+ [2025-10-28 17:54:51] (step=0076800) Train Loss: 0.4427, Train Steps/Sec: 1.20
883
+ [2025-10-28 17:56:14] (step=0076900) Train Loss: 0.4427, Train Steps/Sec: 1.20
884
+ [2025-10-28 17:57:38] (step=0077000) Train Loss: 0.4416, Train Steps/Sec: 1.20
885
+ [2025-10-28 17:59:01] (step=0077100) Train Loss: 0.4437, Train Steps/Sec: 1.20
886
+ [2025-10-28 18:00:24] (step=0077200) Train Loss: 0.4427, Train Steps/Sec: 1.20
887
+ [2025-10-28 18:01:48] (step=0077300) Train Loss: 0.4415, Train Steps/Sec: 1.19
888
+ [2025-10-28 18:03:11] (step=0077400) Train Loss: 0.4434, Train Steps/Sec: 1.20
889
+ [2025-10-28 18:04:34] (step=0077500) Train Loss: 0.4421, Train Steps/Sec: 1.20
890
+ [2025-10-28 18:05:26] Beginning epoch 62...
891
+ [2025-10-28 18:06:00] (step=0077600) Train Loss: 0.4407, Train Steps/Sec: 1.16
892
+ [2025-10-28 18:07:23] (step=0077700) Train Loss: 0.4426, Train Steps/Sec: 1.20
893
+ [2025-10-28 18:08:47] (step=0077800) Train Loss: 0.4415, Train Steps/Sec: 1.20
894
+ [2025-10-28 18:10:10] (step=0077900) Train Loss: 0.4423, Train Steps/Sec: 1.20
895
+ [2025-10-28 18:11:33] (step=0078000) Train Loss: 0.4416, Train Steps/Sec: 1.20
896
+ [2025-10-28 18:12:56] (step=0078100) Train Loss: 0.4421, Train Steps/Sec: 1.20
897
+ [2025-10-28 18:14:20] (step=0078200) Train Loss: 0.4434, Train Steps/Sec: 1.20
898
+ [2025-10-28 18:15:43] (step=0078300) Train Loss: 0.4425, Train Steps/Sec: 1.20
899
+ [2025-10-28 18:17:06] (step=0078400) Train Loss: 0.4411, Train Steps/Sec: 1.20
900
+ [2025-10-28 18:18:29] (step=0078500) Train Loss: 0.4410, Train Steps/Sec: 1.20
901
+ [2025-10-28 18:19:52] (step=0078600) Train Loss: 0.4410, Train Steps/Sec: 1.20
902
+ [2025-10-28 18:21:16] (step=0078700) Train Loss: 0.4420, Train Steps/Sec: 1.20
903
+ [2025-10-28 18:22:39] (step=0078800) Train Loss: 0.4414, Train Steps/Sec: 1.20
904
+ [2025-10-28 18:22:50] Beginning epoch 63...
905
+ [2025-10-28 18:24:04] (step=0078900) Train Loss: 0.4418, Train Steps/Sec: 1.17
906
+ [2025-10-28 18:25:28] (step=0079000) Train Loss: 0.4406, Train Steps/Sec: 1.19
907
+ [2025-10-28 18:26:52] (step=0079100) Train Loss: 0.4414, Train Steps/Sec: 1.20
908
+ [2025-10-28 18:28:15] (step=0079200) Train Loss: 0.4422, Train Steps/Sec: 1.20
909
+ [2025-10-28 18:29:38] (step=0079300) Train Loss: 0.4425, Train Steps/Sec: 1.20
910
+ [2025-10-28 18:31:01] (step=0079400) Train Loss: 0.4412, Train Steps/Sec: 1.20
911
+ [2025-10-28 18:32:24] (step=0079500) Train Loss: 0.4395, Train Steps/Sec: 1.20
912
+ [2025-10-28 18:33:48] (step=0079600) Train Loss: 0.4412, Train Steps/Sec: 1.20
913
+ [2025-10-28 18:35:11] (step=0079700) Train Loss: 0.4410, Train Steps/Sec: 1.20
914
+ [2025-10-28 18:36:34] (step=0079800) Train Loss: 0.4406, Train Steps/Sec: 1.20
915
+ [2025-10-28 18:37:57] (step=0079900) Train Loss: 0.4416, Train Steps/Sec: 1.20
916
+ [2025-10-28 18:39:20] (step=0080000) Train Loss: 0.4401, Train Steps/Sec: 1.20
917
+ [2025-10-28 18:40:14] Beginning epoch 64...
918
+ [2025-10-28 18:40:46] (step=0080100) Train Loss: 0.4424, Train Steps/Sec: 1.17
919
+ [2025-10-28 18:42:09] (step=0080200) Train Loss: 0.4411, Train Steps/Sec: 1.20
920
+ [2025-10-28 18:43:32] (step=0080300) Train Loss: 0.4420, Train Steps/Sec: 1.20
921
+ [2025-10-28 18:44:55] (step=0080400) Train Loss: 0.4426, Train Steps/Sec: 1.20
922
+ [2025-10-28 18:46:19] (step=0080500) Train Loss: 0.4420, Train Steps/Sec: 1.20
923
+ [2025-10-28 18:47:43] (step=0080600) Train Loss: 0.4423, Train Steps/Sec: 1.19
924
+ [2025-10-28 18:49:06] (step=0080700) Train Loss: 0.4431, Train Steps/Sec: 1.20
925
+ [2025-10-28 18:50:29] (step=0080800) Train Loss: 0.4409, Train Steps/Sec: 1.20
926
+ [2025-10-28 18:51:52] (step=0080900) Train Loss: 0.4424, Train Steps/Sec: 1.20
927
+ [2025-10-28 18:53:16] (step=0081000) Train Loss: 0.4427, Train Steps/Sec: 1.20
928
+ [2025-10-28 18:54:39] (step=0081100) Train Loss: 0.4431, Train Steps/Sec: 1.20
929
+ [2025-10-28 18:56:02] (step=0081200) Train Loss: 0.4418, Train Steps/Sec: 1.20
930
+ [2025-10-28 18:57:25] (step=0081300) Train Loss: 0.4416, Train Steps/Sec: 1.20
931
+ [2025-10-28 18:57:38] Beginning epoch 65...
932
+ [2025-10-28 18:58:51] (step=0081400) Train Loss: 0.4409, Train Steps/Sec: 1.17
933
+ [2025-10-28 19:00:14] (step=0081500) Train Loss: 0.4418, Train Steps/Sec: 1.20
934
+ [2025-10-28 19:01:37] (step=0081600) Train Loss: 0.4411, Train Steps/Sec: 1.20
935
+ [2025-10-28 19:03:01] (step=0081700) Train Loss: 0.4412, Train Steps/Sec: 1.20
936
+ [2025-10-28 19:04:24] (step=0081800) Train Loss: 0.4407, Train Steps/Sec: 1.20
937
+ [2025-10-28 19:05:47] (step=0081900) Train Loss: 0.4421, Train Steps/Sec: 1.20
938
+ [2025-10-28 19:07:10] (step=0082000) Train Loss: 0.4420, Train Steps/Sec: 1.20
939
+ [2025-10-28 19:08:34] (step=0082100) Train Loss: 0.4437, Train Steps/Sec: 1.20
940
+ [2025-10-28 19:09:57] (step=0082200) Train Loss: 0.4416, Train Steps/Sec: 1.20
941
+ [2025-10-28 19:11:21] (step=0082300) Train Loss: 0.4430, Train Steps/Sec: 1.19
942
+ [2025-10-28 19:12:44] (step=0082400) Train Loss: 0.4409, Train Steps/Sec: 1.20
943
+ [2025-10-28 19:14:08] (step=0082500) Train Loss: 0.4417, Train Steps/Sec: 1.20
944
+ [2025-10-28 19:15:03] Beginning epoch 66...
945
+ [2025-10-28 19:15:33] (step=0082600) Train Loss: 0.4421, Train Steps/Sec: 1.17
946
+ [2025-10-28 19:16:57] (step=0082700) Train Loss: 0.4424, Train Steps/Sec: 1.20
947
+ [2025-10-28 19:18:20] (step=0082800) Train Loss: 0.4411, Train Steps/Sec: 1.20
948
+ [2025-10-28 19:19:43] (step=0082900) Train Loss: 0.4425, Train Steps/Sec: 1.20
949
+ [2025-10-28 19:21:06] (step=0083000) Train Loss: 0.4396, Train Steps/Sec: 1.20
950
+ [2025-10-28 19:22:30] (step=0083100) Train Loss: 0.4402, Train Steps/Sec: 1.20
951
+ [2025-10-28 19:23:53] (step=0083200) Train Loss: 0.4421, Train Steps/Sec: 1.20
952
+ [2025-10-28 19:25:16] (step=0083300) Train Loss: 0.4413, Train Steps/Sec: 1.20
953
+ [2025-10-28 19:26:39] (step=0083400) Train Loss: 0.4422, Train Steps/Sec: 1.20
954
+ [2025-10-28 19:28:03] (step=0083500) Train Loss: 0.4413, Train Steps/Sec: 1.20
955
+ [2025-10-28 19:29:26] (step=0083600) Train Loss: 0.4406, Train Steps/Sec: 1.20
956
+ [2025-10-28 19:30:49] (step=0083700) Train Loss: 0.4414, Train Steps/Sec: 1.20
957
+ [2025-10-28 19:32:12] (step=0083800) Train Loss: 0.4410, Train Steps/Sec: 1.20
958
+ [2025-10-28 19:32:27] Beginning epoch 67...
959
+ [2025-10-28 19:33:38] (step=0083900) Train Loss: 0.4411, Train Steps/Sec: 1.16
960
+ [2025-10-28 19:35:02] (step=0084000) Train Loss: 0.4394, Train Steps/Sec: 1.19
961
+ [2025-10-28 19:36:25] (step=0084100) Train Loss: 0.4406, Train Steps/Sec: 1.20
962
+ [2025-10-28 19:37:48] (step=0084200) Train Loss: 0.4413, Train Steps/Sec: 1.20
963
+ [2025-10-28 19:39:12] (step=0084300) Train Loss: 0.4417, Train Steps/Sec: 1.20
964
+ [2025-10-28 19:40:35] (step=0084400) Train Loss: 0.4417, Train Steps/Sec: 1.20
965
+ [2025-10-28 19:41:58] (step=0084500) Train Loss: 0.4405, Train Steps/Sec: 1.20
966
+ [2025-10-28 19:43:21] (step=0084600) Train Loss: 0.4414, Train Steps/Sec: 1.20
967
+ [2025-10-28 19:44:44] (step=0084700) Train Loss: 0.4411, Train Steps/Sec: 1.20
968
+ [2025-10-28 19:46:08] (step=0084800) Train Loss: 0.4421, Train Steps/Sec: 1.20
969
+ [2025-10-28 19:47:31] (step=0084900) Train Loss: 0.4402, Train Steps/Sec: 1.20
970
+ [2025-10-28 19:48:54] (step=0085000) Train Loss: 0.4410, Train Steps/Sec: 1.20
971
+ [2025-10-28 19:49:51] Beginning epoch 68...
972
+ [2025-10-28 19:50:20] (step=0085100) Train Loss: 0.4411, Train Steps/Sec: 1.16
973
+ [2025-10-28 19:51:43] (step=0085200) Train Loss: 0.4388, Train Steps/Sec: 1.20
974
+ [2025-10-28 19:53:06] (step=0085300) Train Loss: 0.4405, Train Steps/Sec: 1.20
975
+ [2025-10-28 19:54:29] (step=0085400) Train Loss: 0.4422, Train Steps/Sec: 1.20
976
+ [2025-10-28 19:55:53] (step=0085500) Train Loss: 0.4416, Train Steps/Sec: 1.20
977
+ [2025-10-28 19:57:16] (step=0085600) Train Loss: 0.4417, Train Steps/Sec: 1.19
978
+ [2025-10-28 19:58:40] (step=0085700) Train Loss: 0.4394, Train Steps/Sec: 1.20
979
+ [2025-10-28 20:00:03] (step=0085800) Train Loss: 0.4402, Train Steps/Sec: 1.20
980
+ [2025-10-28 20:01:26] (step=0085900) Train Loss: 0.4392, Train Steps/Sec: 1.20
981
+ [2025-10-28 20:02:49] (step=0086000) Train Loss: 0.4414, Train Steps/Sec: 1.20
982
+ [2025-10-28 20:04:13] (step=0086100) Train Loss: 0.4405, Train Steps/Sec: 1.20
983
+ [2025-10-28 20:05:36] (step=0086200) Train Loss: 0.4436, Train Steps/Sec: 1.20
984
+ [2025-10-28 20:06:59] (step=0086300) Train Loss: 0.4411, Train Steps/Sec: 1.20
985
+ [2025-10-28 20:07:15] Beginning epoch 69...
986
+ [2025-10-28 20:08:25] (step=0086400) Train Loss: 0.4414, Train Steps/Sec: 1.17
987
+ [2025-10-28 20:09:48] (step=0086500) Train Loss: 0.4422, Train Steps/Sec: 1.20
988
+ [2025-10-28 20:11:11] (step=0086600) Train Loss: 0.4417, Train Steps/Sec: 1.20
989
+ [2025-10-28 20:12:34] (step=0086700) Train Loss: 0.4419, Train Steps/Sec: 1.20
990
+ [2025-10-28 20:13:57] (step=0086800) Train Loss: 0.4411, Train Steps/Sec: 1.20
991
+ [2025-10-28 20:15:21] (step=0086900) Train Loss: 0.4409, Train Steps/Sec: 1.20
992
+ [2025-10-28 20:16:44] (step=0087000) Train Loss: 0.4406, Train Steps/Sec: 1.20
993
+ [2025-10-28 20:18:07] (step=0087100) Train Loss: 0.4403, Train Steps/Sec: 1.20
994
+ [2025-10-28 20:19:30] (step=0087200) Train Loss: 0.4408, Train Steps/Sec: 1.20
995
+ [2025-10-28 20:20:54] (step=0087300) Train Loss: 0.4414, Train Steps/Sec: 1.19
996
+ [2025-10-28 20:22:17] (step=0087400) Train Loss: 0.4404, Train Steps/Sec: 1.20
997
+ [2025-10-28 20:23:41] (step=0087500) Train Loss: 0.4403, Train Steps/Sec: 1.20
998
+ [2025-10-28 20:24:39] Beginning epoch 70...
999
+ [2025-10-28 20:25:06] (step=0087600) Train Loss: 0.4411, Train Steps/Sec: 1.16
1000
+ [2025-10-28 20:26:30] (step=0087700) Train Loss: 0.4412, Train Steps/Sec: 1.20
1001
+ [2025-10-28 20:27:53] (step=0087800) Train Loss: 0.4403, Train Steps/Sec: 1.20
1002
+ [2025-10-28 20:29:16] (step=0087900) Train Loss: 0.4401, Train Steps/Sec: 1.20
1003
+ [2025-10-28 20:30:39] (step=0088000) Train Loss: 0.4402, Train Steps/Sec: 1.20
1004
+ [2025-10-28 20:32:02] (step=0088100) Train Loss: 0.4412, Train Steps/Sec: 1.20
1005
+ [2025-10-28 20:33:25] (step=0088200) Train Loss: 0.4397, Train Steps/Sec: 1.20
1006
+ [2025-10-28 20:34:48] (step=0088300) Train Loss: 0.4408, Train Steps/Sec: 1.20
1007
+ [2025-10-28 20:36:11] (step=0088400) Train Loss: 0.4390, Train Steps/Sec: 1.20
1008
+ [2025-10-28 20:37:34] (step=0088500) Train Loss: 0.4397, Train Steps/Sec: 1.20
1009
+ [2025-10-28 20:38:57] (step=0088600) Train Loss: 0.4404, Train Steps/Sec: 1.20
1010
+ [2025-10-28 20:40:20] (step=0088700) Train Loss: 0.4406, Train Steps/Sec: 1.20
1011
+ [2025-10-28 20:41:43] (step=0088800) Train Loss: 0.4412, Train Steps/Sec: 1.20
1012
+ [2025-10-28 20:42:01] Beginning epoch 71...
1013
+ [2025-10-28 20:43:10] (step=0088900) Train Loss: 0.4401, Train Steps/Sec: 1.16
1014
+ [2025-10-28 20:44:33] (step=0089000) Train Loss: 0.4399, Train Steps/Sec: 1.20
1015
+ [2025-10-28 20:45:56] (step=0089100) Train Loss: 0.4397, Train Steps/Sec: 1.20
1016
+ [2025-10-28 20:47:20] (step=0089200) Train Loss: 0.4403, Train Steps/Sec: 1.20
1017
+ [2025-10-28 20:48:43] (step=0089300) Train Loss: 0.4398, Train Steps/Sec: 1.20
1018
+ [2025-10-28 20:50:06] (step=0089400) Train Loss: 0.4410, Train Steps/Sec: 1.20
1019
+ [2025-10-28 20:51:29] (step=0089500) Train Loss: 0.4421, Train Steps/Sec: 1.20
1020
+ [2025-10-28 20:52:52] (step=0089600) Train Loss: 0.4417, Train Steps/Sec: 1.20
1021
+ [2025-10-28 20:54:16] (step=0089700) Train Loss: 0.4400, Train Steps/Sec: 1.20
1022
+ [2025-10-28 20:55:39] (step=0089800) Train Loss: 0.4390, Train Steps/Sec: 1.20
1023
+ [2025-10-28 20:57:02] (step=0089900) Train Loss: 0.4414, Train Steps/Sec: 1.20
1024
+ [2025-10-28 20:58:25] (step=0090000) Train Loss: 0.4408, Train Steps/Sec: 1.20
1025
+ [2025-10-28 20:59:25] Beginning epoch 72...
1026
+ [2025-10-28 20:59:51] (step=0090100) Train Loss: 0.4400, Train Steps/Sec: 1.17
1027
+ [2025-10-28 21:01:14] (step=0090200) Train Loss: 0.4419, Train Steps/Sec: 1.20
1028
+ [2025-10-28 21:02:37] (step=0090300) Train Loss: 0.4392, Train Steps/Sec: 1.20
1029
+ [2025-10-28 21:04:00] (step=0090400) Train Loss: 0.4393, Train Steps/Sec: 1.20
1030
+ [2025-10-28 21:05:24] (step=0090500) Train Loss: 0.4389, Train Steps/Sec: 1.20
1031
+ [2025-10-28 21:06:48] (step=0090600) Train Loss: 0.4387, Train Steps/Sec: 1.19
1032
+ [2025-10-28 21:08:11] (step=0090700) Train Loss: 0.4408, Train Steps/Sec: 1.20
1033
+ [2025-10-28 21:09:34] (step=0090800) Train Loss: 0.4408, Train Steps/Sec: 1.20
1034
+ [2025-10-28 21:10:57] (step=0090900) Train Loss: 0.4403, Train Steps/Sec: 1.20
1035
+ [2025-10-28 21:12:20] (step=0091000) Train Loss: 0.4383, Train Steps/Sec: 1.20
1036
+ [2025-10-28 21:13:43] (step=0091100) Train Loss: 0.4406, Train Steps/Sec: 1.20
1037
+ [2025-10-28 21:15:06] (step=0091200) Train Loss: 0.4398, Train Steps/Sec: 1.20
1038
+ [2025-10-28 21:16:29] (step=0091300) Train Loss: 0.4392, Train Steps/Sec: 1.20
1039
+ [2025-10-28 21:16:49] Beginning epoch 73...
1040
+ [2025-10-28 21:17:55] (step=0091400) Train Loss: 0.4400, Train Steps/Sec: 1.17
1041
+ [2025-10-28 21:19:18] (step=0091500) Train Loss: 0.4404, Train Steps/Sec: 1.20
1042
+ [2025-10-28 21:20:42] (step=0091600) Train Loss: 0.4383, Train Steps/Sec: 1.20
1043
+ [2025-10-28 21:22:05] (step=0091700) Train Loss: 0.4388, Train Steps/Sec: 1.20
1044
+ [2025-10-28 21:23:28] (step=0091800) Train Loss: 0.4376, Train Steps/Sec: 1.20
1045
+ [2025-10-28 21:24:52] (step=0091900) Train Loss: 0.4400, Train Steps/Sec: 1.20
1046
+ [2025-10-28 21:26:15] (step=0092000) Train Loss: 0.4389, Train Steps/Sec: 1.20
1047
+ [2025-10-28 21:27:38] (step=0092100) Train Loss: 0.4373, Train Steps/Sec: 1.20
1048
+ [2025-10-28 21:29:01] (step=0092200) Train Loss: 0.4409, Train Steps/Sec: 1.20
1049
+ [2025-10-28 21:30:25] (step=0092300) Train Loss: 0.4419, Train Steps/Sec: 1.19
1050
+ [2025-10-28 21:31:48] (step=0092400) Train Loss: 0.4399, Train Steps/Sec: 1.20
1051
+ [2025-10-28 21:33:12] (step=0092500) Train Loss: 0.4401, Train Steps/Sec: 1.20
1052
+ [2025-10-28 21:34:14] Beginning epoch 74...
1053
+ [2025-10-28 21:34:38] (step=0092600) Train Loss: 0.4393, Train Steps/Sec: 1.16
1054
+ [2025-10-28 21:36:01] (step=0092700) Train Loss: 0.4395, Train Steps/Sec: 1.20
1055
+ [2025-10-28 21:37:24] (step=0092800) Train Loss: 0.4400, Train Steps/Sec: 1.20
1056
+ [2025-10-28 21:38:47] (step=0092900) Train Loss: 0.4408, Train Steps/Sec: 1.20
1057
+ [2025-10-28 21:40:10] (step=0093000) Train Loss: 0.4406, Train Steps/Sec: 1.20
1058
+ [2025-10-28 21:41:34] (step=0093100) Train Loss: 0.4397, Train Steps/Sec: 1.20
1059
+ [2025-10-28 21:42:57] (step=0093200) Train Loss: 0.4408, Train Steps/Sec: 1.20
1060
+ [2025-10-28 21:44:20] (step=0093300) Train Loss: 0.4392, Train Steps/Sec: 1.20
1061
+ [2025-10-28 21:45:43] (step=0093400) Train Loss: 0.4403, Train Steps/Sec: 1.20
1062
+ [2025-10-28 21:47:06] (step=0093500) Train Loss: 0.4387, Train Steps/Sec: 1.20
1063
+ [2025-10-28 21:48:30] (step=0093600) Train Loss: 0.4394, Train Steps/Sec: 1.20
1064
+ [2025-10-28 21:49:53] (step=0093700) Train Loss: 0.4413, Train Steps/Sec: 1.20
1065
+ [2025-10-28 21:51:16] (step=0093800) Train Loss: 0.4392, Train Steps/Sec: 1.20
1066
+ [2025-10-28 21:51:38] Beginning epoch 75...
1067
+ [2025-10-28 21:52:43] (step=0093900) Train Loss: 0.4394, Train Steps/Sec: 1.16
1068
+ [2025-10-28 21:54:06] (step=0094000) Train Loss: 0.4391, Train Steps/Sec: 1.20
1069
+ [2025-10-28 21:55:29] (step=0094100) Train Loss: 0.4405, Train Steps/Sec: 1.20
1070
+ [2025-10-28 21:56:52] (step=0094200) Train Loss: 0.4396, Train Steps/Sec: 1.20
1071
+ [2025-10-28 21:58:16] (step=0094300) Train Loss: 0.4390, Train Steps/Sec: 1.20
1072
+ [2025-10-28 21:59:39] (step=0094400) Train Loss: 0.4397, Train Steps/Sec: 1.20
1073
+ [2025-10-28 22:01:02] (step=0094500) Train Loss: 0.4390, Train Steps/Sec: 1.20
1074
+ [2025-10-28 22:02:25] (step=0094600) Train Loss: 0.4384, Train Steps/Sec: 1.20
1075
+ [2025-10-28 22:03:48] (step=0094700) Train Loss: 0.4418, Train Steps/Sec: 1.20
1076
+ [2025-10-28 22:05:12] (step=0094800) Train Loss: 0.4388, Train Steps/Sec: 1.20
1077
+ [2025-10-28 22:06:35] (step=0094900) Train Loss: 0.4394, Train Steps/Sec: 1.20
1078
+ [2025-10-28 22:07:58] (step=0095000) Train Loss: 0.4397, Train Steps/Sec: 1.20
1079
+ [2025-10-28 22:09:01] Beginning epoch 76...
1080
+ [2025-10-28 22:09:24] (step=0095100) Train Loss: 0.4391, Train Steps/Sec: 1.17
1081
+ [2025-10-28 22:10:47] (step=0095200) Train Loss: 0.4411, Train Steps/Sec: 1.20
1082
+ [2025-10-28 22:12:10] (step=0095300) Train Loss: 0.4383, Train Steps/Sec: 1.20
1083
+ [2025-10-28 22:13:33] (step=0095400) Train Loss: 0.4386, Train Steps/Sec: 1.20
1084
+ [2025-10-28 22:14:56] (step=0095500) Train Loss: 0.4389, Train Steps/Sec: 1.20
1085
+ [2025-10-28 22:16:20] (step=0095600) Train Loss: 0.4396, Train Steps/Sec: 1.19
1086
+ [2025-10-28 22:17:44] (step=0095700) Train Loss: 0.4393, Train Steps/Sec: 1.20
1087
+ [2025-10-28 22:19:07] (step=0095800) Train Loss: 0.4392, Train Steps/Sec: 1.20
1088
+ [2025-10-28 22:20:30] (step=0095900) Train Loss: 0.4387, Train Steps/Sec: 1.20
1089
+ [2025-10-28 22:21:53] (step=0096000) Train Loss: 0.4397, Train Steps/Sec: 1.20
1090
+ [2025-10-28 22:23:16] (step=0096100) Train Loss: 0.4406, Train Steps/Sec: 1.20
1091
+ [2025-10-28 22:24:39] (step=0096200) Train Loss: 0.4395, Train Steps/Sec: 1.20
1092
+ [2025-10-28 22:26:03] (step=0096300) Train Loss: 0.4391, Train Steps/Sec: 1.20
1093
+ [2025-10-28 22:26:25] Beginning epoch 77...
1094
+ [2025-10-28 22:27:28] (step=0096400) Train Loss: 0.4383, Train Steps/Sec: 1.16
1095
+ [2025-10-28 22:28:52] (step=0096500) Train Loss: 0.4391, Train Steps/Sec: 1.20
1096
+ [2025-10-28 22:30:15] (step=0096600) Train Loss: 0.4389, Train Steps/Sec: 1.20
1097
+ [2025-10-28 22:31:38] (step=0096700) Train Loss: 0.4386, Train Steps/Sec: 1.20
1098
+ [2025-10-28 22:33:01] (step=0096800) Train Loss: 0.4393, Train Steps/Sec: 1.20
1099
+ [2025-10-28 22:34:24] (step=0096900) Train Loss: 0.4385, Train Steps/Sec: 1.20
1100
+ [2025-10-28 22:35:48] (step=0097000) Train Loss: 0.4389, Train Steps/Sec: 1.20
1101
+ [2025-10-28 22:37:11] (step=0097100) Train Loss: 0.4398, Train Steps/Sec: 1.20
1102
+ [2025-10-28 22:38:34] (step=0097200) Train Loss: 0.4402, Train Steps/Sec: 1.20
1103
+ [2025-10-28 22:39:58] (step=0097300) Train Loss: 0.4388, Train Steps/Sec: 1.19
1104
+ [2025-10-28 22:41:21] (step=0097400) Train Loss: 0.4391, Train Steps/Sec: 1.20
1105
+ [2025-10-28 22:42:44] (step=0097500) Train Loss: 0.4384, Train Steps/Sec: 1.20
1106
+ [2025-10-28 22:43:50] Beginning epoch 78...
1107
+ [2025-10-28 22:44:10] (step=0097600) Train Loss: 0.4390, Train Steps/Sec: 1.17