Upload folder using huggingface_hub
Browse files
stage2/lightningdit-xl-dinov2-vit-b-spnorm-bf16/checkpoints/0025000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63228a266967cbd4cdc839024da6f873783dc59cd78d3661b3ff9203bf8fd7a5
|
| 3 |
+
size 19230431602
|
stage2/lightningdit-xl-dinov2-vit-b-spnorm-bf16/checkpoints/0050000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41625701742316173981378d494c7be04d2700b5d4321889a2afae2a226c75bd
|
| 3 |
+
size 19230431602
|
stage2/lightningdit-xl-dinov2-vit-b-spnorm-bf16/log.txt
ADDED
|
@@ -0,0 +1,644 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[[34m2025-10-29 12:45:31[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-spnorm-bf16
|
| 2 |
+
[[34m2025-10-29 12:45:33[0m] using MLP layer as FFN
|
| 3 |
+
[[34m2025-10-29 12:45:50[0m] Model Parameters: 1202.04M
|
| 4 |
+
[[34m2025-10-29 12:45:53[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/train)
|
| 5 |
+
[[34m2025-10-29 12:45:53[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 6 |
+
[[34m2025-10-29 12:45:53[0m] Precision mode: bf16
|
| 7 |
+
[[34m2025-10-29 12:45:53[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 8 |
+
[[34m2025-10-29 12:45:53[0m] Optimizer: ADAMW with lr=0.0002, betas=(0.9, 0.95), weight_decay=0.0, eps=1e-08
|
| 9 |
+
Scheduler: linear with warmup_steps=0, decay_end_steps=0, final_lr=0.0002
|
| 10 |
+
[[34m2025-10-29 12:45:53[0m] Training for 80 epochs...
|
| 11 |
+
[[34m2025-10-29 12:45:53[0m] Beginning epoch 0...
|
| 12 |
+
[[34m2025-10-29 13:34:00[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-spnorm-bf16
|
| 13 |
+
[[34m2025-10-29 13:34:03[0m] using MLP layer as FFN
|
| 14 |
+
[[34m2025-10-29 13:34:19[0m] Model Parameters: 1202.04M
|
| 15 |
+
[[34m2025-10-29 13:34:23[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/train)
|
| 16 |
+
[[34m2025-10-29 13:34:23[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 17 |
+
[[34m2025-10-29 13:34:23[0m] Precision mode: bf16
|
| 18 |
+
[[34m2025-10-29 13:34:23[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 19 |
+
[[34m2025-10-29 13:34:23[0m] Optimizer: ADAMW with lr=0.0002, betas=(0.9, 0.95), weight_decay=0.0, eps=1e-08
|
| 20 |
+
Scheduler: linear with warmup_steps=0, decay_end_steps=0, final_lr=0.0002
|
| 21 |
+
[[34m2025-10-29 13:34:23[0m] Training for 80 epochs...
|
| 22 |
+
[[34m2025-10-29 13:34:23[0m] Beginning epoch 0...
|
| 23 |
+
[[34m2025-10-29 13:34:28[0m] Generating EMA samples...
|
| 24 |
+
[[34m2025-10-29 13:34:57[0m] Generating EMA samples done.
|
| 25 |
+
[[34m2025-10-29 13:36:16[0m] (step=0000100) Train Loss: 1.5578, Train Steps/Sec: 0.88
|
| 26 |
+
[[34m2025-10-29 13:37:38[0m] (step=0000200) Train Loss: 1.3409, Train Steps/Sec: 1.23
|
| 27 |
+
[[34m2025-10-29 13:38:59[0m] (step=0000300) Train Loss: 1.2296, Train Steps/Sec: 1.23
|
| 28 |
+
[[34m2025-10-29 13:40:21[0m] (step=0000400) Train Loss: 1.1006, Train Steps/Sec: 1.23
|
| 29 |
+
[[34m2025-10-29 13:41:42[0m] (step=0000500) Train Loss: 1.0210, Train Steps/Sec: 1.23
|
| 30 |
+
[[34m2025-10-29 13:43:04[0m] (step=0000600) Train Loss: 0.9725, Train Steps/Sec: 1.23
|
| 31 |
+
[[34m2025-10-29 13:44:25[0m] (step=0000700) Train Loss: 0.9370, Train Steps/Sec: 1.22
|
| 32 |
+
[[34m2025-10-29 13:45:47[0m] (step=0000800) Train Loss: 0.9114, Train Steps/Sec: 1.23
|
| 33 |
+
[[34m2025-10-29 13:47:08[0m] (step=0000900) Train Loss: 0.8913, Train Steps/Sec: 1.23
|
| 34 |
+
[[34m2025-10-29 13:48:30[0m] (step=0001000) Train Loss: 0.8737, Train Steps/Sec: 1.22
|
| 35 |
+
[[34m2025-10-29 13:49:52[0m] (step=0001100) Train Loss: 0.8584, Train Steps/Sec: 1.23
|
| 36 |
+
[[34m2025-10-29 13:51:13[0m] (step=0001200) Train Loss: 0.8452, Train Steps/Sec: 1.23
|
| 37 |
+
[[34m2025-10-29 13:51:55[0m] Beginning epoch 1...
|
| 38 |
+
[[34m2025-10-29 13:52:37[0m] (step=0001300) Train Loss: 0.8344, Train Steps/Sec: 1.19
|
| 39 |
+
[[34m2025-10-29 13:53:59[0m] (step=0001400) Train Loss: 0.8252, Train Steps/Sec: 1.23
|
| 40 |
+
[[34m2025-10-29 13:55:20[0m] (step=0001500) Train Loss: 0.8152, Train Steps/Sec: 1.23
|
| 41 |
+
[[34m2025-10-29 13:56:42[0m] (step=0001600) Train Loss: 0.8079, Train Steps/Sec: 1.23
|
| 42 |
+
[[34m2025-10-29 13:58:03[0m] (step=0001700) Train Loss: 0.8022, Train Steps/Sec: 1.23
|
| 43 |
+
[[34m2025-10-29 13:59:25[0m] (step=0001800) Train Loss: 0.7955, Train Steps/Sec: 1.23
|
| 44 |
+
[[34m2025-10-29 14:00:47[0m] (step=0001900) Train Loss: 0.7895, Train Steps/Sec: 1.23
|
| 45 |
+
[[34m2025-10-29 14:02:08[0m] (step=0002000) Train Loss: 0.7850, Train Steps/Sec: 1.23
|
| 46 |
+
[[34m2025-10-29 14:03:30[0m] (step=0002100) Train Loss: 0.7789, Train Steps/Sec: 1.22
|
| 47 |
+
[[34m2025-10-29 14:04:51[0m] (step=0002200) Train Loss: 0.7756, Train Steps/Sec: 1.23
|
| 48 |
+
[[34m2025-10-29 14:06:13[0m] (step=0002300) Train Loss: 0.7714, Train Steps/Sec: 1.23
|
| 49 |
+
[[34m2025-10-29 14:07:34[0m] (step=0002400) Train Loss: 0.7682, Train Steps/Sec: 1.23
|
| 50 |
+
[[34m2025-10-29 14:08:56[0m] (step=0002500) Train Loss: 0.7638, Train Steps/Sec: 1.23
|
| 51 |
+
[[34m2025-10-29 14:08:58[0m] Beginning epoch 2...
|
| 52 |
+
[[34m2025-10-29 14:10:21[0m] (step=0002600) Train Loss: 0.7593, Train Steps/Sec: 1.18
|
| 53 |
+
[[34m2025-10-29 14:11:42[0m] (step=0002700) Train Loss: 0.7569, Train Steps/Sec: 1.23
|
| 54 |
+
[[34m2025-10-29 14:13:04[0m] (step=0002800) Train Loss: 0.7557, Train Steps/Sec: 1.23
|
| 55 |
+
[[34m2025-10-29 14:14:25[0m] (step=0002900) Train Loss: 0.7527, Train Steps/Sec: 1.23
|
| 56 |
+
[[34m2025-10-29 14:15:47[0m] (step=0003000) Train Loss: 0.7487, Train Steps/Sec: 1.23
|
| 57 |
+
[[34m2025-10-29 14:17:08[0m] (step=0003100) Train Loss: 0.7476, Train Steps/Sec: 1.23
|
| 58 |
+
[[34m2025-10-29 14:18:30[0m] (step=0003200) Train Loss: 0.7448, Train Steps/Sec: 1.23
|
| 59 |
+
[[34m2025-10-29 14:19:51[0m] (step=0003300) Train Loss: 0.7429, Train Steps/Sec: 1.23
|
| 60 |
+
[[34m2025-10-29 14:21:13[0m] (step=0003400) Train Loss: 0.7398, Train Steps/Sec: 1.23
|
| 61 |
+
[[34m2025-10-29 14:22:35[0m] (step=0003500) Train Loss: 0.7391, Train Steps/Sec: 1.22
|
| 62 |
+
[[34m2025-10-29 14:23:56[0m] (step=0003600) Train Loss: 0.7363, Train Steps/Sec: 1.23
|
| 63 |
+
[[34m2025-10-29 14:25:18[0m] (step=0003700) Train Loss: 0.7352, Train Steps/Sec: 1.23
|
| 64 |
+
[[34m2025-10-29 14:26:02[0m] Beginning epoch 3...
|
| 65 |
+
[[34m2025-10-29 14:26:42[0m] (step=0003800) Train Loss: 0.7329, Train Steps/Sec: 1.19
|
| 66 |
+
[[34m2025-10-29 14:28:04[0m] (step=0003900) Train Loss: 0.7303, Train Steps/Sec: 1.23
|
| 67 |
+
[[34m2025-10-29 14:29:25[0m] (step=0004000) Train Loss: 0.7298, Train Steps/Sec: 1.23
|
| 68 |
+
[[34m2025-10-29 14:30:47[0m] (step=0004100) Train Loss: 0.7292, Train Steps/Sec: 1.23
|
| 69 |
+
[[34m2025-10-29 14:32:08[0m] (step=0004200) Train Loss: 0.7269, Train Steps/Sec: 1.23
|
| 70 |
+
[[34m2025-10-29 14:33:30[0m] (step=0004300) Train Loss: 0.7250, Train Steps/Sec: 1.22
|
| 71 |
+
[[34m2025-10-29 14:34:52[0m] (step=0004400) Train Loss: 0.7230, Train Steps/Sec: 1.23
|
| 72 |
+
[[34m2025-10-29 14:36:14[0m] (step=0004500) Train Loss: 0.7228, Train Steps/Sec: 1.23
|
| 73 |
+
[[34m2025-10-29 14:37:35[0m] (step=0004600) Train Loss: 0.7212, Train Steps/Sec: 1.23
|
| 74 |
+
[[34m2025-10-29 14:38:57[0m] (step=0004700) Train Loss: 0.7205, Train Steps/Sec: 1.23
|
| 75 |
+
[[34m2025-10-29 14:40:18[0m] (step=0004800) Train Loss: 0.7184, Train Steps/Sec: 1.23
|
| 76 |
+
[[34m2025-10-29 14:41:40[0m] (step=0004900) Train Loss: 0.7168, Train Steps/Sec: 1.22
|
| 77 |
+
[[34m2025-10-29 14:43:02[0m] (step=0005000) Train Loss: 0.7164, Train Steps/Sec: 1.23
|
| 78 |
+
[[34m2025-10-29 14:43:05[0m] Beginning epoch 4...
|
| 79 |
+
[[34m2025-10-29 14:44:25[0m] (step=0005100) Train Loss: 0.7141, Train Steps/Sec: 1.19
|
| 80 |
+
[[34m2025-10-29 14:45:47[0m] (step=0005200) Train Loss: 0.7143, Train Steps/Sec: 1.23
|
| 81 |
+
[[34m2025-10-29 14:47:09[0m] (step=0005300) Train Loss: 0.7137, Train Steps/Sec: 1.23
|
| 82 |
+
[[34m2025-10-29 14:48:30[0m] (step=0005400) Train Loss: 0.7111, Train Steps/Sec: 1.23
|
| 83 |
+
[[34m2025-10-29 14:49:52[0m] (step=0005500) Train Loss: 0.7103, Train Steps/Sec: 1.23
|
| 84 |
+
[[34m2025-10-29 14:51:13[0m] (step=0005600) Train Loss: 0.7097, Train Steps/Sec: 1.23
|
| 85 |
+
[[34m2025-10-29 14:52:35[0m] (step=0005700) Train Loss: 0.7081, Train Steps/Sec: 1.23
|
| 86 |
+
[[34m2025-10-29 14:53:56[0m] (step=0005800) Train Loss: 0.7089, Train Steps/Sec: 1.23
|
| 87 |
+
[[34m2025-10-29 14:55:18[0m] (step=0005900) Train Loss: 0.7071, Train Steps/Sec: 1.23
|
| 88 |
+
[[34m2025-10-29 14:56:40[0m] (step=0006000) Train Loss: 0.7061, Train Steps/Sec: 1.22
|
| 89 |
+
[[34m2025-10-29 14:58:02[0m] (step=0006100) Train Loss: 0.7053, Train Steps/Sec: 1.23
|
| 90 |
+
[[34m2025-10-29 14:59:23[0m] (step=0006200) Train Loss: 0.7042, Train Steps/Sec: 1.23
|
| 91 |
+
[[34m2025-10-29 15:00:08[0m] Beginning epoch 5...
|
| 92 |
+
[[34m2025-10-29 15:00:47[0m] (step=0006300) Train Loss: 0.7039, Train Steps/Sec: 1.19
|
| 93 |
+
[[34m2025-10-29 15:02:09[0m] (step=0006400) Train Loss: 0.7018, Train Steps/Sec: 1.23
|
| 94 |
+
[[34m2025-10-29 15:03:30[0m] (step=0006500) Train Loss: 0.7000, Train Steps/Sec: 1.23
|
| 95 |
+
[[34m2025-10-29 15:04:52[0m] (step=0006600) Train Loss: 0.7007, Train Steps/Sec: 1.23
|
| 96 |
+
[[34m2025-10-29 15:06:13[0m] (step=0006700) Train Loss: 0.6998, Train Steps/Sec: 1.23
|
| 97 |
+
[[34m2025-10-29 15:07:35[0m] (step=0006800) Train Loss: 0.6983, Train Steps/Sec: 1.23
|
| 98 |
+
[[34m2025-10-29 15:08:56[0m] (step=0006900) Train Loss: 0.6984, Train Steps/Sec: 1.23
|
| 99 |
+
[[34m2025-10-29 15:10:18[0m] (step=0007000) Train Loss: 0.6983, Train Steps/Sec: 1.23
|
| 100 |
+
[[34m2025-10-29 15:11:39[0m] (step=0007100) Train Loss: 0.6974, Train Steps/Sec: 1.23
|
| 101 |
+
[[34m2025-10-29 15:13:01[0m] (step=0007200) Train Loss: 0.6968, Train Steps/Sec: 1.23
|
| 102 |
+
[[34m2025-10-29 15:14:23[0m] (step=0007300) Train Loss: 0.6942, Train Steps/Sec: 1.23
|
| 103 |
+
[[34m2025-10-29 15:15:44[0m] (step=0007400) Train Loss: 0.6956, Train Steps/Sec: 1.23
|
| 104 |
+
[[34m2025-10-29 15:17:06[0m] (step=0007500) Train Loss: 0.6939, Train Steps/Sec: 1.23
|
| 105 |
+
[[34m2025-10-29 15:17:11[0m] Beginning epoch 6...
|
| 106 |
+
[[34m2025-10-29 15:18:30[0m] (step=0007600) Train Loss: 0.6931, Train Steps/Sec: 1.19
|
| 107 |
+
[[34m2025-10-29 15:19:52[0m] (step=0007700) Train Loss: 0.6929, Train Steps/Sec: 1.22
|
| 108 |
+
[[34m2025-10-29 15:21:13[0m] (step=0007800) Train Loss: 0.6926, Train Steps/Sec: 1.23
|
| 109 |
+
[[34m2025-10-29 15:22:35[0m] (step=0007900) Train Loss: 0.6928, Train Steps/Sec: 1.23
|
| 110 |
+
[[34m2025-10-29 15:23:56[0m] (step=0008000) Train Loss: 0.6915, Train Steps/Sec: 1.23
|
| 111 |
+
[[34m2025-10-29 15:25:18[0m] (step=0008100) Train Loss: 0.6900, Train Steps/Sec: 1.23
|
| 112 |
+
[[34m2025-10-29 15:26:40[0m] (step=0008200) Train Loss: 0.6891, Train Steps/Sec: 1.23
|
| 113 |
+
[[34m2025-10-29 15:28:01[0m] (step=0008300) Train Loss: 0.6890, Train Steps/Sec: 1.23
|
| 114 |
+
[[34m2025-10-29 15:29:23[0m] (step=0008400) Train Loss: 0.6879, Train Steps/Sec: 1.23
|
| 115 |
+
[[34m2025-10-29 15:30:44[0m] (step=0008500) Train Loss: 0.6877, Train Steps/Sec: 1.23
|
| 116 |
+
[[34m2025-10-29 15:32:06[0m] (step=0008600) Train Loss: 0.6874, Train Steps/Sec: 1.23
|
| 117 |
+
[[34m2025-10-29 15:33:27[0m] (step=0008700) Train Loss: 0.6875, Train Steps/Sec: 1.23
|
| 118 |
+
[[34m2025-10-29 15:34:14[0m] Beginning epoch 7...
|
| 119 |
+
[[34m2025-10-29 15:34:51[0m] (step=0008800) Train Loss: 0.6867, Train Steps/Sec: 1.19
|
| 120 |
+
[[34m2025-10-29 15:36:13[0m] (step=0008900) Train Loss: 0.6851, Train Steps/Sec: 1.23
|
| 121 |
+
[[34m2025-10-29 15:37:34[0m] (step=0009000) Train Loss: 0.6839, Train Steps/Sec: 1.23
|
| 122 |
+
[[34m2025-10-29 15:38:56[0m] (step=0009100) Train Loss: 0.6849, Train Steps/Sec: 1.23
|
| 123 |
+
[[34m2025-10-29 15:40:18[0m] (step=0009200) Train Loss: 0.6850, Train Steps/Sec: 1.22
|
| 124 |
+
[[34m2025-10-29 15:41:40[0m] (step=0009300) Train Loss: 0.6840, Train Steps/Sec: 1.21
|
| 125 |
+
[[34m2025-10-29 15:43:02[0m] (step=0009400) Train Loss: 0.6843, Train Steps/Sec: 1.23
|
| 126 |
+
[[34m2025-10-29 15:44:23[0m] (step=0009500) Train Loss: 0.6821, Train Steps/Sec: 1.23
|
| 127 |
+
[[34m2025-10-29 15:45:45[0m] (step=0009600) Train Loss: 0.6814, Train Steps/Sec: 1.23
|
| 128 |
+
[[34m2025-10-29 15:47:06[0m] (step=0009700) Train Loss: 0.6825, Train Steps/Sec: 1.23
|
| 129 |
+
[[34m2025-10-29 15:48:28[0m] (step=0009800) Train Loss: 0.6809, Train Steps/Sec: 1.23
|
| 130 |
+
[[34m2025-10-29 15:49:49[0m] (step=0009900) Train Loss: 0.6809, Train Steps/Sec: 1.23
|
| 131 |
+
[[34m2025-10-29 15:51:11[0m] (step=0010000) Train Loss: 0.6798, Train Steps/Sec: 1.23
|
| 132 |
+
[[34m2025-10-29 15:51:18[0m] Beginning epoch 8...
|
| 133 |
+
[[34m2025-10-29 15:52:35[0m] (step=0010100) Train Loss: 0.6788, Train Steps/Sec: 1.19
|
| 134 |
+
[[34m2025-10-29 15:53:57[0m] (step=0010200) Train Loss: 0.6787, Train Steps/Sec: 1.23
|
| 135 |
+
[[34m2025-10-29 15:55:18[0m] (step=0010300) Train Loss: 0.6778, Train Steps/Sec: 1.23
|
| 136 |
+
[[34m2025-10-29 15:56:40[0m] (step=0010400) Train Loss: 0.6791, Train Steps/Sec: 1.23
|
| 137 |
+
[[34m2025-10-29 15:58:01[0m] (step=0010500) Train Loss: 0.6768, Train Steps/Sec: 1.23
|
| 138 |
+
[[34m2025-10-29 15:59:23[0m] (step=0010600) Train Loss: 0.6769, Train Steps/Sec: 1.22
|
| 139 |
+
[[34m2025-10-29 16:00:44[0m] (step=0010700) Train Loss: 0.6754, Train Steps/Sec: 1.23
|
| 140 |
+
[[34m2025-10-29 16:02:06[0m] (step=0010800) Train Loss: 0.6761, Train Steps/Sec: 1.23
|
| 141 |
+
[[34m2025-10-29 16:03:28[0m] (step=0010900) Train Loss: 0.6763, Train Steps/Sec: 1.23
|
| 142 |
+
[[34m2025-10-29 16:04:50[0m] (step=0011000) Train Loss: 0.6751, Train Steps/Sec: 1.21
|
| 143 |
+
[[34m2025-10-29 16:06:12[0m] (step=0011100) Train Loss: 0.6753, Train Steps/Sec: 1.23
|
| 144 |
+
[[34m2025-10-29 16:07:33[0m] (step=0011200) Train Loss: 0.6760, Train Steps/Sec: 1.23
|
| 145 |
+
[[34m2025-10-29 16:08:22[0m] Beginning epoch 9...
|
| 146 |
+
[[34m2025-10-29 16:08:57[0m] (step=0011300) Train Loss: 0.6740, Train Steps/Sec: 1.19
|
| 147 |
+
[[34m2025-10-29 16:10:19[0m] (step=0011400) Train Loss: 0.6743, Train Steps/Sec: 1.23
|
| 148 |
+
[[34m2025-10-29 16:11:40[0m] (step=0011500) Train Loss: 0.6729, Train Steps/Sec: 1.23
|
| 149 |
+
[[34m2025-10-29 16:13:02[0m] (step=0011600) Train Loss: 0.6722, Train Steps/Sec: 1.23
|
| 150 |
+
[[34m2025-10-29 16:14:23[0m] (step=0011700) Train Loss: 0.6734, Train Steps/Sec: 1.23
|
| 151 |
+
[[34m2025-10-29 16:15:45[0m] (step=0011800) Train Loss: 0.6720, Train Steps/Sec: 1.23
|
| 152 |
+
[[34m2025-10-29 16:17:06[0m] (step=0011900) Train Loss: 0.6726, Train Steps/Sec: 1.23
|
| 153 |
+
[[34m2025-10-29 16:18:28[0m] (step=0012000) Train Loss: 0.6708, Train Steps/Sec: 1.22
|
| 154 |
+
[[34m2025-10-29 16:19:50[0m] (step=0012100) Train Loss: 0.6709, Train Steps/Sec: 1.23
|
| 155 |
+
[[34m2025-10-29 16:21:11[0m] (step=0012200) Train Loss: 0.6708, Train Steps/Sec: 1.23
|
| 156 |
+
[[34m2025-10-29 16:22:33[0m] (step=0012300) Train Loss: 0.6692, Train Steps/Sec: 1.23
|
| 157 |
+
[[34m2025-10-29 16:23:54[0m] (step=0012400) Train Loss: 0.6691, Train Steps/Sec: 1.23
|
| 158 |
+
[[34m2025-10-29 16:25:16[0m] (step=0012500) Train Loss: 0.6697, Train Steps/Sec: 1.23
|
| 159 |
+
[[34m2025-10-29 16:25:24[0m] Beginning epoch 10...
|
| 160 |
+
[[34m2025-10-29 16:26:40[0m] (step=0012600) Train Loss: 0.6676, Train Steps/Sec: 1.19
|
| 161 |
+
[[34m2025-10-29 16:28:02[0m] (step=0012700) Train Loss: 0.6686, Train Steps/Sec: 1.21
|
| 162 |
+
[[34m2025-10-29 16:29:23[0m] (step=0012800) Train Loss: 0.6688, Train Steps/Sec: 1.23
|
| 163 |
+
[[34m2025-10-29 16:30:45[0m] (step=0012900) Train Loss: 0.6676, Train Steps/Sec: 1.23
|
| 164 |
+
[[34m2025-10-29 16:32:07[0m] (step=0013000) Train Loss: 0.6664, Train Steps/Sec: 1.23
|
| 165 |
+
[[34m2025-10-29 16:33:28[0m] (step=0013100) Train Loss: 0.6676, Train Steps/Sec: 1.23
|
| 166 |
+
[[34m2025-10-29 16:34:50[0m] (step=0013200) Train Loss: 0.6675, Train Steps/Sec: 1.23
|
| 167 |
+
[[34m2025-10-29 16:36:11[0m] (step=0013300) Train Loss: 0.6676, Train Steps/Sec: 1.23
|
| 168 |
+
[[34m2025-10-29 16:37:33[0m] (step=0013400) Train Loss: 0.6664, Train Steps/Sec: 1.22
|
| 169 |
+
[[34m2025-10-29 16:38:54[0m] (step=0013500) Train Loss: 0.6660, Train Steps/Sec: 1.23
|
| 170 |
+
[[34m2025-10-29 16:40:16[0m] (step=0013600) Train Loss: 0.6643, Train Steps/Sec: 1.23
|
| 171 |
+
[[34m2025-10-29 16:41:37[0m] (step=0013700) Train Loss: 0.6656, Train Steps/Sec: 1.23
|
| 172 |
+
[[34m2025-10-29 16:42:28[0m] Beginning epoch 11...
|
| 173 |
+
[[34m2025-10-29 16:43:01[0m] (step=0013800) Train Loss: 0.6642, Train Steps/Sec: 1.19
|
| 174 |
+
[[34m2025-10-29 16:44:23[0m] (step=0013900) Train Loss: 0.6642, Train Steps/Sec: 1.23
|
| 175 |
+
[[34m2025-10-29 16:45:44[0m] (step=0014000) Train Loss: 0.6628, Train Steps/Sec: 1.23
|
| 176 |
+
[[34m2025-10-29 16:47:06[0m] (step=0014100) Train Loss: 0.6645, Train Steps/Sec: 1.23
|
| 177 |
+
[[34m2025-10-29 16:48:27[0m] (step=0014200) Train Loss: 0.6642, Train Steps/Sec: 1.23
|
| 178 |
+
[[34m2025-10-29 16:49:50[0m] (step=0014300) Train Loss: 0.6625, Train Steps/Sec: 1.22
|
| 179 |
+
[[34m2025-10-29 16:51:12[0m] (step=0014400) Train Loss: 0.6618, Train Steps/Sec: 1.22
|
| 180 |
+
[[34m2025-10-29 16:52:33[0m] (step=0014500) Train Loss: 0.6610, Train Steps/Sec: 1.23
|
| 181 |
+
[[34m2025-10-29 16:53:55[0m] (step=0014600) Train Loss: 0.6615, Train Steps/Sec: 1.23
|
| 182 |
+
[[34m2025-10-29 16:55:16[0m] (step=0014700) Train Loss: 0.6626, Train Steps/Sec: 1.23
|
| 183 |
+
[[34m2025-10-29 16:56:38[0m] (step=0014800) Train Loss: 0.6609, Train Steps/Sec: 1.23
|
| 184 |
+
[[34m2025-10-29 16:57:59[0m] (step=0014900) Train Loss: 0.6596, Train Steps/Sec: 1.23
|
| 185 |
+
[[34m2025-10-29 16:59:21[0m] (step=0015000) Train Loss: 0.6619, Train Steps/Sec: 1.23
|
| 186 |
+
[[34m2025-10-29 16:59:31[0m] Beginning epoch 12...
|
| 187 |
+
[[34m2025-10-29 17:00:45[0m] (step=0015100) Train Loss: 0.6600, Train Steps/Sec: 1.19
|
| 188 |
+
[[34m2025-10-29 17:02:06[0m] (step=0015200) Train Loss: 0.6580, Train Steps/Sec: 1.23
|
| 189 |
+
[[34m2025-10-29 17:03:28[0m] (step=0015300) Train Loss: 0.6602, Train Steps/Sec: 1.23
|
| 190 |
+
[[34m2025-10-29 17:04:49[0m] (step=0015400) Train Loss: 0.6600, Train Steps/Sec: 1.23
|
| 191 |
+
[[34m2025-10-29 17:06:11[0m] (step=0015500) Train Loss: 0.6595, Train Steps/Sec: 1.23
|
| 192 |
+
[[34m2025-10-29 17:07:32[0m] (step=0015600) Train Loss: 0.6588, Train Steps/Sec: 1.23
|
| 193 |
+
[[34m2025-10-29 17:08:54[0m] (step=0015700) Train Loss: 0.6584, Train Steps/Sec: 1.23
|
| 194 |
+
[[34m2025-10-29 17:10:16[0m] (step=0015800) Train Loss: 0.6587, Train Steps/Sec: 1.23
|
| 195 |
+
[[34m2025-10-29 17:11:37[0m] (step=0015900) Train Loss: 0.6574, Train Steps/Sec: 1.23
|
| 196 |
+
[[34m2025-10-29 17:12:59[0m] (step=0016000) Train Loss: 0.6576, Train Steps/Sec: 1.21
|
| 197 |
+
[[34m2025-10-29 17:14:21[0m] (step=0016100) Train Loss: 0.6586, Train Steps/Sec: 1.23
|
| 198 |
+
[[34m2025-10-29 17:15:43[0m] (step=0016200) Train Loss: 0.6575, Train Steps/Sec: 1.22
|
| 199 |
+
[[34m2025-10-29 17:16:34[0m] Beginning epoch 13...
|
| 200 |
+
[[34m2025-10-29 17:17:06[0m] (step=0016300) Train Loss: 0.6556, Train Steps/Sec: 1.19
|
| 201 |
+
[[34m2025-10-29 17:18:28[0m] (step=0016400) Train Loss: 0.6558, Train Steps/Sec: 1.23
|
| 202 |
+
[[34m2025-10-29 17:19:50[0m] (step=0016500) Train Loss: 0.6544, Train Steps/Sec: 1.23
|
| 203 |
+
[[34m2025-10-29 17:21:11[0m] (step=0016600) Train Loss: 0.6552, Train Steps/Sec: 1.23
|
| 204 |
+
[[34m2025-10-29 17:22:33[0m] (step=0016700) Train Loss: 0.6570, Train Steps/Sec: 1.23
|
| 205 |
+
[[34m2025-10-29 17:23:54[0m] (step=0016800) Train Loss: 0.6554, Train Steps/Sec: 1.23
|
| 206 |
+
[[34m2025-10-29 17:25:16[0m] (step=0016900) Train Loss: 0.6549, Train Steps/Sec: 1.23
|
| 207 |
+
[[34m2025-10-29 17:26:37[0m] (step=0017000) Train Loss: 0.6536, Train Steps/Sec: 1.23
|
| 208 |
+
[[34m2025-10-29 17:27:59[0m] (step=0017100) Train Loss: 0.6554, Train Steps/Sec: 1.23
|
| 209 |
+
[[34m2025-10-29 17:29:20[0m] (step=0017200) Train Loss: 0.6547, Train Steps/Sec: 1.23
|
| 210 |
+
[[34m2025-10-29 17:30:42[0m] (step=0017300) Train Loss: 0.6540, Train Steps/Sec: 1.23
|
| 211 |
+
[[34m2025-10-29 17:32:03[0m] (step=0017400) Train Loss: 0.6532, Train Steps/Sec: 1.23
|
| 212 |
+
[[34m2025-10-29 17:33:25[0m] (step=0017500) Train Loss: 0.6544, Train Steps/Sec: 1.23
|
| 213 |
+
[[34m2025-10-29 17:33:37[0m] Beginning epoch 14...
|
| 214 |
+
[[34m2025-10-29 17:34:49[0m] (step=0017600) Train Loss: 0.6518, Train Steps/Sec: 1.19
|
| 215 |
+
[[34m2025-10-29 17:36:12[0m] (step=0017700) Train Loss: 0.6514, Train Steps/Sec: 1.21
|
| 216 |
+
[[34m2025-10-29 17:37:33[0m] (step=0017800) Train Loss: 0.6515, Train Steps/Sec: 1.23
|
| 217 |
+
[[34m2025-10-29 17:38:55[0m] (step=0017900) Train Loss: 0.6524, Train Steps/Sec: 1.23
|
| 218 |
+
[[34m2025-10-29 17:40:16[0m] (step=0018000) Train Loss: 0.6525, Train Steps/Sec: 1.23
|
| 219 |
+
[[34m2025-10-29 17:41:38[0m] (step=0018100) Train Loss: 0.6508, Train Steps/Sec: 1.23
|
| 220 |
+
[[34m2025-10-29 17:42:59[0m] (step=0018200) Train Loss: 0.6508, Train Steps/Sec: 1.23
|
| 221 |
+
[[34m2025-10-29 17:44:21[0m] (step=0018300) Train Loss: 0.6514, Train Steps/Sec: 1.23
|
| 222 |
+
[[34m2025-10-29 17:45:42[0m] (step=0018400) Train Loss: 0.6510, Train Steps/Sec: 1.23
|
| 223 |
+
[[34m2025-10-29 17:47:04[0m] (step=0018500) Train Loss: 0.6507, Train Steps/Sec: 1.23
|
| 224 |
+
[[34m2025-10-29 17:48:25[0m] (step=0018600) Train Loss: 0.6513, Train Steps/Sec: 1.23
|
| 225 |
+
[[34m2025-10-29 17:49:47[0m] (step=0018700) Train Loss: 0.6505, Train Steps/Sec: 1.23
|
| 226 |
+
[[34m2025-10-29 17:50:40[0m] Beginning epoch 15...
|
| 227 |
+
[[34m2025-10-29 17:51:11[0m] (step=0018800) Train Loss: 0.6505, Train Steps/Sec: 1.19
|
| 228 |
+
[[34m2025-10-29 17:52:32[0m] (step=0018900) Train Loss: 0.6491, Train Steps/Sec: 1.23
|
| 229 |
+
[[34m2025-10-29 17:53:54[0m] (step=0019000) Train Loss: 0.6471, Train Steps/Sec: 1.22
|
| 230 |
+
[[34m2025-10-29 17:55:16[0m] (step=0019100) Train Loss: 0.6486, Train Steps/Sec: 1.23
|
| 231 |
+
[[34m2025-10-29 17:56:37[0m] (step=0019200) Train Loss: 0.6486, Train Steps/Sec: 1.23
|
| 232 |
+
[[34m2025-10-29 17:57:59[0m] (step=0019300) Train Loss: 0.6484, Train Steps/Sec: 1.22
|
| 233 |
+
[[34m2025-10-29 17:59:21[0m] (step=0019400) Train Loss: 0.6493, Train Steps/Sec: 1.22
|
| 234 |
+
[[34m2025-10-29 18:00:43[0m] (step=0019500) Train Loss: 0.6486, Train Steps/Sec: 1.23
|
| 235 |
+
[[34m2025-10-29 18:02:04[0m] (step=0019600) Train Loss: 0.6498, Train Steps/Sec: 1.23
|
| 236 |
+
[[34m2025-10-29 18:03:26[0m] (step=0019700) Train Loss: 0.6479, Train Steps/Sec: 1.23
|
| 237 |
+
[[34m2025-10-29 18:04:47[0m] (step=0019800) Train Loss: 0.6475, Train Steps/Sec: 1.23
|
| 238 |
+
[[34m2025-10-29 18:06:09[0m] (step=0019900) Train Loss: 0.6472, Train Steps/Sec: 1.23
|
| 239 |
+
[[34m2025-10-29 18:07:30[0m] (step=0020000) Train Loss: 0.6475, Train Steps/Sec: 1.23
|
| 240 |
+
[[34m2025-10-29 18:07:44[0m] Beginning epoch 16...
|
| 241 |
+
[[34m2025-10-29 18:08:54[0m] (step=0020100) Train Loss: 0.6467, Train Steps/Sec: 1.19
|
| 242 |
+
[[34m2025-10-29 18:10:16[0m] (step=0020200) Train Loss: 0.6466, Train Steps/Sec: 1.23
|
| 243 |
+
[[34m2025-10-29 18:11:37[0m] (step=0020300) Train Loss: 0.6471, Train Steps/Sec: 1.23
|
| 244 |
+
[[34m2025-10-29 18:12:59[0m] (step=0020400) Train Loss: 0.6472, Train Steps/Sec: 1.23
|
| 245 |
+
[[34m2025-10-29 18:14:21[0m] (step=0020500) Train Loss: 0.6458, Train Steps/Sec: 1.23
|
| 246 |
+
[[34m2025-10-29 18:15:42[0m] (step=0020600) Train Loss: 0.6439, Train Steps/Sec: 1.23
|
| 247 |
+
[[34m2025-10-29 18:17:04[0m] (step=0020700) Train Loss: 0.6450, Train Steps/Sec: 1.23
|
| 248 |
+
[[34m2025-10-29 18:18:25[0m] (step=0020800) Train Loss: 0.6462, Train Steps/Sec: 1.23
|
| 249 |
+
[[34m2025-10-29 18:19:47[0m] (step=0020900) Train Loss: 0.6449, Train Steps/Sec: 1.23
|
| 250 |
+
[[34m2025-10-29 18:21:09[0m] (step=0021000) Train Loss: 0.6460, Train Steps/Sec: 1.22
|
| 251 |
+
[[34m2025-10-29 18:22:31[0m] (step=0021100) Train Loss: 0.6447, Train Steps/Sec: 1.22
|
| 252 |
+
[[34m2025-10-29 18:23:52[0m] (step=0021200) Train Loss: 0.6446, Train Steps/Sec: 1.23
|
| 253 |
+
[[34m2025-10-29 18:24:47[0m] Beginning epoch 17...
|
| 254 |
+
[[34m2025-10-29 18:25:16[0m] (step=0021300) Train Loss: 0.6446, Train Steps/Sec: 1.19
|
| 255 |
+
[[34m2025-10-29 18:26:37[0m] (step=0021400) Train Loss: 0.6442, Train Steps/Sec: 1.23
|
| 256 |
+
[[34m2025-10-29 18:27:59[0m] (step=0021500) Train Loss: 0.6436, Train Steps/Sec: 1.23
|
| 257 |
+
[[34m2025-10-29 18:29:21[0m] (step=0021600) Train Loss: 0.6436, Train Steps/Sec: 1.23
|
| 258 |
+
[[34m2025-10-29 18:30:42[0m] (step=0021700) Train Loss: 0.6446, Train Steps/Sec: 1.23
|
| 259 |
+
[[34m2025-10-29 18:32:04[0m] (step=0021800) Train Loss: 0.6431, Train Steps/Sec: 1.23
|
| 260 |
+
[[34m2025-10-29 18:33:25[0m] (step=0021900) Train Loss: 0.6428, Train Steps/Sec: 1.23
|
| 261 |
+
[[34m2025-10-29 18:34:47[0m] (step=0022000) Train Loss: 0.6426, Train Steps/Sec: 1.23
|
| 262 |
+
[[34m2025-10-29 18:36:08[0m] (step=0022100) Train Loss: 0.6423, Train Steps/Sec: 1.23
|
| 263 |
+
[[34m2025-10-29 18:37:30[0m] (step=0022200) Train Loss: 0.6423, Train Steps/Sec: 1.23
|
| 264 |
+
[[34m2025-10-29 18:38:51[0m] (step=0022300) Train Loss: 0.6437, Train Steps/Sec: 1.23
|
| 265 |
+
[[34m2025-10-29 18:40:13[0m] (step=0022400) Train Loss: 0.6426, Train Steps/Sec: 1.23
|
| 266 |
+
[[34m2025-10-29 18:41:34[0m] (step=0022500) Train Loss: 0.6418, Train Steps/Sec: 1.23
|
| 267 |
+
[[34m2025-10-29 18:41:49[0m] Beginning epoch 18...
|
| 268 |
+
[[34m2025-10-29 18:42:58[0m] (step=0022600) Train Loss: 0.6416, Train Steps/Sec: 1.19
|
| 269 |
+
[[34m2025-10-29 18:44:21[0m] (step=0022700) Train Loss: 0.6401, Train Steps/Sec: 1.21
|
| 270 |
+
[[34m2025-10-29 18:45:42[0m] (step=0022800) Train Loss: 0.6417, Train Steps/Sec: 1.23
|
| 271 |
+
[[34m2025-10-29 18:47:04[0m] (step=0022900) Train Loss: 0.6411, Train Steps/Sec: 1.23
|
| 272 |
+
[[34m2025-10-29 18:48:25[0m] (step=0023000) Train Loss: 0.6402, Train Steps/Sec: 1.23
|
| 273 |
+
[[34m2025-10-29 18:49:47[0m] (step=0023100) Train Loss: 0.6409, Train Steps/Sec: 1.23
|
| 274 |
+
[[34m2025-10-29 18:51:08[0m] (step=0023200) Train Loss: 0.6397, Train Steps/Sec: 1.22
|
| 275 |
+
[[34m2025-10-29 18:52:30[0m] (step=0023300) Train Loss: 0.6409, Train Steps/Sec: 1.23
|
| 276 |
+
[[34m2025-10-29 18:53:51[0m] (step=0023400) Train Loss: 0.6414, Train Steps/Sec: 1.23
|
| 277 |
+
[[34m2025-10-29 18:55:13[0m] (step=0023500) Train Loss: 0.6390, Train Steps/Sec: 1.23
|
| 278 |
+
[[34m2025-10-29 18:56:35[0m] (step=0023600) Train Loss: 0.6385, Train Steps/Sec: 1.23
|
| 279 |
+
[[34m2025-10-29 18:57:56[0m] (step=0023700) Train Loss: 0.6401, Train Steps/Sec: 1.23
|
| 280 |
+
[[34m2025-10-29 18:58:53[0m] Beginning epoch 19...
|
| 281 |
+
[[34m2025-10-29 18:59:20[0m] (step=0023800) Train Loss: 0.6397, Train Steps/Sec: 1.19
|
| 282 |
+
[[34m2025-10-29 19:00:41[0m] (step=0023900) Train Loss: 0.6401, Train Steps/Sec: 1.23
|
| 283 |
+
[[34m2025-10-29 19:02:03[0m] (step=0024000) Train Loss: 0.6390, Train Steps/Sec: 1.23
|
| 284 |
+
[[34m2025-10-29 19:03:24[0m] (step=0024100) Train Loss: 0.6399, Train Steps/Sec: 1.23
|
| 285 |
+
[[34m2025-10-29 19:04:46[0m] (step=0024200) Train Loss: 0.6378, Train Steps/Sec: 1.23
|
| 286 |
+
[[34m2025-10-29 19:06:08[0m] (step=0024300) Train Loss: 0.6387, Train Steps/Sec: 1.22
|
| 287 |
+
[[34m2025-10-29 19:07:30[0m] (step=0024400) Train Loss: 0.6379, Train Steps/Sec: 1.21
|
| 288 |
+
[[34m2025-10-29 19:08:51[0m] (step=0024500) Train Loss: 0.6385, Train Steps/Sec: 1.23
|
| 289 |
+
[[34m2025-10-29 19:10:13[0m] (step=0024600) Train Loss: 0.6384, Train Steps/Sec: 1.22
|
| 290 |
+
[[34m2025-10-29 19:11:35[0m] (step=0024700) Train Loss: 0.6380, Train Steps/Sec: 1.23
|
| 291 |
+
[[34m2025-10-29 19:12:56[0m] (step=0024800) Train Loss: 0.6387, Train Steps/Sec: 1.23
|
| 292 |
+
[[34m2025-10-29 19:14:18[0m] (step=0024900) Train Loss: 0.6377, Train Steps/Sec: 1.23
|
| 293 |
+
[[34m2025-10-29 19:15:39[0m] (step=0025000) Train Loss: 0.6373, Train Steps/Sec: 1.23
|
| 294 |
+
[[34m2025-10-29 19:16:29[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-spnorm-bf16/checkpoints/0025000.pt
|
| 295 |
+
[[34m2025-10-29 19:16:29[0m] Generating EMA samples...
|
| 296 |
+
[[34m2025-10-29 19:16:57[0m] Generating EMA samples done.
|
| 297 |
+
[[34m2025-10-29 19:17:13[0m] Beginning epoch 20...
|
| 298 |
+
[[34m2025-10-29 19:18:20[0m] (step=0025100) Train Loss: 0.6365, Train Steps/Sec: 0.62
|
| 299 |
+
[[34m2025-10-29 19:19:42[0m] (step=0025200) Train Loss: 0.6371, Train Steps/Sec: 1.23
|
| 300 |
+
[[34m2025-10-29 19:21:03[0m] (step=0025300) Train Loss: 0.6378, Train Steps/Sec: 1.23
|
| 301 |
+
[[34m2025-10-29 19:22:25[0m] (step=0025400) Train Loss: 0.6374, Train Steps/Sec: 1.23
|
| 302 |
+
[[34m2025-10-29 19:23:46[0m] (step=0025500) Train Loss: 0.6372, Train Steps/Sec: 1.23
|
| 303 |
+
[[34m2025-10-29 19:25:08[0m] (step=0025600) Train Loss: 0.6362, Train Steps/Sec: 1.23
|
| 304 |
+
[[34m2025-10-29 19:26:29[0m] (step=0025700) Train Loss: 0.6363, Train Steps/Sec: 1.23
|
| 305 |
+
[[34m2025-10-29 19:27:51[0m] (step=0025800) Train Loss: 0.6376, Train Steps/Sec: 1.23
|
| 306 |
+
[[34m2025-10-29 19:29:12[0m] (step=0025900) Train Loss: 0.6367, Train Steps/Sec: 1.23
|
| 307 |
+
[[34m2025-10-29 19:30:34[0m] (step=0026000) Train Loss: 0.6378, Train Steps/Sec: 1.22
|
| 308 |
+
[[34m2025-10-29 19:31:57[0m] (step=0026100) Train Loss: 0.6361, Train Steps/Sec: 1.22
|
| 309 |
+
[[34m2025-10-29 19:33:18[0m] (step=0026200) Train Loss: 0.6347, Train Steps/Sec: 1.23
|
| 310 |
+
[[34m2025-10-29 19:34:16[0m] Beginning epoch 21...
|
| 311 |
+
[[34m2025-10-29 19:34:42[0m] (step=0026300) Train Loss: 0.6353, Train Steps/Sec: 1.19
|
| 312 |
+
[[34m2025-10-29 19:36:04[0m] (step=0026400) Train Loss: 0.6348, Train Steps/Sec: 1.23
|
| 313 |
+
[[34m2025-10-29 19:37:25[0m] (step=0026500) Train Loss: 0.6348, Train Steps/Sec: 1.23
|
| 314 |
+
[[34m2025-10-29 19:38:47[0m] (step=0026600) Train Loss: 0.6368, Train Steps/Sec: 1.23
|
| 315 |
+
[[34m2025-10-29 19:40:08[0m] (step=0026700) Train Loss: 0.6347, Train Steps/Sec: 1.23
|
| 316 |
+
[[34m2025-10-29 19:41:30[0m] (step=0026800) Train Loss: 0.6343, Train Steps/Sec: 1.23
|
| 317 |
+
[[34m2025-10-29 19:42:51[0m] (step=0026900) Train Loss: 0.6361, Train Steps/Sec: 1.23
|
| 318 |
+
[[34m2025-10-29 19:44:13[0m] (step=0027000) Train Loss: 0.6365, Train Steps/Sec: 1.23
|
| 319 |
+
[[34m2025-10-29 19:45:34[0m] (step=0027100) Train Loss: 0.6348, Train Steps/Sec: 1.23
|
| 320 |
+
[[34m2025-10-29 19:46:56[0m] (step=0027200) Train Loss: 0.6349, Train Steps/Sec: 1.23
|
| 321 |
+
[[34m2025-10-29 19:48:17[0m] (step=0027300) Train Loss: 0.6345, Train Steps/Sec: 1.23
|
| 322 |
+
[[34m2025-10-29 19:49:39[0m] (step=0027400) Train Loss: 0.6351, Train Steps/Sec: 1.22
|
| 323 |
+
[[34m2025-10-29 19:51:01[0m] (step=0027500) Train Loss: 0.6329, Train Steps/Sec: 1.23
|
| 324 |
+
[[34m2025-10-29 19:51:19[0m] Beginning epoch 22...
|
| 325 |
+
[[34m2025-10-29 19:52:25[0m] (step=0027600) Train Loss: 0.6333, Train Steps/Sec: 1.19
|
| 326 |
+
[[34m2025-10-29 19:53:47[0m] (step=0027700) Train Loss: 0.6322, Train Steps/Sec: 1.21
|
| 327 |
+
[[34m2025-10-29 19:55:09[0m] (step=0027800) Train Loss: 0.6335, Train Steps/Sec: 1.22
|
| 328 |
+
[[34m2025-10-29 19:56:30[0m] (step=0027900) Train Loss: 0.6332, Train Steps/Sec: 1.23
|
| 329 |
+
[[34m2025-10-29 19:57:52[0m] (step=0028000) Train Loss: 0.6337, Train Steps/Sec: 1.23
|
| 330 |
+
[[34m2025-10-29 19:59:14[0m] (step=0028100) Train Loss: 0.6319, Train Steps/Sec: 1.23
|
| 331 |
+
[[34m2025-10-29 20:00:35[0m] (step=0028200) Train Loss: 0.6340, Train Steps/Sec: 1.23
|
| 332 |
+
[[34m2025-10-29 20:01:57[0m] (step=0028300) Train Loss: 0.6327, Train Steps/Sec: 1.23
|
| 333 |
+
[[34m2025-10-29 20:03:18[0m] (step=0028400) Train Loss: 0.6325, Train Steps/Sec: 1.23
|
| 334 |
+
[[34m2025-10-29 20:04:40[0m] (step=0028500) Train Loss: 0.6328, Train Steps/Sec: 1.23
|
| 335 |
+
[[34m2025-10-29 20:06:01[0m] (step=0028600) Train Loss: 0.6330, Train Steps/Sec: 1.23
|
| 336 |
+
[[34m2025-10-29 20:07:23[0m] (step=0028700) Train Loss: 0.6330, Train Steps/Sec: 1.23
|
| 337 |
+
[[34m2025-10-29 20:08:23[0m] Beginning epoch 23...
|
| 338 |
+
[[34m2025-10-29 20:08:47[0m] (step=0028800) Train Loss: 0.6320, Train Steps/Sec: 1.19
|
| 339 |
+
[[34m2025-10-29 20:10:08[0m] (step=0028900) Train Loss: 0.6322, Train Steps/Sec: 1.23
|
| 340 |
+
[[34m2025-10-29 20:11:30[0m] (step=0029000) Train Loss: 0.6318, Train Steps/Sec: 1.23
|
| 341 |
+
[[34m2025-10-29 20:12:51[0m] (step=0029100) Train Loss: 0.6327, Train Steps/Sec: 1.23
|
| 342 |
+
[[34m2025-10-29 20:14:13[0m] (step=0029200) Train Loss: 0.6325, Train Steps/Sec: 1.23
|
| 343 |
+
[[34m2025-10-29 20:15:34[0m] (step=0029300) Train Loss: 0.6312, Train Steps/Sec: 1.23
|
| 344 |
+
[[34m2025-10-29 20:16:57[0m] (step=0029400) Train Loss: 0.6301, Train Steps/Sec: 1.21
|
| 345 |
+
[[34m2025-10-29 20:18:19[0m] (step=0029500) Train Loss: 0.6295, Train Steps/Sec: 1.22
|
| 346 |
+
[[34m2025-10-29 20:19:40[0m] (step=0029600) Train Loss: 0.6318, Train Steps/Sec: 1.23
|
| 347 |
+
[[34m2025-10-29 20:21:02[0m] (step=0029700) Train Loss: 0.6315, Train Steps/Sec: 1.23
|
| 348 |
+
[[34m2025-10-29 20:22:23[0m] (step=0029800) Train Loss: 0.6317, Train Steps/Sec: 1.23
|
| 349 |
+
[[34m2025-10-29 20:23:45[0m] (step=0029900) Train Loss: 0.6317, Train Steps/Sec: 1.23
|
| 350 |
+
[[34m2025-10-29 20:25:06[0m] (step=0030000) Train Loss: 0.6310, Train Steps/Sec: 1.23
|
| 351 |
+
[[34m2025-10-29 20:25:26[0m] Beginning epoch 24...
|
| 352 |
+
[[34m2025-10-29 20:26:30[0m] (step=0030100) Train Loss: 0.6316, Train Steps/Sec: 1.19
|
| 353 |
+
[[34m2025-10-29 20:27:52[0m] (step=0030200) Train Loss: 0.6309, Train Steps/Sec: 1.23
|
| 354 |
+
[[34m2025-10-29 20:29:13[0m] (step=0030300) Train Loss: 0.6314, Train Steps/Sec: 1.23
|
| 355 |
+
[[34m2025-10-29 20:30:35[0m] (step=0030400) Train Loss: 0.6292, Train Steps/Sec: 1.23
|
| 356 |
+
[[34m2025-10-29 20:31:56[0m] (step=0030500) Train Loss: 0.6289, Train Steps/Sec: 1.23
|
| 357 |
+
[[34m2025-10-29 20:33:18[0m] (step=0030600) Train Loss: 0.6312, Train Steps/Sec: 1.23
|
| 358 |
+
[[34m2025-10-29 20:34:39[0m] (step=0030700) Train Loss: 0.6300, Train Steps/Sec: 1.23
|
| 359 |
+
[[34m2025-10-29 20:36:01[0m] (step=0030800) Train Loss: 0.6299, Train Steps/Sec: 1.23
|
| 360 |
+
[[34m2025-10-29 20:37:23[0m] (step=0030900) Train Loss: 0.6301, Train Steps/Sec: 1.23
|
| 361 |
+
[[34m2025-10-29 20:38:44[0m] (step=0031000) Train Loss: 0.6288, Train Steps/Sec: 1.22
|
| 362 |
+
[[34m2025-10-29 20:40:06[0m] (step=0031100) Train Loss: 0.6297, Train Steps/Sec: 1.22
|
| 363 |
+
[[34m2025-10-29 20:41:28[0m] (step=0031200) Train Loss: 0.6290, Train Steps/Sec: 1.23
|
| 364 |
+
[[34m2025-10-29 20:42:30[0m] Beginning epoch 25...
|
| 365 |
+
[[34m2025-10-29 20:42:52[0m] (step=0031300) Train Loss: 0.6287, Train Steps/Sec: 1.19
|
| 366 |
+
[[34m2025-10-29 20:44:13[0m] (step=0031400) Train Loss: 0.6295, Train Steps/Sec: 1.23
|
| 367 |
+
[[34m2025-10-29 20:45:35[0m] (step=0031500) Train Loss: 0.6290, Train Steps/Sec: 1.23
|
| 368 |
+
[[34m2025-10-29 20:46:56[0m] (step=0031600) Train Loss: 0.6285, Train Steps/Sec: 1.23
|
| 369 |
+
[[34m2025-10-29 20:48:18[0m] (step=0031700) Train Loss: 0.6294, Train Steps/Sec: 1.23
|
| 370 |
+
[[34m2025-10-29 20:49:40[0m] (step=0031800) Train Loss: 0.6280, Train Steps/Sec: 1.23
|
| 371 |
+
[[34m2025-10-29 20:51:01[0m] (step=0031900) Train Loss: 0.6270, Train Steps/Sec: 1.23
|
| 372 |
+
[[34m2025-10-29 20:52:23[0m] (step=0032000) Train Loss: 0.6279, Train Steps/Sec: 1.23
|
| 373 |
+
[[34m2025-10-29 20:53:44[0m] (step=0032100) Train Loss: 0.6285, Train Steps/Sec: 1.23
|
| 374 |
+
[[34m2025-10-29 20:55:06[0m] (step=0032200) Train Loss: 0.6294, Train Steps/Sec: 1.23
|
| 375 |
+
[[34m2025-10-29 20:56:27[0m] (step=0032300) Train Loss: 0.6291, Train Steps/Sec: 1.23
|
| 376 |
+
[[34m2025-10-29 20:57:49[0m] (step=0032400) Train Loss: 0.6279, Train Steps/Sec: 1.23
|
| 377 |
+
[[34m2025-10-29 20:59:10[0m] (step=0032500) Train Loss: 0.6288, Train Steps/Sec: 1.23
|
| 378 |
+
[[34m2025-10-29 20:59:32[0m] Beginning epoch 26...
|
| 379 |
+
[[34m2025-10-29 21:00:34[0m] (step=0032600) Train Loss: 0.6279, Train Steps/Sec: 1.19
|
| 380 |
+
[[34m2025-10-29 21:01:56[0m] (step=0032700) Train Loss: 0.6265, Train Steps/Sec: 1.22
|
| 381 |
+
[[34m2025-10-29 21:03:18[0m] (step=0032800) Train Loss: 0.6268, Train Steps/Sec: 1.22
|
| 382 |
+
[[34m2025-10-29 21:04:40[0m] (step=0032900) Train Loss: 0.6264, Train Steps/Sec: 1.23
|
| 383 |
+
[[34m2025-10-29 21:06:01[0m] (step=0033000) Train Loss: 0.6281, Train Steps/Sec: 1.23
|
| 384 |
+
[[34m2025-10-29 21:07:23[0m] (step=0033100) Train Loss: 0.6282, Train Steps/Sec: 1.22
|
| 385 |
+
[[34m2025-10-29 21:08:45[0m] (step=0033200) Train Loss: 0.6273, Train Steps/Sec: 1.23
|
| 386 |
+
[[34m2025-10-29 21:10:06[0m] (step=0033300) Train Loss: 0.6280, Train Steps/Sec: 1.23
|
| 387 |
+
[[34m2025-10-29 21:11:28[0m] (step=0033400) Train Loss: 0.6307, Train Steps/Sec: 1.23
|
| 388 |
+
[[34m2025-10-29 21:12:49[0m] (step=0033500) Train Loss: 0.6290, Train Steps/Sec: 1.23
|
| 389 |
+
[[34m2025-10-29 21:14:11[0m] (step=0033600) Train Loss: 0.6278, Train Steps/Sec: 1.23
|
| 390 |
+
[[34m2025-10-29 21:15:32[0m] (step=0033700) Train Loss: 0.6261, Train Steps/Sec: 1.23
|
| 391 |
+
[[34m2025-10-29 21:16:36[0m] Beginning epoch 27...
|
| 392 |
+
[[34m2025-10-29 21:16:56[0m] (step=0033800) Train Loss: 0.6268, Train Steps/Sec: 1.19
|
| 393 |
+
[[34m2025-10-29 21:18:18[0m] (step=0033900) Train Loss: 0.6278, Train Steps/Sec: 1.23
|
| 394 |
+
[[34m2025-10-29 21:19:39[0m] (step=0034000) Train Loss: 0.6268, Train Steps/Sec: 1.23
|
| 395 |
+
[[34m2025-10-29 21:21:01[0m] (step=0034100) Train Loss: 0.6269, Train Steps/Sec: 1.23
|
| 396 |
+
[[34m2025-10-29 21:22:22[0m] (step=0034200) Train Loss: 0.6274, Train Steps/Sec: 1.23
|
| 397 |
+
[[34m2025-10-29 21:23:44[0m] (step=0034300) Train Loss: 0.6259, Train Steps/Sec: 1.23
|
| 398 |
+
[[34m2025-10-29 21:25:06[0m] (step=0034400) Train Loss: 0.6252, Train Steps/Sec: 1.21
|
| 399 |
+
[[34m2025-10-29 21:26:28[0m] (step=0034500) Train Loss: 0.6251, Train Steps/Sec: 1.22
|
| 400 |
+
[[34m2025-10-29 21:27:50[0m] (step=0034600) Train Loss: 0.6270, Train Steps/Sec: 1.23
|
| 401 |
+
[[34m2025-10-29 21:29:11[0m] (step=0034700) Train Loss: 0.6264, Train Steps/Sec: 1.23
|
| 402 |
+
[[34m2025-10-29 21:30:33[0m] (step=0034800) Train Loss: 0.6265, Train Steps/Sec: 1.23
|
| 403 |
+
[[34m2025-10-29 21:31:54[0m] (step=0034900) Train Loss: 0.6260, Train Steps/Sec: 1.23
|
| 404 |
+
[[34m2025-10-29 21:33:16[0m] (step=0035000) Train Loss: 0.6262, Train Steps/Sec: 1.23
|
| 405 |
+
[[34m2025-10-29 21:33:39[0m] Beginning epoch 28...
|
| 406 |
+
[[34m2025-10-29 21:34:40[0m] (step=0035100) Train Loss: 0.6254, Train Steps/Sec: 1.19
|
| 407 |
+
[[34m2025-10-29 21:36:01[0m] (step=0035200) Train Loss: 0.6261, Train Steps/Sec: 1.23
|
| 408 |
+
[[34m2025-10-29 21:37:22[0m] (step=0035300) Train Loss: 0.6256, Train Steps/Sec: 1.23
|
| 409 |
+
[[34m2025-10-29 21:38:44[0m] (step=0035400) Train Loss: 0.6267, Train Steps/Sec: 1.23
|
| 410 |
+
[[34m2025-10-29 21:40:06[0m] (step=0035500) Train Loss: 0.6242, Train Steps/Sec: 1.23
|
| 411 |
+
[[34m2025-10-29 21:41:27[0m] (step=0035600) Train Loss: 0.6251, Train Steps/Sec: 1.23
|
| 412 |
+
[[34m2025-10-29 21:42:49[0m] (step=0035700) Train Loss: 0.6238, Train Steps/Sec: 1.23
|
| 413 |
+
[[34m2025-10-29 21:44:10[0m] (step=0035800) Train Loss: 0.6243, Train Steps/Sec: 1.23
|
| 414 |
+
[[34m2025-10-29 21:45:32[0m] (step=0035900) Train Loss: 0.6258, Train Steps/Sec: 1.23
|
| 415 |
+
[[34m2025-10-29 21:46:53[0m] (step=0036000) Train Loss: 0.6256, Train Steps/Sec: 1.22
|
| 416 |
+
[[34m2025-10-29 21:48:16[0m] (step=0036100) Train Loss: 0.6248, Train Steps/Sec: 1.22
|
| 417 |
+
[[34m2025-10-29 21:49:37[0m] (step=0036200) Train Loss: 0.6249, Train Steps/Sec: 1.23
|
| 418 |
+
[[34m2025-10-29 21:50:42[0m] Beginning epoch 29...
|
| 419 |
+
[[34m2025-10-29 21:51:01[0m] (step=0036300) Train Loss: 0.6251, Train Steps/Sec: 1.19
|
| 420 |
+
[[34m2025-10-29 21:52:23[0m] (step=0036400) Train Loss: 0.6247, Train Steps/Sec: 1.23
|
| 421 |
+
[[34m2025-10-29 21:53:44[0m] (step=0036500) Train Loss: 0.6234, Train Steps/Sec: 1.23
|
| 422 |
+
[[34m2025-10-29 21:55:06[0m] (step=0036600) Train Loss: 0.6236, Train Steps/Sec: 1.23
|
| 423 |
+
[[34m2025-10-29 21:56:27[0m] (step=0036700) Train Loss: 0.6246, Train Steps/Sec: 1.23
|
| 424 |
+
[[34m2025-10-29 21:57:49[0m] (step=0036800) Train Loss: 0.6247, Train Steps/Sec: 1.23
|
| 425 |
+
[[34m2025-10-29 21:59:10[0m] (step=0036900) Train Loss: 0.6247, Train Steps/Sec: 1.23
|
| 426 |
+
[[34m2025-10-29 22:00:32[0m] (step=0037000) Train Loss: 0.6244, Train Steps/Sec: 1.23
|
| 427 |
+
[[34m2025-10-29 22:01:53[0m] (step=0037100) Train Loss: 0.6241, Train Steps/Sec: 1.23
|
| 428 |
+
[[34m2025-10-29 22:03:15[0m] (step=0037200) Train Loss: 0.6230, Train Steps/Sec: 1.23
|
| 429 |
+
[[34m2025-10-29 22:04:36[0m] (step=0037300) Train Loss: 0.6242, Train Steps/Sec: 1.23
|
| 430 |
+
[[34m2025-10-29 22:05:58[0m] (step=0037400) Train Loss: 0.6226, Train Steps/Sec: 1.23
|
| 431 |
+
[[34m2025-10-29 22:07:19[0m] (step=0037500) Train Loss: 0.6234, Train Steps/Sec: 1.23
|
| 432 |
+
[[34m2025-10-29 22:07:44[0m] Beginning epoch 30...
|
| 433 |
+
[[34m2025-10-29 22:08:43[0m] (step=0037600) Train Loss: 0.6236, Train Steps/Sec: 1.19
|
| 434 |
+
[[34m2025-10-29 22:10:05[0m] (step=0037700) Train Loss: 0.6243, Train Steps/Sec: 1.22
|
| 435 |
+
[[34m2025-10-29 22:11:27[0m] (step=0037800) Train Loss: 0.6244, Train Steps/Sec: 1.22
|
| 436 |
+
[[34m2025-10-29 22:12:49[0m] (step=0037900) Train Loss: 0.6237, Train Steps/Sec: 1.23
|
| 437 |
+
[[34m2025-10-29 22:14:10[0m] (step=0038000) Train Loss: 0.6231, Train Steps/Sec: 1.23
|
| 438 |
+
[[34m2025-10-29 22:15:32[0m] (step=0038100) Train Loss: 0.6232, Train Steps/Sec: 1.23
|
| 439 |
+
[[34m2025-10-29 22:16:53[0m] (step=0038200) Train Loss: 0.6239, Train Steps/Sec: 1.23
|
| 440 |
+
[[34m2025-10-29 22:18:15[0m] (step=0038300) Train Loss: 0.6237, Train Steps/Sec: 1.23
|
| 441 |
+
[[34m2025-10-29 22:19:36[0m] (step=0038400) Train Loss: 0.6230, Train Steps/Sec: 1.23
|
| 442 |
+
[[34m2025-10-29 22:20:58[0m] (step=0038500) Train Loss: 0.6227, Train Steps/Sec: 1.23
|
| 443 |
+
[[34m2025-10-29 22:22:19[0m] (step=0038600) Train Loss: 0.6212, Train Steps/Sec: 1.23
|
| 444 |
+
[[34m2025-10-29 22:23:41[0m] (step=0038700) Train Loss: 0.6238, Train Steps/Sec: 1.23
|
| 445 |
+
[[34m2025-10-29 22:24:48[0m] Beginning epoch 31...
|
| 446 |
+
[[34m2025-10-29 22:25:06[0m] (step=0038800) Train Loss: 0.6240, Train Steps/Sec: 1.18
|
| 447 |
+
[[34m2025-10-29 22:26:27[0m] (step=0038900) Train Loss: 0.6232, Train Steps/Sec: 1.23
|
| 448 |
+
[[34m2025-10-29 22:27:49[0m] (step=0039000) Train Loss: 0.6213, Train Steps/Sec: 1.23
|
| 449 |
+
[[34m2025-10-29 22:29:10[0m] (step=0039100) Train Loss: 0.6226, Train Steps/Sec: 1.23
|
| 450 |
+
[[34m2025-10-29 22:30:32[0m] (step=0039200) Train Loss: 0.6217, Train Steps/Sec: 1.23
|
| 451 |
+
[[34m2025-10-29 22:31:53[0m] (step=0039300) Train Loss: 0.6231, Train Steps/Sec: 1.23
|
| 452 |
+
[[34m2025-10-29 22:33:15[0m] (step=0039400) Train Loss: 0.6217, Train Steps/Sec: 1.22
|
| 453 |
+
[[34m2025-10-29 22:34:37[0m] (step=0039500) Train Loss: 0.6214, Train Steps/Sec: 1.22
|
| 454 |
+
[[34m2025-10-29 22:35:59[0m] (step=0039600) Train Loss: 0.6215, Train Steps/Sec: 1.23
|
| 455 |
+
[[34m2025-10-29 22:37:20[0m] (step=0039700) Train Loss: 0.6231, Train Steps/Sec: 1.23
|
| 456 |
+
[[34m2025-10-29 22:38:42[0m] (step=0039800) Train Loss: 0.6220, Train Steps/Sec: 1.23
|
| 457 |
+
[[34m2025-10-29 22:40:03[0m] (step=0039900) Train Loss: 0.6229, Train Steps/Sec: 1.23
|
| 458 |
+
[[34m2025-10-29 22:41:25[0m] (step=0040000) Train Loss: 0.6220, Train Steps/Sec: 1.23
|
| 459 |
+
[[34m2025-10-29 22:41:52[0m] Beginning epoch 32...
|
| 460 |
+
[[34m2025-10-29 22:42:50[0m] (step=0040100) Train Loss: 0.6213, Train Steps/Sec: 1.18
|
| 461 |
+
[[34m2025-10-29 22:44:11[0m] (step=0040200) Train Loss: 0.6229, Train Steps/Sec: 1.22
|
| 462 |
+
[[34m2025-10-29 22:45:33[0m] (step=0040300) Train Loss: 0.6216, Train Steps/Sec: 1.23
|
| 463 |
+
[[34m2025-10-29 22:46:54[0m] (step=0040400) Train Loss: 0.6218, Train Steps/Sec: 1.23
|
| 464 |
+
[[34m2025-10-29 22:48:16[0m] (step=0040500) Train Loss: 0.6197, Train Steps/Sec: 1.23
|
| 465 |
+
[[34m2025-10-29 22:49:37[0m] (step=0040600) Train Loss: 0.6215, Train Steps/Sec: 1.23
|
| 466 |
+
[[34m2025-10-29 22:50:59[0m] (step=0040700) Train Loss: 0.6228, Train Steps/Sec: 1.23
|
| 467 |
+
[[34m2025-10-29 22:52:20[0m] (step=0040800) Train Loss: 0.6203, Train Steps/Sec: 1.23
|
| 468 |
+
[[34m2025-10-29 22:53:42[0m] (step=0040900) Train Loss: 0.6197, Train Steps/Sec: 1.23
|
| 469 |
+
[[34m2025-10-29 22:55:03[0m] (step=0041000) Train Loss: 0.6214, Train Steps/Sec: 1.23
|
| 470 |
+
[[34m2025-10-29 22:56:25[0m] (step=0041100) Train Loss: 0.6199, Train Steps/Sec: 1.22
|
| 471 |
+
[[34m2025-10-29 22:57:47[0m] (step=0041200) Train Loss: 0.6201, Train Steps/Sec: 1.22
|
| 472 |
+
[[34m2025-10-29 22:58:55[0m] Beginning epoch 33...
|
| 473 |
+
[[34m2025-10-29 22:59:11[0m] (step=0041300) Train Loss: 0.6208, Train Steps/Sec: 1.19
|
| 474 |
+
[[34m2025-10-29 23:00:32[0m] (step=0041400) Train Loss: 0.6202, Train Steps/Sec: 1.23
|
| 475 |
+
[[34m2025-10-29 23:01:54[0m] (step=0041500) Train Loss: 0.6197, Train Steps/Sec: 1.23
|
| 476 |
+
[[34m2025-10-29 23:03:16[0m] (step=0041600) Train Loss: 0.6208, Train Steps/Sec: 1.23
|
| 477 |
+
[[34m2025-10-29 23:04:37[0m] (step=0041700) Train Loss: 0.6198, Train Steps/Sec: 1.23
|
| 478 |
+
[[34m2025-10-29 23:05:59[0m] (step=0041800) Train Loss: 0.6198, Train Steps/Sec: 1.23
|
| 479 |
+
[[34m2025-10-29 23:07:20[0m] (step=0041900) Train Loss: 0.6218, Train Steps/Sec: 1.23
|
| 480 |
+
[[34m2025-10-29 23:08:41[0m] (step=0042000) Train Loss: 0.6204, Train Steps/Sec: 1.23
|
| 481 |
+
[[34m2025-10-29 23:10:03[0m] (step=0042100) Train Loss: 0.6209, Train Steps/Sec: 1.23
|
| 482 |
+
[[34m2025-10-29 23:11:24[0m] (step=0042200) Train Loss: 0.6198, Train Steps/Sec: 1.23
|
| 483 |
+
[[34m2025-10-29 23:12:46[0m] (step=0042300) Train Loss: 0.6200, Train Steps/Sec: 1.23
|
| 484 |
+
[[34m2025-10-29 23:14:07[0m] (step=0042400) Train Loss: 0.6196, Train Steps/Sec: 1.23
|
| 485 |
+
[[34m2025-10-29 23:15:29[0m] (step=0042500) Train Loss: 0.6186, Train Steps/Sec: 1.23
|
| 486 |
+
[[34m2025-10-29 23:15:57[0m] Beginning epoch 34...
|
| 487 |
+
[[34m2025-10-29 23:16:53[0m] (step=0042600) Train Loss: 0.6204, Train Steps/Sec: 1.19
|
| 488 |
+
[[34m2025-10-29 23:18:15[0m] (step=0042700) Train Loss: 0.6199, Train Steps/Sec: 1.22
|
| 489 |
+
[[34m2025-10-29 23:19:37[0m] (step=0042800) Train Loss: 0.6206, Train Steps/Sec: 1.22
|
| 490 |
+
[[34m2025-10-29 23:20:58[0m] (step=0042900) Train Loss: 0.6195, Train Steps/Sec: 1.23
|
| 491 |
+
[[34m2025-10-29 23:22:20[0m] (step=0043000) Train Loss: 0.6205, Train Steps/Sec: 1.22
|
| 492 |
+
[[34m2025-10-29 23:23:42[0m] (step=0043100) Train Loss: 0.6180, Train Steps/Sec: 1.23
|
| 493 |
+
[[34m2025-10-29 23:25:03[0m] (step=0043200) Train Loss: 0.6208, Train Steps/Sec: 1.23
|
| 494 |
+
[[34m2025-10-29 23:26:25[0m] (step=0043300) Train Loss: 0.6193, Train Steps/Sec: 1.23
|
| 495 |
+
[[34m2025-10-29 23:27:46[0m] (step=0043400) Train Loss: 0.6203, Train Steps/Sec: 1.23
|
| 496 |
+
[[34m2025-10-29 23:29:08[0m] (step=0043500) Train Loss: 0.6197, Train Steps/Sec: 1.23
|
| 497 |
+
[[34m2025-10-29 23:30:29[0m] (step=0043600) Train Loss: 0.6196, Train Steps/Sec: 1.23
|
| 498 |
+
[[34m2025-10-29 23:31:50[0m] (step=0043700) Train Loss: 0.6193, Train Steps/Sec: 1.23
|
| 499 |
+
[[34m2025-10-29 23:33:00[0m] Beginning epoch 35...
|
| 500 |
+
[[34m2025-10-29 23:33:14[0m] (step=0043800) Train Loss: 0.6201, Train Steps/Sec: 1.19
|
| 501 |
+
[[34m2025-10-29 23:34:36[0m] (step=0043900) Train Loss: 0.6189, Train Steps/Sec: 1.23
|
| 502 |
+
[[34m2025-10-29 23:35:57[0m] (step=0044000) Train Loss: 0.6185, Train Steps/Sec: 1.23
|
| 503 |
+
[[34m2025-10-29 23:37:19[0m] (step=0044100) Train Loss: 0.6194, Train Steps/Sec: 1.23
|
| 504 |
+
[[34m2025-10-29 23:38:40[0m] (step=0044200) Train Loss: 0.6191, Train Steps/Sec: 1.23
|
| 505 |
+
[[34m2025-10-29 23:40:02[0m] (step=0044300) Train Loss: 0.6194, Train Steps/Sec: 1.23
|
| 506 |
+
[[34m2025-10-29 23:41:24[0m] (step=0044400) Train Loss: 0.6179, Train Steps/Sec: 1.22
|
| 507 |
+
[[34m2025-10-29 23:42:46[0m] (step=0044500) Train Loss: 0.6185, Train Steps/Sec: 1.22
|
| 508 |
+
[[34m2025-10-29 23:44:08[0m] (step=0044600) Train Loss: 0.6180, Train Steps/Sec: 1.23
|
| 509 |
+
[[34m2025-10-29 23:45:29[0m] (step=0044700) Train Loss: 0.6207, Train Steps/Sec: 1.23
|
| 510 |
+
[[34m2025-10-29 23:46:51[0m] (step=0044800) Train Loss: 0.6189, Train Steps/Sec: 1.23
|
| 511 |
+
[[34m2025-10-29 23:48:12[0m] (step=0044900) Train Loss: 0.6183, Train Steps/Sec: 1.23
|
| 512 |
+
[[34m2025-10-29 23:49:34[0m] (step=0045000) Train Loss: 0.6190, Train Steps/Sec: 1.23
|
| 513 |
+
[[34m2025-10-29 23:50:03[0m] Beginning epoch 36...
|
| 514 |
+
[[34m2025-10-29 23:50:58[0m] (step=0045100) Train Loss: 0.6198, Train Steps/Sec: 1.19
|
| 515 |
+
[[34m2025-10-29 23:52:19[0m] (step=0045200) Train Loss: 0.6184, Train Steps/Sec: 1.23
|
| 516 |
+
[[34m2025-10-29 23:53:41[0m] (step=0045300) Train Loss: 0.6175, Train Steps/Sec: 1.23
|
| 517 |
+
[[34m2025-10-29 23:55:02[0m] (step=0045400) Train Loss: 0.6187, Train Steps/Sec: 1.23
|
| 518 |
+
[[34m2025-10-29 23:56:24[0m] (step=0045500) Train Loss: 0.6187, Train Steps/Sec: 1.23
|
| 519 |
+
[[34m2025-10-29 23:57:45[0m] (step=0045600) Train Loss: 0.6181, Train Steps/Sec: 1.23
|
| 520 |
+
[[34m2025-10-29 23:59:07[0m] (step=0045700) Train Loss: 0.6185, Train Steps/Sec: 1.23
|
| 521 |
+
[[34m2025-10-30 00:00:28[0m] (step=0045800) Train Loss: 0.6188, Train Steps/Sec: 1.23
|
| 522 |
+
[[34m2025-10-30 00:01:50[0m] (step=0045900) Train Loss: 0.6170, Train Steps/Sec: 1.22
|
| 523 |
+
[[34m2025-10-30 00:03:11[0m] (step=0046000) Train Loss: 0.6172, Train Steps/Sec: 1.23
|
| 524 |
+
[[34m2025-10-30 00:04:34[0m] (step=0046100) Train Loss: 0.6168, Train Steps/Sec: 1.22
|
| 525 |
+
[[34m2025-10-30 00:05:55[0m] (step=0046200) Train Loss: 0.6189, Train Steps/Sec: 1.22
|
| 526 |
+
[[34m2025-10-30 00:07:07[0m] Beginning epoch 37...
|
| 527 |
+
[[34m2025-10-30 00:07:19[0m] (step=0046300) Train Loss: 0.6189, Train Steps/Sec: 1.19
|
| 528 |
+
[[34m2025-10-30 00:08:41[0m] (step=0046400) Train Loss: 0.6191, Train Steps/Sec: 1.23
|
| 529 |
+
[[34m2025-10-30 00:10:02[0m] (step=0046500) Train Loss: 0.6166, Train Steps/Sec: 1.23
|
| 530 |
+
[[34m2025-10-30 00:11:24[0m] (step=0046600) Train Loss: 0.6165, Train Steps/Sec: 1.23
|
| 531 |
+
[[34m2025-10-30 00:12:45[0m] (step=0046700) Train Loss: 0.6171, Train Steps/Sec: 1.23
|
| 532 |
+
[[34m2025-10-30 00:14:07[0m] (step=0046800) Train Loss: 0.6173, Train Steps/Sec: 1.23
|
| 533 |
+
[[34m2025-10-30 00:15:28[0m] (step=0046900) Train Loss: 0.6184, Train Steps/Sec: 1.23
|
| 534 |
+
[[34m2025-10-30 00:16:50[0m] (step=0047000) Train Loss: 0.6170, Train Steps/Sec: 1.23
|
| 535 |
+
[[34m2025-10-30 00:18:11[0m] (step=0047100) Train Loss: 0.6176, Train Steps/Sec: 1.23
|
| 536 |
+
[[34m2025-10-30 00:19:33[0m] (step=0047200) Train Loss: 0.6187, Train Steps/Sec: 1.23
|
| 537 |
+
[[34m2025-10-30 00:20:54[0m] (step=0047300) Train Loss: 0.6184, Train Steps/Sec: 1.23
|
| 538 |
+
[[34m2025-10-30 00:22:16[0m] (step=0047400) Train Loss: 0.6178, Train Steps/Sec: 1.23
|
| 539 |
+
[[34m2025-10-30 00:23:37[0m] (step=0047500) Train Loss: 0.6177, Train Steps/Sec: 1.23
|
| 540 |
+
[[34m2025-10-30 00:24:09[0m] Beginning epoch 38...
|
| 541 |
+
[[34m2025-10-30 00:25:01[0m] (step=0047600) Train Loss: 0.6160, Train Steps/Sec: 1.19
|
| 542 |
+
[[34m2025-10-30 00:26:23[0m] (step=0047700) Train Loss: 0.6170, Train Steps/Sec: 1.22
|
| 543 |
+
[[34m2025-10-30 00:27:45[0m] (step=0047800) Train Loss: 0.6161, Train Steps/Sec: 1.22
|
| 544 |
+
[[34m2025-10-30 00:29:07[0m] (step=0047900) Train Loss: 0.6175, Train Steps/Sec: 1.23
|
| 545 |
+
[[34m2025-10-30 00:30:28[0m] (step=0048000) Train Loss: 0.6173, Train Steps/Sec: 1.23
|
| 546 |
+
[[34m2025-10-30 00:31:50[0m] (step=0048100) Train Loss: 0.6187, Train Steps/Sec: 1.23
|
| 547 |
+
[[34m2025-10-30 00:33:11[0m] (step=0048200) Train Loss: 0.6191, Train Steps/Sec: 1.23
|
| 548 |
+
[[34m2025-10-30 00:34:33[0m] (step=0048300) Train Loss: 0.6159, Train Steps/Sec: 1.23
|
| 549 |
+
[[34m2025-10-30 00:35:54[0m] (step=0048400) Train Loss: 0.6183, Train Steps/Sec: 1.23
|
| 550 |
+
[[34m2025-10-30 00:37:16[0m] (step=0048500) Train Loss: 0.6165, Train Steps/Sec: 1.23
|
| 551 |
+
[[34m2025-10-30 00:38:37[0m] (step=0048600) Train Loss: 0.6171, Train Steps/Sec: 1.23
|
| 552 |
+
[[34m2025-10-30 00:39:59[0m] (step=0048700) Train Loss: 0.6174, Train Steps/Sec: 1.23
|
| 553 |
+
[[34m2025-10-30 00:41:12[0m] Beginning epoch 39...
|
| 554 |
+
[[34m2025-10-30 00:41:23[0m] (step=0048800) Train Loss: 0.6161, Train Steps/Sec: 1.19
|
| 555 |
+
[[34m2025-10-30 00:42:45[0m] (step=0048900) Train Loss: 0.6137, Train Steps/Sec: 1.23
|
| 556 |
+
[[34m2025-10-30 00:44:06[0m] (step=0049000) Train Loss: 0.6157, Train Steps/Sec: 1.23
|
| 557 |
+
[[34m2025-10-30 00:45:28[0m] (step=0049100) Train Loss: 0.6157, Train Steps/Sec: 1.23
|
| 558 |
+
[[34m2025-10-30 00:46:49[0m] (step=0049200) Train Loss: 0.6173, Train Steps/Sec: 1.23
|
| 559 |
+
[[34m2025-10-30 00:48:11[0m] (step=0049300) Train Loss: 0.6155, Train Steps/Sec: 1.23
|
| 560 |
+
[[34m2025-10-30 00:49:32[0m] (step=0049400) Train Loss: 0.6157, Train Steps/Sec: 1.22
|
| 561 |
+
[[34m2025-10-30 00:50:55[0m] (step=0049500) Train Loss: 0.6156, Train Steps/Sec: 1.22
|
| 562 |
+
[[34m2025-10-30 00:52:16[0m] (step=0049600) Train Loss: 0.6152, Train Steps/Sec: 1.23
|
| 563 |
+
[[34m2025-10-30 00:53:38[0m] (step=0049700) Train Loss: 0.6167, Train Steps/Sec: 1.23
|
| 564 |
+
[[34m2025-10-30 00:54:59[0m] (step=0049800) Train Loss: 0.6150, Train Steps/Sec: 1.23
|
| 565 |
+
[[34m2025-10-30 00:56:21[0m] (step=0049900) Train Loss: 0.6153, Train Steps/Sec: 1.23
|
| 566 |
+
[[34m2025-10-30 00:57:42[0m] (step=0050000) Train Loss: 0.6171, Train Steps/Sec: 1.23
|
| 567 |
+
[[34m2025-10-30 00:58:38[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-spnorm-bf16/checkpoints/0050000.pt
|
| 568 |
+
[[34m2025-10-30 00:58:38[0m] Generating EMA samples...
|
| 569 |
+
[[34m2025-10-30 00:59:06[0m] Generating EMA samples done.
|
| 570 |
+
[[34m2025-10-30 00:59:39[0m] Beginning epoch 40...
|
| 571 |
+
[[34m2025-10-30 01:00:29[0m] (step=0050100) Train Loss: 0.6155, Train Steps/Sec: 0.60
|
| 572 |
+
[[34m2025-10-30 01:01:51[0m] (step=0050200) Train Loss: 0.6157, Train Steps/Sec: 1.23
|
| 573 |
+
[[34m2025-10-30 01:03:12[0m] (step=0050300) Train Loss: 0.6158, Train Steps/Sec: 1.23
|
| 574 |
+
[[34m2025-10-30 01:04:34[0m] (step=0050400) Train Loss: 0.6179, Train Steps/Sec: 1.23
|
| 575 |
+
[[34m2025-10-30 01:05:55[0m] (step=0050500) Train Loss: 0.6155, Train Steps/Sec: 1.23
|
| 576 |
+
[[34m2025-10-30 01:07:17[0m] (step=0050600) Train Loss: 0.6144, Train Steps/Sec: 1.23
|
| 577 |
+
[[34m2025-10-30 01:08:38[0m] (step=0050700) Train Loss: 0.6157, Train Steps/Sec: 1.23
|
| 578 |
+
[[34m2025-10-30 01:10:00[0m] (step=0050800) Train Loss: 0.6172, Train Steps/Sec: 1.23
|
| 579 |
+
[[34m2025-10-30 01:11:21[0m] (step=0050900) Train Loss: 0.6173, Train Steps/Sec: 1.23
|
| 580 |
+
[[34m2025-10-30 01:12:43[0m] (step=0051000) Train Loss: 0.6164, Train Steps/Sec: 1.23
|
| 581 |
+
[[34m2025-10-30 01:14:05[0m] (step=0051100) Train Loss: 0.6165, Train Steps/Sec: 1.22
|
| 582 |
+
[[34m2025-10-30 01:15:27[0m] (step=0051200) Train Loss: 0.6156, Train Steps/Sec: 1.22
|
| 583 |
+
[[34m2025-10-30 01:16:41[0m] Beginning epoch 41...
|
| 584 |
+
[[34m2025-10-30 01:16:50[0m] (step=0051300) Train Loss: 0.6145, Train Steps/Sec: 1.19
|
| 585 |
+
[[34m2025-10-30 01:18:12[0m] (step=0051400) Train Loss: 0.6152, Train Steps/Sec: 1.23
|
| 586 |
+
[[34m2025-10-30 01:19:34[0m] (step=0051500) Train Loss: 0.6149, Train Steps/Sec: 1.22
|
| 587 |
+
[[34m2025-10-30 01:20:55[0m] (step=0051600) Train Loss: 0.6157, Train Steps/Sec: 1.23
|
| 588 |
+
[[34m2025-10-30 01:22:17[0m] (step=0051700) Train Loss: 0.6152, Train Steps/Sec: 1.23
|
| 589 |
+
[[34m2025-10-30 01:23:38[0m] (step=0051800) Train Loss: 0.6169, Train Steps/Sec: 1.23
|
| 590 |
+
[[34m2025-10-30 01:25:00[0m] (step=0051900) Train Loss: 0.6166, Train Steps/Sec: 1.23
|
| 591 |
+
[[34m2025-10-30 01:26:21[0m] (step=0052000) Train Loss: 0.6167, Train Steps/Sec: 1.23
|
| 592 |
+
[[34m2025-10-30 01:27:43[0m] (step=0052100) Train Loss: 0.6168, Train Steps/Sec: 1.23
|
| 593 |
+
[[34m2025-10-30 01:29:04[0m] (step=0052200) Train Loss: 0.6165, Train Steps/Sec: 1.23
|
| 594 |
+
[[34m2025-10-30 01:30:25[0m] (step=0052300) Train Loss: 0.6166, Train Steps/Sec: 1.23
|
| 595 |
+
[[34m2025-10-30 01:31:47[0m] (step=0052400) Train Loss: 0.6166, Train Steps/Sec: 1.23
|
| 596 |
+
[[34m2025-10-30 01:33:08[0m] (step=0052500) Train Loss: 1.4301, Train Steps/Sec: 1.23
|
| 597 |
+
[[34m2025-10-30 01:33:43[0m] Beginning epoch 42...
|
| 598 |
+
[[34m2025-10-30 01:34:32[0m] (step=0052600) Train Loss: 1.6885, Train Steps/Sec: 1.19
|
| 599 |
+
[[34m2025-10-30 01:35:54[0m] (step=0052700) Train Loss: 1.6226, Train Steps/Sec: 1.23
|
| 600 |
+
[[34m2025-10-30 01:37:16[0m] (step=0052800) Train Loss: 2.1252, Train Steps/Sec: 1.22
|
| 601 |
+
[[34m2025-10-30 01:38:34[0m] (step=0052900) Train Loss: nan, Train Steps/Sec: 1.28
|
| 602 |
+
[[34m2025-10-30 01:39:52[0m] (step=0053000) Train Loss: nan, Train Steps/Sec: 1.29
|
| 603 |
+
[[34m2025-10-30 01:41:09[0m] (step=0053100) Train Loss: nan, Train Steps/Sec: 1.29
|
| 604 |
+
[[34m2025-10-30 01:42:27[0m] (step=0053200) Train Loss: nan, Train Steps/Sec: 1.29
|
| 605 |
+
[[34m2025-10-30 01:43:44[0m] (step=0053300) Train Loss: nan, Train Steps/Sec: 1.29
|
| 606 |
+
[[34m2025-10-30 01:45:02[0m] (step=0053400) Train Loss: nan, Train Steps/Sec: 1.29
|
| 607 |
+
[[34m2025-10-30 01:46:19[0m] (step=0053500) Train Loss: nan, Train Steps/Sec: 1.29
|
| 608 |
+
[[34m2025-10-30 01:47:37[0m] (step=0053600) Train Loss: nan, Train Steps/Sec: 1.29
|
| 609 |
+
[[34m2025-10-30 01:48:54[0m] (step=0053700) Train Loss: nan, Train Steps/Sec: 1.29
|
| 610 |
+
[[34m2025-10-30 01:50:07[0m] Beginning epoch 43...
|
| 611 |
+
[[34m2025-10-30 01:50:14[0m] (step=0053800) Train Loss: nan, Train Steps/Sec: 1.25
|
| 612 |
+
[[34m2025-10-30 01:51:32[0m] (step=0053900) Train Loss: nan, Train Steps/Sec: 1.29
|
| 613 |
+
[[34m2025-10-30 01:52:49[0m] (step=0054000) Train Loss: nan, Train Steps/Sec: 1.29
|
| 614 |
+
[[34m2025-10-30 01:54:07[0m] (step=0054100) Train Loss: nan, Train Steps/Sec: 1.29
|
| 615 |
+
[[34m2025-10-30 01:55:24[0m] (step=0054200) Train Loss: nan, Train Steps/Sec: 1.29
|
| 616 |
+
[[34m2025-10-30 01:56:42[0m] (step=0054300) Train Loss: nan, Train Steps/Sec: 1.29
|
| 617 |
+
[[34m2025-10-30 01:58:00[0m] (step=0054400) Train Loss: nan, Train Steps/Sec: 1.28
|
| 618 |
+
[[34m2025-10-30 01:59:18[0m] (step=0054500) Train Loss: nan, Train Steps/Sec: 1.28
|
| 619 |
+
[[34m2025-10-30 02:00:36[0m] (step=0054600) Train Loss: nan, Train Steps/Sec: 1.29
|
| 620 |
+
[[34m2025-10-30 02:01:53[0m] (step=0054700) Train Loss: nan, Train Steps/Sec: 1.29
|
| 621 |
+
[[34m2025-10-30 02:03:11[0m] (step=0054800) Train Loss: nan, Train Steps/Sec: 1.29
|
| 622 |
+
[[34m2025-10-30 02:04:28[0m] (step=0054900) Train Loss: nan, Train Steps/Sec: 1.29
|
| 623 |
+
[[34m2025-10-30 02:05:46[0m] (step=0055000) Train Loss: nan, Train Steps/Sec: 1.29
|
| 624 |
+
[[34m2025-10-30 02:06:20[0m] Beginning epoch 44...
|
| 625 |
+
[[34m2025-10-30 02:07:06[0m] (step=0055100) Train Loss: nan, Train Steps/Sec: 1.25
|
| 626 |
+
[[34m2025-10-30 02:08:23[0m] (step=0055200) Train Loss: nan, Train Steps/Sec: 1.29
|
| 627 |
+
[[34m2025-10-30 02:09:41[0m] (step=0055300) Train Loss: nan, Train Steps/Sec: 1.29
|
| 628 |
+
[[34m2025-10-30 02:10:58[0m] (step=0055400) Train Loss: nan, Train Steps/Sec: 1.29
|
| 629 |
+
[[34m2025-10-30 02:12:16[0m] (step=0055500) Train Loss: nan, Train Steps/Sec: 1.29
|
| 630 |
+
[[34m2025-10-30 02:13:33[0m] (step=0055600) Train Loss: nan, Train Steps/Sec: 1.29
|
| 631 |
+
[[34m2025-10-30 02:14:51[0m] (step=0055700) Train Loss: nan, Train Steps/Sec: 1.29
|
| 632 |
+
[[34m2025-10-30 02:16:08[0m] (step=0055800) Train Loss: nan, Train Steps/Sec: 1.29
|
| 633 |
+
[[34m2025-10-30 02:17:26[0m] (step=0055900) Train Loss: nan, Train Steps/Sec: 1.29
|
| 634 |
+
[[34m2025-10-30 02:18:43[0m] (step=0056000) Train Loss: nan, Train Steps/Sec: 1.29
|
| 635 |
+
[[34m2025-10-30 02:20:01[0m] (step=0056100) Train Loss: nan, Train Steps/Sec: 1.29
|
| 636 |
+
[[34m2025-10-30 02:21:19[0m] (step=0056200) Train Loss: nan, Train Steps/Sec: 1.28
|
| 637 |
+
[[34m2025-10-30 02:22:34[0m] Beginning epoch 45...
|
| 638 |
+
[[34m2025-10-30 02:22:39[0m] (step=0056300) Train Loss: nan, Train Steps/Sec: 1.25
|
| 639 |
+
[[34m2025-10-30 02:23:57[0m] (step=0056400) Train Loss: nan, Train Steps/Sec: 1.29
|
| 640 |
+
[[34m2025-10-30 02:25:14[0m] (step=0056500) Train Loss: nan, Train Steps/Sec: 1.29
|
| 641 |
+
[[34m2025-10-30 02:26:32[0m] (step=0056600) Train Loss: nan, Train Steps/Sec: 1.29
|
| 642 |
+
[[34m2025-10-30 02:27:49[0m] (step=0056700) Train Loss: nan, Train Steps/Sec: 1.29
|
| 643 |
+
[[34m2025-10-30 02:29:07[0m] (step=0056800) Train Loss: nan, Train Steps/Sec: 1.29
|
| 644 |
+
[[34m2025-10-30 02:30:25[0m] (step=0056900) Train Loss: nan, Train Steps/Sec: 1.29
|