Upload folder using huggingface_hub
Browse files
stage2/lightningdit-xl-spatialpe-vit-g-bf16/checkpoints/0025000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc073e7b9e0baf0e6f698c7fd4bfbc2172c3b32cc39993ec9150b7590a7eb1b2
|
| 3 |
+
size 19268192626
|
stage2/lightningdit-xl-spatialpe-vit-g-bf16/checkpoints/0050000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2efceb9187404edb8aecff939bfa976eb34be22938ab730f244944ed2389e38f
|
| 3 |
+
size 19268192626
|
stage2/lightningdit-xl-spatialpe-vit-g-bf16/log.txt
ADDED
|
@@ -0,0 +1,967 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[[34m2025-10-28 00:21:17[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-spatialpe-vit-g-bf16
|
| 2 |
+
[[34m2025-10-28 00:21:39[0m] Missing keys for loading vision encoder: []
|
| 3 |
+
[[34m2025-10-28 00:21:39[0m] Unexpected keys for loading vision encoder: []
|
| 4 |
+
[[34m2025-10-28 00:21:55[0m] Model Parameters: 1204.40M
|
| 5 |
+
[[34m2025-10-28 00:22:01[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/train)
|
| 6 |
+
[[34m2025-10-28 00:22:01[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 7 |
+
[[34m2025-10-28 00:22:01[0m] Precision mode: bf16
|
| 8 |
+
[[34m2025-10-28 00:22:01[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 9 |
+
[[34m2025-10-28 00:22:01[0m] 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 |
+
[[34m2025-10-28 00:22:01[0m] Training for 80 epochs...
|
| 12 |
+
[[34m2025-10-28 00:22:01[0m] Beginning epoch 0...
|
| 13 |
+
[[34m2025-10-28 00:53:57[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-spatialpe-vit-g-bf16
|
| 14 |
+
[[34m2025-10-28 00:54:18[0m] Missing keys for loading vision encoder: []
|
| 15 |
+
[[34m2025-10-28 00:54:18[0m] Unexpected keys for loading vision encoder: []
|
| 16 |
+
[[34m2025-10-28 00:54:36[0m] Model Parameters: 1204.40M
|
| 17 |
+
[[34m2025-10-28 00:54:40[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/spatialpe-vit-g_hfdataset_precentercrop_True_train_bfloat16)
|
| 18 |
+
[[34m2025-10-28 00:54:40[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 19 |
+
[[34m2025-10-28 00:54:40[0m] Precision mode: bf16
|
| 20 |
+
[[34m2025-10-28 00:54:40[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 21 |
+
[[34m2025-10-28 00:54:40[0m] Optimizer: ADAMW with lr=0.0002, betas=(0.9, 0.95), weight_decay=0.0, eps=1e-08
|
| 22 |
+
Scheduler: linear with warmup_steps=0, decay_end_steps=0, final_lr=0.0002
|
| 23 |
+
[[34m2025-10-28 00:54:41[0m] Training for 80 epochs...
|
| 24 |
+
[[34m2025-10-28 00:54:41[0m] Beginning epoch 0...
|
| 25 |
+
[[34m2025-10-28 00:54:52[0m] Generating EMA samples...
|
| 26 |
+
[[34m2025-10-28 00:55:21[0m] Generating EMA samples done.
|
| 27 |
+
[[34m2025-10-28 00:56:49[0m] (step=0000100) Train Loss: 1.6467, Train Steps/Sec: 0.78
|
| 28 |
+
[[34m2025-10-28 00:58:17[0m] (step=0000200) Train Loss: 1.2729, Train Steps/Sec: 1.13
|
| 29 |
+
[[34m2025-10-28 00:59:45[0m] (step=0000300) Train Loss: 1.1285, Train Steps/Sec: 1.13
|
| 30 |
+
[[34m2025-10-28 01:01:14[0m] (step=0000400) Train Loss: 1.0258, Train Steps/Sec: 1.13
|
| 31 |
+
[[34m2025-10-28 01:02:42[0m] (step=0000500) Train Loss: 0.9680, Train Steps/Sec: 1.13
|
| 32 |
+
[[34m2025-10-28 01:04:10[0m] (step=0000600) Train Loss: 0.9305, Train Steps/Sec: 1.13
|
| 33 |
+
[[34m2025-10-28 01:05:38[0m] (step=0000700) Train Loss: 0.9013, Train Steps/Sec: 1.13
|
| 34 |
+
[[34m2025-10-28 01:07:07[0m] (step=0000800) Train Loss: 0.8809, Train Steps/Sec: 1.13
|
| 35 |
+
[[34m2025-10-28 01:08:35[0m] (step=0000900) Train Loss: 0.8634, Train Steps/Sec: 1.13
|
| 36 |
+
[[34m2025-10-28 01:10:03[0m] (step=0001000) Train Loss: 0.8494, Train Steps/Sec: 1.13
|
| 37 |
+
[[34m2025-10-28 01:11:31[0m] (step=0001100) Train Loss: 0.8368, Train Steps/Sec: 1.13
|
| 38 |
+
[[34m2025-10-28 01:13:00[0m] (step=0001200) Train Loss: 0.8263, Train Steps/Sec: 1.13
|
| 39 |
+
[[34m2025-10-28 01:13:46[0m] Beginning epoch 1...
|
| 40 |
+
[[34m2025-10-28 01:14:32[0m] (step=0001300) Train Loss: 0.8144, Train Steps/Sec: 1.08
|
| 41 |
+
[[34m2025-10-28 01:16:00[0m] (step=0001400) Train Loss: 0.8063, Train Steps/Sec: 1.13
|
| 42 |
+
[[34m2025-10-28 01:17:29[0m] (step=0001500) Train Loss: 0.7979, Train Steps/Sec: 1.13
|
| 43 |
+
[[34m2025-10-28 01:18:57[0m] (step=0001600) Train Loss: 0.7920, Train Steps/Sec: 1.13
|
| 44 |
+
[[34m2025-10-28 01:20:25[0m] (step=0001700) Train Loss: 0.7843, Train Steps/Sec: 1.13
|
| 45 |
+
[[34m2025-10-28 01:21:54[0m] (step=0001800) Train Loss: 0.7783, Train Steps/Sec: 1.13
|
| 46 |
+
[[34m2025-10-28 01:23:22[0m] (step=0001900) Train Loss: 0.7735, Train Steps/Sec: 1.13
|
| 47 |
+
[[34m2025-10-28 01:24:50[0m] (step=0002000) Train Loss: 0.7679, Train Steps/Sec: 1.13
|
| 48 |
+
[[34m2025-10-28 01:26:18[0m] (step=0002100) Train Loss: 0.7632, Train Steps/Sec: 1.13
|
| 49 |
+
[[34m2025-10-28 01:27:47[0m] (step=0002200) Train Loss: 0.7598, Train Steps/Sec: 1.13
|
| 50 |
+
[[34m2025-10-28 01:29:15[0m] (step=0002300) Train Loss: 0.7543, Train Steps/Sec: 1.13
|
| 51 |
+
[[34m2025-10-28 01:30:43[0m] (step=0002400) Train Loss: 0.7508, Train Steps/Sec: 1.13
|
| 52 |
+
[[34m2025-10-28 01:32:11[0m] (step=0002500) Train Loss: 0.7472, Train Steps/Sec: 1.13
|
| 53 |
+
[[34m2025-10-28 01:32:14[0m] Beginning epoch 2...
|
| 54 |
+
[[34m2025-10-28 01:33:44[0m] (step=0002600) Train Loss: 0.7452, Train Steps/Sec: 1.08
|
| 55 |
+
[[34m2025-10-28 01:35:13[0m] (step=0002700) Train Loss: 0.7403, Train Steps/Sec: 1.13
|
| 56 |
+
[[34m2025-10-28 01:36:41[0m] (step=0002800) Train Loss: 0.7364, Train Steps/Sec: 1.13
|
| 57 |
+
[[34m2025-10-28 01:38:09[0m] (step=0002900) Train Loss: 0.7343, Train Steps/Sec: 1.13
|
| 58 |
+
[[34m2025-10-28 01:39:37[0m] (step=0003000) Train Loss: 0.7326, Train Steps/Sec: 1.13
|
| 59 |
+
[[34m2025-10-28 01:41:06[0m] (step=0003100) Train Loss: 0.7286, Train Steps/Sec: 1.13
|
| 60 |
+
[[34m2025-10-28 01:42:34[0m] (step=0003200) Train Loss: 0.7265, Train Steps/Sec: 1.13
|
| 61 |
+
[[34m2025-10-28 01:44:02[0m] (step=0003300) Train Loss: 0.7241, Train Steps/Sec: 1.13
|
| 62 |
+
[[34m2025-10-28 01:45:30[0m] (step=0003400) Train Loss: 0.7216, Train Steps/Sec: 1.13
|
| 63 |
+
[[34m2025-10-28 01:46:58[0m] (step=0003500) Train Loss: 0.7196, Train Steps/Sec: 1.13
|
| 64 |
+
[[34m2025-10-28 01:48:27[0m] (step=0003600) Train Loss: 0.7174, Train Steps/Sec: 1.13
|
| 65 |
+
[[34m2025-10-28 01:49:55[0m] (step=0003700) Train Loss: 0.7139, Train Steps/Sec: 1.13
|
| 66 |
+
[[34m2025-10-28 01:50:42[0m] Beginning epoch 3...
|
| 67 |
+
[[34m2025-10-28 01:51:27[0m] (step=0003800) Train Loss: 0.7134, Train Steps/Sec: 1.08
|
| 68 |
+
[[34m2025-10-28 01:52:55[0m] (step=0003900) Train Loss: 0.7109, Train Steps/Sec: 1.13
|
| 69 |
+
[[34m2025-10-28 01:54:24[0m] (step=0004000) Train Loss: 0.7099, Train Steps/Sec: 1.13
|
| 70 |
+
[[34m2025-10-28 01:55:52[0m] (step=0004100) Train Loss: 0.7072, Train Steps/Sec: 1.13
|
| 71 |
+
[[34m2025-10-28 01:57:20[0m] (step=0004200) Train Loss: 0.7056, Train Steps/Sec: 1.13
|
| 72 |
+
[[34m2025-10-28 01:58:48[0m] (step=0004300) Train Loss: 0.7053, Train Steps/Sec: 1.13
|
| 73 |
+
[[34m2025-10-28 02:00:17[0m] (step=0004400) Train Loss: 0.7026, Train Steps/Sec: 1.13
|
| 74 |
+
[[34m2025-10-28 02:01:45[0m] (step=0004500) Train Loss: 0.7022, Train Steps/Sec: 1.13
|
| 75 |
+
[[34m2025-10-28 02:03:13[0m] (step=0004600) Train Loss: 0.6998, Train Steps/Sec: 1.13
|
| 76 |
+
[[34m2025-10-28 02:04:41[0m] (step=0004700) Train Loss: 0.6991, Train Steps/Sec: 1.13
|
| 77 |
+
[[34m2025-10-28 02:06:10[0m] (step=0004800) Train Loss: 0.6981, Train Steps/Sec: 1.13
|
| 78 |
+
[[34m2025-10-28 02:07:38[0m] (step=0004900) Train Loss: 0.6953, Train Steps/Sec: 1.13
|
| 79 |
+
[[34m2025-10-28 02:09:06[0m] (step=0005000) Train Loss: 0.6943, Train Steps/Sec: 1.13
|
| 80 |
+
[[34m2025-10-28 02:09:10[0m] Beginning epoch 4...
|
| 81 |
+
[[34m2025-10-28 02:10:38[0m] (step=0005100) Train Loss: 0.6928, Train Steps/Sec: 1.09
|
| 82 |
+
[[34m2025-10-28 02:12:06[0m] (step=0005200) Train Loss: 0.6915, Train Steps/Sec: 1.13
|
| 83 |
+
[[34m2025-10-28 02:13:35[0m] (step=0005300) Train Loss: 0.6908, Train Steps/Sec: 1.13
|
| 84 |
+
[[34m2025-10-28 02:15:03[0m] (step=0005400) Train Loss: 0.6895, Train Steps/Sec: 1.13
|
| 85 |
+
[[34m2025-10-28 02:16:31[0m] (step=0005500) Train Loss: 0.6878, Train Steps/Sec: 1.13
|
| 86 |
+
[[34m2025-10-28 02:17:59[0m] (step=0005600) Train Loss: 0.6867, Train Steps/Sec: 1.13
|
| 87 |
+
[[34m2025-10-28 02:19:28[0m] (step=0005700) Train Loss: 0.6863, Train Steps/Sec: 1.13
|
| 88 |
+
[[34m2025-10-28 02:20:56[0m] (step=0005800) Train Loss: 0.6855, Train Steps/Sec: 1.13
|
| 89 |
+
[[34m2025-10-28 02:22:24[0m] (step=0005900) Train Loss: 0.6830, Train Steps/Sec: 1.13
|
| 90 |
+
[[34m2025-10-28 02:23:52[0m] (step=0006000) Train Loss: 0.6835, Train Steps/Sec: 1.13
|
| 91 |
+
[[34m2025-10-28 02:25:21[0m] (step=0006100) Train Loss: 0.6826, Train Steps/Sec: 1.13
|
| 92 |
+
[[34m2025-10-28 02:26:49[0m] (step=0006200) Train Loss: 0.6804, Train Steps/Sec: 1.13
|
| 93 |
+
[[34m2025-10-28 02:27:38[0m] Beginning epoch 5...
|
| 94 |
+
[[34m2025-10-28 02:28:21[0m] (step=0006300) Train Loss: 0.6793, Train Steps/Sec: 1.08
|
| 95 |
+
[[34m2025-10-28 02:29:49[0m] (step=0006400) Train Loss: 0.6804, Train Steps/Sec: 1.13
|
| 96 |
+
[[34m2025-10-28 02:31:17[0m] (step=0006500) Train Loss: 0.6790, Train Steps/Sec: 1.13
|
| 97 |
+
[[34m2025-10-28 02:32:46[0m] (step=0006600) Train Loss: 0.6786, Train Steps/Sec: 1.13
|
| 98 |
+
[[34m2025-10-28 02:34:14[0m] (step=0006700) Train Loss: 0.6768, Train Steps/Sec: 1.13
|
| 99 |
+
[[34m2025-10-28 02:35:42[0m] (step=0006800) Train Loss: 0.6757, Train Steps/Sec: 1.13
|
| 100 |
+
[[34m2025-10-28 02:37:10[0m] (step=0006900) Train Loss: 0.6750, Train Steps/Sec: 1.13
|
| 101 |
+
[[34m2025-10-28 02:38:39[0m] (step=0007000) Train Loss: 0.6742, Train Steps/Sec: 1.13
|
| 102 |
+
[[34m2025-10-28 02:40:07[0m] (step=0007100) Train Loss: 0.6740, Train Steps/Sec: 1.13
|
| 103 |
+
[[34m2025-10-28 02:41:36[0m] (step=0007200) Train Loss: 0.6729, Train Steps/Sec: 1.13
|
| 104 |
+
[[34m2025-10-28 02:43:04[0m] (step=0007300) Train Loss: 0.6710, Train Steps/Sec: 1.13
|
| 105 |
+
[[34m2025-10-28 02:44:32[0m] (step=0007400) Train Loss: 0.6710, Train Steps/Sec: 1.13
|
| 106 |
+
[[34m2025-10-28 02:46:00[0m] (step=0007500) Train Loss: 0.6711, Train Steps/Sec: 1.13
|
| 107 |
+
[[34m2025-10-28 02:46:06[0m] Beginning epoch 6...
|
| 108 |
+
[[34m2025-10-28 02:47:33[0m] (step=0007600) Train Loss: 0.6697, Train Steps/Sec: 1.08
|
| 109 |
+
[[34m2025-10-28 02:49:01[0m] (step=0007700) Train Loss: 0.6690, Train Steps/Sec: 1.13
|
| 110 |
+
[[34m2025-10-28 02:50:29[0m] (step=0007800) Train Loss: 0.6689, Train Steps/Sec: 1.13
|
| 111 |
+
[[34m2025-10-28 02:51:58[0m] (step=0007900) Train Loss: 0.6681, Train Steps/Sec: 1.12
|
| 112 |
+
[[34m2025-10-28 02:53:27[0m] (step=0008000) Train Loss: 0.6663, Train Steps/Sec: 1.13
|
| 113 |
+
[[34m2025-10-28 02:54:55[0m] (step=0008100) Train Loss: 0.6675, Train Steps/Sec: 1.13
|
| 114 |
+
[[34m2025-10-28 02:56:23[0m] (step=0008200) Train Loss: 0.6660, Train Steps/Sec: 1.13
|
| 115 |
+
[[34m2025-10-28 02:57:51[0m] (step=0008300) Train Loss: 0.6654, Train Steps/Sec: 1.13
|
| 116 |
+
[[34m2025-10-28 02:59:19[0m] (step=0008400) Train Loss: 0.6652, Train Steps/Sec: 1.13
|
| 117 |
+
[[34m2025-10-28 03:00:47[0m] (step=0008500) Train Loss: 0.6633, Train Steps/Sec: 1.13
|
| 118 |
+
[[34m2025-10-28 03:02:15[0m] (step=0008600) Train Loss: 0.6641, Train Steps/Sec: 1.13
|
| 119 |
+
[[34m2025-10-28 03:03:44[0m] (step=0008700) Train Loss: 0.6649, Train Steps/Sec: 1.13
|
| 120 |
+
[[34m2025-10-28 03:04:35[0m] Beginning epoch 7...
|
| 121 |
+
[[34m2025-10-28 03:05:17[0m] (step=0008800) Train Loss: 0.6632, Train Steps/Sec: 1.08
|
| 122 |
+
[[34m2025-10-28 03:06:45[0m] (step=0008900) Train Loss: 0.6617, Train Steps/Sec: 1.13
|
| 123 |
+
[[34m2025-10-28 03:08:13[0m] (step=0009000) Train Loss: 0.6620, Train Steps/Sec: 1.13
|
| 124 |
+
[[34m2025-10-28 03:09:41[0m] (step=0009100) Train Loss: 0.6619, Train Steps/Sec: 1.13
|
| 125 |
+
[[34m2025-10-28 03:11:09[0m] (step=0009200) Train Loss: 0.6627, Train Steps/Sec: 1.13
|
| 126 |
+
[[34m2025-10-28 03:12:37[0m] (step=0009300) Train Loss: 0.6606, Train Steps/Sec: 1.13
|
| 127 |
+
[[34m2025-10-28 03:14:06[0m] (step=0009400) Train Loss: 0.6597, Train Steps/Sec: 1.13
|
| 128 |
+
[[34m2025-10-28 03:15:34[0m] (step=0009500) Train Loss: 0.6597, Train Steps/Sec: 1.13
|
| 129 |
+
[[34m2025-10-28 03:17:03[0m] (step=0009600) Train Loss: 0.6586, Train Steps/Sec: 1.12
|
| 130 |
+
[[34m2025-10-28 03:18:31[0m] (step=0009700) Train Loss: 0.6590, Train Steps/Sec: 1.13
|
| 131 |
+
[[34m2025-10-28 03:19:59[0m] (step=0009800) Train Loss: 0.6580, Train Steps/Sec: 1.13
|
| 132 |
+
[[34m2025-10-28 03:21:27[0m] (step=0009900) Train Loss: 0.6586, Train Steps/Sec: 1.13
|
| 133 |
+
[[34m2025-10-28 03:22:55[0m] (step=0010000) Train Loss: 0.6574, Train Steps/Sec: 1.13
|
| 134 |
+
[[34m2025-10-28 03:23:03[0m] Beginning epoch 8...
|
| 135 |
+
[[34m2025-10-28 03:24:28[0m] (step=0010100) Train Loss: 0.6546, Train Steps/Sec: 1.08
|
| 136 |
+
[[34m2025-10-28 03:25:56[0m] (step=0010200) Train Loss: 0.6576, Train Steps/Sec: 1.13
|
| 137 |
+
[[34m2025-10-28 03:27:24[0m] (step=0010300) Train Loss: 0.6554, Train Steps/Sec: 1.13
|
| 138 |
+
[[34m2025-10-28 03:28:53[0m] (step=0010400) Train Loss: 0.6555, Train Steps/Sec: 1.13
|
| 139 |
+
[[34m2025-10-28 03:30:21[0m] (step=0010500) Train Loss: 0.6551, Train Steps/Sec: 1.13
|
| 140 |
+
[[34m2025-10-28 03:31:50[0m] (step=0010600) Train Loss: 0.6548, Train Steps/Sec: 1.13
|
| 141 |
+
[[34m2025-10-28 03:33:18[0m] (step=0010700) Train Loss: 0.6542, Train Steps/Sec: 1.13
|
| 142 |
+
[[34m2025-10-28 03:34:46[0m] (step=0010800) Train Loss: 0.6531, Train Steps/Sec: 1.13
|
| 143 |
+
[[34m2025-10-28 03:36:14[0m] (step=0010900) Train Loss: 0.6550, Train Steps/Sec: 1.13
|
| 144 |
+
[[34m2025-10-28 03:37:42[0m] (step=0011000) Train Loss: 0.6528, Train Steps/Sec: 1.13
|
| 145 |
+
[[34m2025-10-28 03:39:10[0m] (step=0011100) Train Loss: 0.6522, Train Steps/Sec: 1.13
|
| 146 |
+
[[34m2025-10-28 03:40:39[0m] (step=0011200) Train Loss: 0.6531, Train Steps/Sec: 1.13
|
| 147 |
+
[[34m2025-10-28 03:41:31[0m] Beginning epoch 9...
|
| 148 |
+
[[34m2025-10-28 03:42:11[0m] (step=0011300) Train Loss: 0.6510, Train Steps/Sec: 1.08
|
| 149 |
+
[[34m2025-10-28 03:43:40[0m] (step=0011400) Train Loss: 0.6498, Train Steps/Sec: 1.13
|
| 150 |
+
[[34m2025-10-28 03:45:08[0m] (step=0011500) Train Loss: 0.6505, Train Steps/Sec: 1.13
|
| 151 |
+
[[34m2025-10-28 03:46:36[0m] (step=0011600) Train Loss: 0.6502, Train Steps/Sec: 1.13
|
| 152 |
+
[[34m2025-10-28 03:48:04[0m] (step=0011700) Train Loss: 0.6510, Train Steps/Sec: 1.13
|
| 153 |
+
[[34m2025-10-28 03:49:32[0m] (step=0011800) Train Loss: 0.6499, Train Steps/Sec: 1.13
|
| 154 |
+
[[34m2025-10-28 03:51:00[0m] (step=0011900) Train Loss: 0.6501, Train Steps/Sec: 1.13
|
| 155 |
+
[[34m2025-10-28 03:52:29[0m] (step=0012000) Train Loss: 0.6498, Train Steps/Sec: 1.13
|
| 156 |
+
[[34m2025-10-28 03:53:57[0m] (step=0012100) Train Loss: 0.6496, Train Steps/Sec: 1.13
|
| 157 |
+
[[34m2025-10-28 03:55:25[0m] (step=0012200) Train Loss: 0.6475, Train Steps/Sec: 1.13
|
| 158 |
+
[[34m2025-10-28 03:56:54[0m] (step=0012300) Train Loss: 0.6481, Train Steps/Sec: 1.13
|
| 159 |
+
[[34m2025-10-28 03:58:22[0m] (step=0012400) Train Loss: 0.6480, Train Steps/Sec: 1.13
|
| 160 |
+
[[34m2025-10-28 03:59:50[0m] (step=0012500) Train Loss: 0.6485, Train Steps/Sec: 1.13
|
| 161 |
+
[[34m2025-10-28 03:59:59[0m] Beginning epoch 10...
|
| 162 |
+
[[34m2025-10-28 04:01:22[0m] (step=0012600) Train Loss: 0.6469, Train Steps/Sec: 1.08
|
| 163 |
+
[[34m2025-10-28 04:02:50[0m] (step=0012700) Train Loss: 0.6476, Train Steps/Sec: 1.13
|
| 164 |
+
[[34m2025-10-28 04:04:19[0m] (step=0012800) Train Loss: 0.6462, Train Steps/Sec: 1.13
|
| 165 |
+
[[34m2025-10-28 04:05:47[0m] (step=0012900) Train Loss: 0.6465, Train Steps/Sec: 1.13
|
| 166 |
+
[[34m2025-10-28 04:07:15[0m] (step=0013000) Train Loss: 0.6462, Train Steps/Sec: 1.13
|
| 167 |
+
[[34m2025-10-28 04:08:44[0m] (step=0013100) Train Loss: 0.6459, Train Steps/Sec: 1.13
|
| 168 |
+
[[34m2025-10-28 04:10:12[0m] (step=0013200) Train Loss: 0.6466, Train Steps/Sec: 1.13
|
| 169 |
+
[[34m2025-10-28 04:11:40[0m] (step=0013300) Train Loss: 0.6445, Train Steps/Sec: 1.13
|
| 170 |
+
[[34m2025-10-28 04:13:08[0m] (step=0013400) Train Loss: 0.6452, Train Steps/Sec: 1.13
|
| 171 |
+
[[34m2025-10-28 04:14:37[0m] (step=0013500) Train Loss: 0.6446, Train Steps/Sec: 1.13
|
| 172 |
+
[[34m2025-10-28 04:16:05[0m] (step=0013600) Train Loss: 0.6456, Train Steps/Sec: 1.13
|
| 173 |
+
[[34m2025-10-28 04:17:33[0m] (step=0013700) Train Loss: 0.6440, Train Steps/Sec: 1.13
|
| 174 |
+
[[34m2025-10-28 04:18:27[0m] Beginning epoch 11...
|
| 175 |
+
[[34m2025-10-28 04:19:05[0m] (step=0013800) Train Loss: 0.6437, Train Steps/Sec: 1.08
|
| 176 |
+
[[34m2025-10-28 04:20:34[0m] (step=0013900) Train Loss: 0.6437, Train Steps/Sec: 1.13
|
| 177 |
+
[[34m2025-10-28 04:22:02[0m] (step=0014000) Train Loss: 0.6426, Train Steps/Sec: 1.13
|
| 178 |
+
[[34m2025-10-28 04:23:31[0m] (step=0014100) Train Loss: 0.6432, Train Steps/Sec: 1.13
|
| 179 |
+
[[34m2025-10-28 04:24:59[0m] (step=0014200) Train Loss: 0.6430, Train Steps/Sec: 1.13
|
| 180 |
+
[[34m2025-10-28 04:26:27[0m] (step=0014300) Train Loss: 0.6429, Train Steps/Sec: 1.13
|
| 181 |
+
[[34m2025-10-28 04:27:55[0m] (step=0014400) Train Loss: 0.6420, Train Steps/Sec: 1.13
|
| 182 |
+
[[34m2025-10-28 04:29:23[0m] (step=0014500) Train Loss: 0.6418, Train Steps/Sec: 1.13
|
| 183 |
+
[[34m2025-10-28 04:30:51[0m] (step=0014600) Train Loss: 0.6419, Train Steps/Sec: 1.13
|
| 184 |
+
[[34m2025-10-28 04:32:20[0m] (step=0014700) Train Loss: 0.6424, Train Steps/Sec: 1.13
|
| 185 |
+
[[34m2025-10-28 04:33:48[0m] (step=0014800) Train Loss: 0.6415, Train Steps/Sec: 1.13
|
| 186 |
+
[[34m2025-10-28 04:35:17[0m] (step=0014900) Train Loss: 0.6423, Train Steps/Sec: 1.13
|
| 187 |
+
[[34m2025-10-28 04:36:45[0m] (step=0015000) Train Loss: 0.6396, Train Steps/Sec: 1.14
|
| 188 |
+
[[34m2025-10-28 04:36:56[0m] Beginning epoch 12...
|
| 189 |
+
[[34m2025-10-28 04:38:17[0m] (step=0015100) Train Loss: 0.6412, Train Steps/Sec: 1.09
|
| 190 |
+
[[34m2025-10-28 04:39:45[0m] (step=0015200) Train Loss: 0.6398, Train Steps/Sec: 1.13
|
| 191 |
+
[[34m2025-10-28 04:41:13[0m] (step=0015300) Train Loss: 0.6419, Train Steps/Sec: 1.13
|
| 192 |
+
[[34m2025-10-28 04:42:41[0m] (step=0015400) Train Loss: 0.6394, Train Steps/Sec: 1.13
|
| 193 |
+
[[34m2025-10-28 04:44:09[0m] (step=0015500) Train Loss: 0.6407, Train Steps/Sec: 1.13
|
| 194 |
+
[[34m2025-10-28 04:45:38[0m] (step=0015600) Train Loss: 0.6386, Train Steps/Sec: 1.13
|
| 195 |
+
[[34m2025-10-28 04:47:07[0m] (step=0015700) Train Loss: 0.6402, Train Steps/Sec: 1.13
|
| 196 |
+
[[34m2025-10-28 04:48:35[0m] (step=0015800) Train Loss: 0.6393, Train Steps/Sec: 1.13
|
| 197 |
+
[[34m2025-10-28 04:50:03[0m] (step=0015900) Train Loss: 0.6389, Train Steps/Sec: 1.13
|
| 198 |
+
[[34m2025-10-28 04:51:31[0m] (step=0016000) Train Loss: 0.6368, Train Steps/Sec: 1.13
|
| 199 |
+
[[34m2025-10-28 04:52:59[0m] (step=0016100) Train Loss: 0.6388, Train Steps/Sec: 1.13
|
| 200 |
+
[[34m2025-10-28 04:54:27[0m] (step=0016200) Train Loss: 0.6387, Train Steps/Sec: 1.13
|
| 201 |
+
[[34m2025-10-28 04:55:24[0m] Beginning epoch 13...
|
| 202 |
+
[[34m2025-10-28 04:56:00[0m] (step=0016300) Train Loss: 0.6379, Train Steps/Sec: 1.08
|
| 203 |
+
[[34m2025-10-28 04:57:28[0m] (step=0016400) Train Loss: 0.6376, Train Steps/Sec: 1.13
|
| 204 |
+
[[34m2025-10-28 04:58:57[0m] (step=0016500) Train Loss: 0.6372, Train Steps/Sec: 1.12
|
| 205 |
+
[[34m2025-10-28 05:00:25[0m] (step=0016600) Train Loss: 0.6386, Train Steps/Sec: 1.13
|
| 206 |
+
[[34m2025-10-28 05:01:53[0m] (step=0016700) Train Loss: 0.6349, Train Steps/Sec: 1.13
|
| 207 |
+
[[34m2025-10-28 05:03:21[0m] (step=0016800) Train Loss: 0.6376, Train Steps/Sec: 1.13
|
| 208 |
+
[[34m2025-10-28 05:04:49[0m] (step=0016900) Train Loss: 0.6372, Train Steps/Sec: 1.13
|
| 209 |
+
[[34m2025-10-28 05:06:18[0m] (step=0017000) Train Loss: 0.6366, Train Steps/Sec: 1.13
|
| 210 |
+
[[34m2025-10-28 05:07:46[0m] (step=0017100) Train Loss: 0.6371, Train Steps/Sec: 1.13
|
| 211 |
+
[[34m2025-10-28 05:09:14[0m] (step=0017200) Train Loss: 0.6364, Train Steps/Sec: 1.13
|
| 212 |
+
[[34m2025-10-28 05:10:42[0m] (step=0017300) Train Loss: 0.6362, Train Steps/Sec: 1.13
|
| 213 |
+
[[34m2025-10-28 05:12:11[0m] (step=0017400) Train Loss: 0.6338, Train Steps/Sec: 1.13
|
| 214 |
+
[[34m2025-10-28 05:13:39[0m] (step=0017500) Train Loss: 0.6364, Train Steps/Sec: 1.14
|
| 215 |
+
[[34m2025-10-28 05:13:52[0m] Beginning epoch 14...
|
| 216 |
+
[[34m2025-10-28 05:15:11[0m] (step=0017600) Train Loss: 0.6349, Train Steps/Sec: 1.08
|
| 217 |
+
[[34m2025-10-28 05:16:39[0m] (step=0017700) Train Loss: 0.6349, Train Steps/Sec: 1.13
|
| 218 |
+
[[34m2025-10-28 05:18:07[0m] (step=0017800) Train Loss: 0.6342, Train Steps/Sec: 1.13
|
| 219 |
+
[[34m2025-10-28 05:19:36[0m] (step=0017900) Train Loss: 0.6349, Train Steps/Sec: 1.13
|
| 220 |
+
[[34m2025-10-28 05:21:04[0m] (step=0018000) Train Loss: 0.6350, Train Steps/Sec: 1.13
|
| 221 |
+
[[34m2025-10-28 05:22:32[0m] (step=0018100) Train Loss: 0.6350, Train Steps/Sec: 1.13
|
| 222 |
+
[[34m2025-10-28 05:24:01[0m] (step=0018200) Train Loss: 0.6348, Train Steps/Sec: 1.13
|
| 223 |
+
[[34m2025-10-28 05:25:29[0m] (step=0018300) Train Loss: 0.6347, Train Steps/Sec: 1.13
|
| 224 |
+
[[34m2025-10-28 05:26:57[0m] (step=0018400) Train Loss: 0.6344, Train Steps/Sec: 1.14
|
| 225 |
+
[[34m2025-10-28 05:28:25[0m] (step=0018500) Train Loss: 0.6341, Train Steps/Sec: 1.13
|
| 226 |
+
[[34m2025-10-28 05:29:53[0m] (step=0018600) Train Loss: 0.6328, Train Steps/Sec: 1.13
|
| 227 |
+
[[34m2025-10-28 05:31:21[0m] (step=0018700) Train Loss: 0.6325, Train Steps/Sec: 1.13
|
| 228 |
+
[[34m2025-10-28 05:32:19[0m] Beginning epoch 15...
|
| 229 |
+
[[34m2025-10-28 05:32:54[0m] (step=0018800) Train Loss: 0.6343, Train Steps/Sec: 1.08
|
| 230 |
+
[[34m2025-10-28 05:34:22[0m] (step=0018900) Train Loss: 0.6322, Train Steps/Sec: 1.13
|
| 231 |
+
[[34m2025-10-28 05:35:50[0m] (step=0019000) Train Loss: 0.6319, Train Steps/Sec: 1.13
|
| 232 |
+
[[34m2025-10-28 05:37:19[0m] (step=0019100) Train Loss: 0.6316, Train Steps/Sec: 1.13
|
| 233 |
+
[[34m2025-10-28 05:38:47[0m] (step=0019200) Train Loss: 0.6314, Train Steps/Sec: 1.14
|
| 234 |
+
[[34m2025-10-28 05:40:15[0m] (step=0019300) Train Loss: 0.6320, Train Steps/Sec: 1.14
|
| 235 |
+
[[34m2025-10-28 05:41:43[0m] (step=0019400) Train Loss: 0.6315, Train Steps/Sec: 1.14
|
| 236 |
+
[[34m2025-10-28 05:43:12[0m] (step=0019500) Train Loss: 0.6316, Train Steps/Sec: 1.14
|
| 237 |
+
[[34m2025-10-28 05:44:40[0m] (step=0019600) Train Loss: 0.6315, Train Steps/Sec: 1.13
|
| 238 |
+
[[34m2025-10-28 05:46:08[0m] (step=0019700) Train Loss: 0.6298, Train Steps/Sec: 1.14
|
| 239 |
+
[[34m2025-10-28 05:47:36[0m] (step=0019800) Train Loss: 0.6320, Train Steps/Sec: 1.13
|
| 240 |
+
[[34m2025-10-28 05:49:04[0m] (step=0019900) Train Loss: 0.6316, Train Steps/Sec: 1.13
|
| 241 |
+
[[34m2025-10-28 05:50:33[0m] (step=0020000) Train Loss: 0.6305, Train Steps/Sec: 1.13
|
| 242 |
+
[[34m2025-10-28 05:50:47[0m] Beginning epoch 16...
|
| 243 |
+
[[34m2025-10-28 05:52:05[0m] (step=0020100) Train Loss: 0.6315, Train Steps/Sec: 1.08
|
| 244 |
+
[[34m2025-10-28 05:53:33[0m] (step=0020200) Train Loss: 0.6302, Train Steps/Sec: 1.14
|
| 245 |
+
[[34m2025-10-28 05:55:01[0m] (step=0020300) Train Loss: 0.6309, Train Steps/Sec: 1.13
|
| 246 |
+
[[34m2025-10-28 05:56:30[0m] (step=0020400) Train Loss: 0.6304, Train Steps/Sec: 1.13
|
| 247 |
+
[[34m2025-10-28 05:57:58[0m] (step=0020500) Train Loss: 0.6301, Train Steps/Sec: 1.13
|
| 248 |
+
[[34m2025-10-28 05:59:26[0m] (step=0020600) Train Loss: 0.6294, Train Steps/Sec: 1.13
|
| 249 |
+
[[34m2025-10-28 06:00:54[0m] (step=0020700) Train Loss: 0.6307, Train Steps/Sec: 1.13
|
| 250 |
+
[[34m2025-10-28 06:02:23[0m] (step=0020800) Train Loss: 0.6294, Train Steps/Sec: 1.12
|
| 251 |
+
[[34m2025-10-28 06:03:51[0m] (step=0020900) Train Loss: 0.6306, Train Steps/Sec: 1.13
|
| 252 |
+
[[34m2025-10-28 06:05:19[0m] (step=0021000) Train Loss: 0.6300, Train Steps/Sec: 1.14
|
| 253 |
+
[[34m2025-10-28 06:06:47[0m] (step=0021100) Train Loss: 0.6280, Train Steps/Sec: 1.13
|
| 254 |
+
[[34m2025-10-28 06:08:16[0m] (step=0021200) Train Loss: 0.6287, Train Steps/Sec: 1.13
|
| 255 |
+
[[34m2025-10-28 06:09:15[0m] Beginning epoch 17...
|
| 256 |
+
[[34m2025-10-28 06:09:48[0m] (step=0021300) Train Loss: 0.6290, Train Steps/Sec: 1.08
|
| 257 |
+
[[34m2025-10-28 06:11:16[0m] (step=0021400) Train Loss: 0.6286, Train Steps/Sec: 1.13
|
| 258 |
+
[[34m2025-10-28 06:12:44[0m] (step=0021500) Train Loss: 0.6289, Train Steps/Sec: 1.13
|
| 259 |
+
[[34m2025-10-28 06:14:12[0m] (step=0021600) Train Loss: 0.6297, Train Steps/Sec: 1.13
|
| 260 |
+
[[34m2025-10-28 06:15:41[0m] (step=0021700) Train Loss: 0.6299, Train Steps/Sec: 1.13
|
| 261 |
+
[[34m2025-10-28 06:17:09[0m] (step=0021800) Train Loss: 0.6293, Train Steps/Sec: 1.13
|
| 262 |
+
[[34m2025-10-28 06:18:38[0m] (step=0021900) Train Loss: 0.6270, Train Steps/Sec: 1.13
|
| 263 |
+
[[34m2025-10-28 06:20:06[0m] (step=0022000) Train Loss: 0.6276, Train Steps/Sec: 1.13
|
| 264 |
+
[[34m2025-10-28 06:21:34[0m] (step=0022100) Train Loss: 0.6285, Train Steps/Sec: 1.13
|
| 265 |
+
[[34m2025-10-28 06:23:02[0m] (step=0022200) Train Loss: 0.6283, Train Steps/Sec: 1.13
|
| 266 |
+
[[34m2025-10-28 06:24:30[0m] (step=0022300) Train Loss: 0.6266, Train Steps/Sec: 1.13
|
| 267 |
+
[[34m2025-10-28 06:25:59[0m] (step=0022400) Train Loss: 0.6267, Train Steps/Sec: 1.13
|
| 268 |
+
[[34m2025-10-28 06:27:27[0m] (step=0022500) Train Loss: 0.6276, Train Steps/Sec: 1.13
|
| 269 |
+
[[34m2025-10-28 06:27:44[0m] Beginning epoch 18...
|
| 270 |
+
[[34m2025-10-28 06:29:00[0m] (step=0022600) Train Loss: 0.6264, Train Steps/Sec: 1.07
|
| 271 |
+
[[34m2025-10-28 06:30:28[0m] (step=0022700) Train Loss: 0.6271, Train Steps/Sec: 1.13
|
| 272 |
+
[[34m2025-10-28 06:31:57[0m] (step=0022800) Train Loss: 0.6280, Train Steps/Sec: 1.13
|
| 273 |
+
[[34m2025-10-28 06:33:25[0m] (step=0022900) Train Loss: 0.6261, Train Steps/Sec: 1.13
|
| 274 |
+
[[34m2025-10-28 06:34:53[0m] (step=0023000) Train Loss: 0.6253, Train Steps/Sec: 1.13
|
| 275 |
+
[[34m2025-10-28 06:36:21[0m] (step=0023100) Train Loss: 0.6253, Train Steps/Sec: 1.13
|
| 276 |
+
[[34m2025-10-28 06:37:49[0m] (step=0023200) Train Loss: 0.6273, Train Steps/Sec: 1.13
|
| 277 |
+
[[34m2025-10-28 06:39:18[0m] (step=0023300) Train Loss: 0.6282, Train Steps/Sec: 1.13
|
| 278 |
+
[[34m2025-10-28 06:40:46[0m] (step=0023400) Train Loss: 0.6258, Train Steps/Sec: 1.13
|
| 279 |
+
[[34m2025-10-28 06:42:15[0m] (step=0023500) Train Loss: 0.6261, Train Steps/Sec: 1.13
|
| 280 |
+
[[34m2025-10-28 06:43:43[0m] (step=0023600) Train Loss: 0.6269, Train Steps/Sec: 1.13
|
| 281 |
+
[[34m2025-10-28 06:45:11[0m] (step=0023700) Train Loss: 0.6246, Train Steps/Sec: 1.13
|
| 282 |
+
[[34m2025-10-28 06:46:12[0m] Beginning epoch 19...
|
| 283 |
+
[[34m2025-10-28 06:46:44[0m] (step=0023800) Train Loss: 0.6247, Train Steps/Sec: 1.08
|
| 284 |
+
[[34m2025-10-28 06:48:12[0m] (step=0023900) Train Loss: 0.6260, Train Steps/Sec: 1.13
|
| 285 |
+
[[34m2025-10-28 06:49:40[0m] (step=0024000) Train Loss: 0.6254, Train Steps/Sec: 1.13
|
| 286 |
+
[[34m2025-10-28 06:51:08[0m] (step=0024100) Train Loss: 0.6239, Train Steps/Sec: 1.13
|
| 287 |
+
[[34m2025-10-28 06:52:37[0m] (step=0024200) Train Loss: 0.6239, Train Steps/Sec: 1.13
|
| 288 |
+
[[34m2025-10-28 06:54:06[0m] (step=0024300) Train Loss: 0.6246, Train Steps/Sec: 1.12
|
| 289 |
+
[[34m2025-10-28 06:55:34[0m] (step=0024400) Train Loss: 0.6266, Train Steps/Sec: 1.13
|
| 290 |
+
[[34m2025-10-28 06:57:02[0m] (step=0024500) Train Loss: 0.6251, Train Steps/Sec: 1.13
|
| 291 |
+
[[34m2025-10-28 06:58:30[0m] (step=0024600) Train Loss: 0.6253, Train Steps/Sec: 1.13
|
| 292 |
+
[[34m2025-10-28 06:59:58[0m] (step=0024700) Train Loss: 0.6251, Train Steps/Sec: 1.13
|
| 293 |
+
[[34m2025-10-28 07:01:27[0m] (step=0024800) Train Loss: 0.6234, Train Steps/Sec: 1.13
|
| 294 |
+
[[34m2025-10-28 07:02:55[0m] (step=0024900) Train Loss: 0.6241, Train Steps/Sec: 1.13
|
| 295 |
+
[[34m2025-10-28 07:04:23[0m] (step=0025000) Train Loss: 0.6254, Train Steps/Sec: 1.13
|
| 296 |
+
[[34m2025-10-28 07:05:16[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-spatialpe-vit-g-bf16/checkpoints/0025000.pt
|
| 297 |
+
[[34m2025-10-28 07:05:16[0m] Generating EMA samples...
|
| 298 |
+
[[34m2025-10-28 07:05:44[0m] Generating EMA samples done.
|
| 299 |
+
[[34m2025-10-28 07:06:02[0m] Beginning epoch 20...
|
| 300 |
+
[[34m2025-10-28 07:07:19[0m] (step=0025100) Train Loss: 0.6230, Train Steps/Sec: 0.57
|
| 301 |
+
[[34m2025-10-28 07:08:47[0m] (step=0025200) Train Loss: 0.6256, Train Steps/Sec: 1.13
|
| 302 |
+
[[34m2025-10-28 07:10:15[0m] (step=0025300) Train Loss: 0.6237, Train Steps/Sec: 1.13
|
| 303 |
+
[[34m2025-10-28 07:11:43[0m] (step=0025400) Train Loss: 0.6248, Train Steps/Sec: 1.13
|
| 304 |
+
[[34m2025-10-28 07:13:12[0m] (step=0025500) Train Loss: 0.6239, Train Steps/Sec: 1.13
|
| 305 |
+
[[34m2025-10-28 07:14:40[0m] (step=0025600) Train Loss: 0.6244, Train Steps/Sec: 1.13
|
| 306 |
+
[[34m2025-10-28 07:16:08[0m] (step=0025700) Train Loss: 0.6225, Train Steps/Sec: 1.13
|
| 307 |
+
[[34m2025-10-28 07:17:36[0m] (step=0025800) Train Loss: 0.6226, Train Steps/Sec: 1.13
|
| 308 |
+
[[34m2025-10-28 07:19:05[0m] (step=0025900) Train Loss: 0.6219, Train Steps/Sec: 1.13
|
| 309 |
+
[[34m2025-10-28 07:20:33[0m] (step=0026000) Train Loss: 0.6232, Train Steps/Sec: 1.13
|
| 310 |
+
[[34m2025-10-28 07:22:01[0m] (step=0026100) Train Loss: 0.6223, Train Steps/Sec: 1.13
|
| 311 |
+
[[34m2025-10-28 07:23:29[0m] (step=0026200) Train Loss: 0.6219, Train Steps/Sec: 1.13
|
| 312 |
+
[[34m2025-10-28 07:24:33[0m] Beginning epoch 21...
|
| 313 |
+
[[34m2025-10-28 07:25:03[0m] (step=0026300) Train Loss: 0.6226, Train Steps/Sec: 1.06
|
| 314 |
+
[[34m2025-10-28 07:26:32[0m] (step=0026400) Train Loss: 0.6217, Train Steps/Sec: 1.13
|
| 315 |
+
[[34m2025-10-28 07:28:00[0m] (step=0026500) Train Loss: 0.6226, Train Steps/Sec: 1.13
|
| 316 |
+
[[34m2025-10-28 07:29:28[0m] (step=0026600) Train Loss: 0.6232, Train Steps/Sec: 1.13
|
| 317 |
+
[[34m2025-10-28 07:30:56[0m] (step=0026700) Train Loss: 0.6232, Train Steps/Sec: 1.13
|
| 318 |
+
[[34m2025-10-28 07:32:25[0m] (step=0026800) Train Loss: 0.6212, Train Steps/Sec: 1.13
|
| 319 |
+
[[34m2025-10-28 07:33:54[0m] (step=0026900) Train Loss: 0.6229, Train Steps/Sec: 1.13
|
| 320 |
+
[[34m2025-10-28 07:35:22[0m] (step=0027000) Train Loss: 0.6219, Train Steps/Sec: 1.13
|
| 321 |
+
[[34m2025-10-28 07:36:50[0m] (step=0027100) Train Loss: 0.6225, Train Steps/Sec: 1.13
|
| 322 |
+
[[34m2025-10-28 07:38:18[0m] (step=0027200) Train Loss: 0.6208, Train Steps/Sec: 1.13
|
| 323 |
+
[[34m2025-10-28 07:39:47[0m] (step=0027300) Train Loss: 0.6220, Train Steps/Sec: 1.13
|
| 324 |
+
[[34m2025-10-28 07:41:15[0m] (step=0027400) Train Loss: 0.6211, Train Steps/Sec: 1.13
|
| 325 |
+
[[34m2025-10-28 07:42:43[0m] (step=0027500) Train Loss: 0.6218, Train Steps/Sec: 1.13
|
| 326 |
+
[[34m2025-10-28 07:43:03[0m] Beginning epoch 22...
|
| 327 |
+
[[34m2025-10-28 07:44:17[0m] (step=0027600) Train Loss: 0.6206, Train Steps/Sec: 1.06
|
| 328 |
+
[[34m2025-10-28 07:45:46[0m] (step=0027700) Train Loss: 0.6204, Train Steps/Sec: 1.13
|
| 329 |
+
[[34m2025-10-28 07:47:14[0m] (step=0027800) Train Loss: 0.6209, Train Steps/Sec: 1.13
|
| 330 |
+
[[34m2025-10-28 07:48:42[0m] (step=0027900) Train Loss: 0.6205, Train Steps/Sec: 1.13
|
| 331 |
+
[[34m2025-10-28 07:50:10[0m] (step=0028000) Train Loss: 0.6210, Train Steps/Sec: 1.13
|
| 332 |
+
[[34m2025-10-28 07:51:38[0m] (step=0028100) Train Loss: 0.6207, Train Steps/Sec: 1.13
|
| 333 |
+
[[34m2025-10-28 07:53:07[0m] (step=0028200) Train Loss: 0.6197, Train Steps/Sec: 1.13
|
| 334 |
+
[[34m2025-10-28 07:54:35[0m] (step=0028300) Train Loss: 0.6223, Train Steps/Sec: 1.13
|
| 335 |
+
[[34m2025-10-28 07:56:03[0m] (step=0028400) Train Loss: 0.6207, Train Steps/Sec: 1.13
|
| 336 |
+
[[34m2025-10-28 07:57:31[0m] (step=0028500) Train Loss: 0.6216, Train Steps/Sec: 1.13
|
| 337 |
+
[[34m2025-10-28 07:59:00[0m] (step=0028600) Train Loss: 0.6201, Train Steps/Sec: 1.13
|
| 338 |
+
[[34m2025-10-28 08:00:28[0m] (step=0028700) Train Loss: 0.6212, Train Steps/Sec: 1.14
|
| 339 |
+
[[34m2025-10-28 08:01:33[0m] Beginning epoch 23...
|
| 340 |
+
[[34m2025-10-28 08:02:02[0m] (step=0028800) Train Loss: 0.6197, Train Steps/Sec: 1.06
|
| 341 |
+
[[34m2025-10-28 08:03:30[0m] (step=0028900) Train Loss: 0.6197, Train Steps/Sec: 1.13
|
| 342 |
+
[[34m2025-10-28 08:04:58[0m] (step=0029000) Train Loss: 0.6210, Train Steps/Sec: 1.13
|
| 343 |
+
[[34m2025-10-28 08:06:26[0m] (step=0029100) Train Loss: 0.6204, Train Steps/Sec: 1.13
|
| 344 |
+
[[34m2025-10-28 08:07:55[0m] (step=0029200) Train Loss: 0.6204, Train Steps/Sec: 1.13
|
| 345 |
+
[[34m2025-10-28 08:09:23[0m] (step=0029300) Train Loss: 0.6207, Train Steps/Sec: 1.14
|
| 346 |
+
[[34m2025-10-28 08:10:51[0m] (step=0029400) Train Loss: 0.6183, Train Steps/Sec: 1.13
|
| 347 |
+
[[34m2025-10-28 08:12:20[0m] (step=0029500) Train Loss: 0.6204, Train Steps/Sec: 1.13
|
| 348 |
+
[[34m2025-10-28 08:13:48[0m] (step=0029600) Train Loss: 0.6204, Train Steps/Sec: 1.13
|
| 349 |
+
[[34m2025-10-28 08:15:16[0m] (step=0029700) Train Loss: 0.6193, Train Steps/Sec: 1.14
|
| 350 |
+
[[34m2025-10-28 08:16:44[0m] (step=0029800) Train Loss: 0.6176, Train Steps/Sec: 1.13
|
| 351 |
+
[[34m2025-10-28 08:18:12[0m] (step=0029900) Train Loss: 0.6210, Train Steps/Sec: 1.13
|
| 352 |
+
[[34m2025-10-28 08:19:40[0m] (step=0030000) Train Loss: 0.6184, Train Steps/Sec: 1.13
|
| 353 |
+
[[34m2025-10-28 08:20:02[0m] Beginning epoch 24...
|
| 354 |
+
[[34m2025-10-28 08:21:14[0m] (step=0030100) Train Loss: 0.6196, Train Steps/Sec: 1.07
|
| 355 |
+
[[34m2025-10-28 08:22:42[0m] (step=0030200) Train Loss: 0.6187, Train Steps/Sec: 1.13
|
| 356 |
+
[[34m2025-10-28 08:24:11[0m] (step=0030300) Train Loss: 0.6185, Train Steps/Sec: 1.12
|
| 357 |
+
[[34m2025-10-28 08:25:39[0m] (step=0030400) Train Loss: 0.6190, Train Steps/Sec: 1.14
|
| 358 |
+
[[34m2025-10-28 08:27:07[0m] (step=0030500) Train Loss: 0.6188, Train Steps/Sec: 1.13
|
| 359 |
+
[[34m2025-10-28 08:28:35[0m] (step=0030600) Train Loss: 0.6179, Train Steps/Sec: 1.14
|
| 360 |
+
[[34m2025-10-28 08:30:03[0m] (step=0030700) Train Loss: 0.6191, Train Steps/Sec: 1.13
|
| 361 |
+
[[34m2025-10-28 08:31:32[0m] (step=0030800) Train Loss: 0.6186, Train Steps/Sec: 1.13
|
| 362 |
+
[[34m2025-10-28 08:33:00[0m] (step=0030900) Train Loss: 0.6195, Train Steps/Sec: 1.13
|
| 363 |
+
[[34m2025-10-28 08:34:28[0m] (step=0031000) Train Loss: 0.6174, Train Steps/Sec: 1.13
|
| 364 |
+
[[34m2025-10-28 08:35:56[0m] (step=0031100) Train Loss: 0.6193, Train Steps/Sec: 1.13
|
| 365 |
+
[[34m2025-10-28 08:37:25[0m] (step=0031200) Train Loss: 0.6173, Train Steps/Sec: 1.13
|
| 366 |
+
[[34m2025-10-28 08:38:31[0m] Beginning epoch 25...
|
| 367 |
+
[[34m2025-10-28 08:38:58[0m] (step=0031300) Train Loss: 0.6201, Train Steps/Sec: 1.07
|
| 368 |
+
[[34m2025-10-28 08:40:26[0m] (step=0031400) Train Loss: 0.6174, Train Steps/Sec: 1.13
|
| 369 |
+
[[34m2025-10-28 08:41:55[0m] (step=0031500) Train Loss: 0.6172, Train Steps/Sec: 1.13
|
| 370 |
+
[[34m2025-10-28 08:43:23[0m] (step=0031600) Train Loss: 0.6191, Train Steps/Sec: 1.13
|
| 371 |
+
[[34m2025-10-28 08:44:51[0m] (step=0031700) Train Loss: 0.6172, Train Steps/Sec: 1.13
|
| 372 |
+
[[34m2025-10-28 08:46:19[0m] (step=0031800) Train Loss: 0.6167, Train Steps/Sec: 1.13
|
| 373 |
+
[[34m2025-10-28 08:47:47[0m] (step=0031900) Train Loss: 0.6161, Train Steps/Sec: 1.13
|
| 374 |
+
[[34m2025-10-28 08:49:16[0m] (step=0032000) Train Loss: 0.6171, Train Steps/Sec: 1.13
|
| 375 |
+
[[34m2025-10-28 08:50:44[0m] (step=0032100) Train Loss: 0.6175, Train Steps/Sec: 1.13
|
| 376 |
+
[[34m2025-10-28 08:52:13[0m] (step=0032200) Train Loss: 0.6168, Train Steps/Sec: 1.13
|
| 377 |
+
[[34m2025-10-28 08:53:41[0m] (step=0032300) Train Loss: 0.6180, Train Steps/Sec: 1.13
|
| 378 |
+
[[34m2025-10-28 08:55:09[0m] (step=0032400) Train Loss: 0.6164, Train Steps/Sec: 1.13
|
| 379 |
+
[[34m2025-10-28 08:56:37[0m] (step=0032500) Train Loss: 0.6182, Train Steps/Sec: 1.13
|
| 380 |
+
[[34m2025-10-28 08:57:00[0m] Beginning epoch 26...
|
| 381 |
+
[[34m2025-10-28 08:58:10[0m] (step=0032600) Train Loss: 0.6173, Train Steps/Sec: 1.07
|
| 382 |
+
[[34m2025-10-28 08:59:38[0m] (step=0032700) Train Loss: 0.6171, Train Steps/Sec: 1.13
|
| 383 |
+
[[34m2025-10-28 09:01:07[0m] (step=0032800) Train Loss: 0.6161, Train Steps/Sec: 1.13
|
| 384 |
+
[[34m2025-10-28 09:02:36[0m] (step=0032900) Train Loss: 0.6182, Train Steps/Sec: 1.12
|
| 385 |
+
[[34m2025-10-28 09:04:04[0m] (step=0033000) Train Loss: 0.6163, Train Steps/Sec: 1.13
|
| 386 |
+
[[34m2025-10-28 09:05:32[0m] (step=0033100) Train Loss: 0.6171, Train Steps/Sec: 1.14
|
| 387 |
+
[[34m2025-10-28 09:07:00[0m] (step=0033200) Train Loss: 0.6146, Train Steps/Sec: 1.13
|
| 388 |
+
[[34m2025-10-28 09:08:28[0m] (step=0033300) Train Loss: 0.6183, Train Steps/Sec: 1.13
|
| 389 |
+
[[34m2025-10-28 09:09:56[0m] (step=0033400) Train Loss: 0.6166, Train Steps/Sec: 1.13
|
| 390 |
+
[[34m2025-10-28 09:11:25[0m] (step=0033500) Train Loss: 0.6160, Train Steps/Sec: 1.13
|
| 391 |
+
[[34m2025-10-28 09:12:53[0m] (step=0033600) Train Loss: 0.6164, Train Steps/Sec: 1.13
|
| 392 |
+
[[34m2025-10-28 09:14:21[0m] (step=0033700) Train Loss: 0.6154, Train Steps/Sec: 1.13
|
| 393 |
+
[[34m2025-10-28 09:15:30[0m] Beginning epoch 27...
|
| 394 |
+
[[34m2025-10-28 09:15:54[0m] (step=0033800) Train Loss: 0.6158, Train Steps/Sec: 1.07
|
| 395 |
+
[[34m2025-10-28 09:17:23[0m] (step=0033900) Train Loss: 0.6157, Train Steps/Sec: 1.13
|
| 396 |
+
[[34m2025-10-28 09:18:51[0m] (step=0034000) Train Loss: 0.6159, Train Steps/Sec: 1.13
|
| 397 |
+
[[34m2025-10-28 09:20:19[0m] (step=0034100) Train Loss: 0.6153, Train Steps/Sec: 1.13
|
| 398 |
+
[[34m2025-10-28 09:21:47[0m] (step=0034200) Train Loss: 0.6168, Train Steps/Sec: 1.13
|
| 399 |
+
[[34m2025-10-28 09:23:15[0m] (step=0034300) Train Loss: 0.6142, Train Steps/Sec: 1.13
|
| 400 |
+
[[34m2025-10-28 09:24:44[0m] (step=0034400) Train Loss: 0.6138, Train Steps/Sec: 1.13
|
| 401 |
+
[[34m2025-10-28 09:26:12[0m] (step=0034500) Train Loss: 0.6157, Train Steps/Sec: 1.13
|
| 402 |
+
[[34m2025-10-28 09:27:41[0m] (step=0034600) Train Loss: 0.6171, Train Steps/Sec: 1.13
|
| 403 |
+
[[34m2025-10-28 09:29:09[0m] (step=0034700) Train Loss: 0.6165, Train Steps/Sec: 1.13
|
| 404 |
+
[[34m2025-10-28 09:30:37[0m] (step=0034800) Train Loss: 0.6148, Train Steps/Sec: 1.13
|
| 405 |
+
[[34m2025-10-28 09:32:05[0m] (step=0034900) Train Loss: 0.6143, Train Steps/Sec: 1.13
|
| 406 |
+
[[34m2025-10-28 09:33:34[0m] (step=0035000) Train Loss: 0.6129, Train Steps/Sec: 1.13
|
| 407 |
+
[[34m2025-10-28 09:33:59[0m] Beginning epoch 28...
|
| 408 |
+
[[34m2025-10-28 09:35:07[0m] (step=0035100) Train Loss: 0.6157, Train Steps/Sec: 1.07
|
| 409 |
+
[[34m2025-10-28 09:36:36[0m] (step=0035200) Train Loss: 0.6147, Train Steps/Sec: 1.13
|
| 410 |
+
[[34m2025-10-28 09:38:04[0m] (step=0035300) Train Loss: 0.6135, Train Steps/Sec: 1.13
|
| 411 |
+
[[34m2025-10-28 09:39:32[0m] (step=0035400) Train Loss: 0.6167, Train Steps/Sec: 1.13
|
| 412 |
+
[[34m2025-10-28 09:41:01[0m] (step=0035500) Train Loss: 0.6127, Train Steps/Sec: 1.12
|
| 413 |
+
[[34m2025-10-28 09:42:29[0m] (step=0035600) Train Loss: 0.6131, Train Steps/Sec: 1.13
|
| 414 |
+
[[34m2025-10-28 09:43:57[0m] (step=0035700) Train Loss: 0.6148, Train Steps/Sec: 1.13
|
| 415 |
+
[[34m2025-10-28 09:45:25[0m] (step=0035800) Train Loss: 0.6143, Train Steps/Sec: 1.13
|
| 416 |
+
[[34m2025-10-28 09:46:54[0m] (step=0035900) Train Loss: 0.6140, Train Steps/Sec: 1.13
|
| 417 |
+
[[34m2025-10-28 09:48:22[0m] (step=0036000) Train Loss: 0.6146, Train Steps/Sec: 1.13
|
| 418 |
+
[[34m2025-10-28 09:49:50[0m] (step=0036100) Train Loss: 0.6137, Train Steps/Sec: 1.13
|
| 419 |
+
[[34m2025-10-28 09:51:18[0m] (step=0036200) Train Loss: 0.6140, Train Steps/Sec: 1.13
|
| 420 |
+
[[34m2025-10-28 09:52:29[0m] Beginning epoch 29...
|
| 421 |
+
[[34m2025-10-28 09:52:53[0m] (step=0036300) Train Loss: 0.6143, Train Steps/Sec: 1.05
|
| 422 |
+
[[34m2025-10-28 09:54:22[0m] (step=0036400) Train Loss: 0.6139, Train Steps/Sec: 1.13
|
| 423 |
+
[[34m2025-10-28 09:55:50[0m] (step=0036500) Train Loss: 0.6147, Train Steps/Sec: 1.13
|
| 424 |
+
[[34m2025-10-28 09:57:18[0m] (step=0036600) Train Loss: 0.6128, Train Steps/Sec: 1.13
|
| 425 |
+
[[34m2025-10-28 09:58:46[0m] (step=0036700) Train Loss: 0.6130, Train Steps/Sec: 1.13
|
| 426 |
+
[[34m2025-10-28 10:00:15[0m] (step=0036800) Train Loss: 0.6144, Train Steps/Sec: 1.13
|
| 427 |
+
[[34m2025-10-28 10:01:43[0m] (step=0036900) Train Loss: 0.6138, Train Steps/Sec: 1.13
|
| 428 |
+
[[34m2025-10-28 10:03:11[0m] (step=0037000) Train Loss: 0.6131, Train Steps/Sec: 1.13
|
| 429 |
+
[[34m2025-10-28 10:04:39[0m] (step=0037100) Train Loss: 0.6143, Train Steps/Sec: 1.13
|
| 430 |
+
[[34m2025-10-28 10:06:08[0m] (step=0037200) Train Loss: 0.6116, Train Steps/Sec: 1.13
|
| 431 |
+
[[34m2025-10-28 10:07:36[0m] (step=0037300) Train Loss: 0.6127, Train Steps/Sec: 1.13
|
| 432 |
+
[[34m2025-10-28 10:09:04[0m] (step=0037400) Train Loss: 0.6139, Train Steps/Sec: 1.13
|
| 433 |
+
[[34m2025-10-28 10:10:32[0m] (step=0037500) Train Loss: 0.6139, Train Steps/Sec: 1.13
|
| 434 |
+
[[34m2025-10-28 10:10:59[0m] Beginning epoch 30...
|
| 435 |
+
[[34m2025-10-28 10:12:06[0m] (step=0037600) Train Loss: 0.6143, Train Steps/Sec: 1.07
|
| 436 |
+
[[34m2025-10-28 10:13:34[0m] (step=0037700) Train Loss: 0.6123, Train Steps/Sec: 1.13
|
| 437 |
+
[[34m2025-10-28 10:15:02[0m] (step=0037800) Train Loss: 0.6135, Train Steps/Sec: 1.13
|
| 438 |
+
[[34m2025-10-28 10:16:30[0m] (step=0037900) Train Loss: 0.6126, Train Steps/Sec: 1.13
|
| 439 |
+
[[34m2025-10-28 10:17:58[0m] (step=0038000) Train Loss: 0.6124, Train Steps/Sec: 1.13
|
| 440 |
+
[[34m2025-10-28 10:19:27[0m] (step=0038100) Train Loss: 0.6123, Train Steps/Sec: 1.13
|
| 441 |
+
[[34m2025-10-28 10:20:55[0m] (step=0038200) Train Loss: 0.6132, Train Steps/Sec: 1.13
|
| 442 |
+
[[34m2025-10-28 10:22:24[0m] (step=0038300) Train Loss: 0.6136, Train Steps/Sec: 1.13
|
| 443 |
+
[[34m2025-10-28 10:23:52[0m] (step=0038400) Train Loss: 0.6122, Train Steps/Sec: 1.13
|
| 444 |
+
[[34m2025-10-28 10:25:20[0m] (step=0038500) Train Loss: 0.6115, Train Steps/Sec: 1.13
|
| 445 |
+
[[34m2025-10-28 10:26:48[0m] (step=0038600) Train Loss: 0.6123, Train Steps/Sec: 1.13
|
| 446 |
+
[[34m2025-10-28 10:28:16[0m] (step=0038700) Train Loss: 0.6124, Train Steps/Sec: 1.13
|
| 447 |
+
[[34m2025-10-28 10:29:28[0m] Beginning epoch 31...
|
| 448 |
+
[[34m2025-10-28 10:29:50[0m] (step=0038800) Train Loss: 0.6129, Train Steps/Sec: 1.07
|
| 449 |
+
[[34m2025-10-28 10:31:19[0m] (step=0038900) Train Loss: 0.6122, Train Steps/Sec: 1.13
|
| 450 |
+
[[34m2025-10-28 10:32:47[0m] (step=0039000) Train Loss: 0.6119, Train Steps/Sec: 1.13
|
| 451 |
+
[[34m2025-10-28 10:34:15[0m] (step=0039100) Train Loss: 0.6120, Train Steps/Sec: 1.13
|
| 452 |
+
[[34m2025-10-28 10:35:43[0m] (step=0039200) Train Loss: 0.6127, Train Steps/Sec: 1.13
|
| 453 |
+
[[34m2025-10-28 10:37:11[0m] (step=0039300) Train Loss: 0.6125, Train Steps/Sec: 1.13
|
| 454 |
+
[[34m2025-10-28 10:38:40[0m] (step=0039400) Train Loss: 0.6122, Train Steps/Sec: 1.13
|
| 455 |
+
[[34m2025-10-28 10:40:08[0m] (step=0039500) Train Loss: 0.6141, Train Steps/Sec: 1.13
|
| 456 |
+
[[34m2025-10-28 10:41:36[0m] (step=0039600) Train Loss: 0.6121, Train Steps/Sec: 1.13
|
| 457 |
+
[[34m2025-10-28 10:43:04[0m] (step=0039700) Train Loss: 0.6128, Train Steps/Sec: 1.14
|
| 458 |
+
[[34m2025-10-28 10:44:33[0m] (step=0039800) Train Loss: 0.6131, Train Steps/Sec: 1.13
|
| 459 |
+
[[34m2025-10-28 10:46:01[0m] (step=0039900) Train Loss: 0.6123, Train Steps/Sec: 1.13
|
| 460 |
+
[[34m2025-10-28 10:47:29[0m] (step=0040000) Train Loss: 0.6114, Train Steps/Sec: 1.13
|
| 461 |
+
[[34m2025-10-28 10:47:58[0m] Beginning epoch 32...
|
| 462 |
+
[[34m2025-10-28 10:49:02[0m] (step=0040100) Train Loss: 0.6120, Train Steps/Sec: 1.07
|
| 463 |
+
[[34m2025-10-28 10:50:31[0m] (step=0040200) Train Loss: 0.6122, Train Steps/Sec: 1.13
|
| 464 |
+
[[34m2025-10-28 10:51:59[0m] (step=0040300) Train Loss: 0.6118, Train Steps/Sec: 1.14
|
| 465 |
+
[[34m2025-10-28 10:53:27[0m] (step=0040400) Train Loss: 0.6111, Train Steps/Sec: 1.14
|
| 466 |
+
[[34m2025-10-28 10:54:55[0m] (step=0040500) Train Loss: 0.6115, Train Steps/Sec: 1.14
|
| 467 |
+
[[34m2025-10-28 10:56:23[0m] (step=0040600) Train Loss: 0.6140, Train Steps/Sec: 1.13
|
| 468 |
+
[[34m2025-10-28 10:57:52[0m] (step=0040700) Train Loss: 0.6114, Train Steps/Sec: 1.13
|
| 469 |
+
[[34m2025-10-28 10:59:20[0m] (step=0040800) Train Loss: 0.6126, Train Steps/Sec: 1.13
|
| 470 |
+
[[34m2025-10-28 11:00:48[0m] (step=0040900) Train Loss: 0.6101, Train Steps/Sec: 1.13
|
| 471 |
+
[[34m2025-10-28 11:02:16[0m] (step=0041000) Train Loss: 0.6097, Train Steps/Sec: 1.14
|
| 472 |
+
[[34m2025-10-28 11:03:44[0m] (step=0041100) Train Loss: 0.6113, Train Steps/Sec: 1.13
|
| 473 |
+
[[34m2025-10-28 11:05:12[0m] (step=0041200) Train Loss: 0.6121, Train Steps/Sec: 1.13
|
| 474 |
+
[[34m2025-10-28 11:06:26[0m] Beginning epoch 33...
|
| 475 |
+
[[34m2025-10-28 11:06:46[0m] (step=0041300) Train Loss: 0.6104, Train Steps/Sec: 1.07
|
| 476 |
+
[[34m2025-10-28 11:08:14[0m] (step=0041400) Train Loss: 0.6115, Train Steps/Sec: 1.13
|
| 477 |
+
[[34m2025-10-28 11:09:43[0m] (step=0041500) Train Loss: 0.6104, Train Steps/Sec: 1.12
|
| 478 |
+
[[34m2025-10-28 11:11:12[0m] (step=0041600) Train Loss: 0.6105, Train Steps/Sec: 1.13
|
| 479 |
+
[[34m2025-10-28 11:12:40[0m] (step=0041700) Train Loss: 0.6109, Train Steps/Sec: 1.14
|
| 480 |
+
[[34m2025-10-28 11:14:08[0m] (step=0041800) Train Loss: 0.6109, Train Steps/Sec: 1.13
|
| 481 |
+
[[34m2025-10-28 11:15:36[0m] (step=0041900) Train Loss: 0.6108, Train Steps/Sec: 1.13
|
| 482 |
+
[[34m2025-10-28 11:17:04[0m] (step=0042000) Train Loss: 0.6109, Train Steps/Sec: 1.13
|
| 483 |
+
[[34m2025-10-28 11:18:32[0m] (step=0042100) Train Loss: 0.6113, Train Steps/Sec: 1.13
|
| 484 |
+
[[34m2025-10-28 11:20:00[0m] (step=0042200) Train Loss: 0.6111, Train Steps/Sec: 1.13
|
| 485 |
+
[[34m2025-10-28 11:21:29[0m] (step=0042300) Train Loss: 0.6104, Train Steps/Sec: 1.13
|
| 486 |
+
[[34m2025-10-28 11:22:57[0m] (step=0042400) Train Loss: 0.6105, Train Steps/Sec: 1.13
|
| 487 |
+
[[34m2025-10-28 11:24:25[0m] (step=0042500) Train Loss: 0.6102, Train Steps/Sec: 1.13
|
| 488 |
+
[[34m2025-10-28 11:24:56[0m] Beginning epoch 34...
|
| 489 |
+
[[34m2025-10-28 11:25:59[0m] (step=0042600) Train Loss: 0.6113, Train Steps/Sec: 1.07
|
| 490 |
+
[[34m2025-10-28 11:27:27[0m] (step=0042700) Train Loss: 0.6102, Train Steps/Sec: 1.13
|
| 491 |
+
[[34m2025-10-28 11:28:56[0m] (step=0042800) Train Loss: 0.6095, Train Steps/Sec: 1.13
|
| 492 |
+
[[34m2025-10-28 11:30:24[0m] (step=0042900) Train Loss: 0.6112, Train Steps/Sec: 1.13
|
| 493 |
+
[[34m2025-10-28 11:31:52[0m] (step=0043000) Train Loss: 0.6100, Train Steps/Sec: 1.13
|
| 494 |
+
[[34m2025-10-28 11:33:20[0m] (step=0043100) Train Loss: 0.6120, Train Steps/Sec: 1.13
|
| 495 |
+
[[34m2025-10-28 11:34:49[0m] (step=0043200) Train Loss: 0.6102, Train Steps/Sec: 1.13
|
| 496 |
+
[[34m2025-10-28 11:36:17[0m] (step=0043300) Train Loss: 0.6098, Train Steps/Sec: 1.13
|
| 497 |
+
[[34m2025-10-28 11:37:45[0m] (step=0043400) Train Loss: 0.6086, Train Steps/Sec: 1.13
|
| 498 |
+
[[34m2025-10-28 11:39:14[0m] (step=0043500) Train Loss: 0.6084, Train Steps/Sec: 1.13
|
| 499 |
+
[[34m2025-10-28 11:40:42[0m] (step=0043600) Train Loss: 0.6096, Train Steps/Sec: 1.13
|
| 500 |
+
[[34m2025-10-28 11:42:10[0m] (step=0043700) Train Loss: 0.6083, Train Steps/Sec: 1.13
|
| 501 |
+
[[34m2025-10-28 11:43:25[0m] Beginning epoch 35...
|
| 502 |
+
[[34m2025-10-28 11:43:44[0m] (step=0043800) Train Loss: 0.6108, Train Steps/Sec: 1.07
|
| 503 |
+
[[34m2025-10-28 11:45:12[0m] (step=0043900) Train Loss: 0.6087, Train Steps/Sec: 1.13
|
| 504 |
+
[[34m2025-10-28 11:46:40[0m] (step=0044000) Train Loss: 0.6102, Train Steps/Sec: 1.13
|
| 505 |
+
[[34m2025-10-28 11:48:09[0m] (step=0044100) Train Loss: 0.6090, Train Steps/Sec: 1.13
|
| 506 |
+
[[34m2025-10-28 11:49:37[0m] (step=0044200) Train Loss: 0.6084, Train Steps/Sec: 1.13
|
| 507 |
+
[[34m2025-10-28 11:51:05[0m] (step=0044300) Train Loss: 0.6080, Train Steps/Sec: 1.13
|
| 508 |
+
[[34m2025-10-28 11:52:34[0m] (step=0044400) Train Loss: 0.6097, Train Steps/Sec: 1.13
|
| 509 |
+
[[34m2025-10-28 11:54:02[0m] (step=0044500) Train Loss: 0.6076, Train Steps/Sec: 1.13
|
| 510 |
+
[[34m2025-10-28 11:55:30[0m] (step=0044600) Train Loss: 0.6100, Train Steps/Sec: 1.13
|
| 511 |
+
[[34m2025-10-28 11:56:58[0m] (step=0044700) Train Loss: 0.6096, Train Steps/Sec: 1.13
|
| 512 |
+
[[34m2025-10-28 11:58:26[0m] (step=0044800) Train Loss: 0.6083, Train Steps/Sec: 1.13
|
| 513 |
+
[[34m2025-10-28 11:59:55[0m] (step=0044900) Train Loss: 0.6092, Train Steps/Sec: 1.13
|
| 514 |
+
[[34m2025-10-28 12:01:23[0m] (step=0045000) Train Loss: 0.6091, Train Steps/Sec: 1.13
|
| 515 |
+
[[34m2025-10-28 12:01:55[0m] Beginning epoch 36...
|
| 516 |
+
[[34m2025-10-28 12:02:57[0m] (step=0045100) Train Loss: 0.6082, Train Steps/Sec: 1.07
|
| 517 |
+
[[34m2025-10-28 12:04:25[0m] (step=0045200) Train Loss: 0.6090, Train Steps/Sec: 1.13
|
| 518 |
+
[[34m2025-10-28 12:05:53[0m] (step=0045300) Train Loss: 0.6081, Train Steps/Sec: 1.13
|
| 519 |
+
[[34m2025-10-28 12:07:21[0m] (step=0045400) Train Loss: 0.6091, Train Steps/Sec: 1.13
|
| 520 |
+
[[34m2025-10-28 12:08:50[0m] (step=0045500) Train Loss: 0.6080, Train Steps/Sec: 1.13
|
| 521 |
+
[[34m2025-10-28 12:10:18[0m] (step=0045600) Train Loss: 0.6084, Train Steps/Sec: 1.13
|
| 522 |
+
[[34m2025-10-28 12:11:46[0m] (step=0045700) Train Loss: 0.6097, Train Steps/Sec: 1.13
|
| 523 |
+
[[34m2025-10-28 12:13:14[0m] (step=0045800) Train Loss: 0.6080, Train Steps/Sec: 1.13
|
| 524 |
+
[[34m2025-10-28 12:14:43[0m] (step=0045900) Train Loss: 0.6093, Train Steps/Sec: 1.13
|
| 525 |
+
[[34m2025-10-28 12:16:11[0m] (step=0046000) Train Loss: 0.6083, Train Steps/Sec: 1.13
|
| 526 |
+
[[34m2025-10-28 12:17:39[0m] (step=0046100) Train Loss: 0.6086, Train Steps/Sec: 1.13
|
| 527 |
+
[[34m2025-10-28 12:19:07[0m] (step=0046200) Train Loss: 0.6085, Train Steps/Sec: 1.13
|
| 528 |
+
[[34m2025-10-28 12:20:25[0m] Beginning epoch 37...
|
| 529 |
+
[[34m2025-10-28 12:20:41[0m] (step=0046300) Train Loss: 0.6082, Train Steps/Sec: 1.07
|
| 530 |
+
[[34m2025-10-28 12:22:09[0m] (step=0046400) Train Loss: 0.6088, Train Steps/Sec: 1.13
|
| 531 |
+
[[34m2025-10-28 12:23:37[0m] (step=0046500) Train Loss: 0.6083, Train Steps/Sec: 1.13
|
| 532 |
+
[[34m2025-10-28 12:25:06[0m] (step=0046600) Train Loss: 0.6077, Train Steps/Sec: 1.13
|
| 533 |
+
[[34m2025-10-28 12:26:35[0m] (step=0046700) Train Loss: 0.6070, Train Steps/Sec: 1.12
|
| 534 |
+
[[34m2025-10-28 12:28:03[0m] (step=0046800) Train Loss: 0.6078, Train Steps/Sec: 1.13
|
| 535 |
+
[[34m2025-10-28 12:29:31[0m] (step=0046900) Train Loss: 0.6079, Train Steps/Sec: 1.13
|
| 536 |
+
[[34m2025-10-28 12:30:59[0m] (step=0047000) Train Loss: 0.6081, Train Steps/Sec: 1.13
|
| 537 |
+
[[34m2025-10-28 12:32:27[0m] (step=0047100) Train Loss: 0.6099, Train Steps/Sec: 1.13
|
| 538 |
+
[[34m2025-10-28 12:33:55[0m] (step=0047200) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 539 |
+
[[34m2025-10-28 12:35:24[0m] (step=0047300) Train Loss: 0.6086, Train Steps/Sec: 1.13
|
| 540 |
+
[[34m2025-10-28 12:36:52[0m] (step=0047400) Train Loss: 0.6074, Train Steps/Sec: 1.13
|
| 541 |
+
[[34m2025-10-28 12:38:20[0m] (step=0047500) Train Loss: 0.6070, Train Steps/Sec: 1.13
|
| 542 |
+
[[34m2025-10-28 12:38:54[0m] Beginning epoch 38...
|
| 543 |
+
[[34m2025-10-28 12:39:55[0m] (step=0047600) Train Loss: 0.6065, Train Steps/Sec: 1.06
|
| 544 |
+
[[34m2025-10-28 12:41:23[0m] (step=0047700) Train Loss: 0.6081, Train Steps/Sec: 1.13
|
| 545 |
+
[[34m2025-10-28 12:42:51[0m] (step=0047800) Train Loss: 0.6073, Train Steps/Sec: 1.13
|
| 546 |
+
[[34m2025-10-28 12:44:19[0m] (step=0047900) Train Loss: 0.6057, Train Steps/Sec: 1.13
|
| 547 |
+
[[34m2025-10-28 12:45:47[0m] (step=0048000) Train Loss: 0.6072, Train Steps/Sec: 1.13
|
| 548 |
+
[[34m2025-10-28 12:47:15[0m] (step=0048100) Train Loss: 0.6056, Train Steps/Sec: 1.13
|
| 549 |
+
[[34m2025-10-28 12:48:44[0m] (step=0048200) Train Loss: 0.6075, Train Steps/Sec: 1.13
|
| 550 |
+
[[34m2025-10-28 12:50:12[0m] (step=0048300) Train Loss: 0.6075, Train Steps/Sec: 1.13
|
| 551 |
+
[[34m2025-10-28 12:51:40[0m] (step=0048400) Train Loss: 0.6072, Train Steps/Sec: 1.13
|
| 552 |
+
[[34m2025-10-28 12:53:09[0m] (step=0048500) Train Loss: 0.6081, Train Steps/Sec: 1.13
|
| 553 |
+
[[34m2025-10-28 12:54:37[0m] (step=0048600) Train Loss: 0.6083, Train Steps/Sec: 1.13
|
| 554 |
+
[[34m2025-10-28 12:56:05[0m] (step=0048700) Train Loss: 0.6076, Train Steps/Sec: 1.13
|
| 555 |
+
[[34m2025-10-28 12:57:24[0m] Beginning epoch 39...
|
| 556 |
+
[[34m2025-10-28 12:57:38[0m] (step=0048800) Train Loss: 0.6070, Train Steps/Sec: 1.07
|
| 557 |
+
[[34m2025-10-28 12:59:06[0m] (step=0048900) Train Loss: 0.6084, Train Steps/Sec: 1.13
|
| 558 |
+
[[34m2025-10-28 13:00:34[0m] (step=0049000) Train Loss: 0.6067, Train Steps/Sec: 1.13
|
| 559 |
+
[[34m2025-10-28 13:02:02[0m] (step=0049100) Train Loss: 0.6064, Train Steps/Sec: 1.13
|
| 560 |
+
[[34m2025-10-28 13:03:31[0m] (step=0049200) Train Loss: 0.6064, Train Steps/Sec: 1.13
|
| 561 |
+
[[34m2025-10-28 13:04:59[0m] (step=0049300) Train Loss: 0.6074, Train Steps/Sec: 1.13
|
| 562 |
+
[[34m2025-10-28 13:06:28[0m] (step=0049400) Train Loss: 0.6061, Train Steps/Sec: 1.13
|
| 563 |
+
[[34m2025-10-28 13:07:56[0m] (step=0049500) Train Loss: 0.6058, Train Steps/Sec: 1.13
|
| 564 |
+
[[34m2025-10-28 13:09:24[0m] (step=0049600) Train Loss: 0.6061, Train Steps/Sec: 1.13
|
| 565 |
+
[[34m2025-10-28 13:10:52[0m] (step=0049700) Train Loss: 0.6065, Train Steps/Sec: 1.14
|
| 566 |
+
[[34m2025-10-28 13:12:20[0m] (step=0049800) Train Loss: 0.6058, Train Steps/Sec: 1.13
|
| 567 |
+
[[34m2025-10-28 13:13:48[0m] (step=0049900) Train Loss: 0.6079, Train Steps/Sec: 1.13
|
| 568 |
+
[[34m2025-10-28 13:15:17[0m] (step=0050000) Train Loss: 0.6078, Train Steps/Sec: 1.13
|
| 569 |
+
[[34m2025-10-28 13:16:10[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-spatialpe-vit-g-bf16/checkpoints/0050000.pt
|
| 570 |
+
[[34m2025-10-28 13:16:10[0m] Generating EMA samples...
|
| 571 |
+
[[34m2025-10-28 13:16:38[0m] Generating EMA samples done.
|
| 572 |
+
[[34m2025-10-28 13:17:14[0m] Beginning epoch 40...
|
| 573 |
+
[[34m2025-10-28 13:18:13[0m] (step=0050100) Train Loss: 0.6052, Train Steps/Sec: 0.57
|
| 574 |
+
[[34m2025-10-28 13:19:42[0m] (step=0050200) Train Loss: 0.6061, Train Steps/Sec: 1.13
|
| 575 |
+
[[34m2025-10-28 13:21:10[0m] (step=0050300) Train Loss: 0.6062, Train Steps/Sec: 1.13
|
| 576 |
+
[[34m2025-10-28 13:22:38[0m] (step=0050400) Train Loss: 0.6056, Train Steps/Sec: 1.13
|
| 577 |
+
[[34m2025-10-28 13:24:06[0m] (step=0050500) Train Loss: 0.6058, Train Steps/Sec: 1.14
|
| 578 |
+
[[34m2025-10-28 13:25:34[0m] (step=0050600) Train Loss: 0.6065, Train Steps/Sec: 1.13
|
| 579 |
+
[[34m2025-10-28 13:27:02[0m] (step=0050700) Train Loss: 0.6079, Train Steps/Sec: 1.13
|
| 580 |
+
[[34m2025-10-28 13:28:31[0m] (step=0050800) Train Loss: 0.6059, Train Steps/Sec: 1.13
|
| 581 |
+
[[34m2025-10-28 13:29:59[0m] (step=0050900) Train Loss: 0.6054, Train Steps/Sec: 1.13
|
| 582 |
+
[[34m2025-10-28 13:31:27[0m] (step=0051000) Train Loss: 0.6071, Train Steps/Sec: 1.13
|
| 583 |
+
[[34m2025-10-28 13:32:55[0m] (step=0051100) Train Loss: 0.6063, Train Steps/Sec: 1.13
|
| 584 |
+
[[34m2025-10-28 13:34:24[0m] (step=0051200) Train Loss: 0.6051, Train Steps/Sec: 1.13
|
| 585 |
+
[[34m2025-10-28 13:35:44[0m] Beginning epoch 41...
|
| 586 |
+
[[34m2025-10-28 13:35:58[0m] (step=0051300) Train Loss: 0.6070, Train Steps/Sec: 1.06
|
| 587 |
+
[[34m2025-10-28 13:37:26[0m] (step=0051400) Train Loss: 0.6052, Train Steps/Sec: 1.13
|
| 588 |
+
[[34m2025-10-28 13:38:54[0m] (step=0051500) Train Loss: 0.6052, Train Steps/Sec: 1.13
|
| 589 |
+
[[34m2025-10-28 13:40:22[0m] (step=0051600) Train Loss: 0.6068, Train Steps/Sec: 1.13
|
| 590 |
+
[[34m2025-10-28 13:41:51[0m] (step=0051700) Train Loss: 0.6047, Train Steps/Sec: 1.13
|
| 591 |
+
[[34m2025-10-28 13:43:19[0m] (step=0051800) Train Loss: 0.6050, Train Steps/Sec: 1.13
|
| 592 |
+
[[34m2025-10-28 13:44:47[0m] (step=0051900) Train Loss: 0.6054, Train Steps/Sec: 1.13
|
| 593 |
+
[[34m2025-10-28 13:46:15[0m] (step=0052000) Train Loss: 0.6045, Train Steps/Sec: 1.13
|
| 594 |
+
[[34m2025-10-28 13:47:44[0m] (step=0052100) Train Loss: 0.6065, Train Steps/Sec: 1.13
|
| 595 |
+
[[34m2025-10-28 13:49:12[0m] (step=0052200) Train Loss: 0.6063, Train Steps/Sec: 1.13
|
| 596 |
+
[[34m2025-10-28 13:50:40[0m] (step=0052300) Train Loss: 0.6062, Train Steps/Sec: 1.13
|
| 597 |
+
[[34m2025-10-28 13:52:08[0m] (step=0052400) Train Loss: 0.6061, Train Steps/Sec: 1.13
|
| 598 |
+
[[34m2025-10-28 13:53:36[0m] (step=0052500) Train Loss: 0.6053, Train Steps/Sec: 1.13
|
| 599 |
+
[[34m2025-10-28 13:54:14[0m] Beginning epoch 42...
|
| 600 |
+
[[34m2025-10-28 13:55:11[0m] (step=0052600) Train Loss: 0.6049, Train Steps/Sec: 1.06
|
| 601 |
+
[[34m2025-10-28 13:56:39[0m] (step=0052700) Train Loss: 0.6051, Train Steps/Sec: 1.13
|
| 602 |
+
[[34m2025-10-28 13:58:08[0m] (step=0052800) Train Loss: 0.6065, Train Steps/Sec: 1.13
|
| 603 |
+
[[34m2025-10-28 13:59:36[0m] (step=0052900) Train Loss: 0.6067, Train Steps/Sec: 1.13
|
| 604 |
+
[[34m2025-10-28 14:01:04[0m] (step=0053000) Train Loss: 0.6045, Train Steps/Sec: 1.13
|
| 605 |
+
[[34m2025-10-28 14:02:32[0m] (step=0053100) Train Loss: 0.6047, Train Steps/Sec: 1.13
|
| 606 |
+
[[34m2025-10-28 14:04:00[0m] (step=0053200) Train Loss: 0.6050, Train Steps/Sec: 1.13
|
| 607 |
+
[[34m2025-10-28 14:05:29[0m] (step=0053300) Train Loss: 0.6049, Train Steps/Sec: 1.13
|
| 608 |
+
[[34m2025-10-28 14:06:57[0m] (step=0053400) Train Loss: 0.6043, Train Steps/Sec: 1.13
|
| 609 |
+
[[34m2025-10-28 14:08:25[0m] (step=0053500) Train Loss: 0.6057, Train Steps/Sec: 1.13
|
| 610 |
+
[[34m2025-10-28 14:09:54[0m] (step=0053600) Train Loss: 0.6059, Train Steps/Sec: 1.13
|
| 611 |
+
[[34m2025-10-28 14:11:22[0m] (step=0053700) Train Loss: 0.6055, Train Steps/Sec: 1.13
|
| 612 |
+
[[34m2025-10-28 14:12:45[0m] Beginning epoch 43...
|
| 613 |
+
[[34m2025-10-28 14:12:56[0m] (step=0053800) Train Loss: 0.6055, Train Steps/Sec: 1.06
|
| 614 |
+
[[34m2025-10-28 14:14:24[0m] (step=0053900) Train Loss: 0.6038, Train Steps/Sec: 1.13
|
| 615 |
+
[[34m2025-10-28 14:15:53[0m] (step=0054000) Train Loss: 0.6040, Train Steps/Sec: 1.13
|
| 616 |
+
[[34m2025-10-28 14:17:21[0m] (step=0054100) Train Loss: 0.6062, Train Steps/Sec: 1.13
|
| 617 |
+
[[34m2025-10-28 14:18:49[0m] (step=0054200) Train Loss: 0.6034, Train Steps/Sec: 1.13
|
| 618 |
+
[[34m2025-10-28 14:20:17[0m] (step=0054300) Train Loss: 0.6054, Train Steps/Sec: 1.13
|
| 619 |
+
[[34m2025-10-28 14:21:46[0m] (step=0054400) Train Loss: 0.6052, Train Steps/Sec: 1.13
|
| 620 |
+
[[34m2025-10-28 14:23:14[0m] (step=0054500) Train Loss: 0.6048, Train Steps/Sec: 1.13
|
| 621 |
+
[[34m2025-10-28 14:24:43[0m] (step=0054600) Train Loss: 0.6039, Train Steps/Sec: 1.13
|
| 622 |
+
[[34m2025-10-28 14:26:11[0m] (step=0054700) Train Loss: 0.6042, Train Steps/Sec: 1.13
|
| 623 |
+
[[34m2025-10-28 14:27:39[0m] (step=0054800) Train Loss: 0.6042, Train Steps/Sec: 1.13
|
| 624 |
+
[[34m2025-10-28 14:29:07[0m] (step=0054900) Train Loss: 0.6048, Train Steps/Sec: 1.13
|
| 625 |
+
[[34m2025-10-28 14:30:35[0m] (step=0055000) Train Loss: 0.6047, Train Steps/Sec: 1.13
|
| 626 |
+
[[34m2025-10-28 14:31:15[0m] Beginning epoch 44...
|
| 627 |
+
[[34m2025-10-28 14:32:10[0m] (step=0055100) Train Loss: 0.6055, Train Steps/Sec: 1.06
|
| 628 |
+
[[34m2025-10-28 14:33:38[0m] (step=0055200) Train Loss: 0.6041, Train Steps/Sec: 1.13
|
| 629 |
+
[[34m2025-10-28 14:35:06[0m] (step=0055300) Train Loss: 0.6041, Train Steps/Sec: 1.13
|
| 630 |
+
[[34m2025-10-28 14:36:35[0m] (step=0055400) Train Loss: 0.6042, Train Steps/Sec: 1.13
|
| 631 |
+
[[34m2025-10-28 14:38:03[0m] (step=0055500) Train Loss: 0.6044, Train Steps/Sec: 1.13
|
| 632 |
+
[[34m2025-10-28 14:39:31[0m] (step=0055600) Train Loss: 0.6042, Train Steps/Sec: 1.13
|
| 633 |
+
[[34m2025-10-28 14:41:00[0m] (step=0055700) Train Loss: 0.6046, Train Steps/Sec: 1.13
|
| 634 |
+
[[34m2025-10-28 14:42:28[0m] (step=0055800) Train Loss: 0.6037, Train Steps/Sec: 1.13
|
| 635 |
+
[[34m2025-10-28 14:43:56[0m] (step=0055900) Train Loss: 0.6048, Train Steps/Sec: 1.13
|
| 636 |
+
[[34m2025-10-28 14:45:24[0m] (step=0056000) Train Loss: 0.6031, Train Steps/Sec: 1.13
|
| 637 |
+
[[34m2025-10-28 14:46:52[0m] (step=0056100) Train Loss: 0.6028, Train Steps/Sec: 1.13
|
| 638 |
+
[[34m2025-10-28 14:48:21[0m] (step=0056200) Train Loss: 0.6044, Train Steps/Sec: 1.13
|
| 639 |
+
[[34m2025-10-28 14:49:45[0m] Beginning epoch 45...
|
| 640 |
+
[[34m2025-10-28 14:49:55[0m] (step=0056300) Train Loss: 0.6057, Train Steps/Sec: 1.06
|
| 641 |
+
[[34m2025-10-28 14:51:23[0m] (step=0056400) Train Loss: 0.6026, Train Steps/Sec: 1.13
|
| 642 |
+
[[34m2025-10-28 14:52:51[0m] (step=0056500) Train Loss: 0.6051, Train Steps/Sec: 1.13
|
| 643 |
+
[[34m2025-10-28 14:54:20[0m] (step=0056600) Train Loss: 0.6034, Train Steps/Sec: 1.13
|
| 644 |
+
[[34m2025-10-28 14:55:48[0m] (step=0056700) Train Loss: 0.6039, Train Steps/Sec: 1.13
|
| 645 |
+
[[34m2025-10-28 14:57:16[0m] (step=0056800) Train Loss: 0.6026, Train Steps/Sec: 1.13
|
| 646 |
+
[[34m2025-10-28 14:58:44[0m] (step=0056900) Train Loss: 0.6033, Train Steps/Sec: 1.13
|
| 647 |
+
[[34m2025-10-28 15:00:12[0m] (step=0057000) Train Loss: 0.6042, Train Steps/Sec: 1.13
|
| 648 |
+
[[34m2025-10-28 15:01:41[0m] (step=0057100) Train Loss: 0.6040, Train Steps/Sec: 1.13
|
| 649 |
+
[[34m2025-10-28 15:03:09[0m] (step=0057200) Train Loss: 0.6039, Train Steps/Sec: 1.13
|
| 650 |
+
[[34m2025-10-28 15:04:37[0m] (step=0057300) Train Loss: 0.6042, Train Steps/Sec: 1.13
|
| 651 |
+
[[34m2025-10-28 15:06:06[0m] (step=0057400) Train Loss: 0.6032, Train Steps/Sec: 1.13
|
| 652 |
+
[[34m2025-10-28 15:07:34[0m] (step=0057500) Train Loss: 0.6044, Train Steps/Sec: 1.13
|
| 653 |
+
[[34m2025-10-28 15:08:15[0m] Beginning epoch 46...
|
| 654 |
+
[[34m2025-10-28 15:09:08[0m] (step=0057600) Train Loss: 0.6027, Train Steps/Sec: 1.06
|
| 655 |
+
[[34m2025-10-28 15:10:36[0m] (step=0057700) Train Loss: 0.6038, Train Steps/Sec: 1.13
|
| 656 |
+
[[34m2025-10-28 15:12:04[0m] (step=0057800) Train Loss: 0.6042, Train Steps/Sec: 1.13
|
| 657 |
+
[[34m2025-10-28 15:13:33[0m] (step=0057900) Train Loss: 0.6047, Train Steps/Sec: 1.13
|
| 658 |
+
[[34m2025-10-28 15:15:02[0m] (step=0058000) Train Loss: 0.6041, Train Steps/Sec: 1.13
|
| 659 |
+
[[34m2025-10-28 15:16:30[0m] (step=0058100) Train Loss: 0.6026, Train Steps/Sec: 1.13
|
| 660 |
+
[[34m2025-10-28 15:17:58[0m] (step=0058200) Train Loss: 0.6053, Train Steps/Sec: 1.13
|
| 661 |
+
[[34m2025-10-28 15:19:26[0m] (step=0058300) Train Loss: 0.6044, Train Steps/Sec: 1.13
|
| 662 |
+
[[34m2025-10-28 15:20:54[0m] (step=0058400) Train Loss: 0.6056, Train Steps/Sec: 1.13
|
| 663 |
+
[[34m2025-10-28 15:22:22[0m] (step=0058500) Train Loss: 1.6813, Train Steps/Sec: 1.13
|
| 664 |
+
[[34m2025-10-28 15:23:50[0m] (step=0058600) Train Loss: 1.9872, Train Steps/Sec: 1.13
|
| 665 |
+
[[34m2025-10-28 15:25:19[0m] (step=0058700) Train Loss: 1.7171, Train Steps/Sec: 1.13
|
| 666 |
+
[[34m2025-10-28 15:26:45[0m] Beginning epoch 47...
|
| 667 |
+
[[34m2025-10-28 15:26:53[0m] (step=0058800) Train Loss: 1.7091, Train Steps/Sec: 1.06
|
| 668 |
+
[[34m2025-10-28 15:28:21[0m] (step=0058900) Train Loss: 1.7624, Train Steps/Sec: 1.13
|
| 669 |
+
[[34m2025-10-28 15:29:49[0m] (step=0059000) Train Loss: 2.8110, Train Steps/Sec: 1.13
|
| 670 |
+
[[34m2025-10-28 15:31:18[0m] (step=0059100) Train Loss: 1.5612, Train Steps/Sec: 1.13
|
| 671 |
+
[[34m2025-10-28 15:32:46[0m] (step=0059200) Train Loss: 1.4085, Train Steps/Sec: 1.13
|
| 672 |
+
[[34m2025-10-28 15:34:14[0m] (step=0059300) Train Loss: 1.7414, Train Steps/Sec: 1.13
|
| 673 |
+
[[34m2025-10-28 15:35:42[0m] (step=0059400) Train Loss: 1.4169, Train Steps/Sec: 1.13
|
| 674 |
+
[[34m2025-10-28 15:37:10[0m] (step=0059500) Train Loss: 1.6964, Train Steps/Sec: 1.13
|
| 675 |
+
[[34m2025-10-28 15:38:39[0m] (step=0059600) Train Loss: 1.6169, Train Steps/Sec: 1.13
|
| 676 |
+
[[34m2025-10-28 15:40:07[0m] (step=0059700) Train Loss: 1.4081, Train Steps/Sec: 1.13
|
| 677 |
+
[[34m2025-10-28 15:41:36[0m] (step=0059800) Train Loss: 1.4212, Train Steps/Sec: 1.13
|
| 678 |
+
[[34m2025-10-28 15:43:04[0m] (step=0059900) Train Loss: 1.5733, Train Steps/Sec: 1.13
|
| 679 |
+
[[34m2025-10-28 15:44:32[0m] (step=0060000) Train Loss: 1.3904, Train Steps/Sec: 1.13
|
| 680 |
+
[[34m2025-10-28 15:45:15[0m] Beginning epoch 48...
|
| 681 |
+
[[34m2025-10-28 15:46:06[0m] (step=0060100) Train Loss: 1.0895, Train Steps/Sec: 1.06
|
| 682 |
+
[[34m2025-10-28 15:47:34[0m] (step=0060200) Train Loss: 1.2682, Train Steps/Sec: 1.13
|
| 683 |
+
[[34m2025-10-28 15:49:02[0m] (step=0060300) Train Loss: 1.4114, Train Steps/Sec: 1.13
|
| 684 |
+
[[34m2025-10-28 15:50:31[0m] (step=0060400) Train Loss: 1.4329, Train Steps/Sec: 1.13
|
| 685 |
+
[[34m2025-10-28 15:51:59[0m] (step=0060500) Train Loss: 1.2282, Train Steps/Sec: 1.13
|
| 686 |
+
[[34m2025-10-28 15:53:28[0m] (step=0060600) Train Loss: 1.2971, Train Steps/Sec: 1.13
|
| 687 |
+
[[34m2025-10-28 15:54:56[0m] (step=0060700) Train Loss: 1.5380, Train Steps/Sec: 1.13
|
| 688 |
+
[[34m2025-10-28 15:56:24[0m] (step=0060800) Train Loss: 1.4680, Train Steps/Sec: 1.13
|
| 689 |
+
[[34m2025-10-28 15:57:52[0m] (step=0060900) Train Loss: 1.4340, Train Steps/Sec: 1.13
|
| 690 |
+
[[34m2025-10-28 15:59:20[0m] (step=0061000) Train Loss: 1.2399, Train Steps/Sec: 1.13
|
| 691 |
+
[[34m2025-10-28 16:00:49[0m] (step=0061100) Train Loss: 1.0848, Train Steps/Sec: 1.13
|
| 692 |
+
[[34m2025-10-28 16:02:17[0m] (step=0061200) Train Loss: 1.4618, Train Steps/Sec: 1.13
|
| 693 |
+
[[34m2025-10-28 16:03:45[0m] Beginning epoch 49...
|
| 694 |
+
[[34m2025-10-28 16:03:51[0m] (step=0061300) Train Loss: 1.0316, Train Steps/Sec: 1.06
|
| 695 |
+
[[34m2025-10-28 16:05:20[0m] (step=0061400) Train Loss: 0.8428, Train Steps/Sec: 1.13
|
| 696 |
+
[[34m2025-10-28 16:06:48[0m] (step=0061500) Train Loss: 1.3772, Train Steps/Sec: 1.13
|
| 697 |
+
[[34m2025-10-28 16:08:16[0m] (step=0061600) Train Loss: 1.5703, Train Steps/Sec: 1.13
|
| 698 |
+
[[34m2025-10-28 16:09:45[0m] (step=0061700) Train Loss: 1.4128, Train Steps/Sec: 1.13
|
| 699 |
+
[[34m2025-10-28 16:11:13[0m] (step=0061800) Train Loss: 1.4401, Train Steps/Sec: 1.13
|
| 700 |
+
[[34m2025-10-28 16:12:41[0m] (step=0061900) Train Loss: 1.2260, Train Steps/Sec: 1.13
|
| 701 |
+
[[34m2025-10-28 16:14:09[0m] (step=0062000) Train Loss: 1.3542, Train Steps/Sec: 1.13
|
| 702 |
+
[[34m2025-10-28 16:15:37[0m] (step=0062100) Train Loss: 1.6677, Train Steps/Sec: 1.13
|
| 703 |
+
[[34m2025-10-28 16:17:06[0m] (step=0062200) Train Loss: 4.1388, Train Steps/Sec: 1.13
|
| 704 |
+
[[34m2025-10-28 16:18:34[0m] (step=0062300) Train Loss: 1.0619, Train Steps/Sec: 1.13
|
| 705 |
+
[[34m2025-10-28 16:20:02[0m] (step=0062400) Train Loss: 3.5517, Train Steps/Sec: 1.13
|
| 706 |
+
[[34m2025-10-28 16:21:30[0m] (step=0062500) Train Loss: 1.8764, Train Steps/Sec: 1.13
|
| 707 |
+
[[34m2025-10-28 16:22:15[0m] Beginning epoch 50...
|
| 708 |
+
[[34m2025-10-28 16:23:05[0m] (step=0062600) Train Loss: 1.6090, Train Steps/Sec: 1.06
|
| 709 |
+
[[34m2025-10-28 16:24:33[0m] (step=0062700) Train Loss: 2.1292, Train Steps/Sec: 1.13
|
| 710 |
+
[[34m2025-10-28 16:26:01[0m] (step=0062800) Train Loss: 2.4507, Train Steps/Sec: 1.13
|
| 711 |
+
[[34m2025-10-28 16:27:30[0m] (step=0062900) Train Loss: 2.4119, Train Steps/Sec: 1.13
|
| 712 |
+
[[34m2025-10-28 16:28:58[0m] (step=0063000) Train Loss: nan, Train Steps/Sec: 1.13
|
| 713 |
+
[[34m2025-10-28 16:30:23[0m] (step=0063100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 714 |
+
[[34m2025-10-28 16:31:47[0m] (step=0063200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 715 |
+
[[34m2025-10-28 16:33:12[0m] (step=0063300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 716 |
+
[[34m2025-10-28 16:34:36[0m] (step=0063400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 717 |
+
[[34m2025-10-28 16:36:01[0m] (step=0063500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 718 |
+
[[34m2025-10-28 16:37:25[0m] (step=0063600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 719 |
+
[[34m2025-10-28 16:38:50[0m] (step=0063700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 720 |
+
[[34m2025-10-28 16:40:14[0m] (step=0063800) Train Loss: nan, Train Steps/Sec: 1.19
|
| 721 |
+
[[34m2025-10-28 16:40:15[0m] Beginning epoch 51...
|
| 722 |
+
[[34m2025-10-28 16:41:44[0m] (step=0063900) Train Loss: nan, Train Steps/Sec: 1.11
|
| 723 |
+
[[34m2025-10-28 16:43:09[0m] (step=0064000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 724 |
+
[[34m2025-10-28 16:44:34[0m] (step=0064100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 725 |
+
[[34m2025-10-28 16:45:58[0m] (step=0064200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 726 |
+
[[34m2025-10-28 16:47:23[0m] (step=0064300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 727 |
+
[[34m2025-10-28 16:48:47[0m] (step=0064400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 728 |
+
[[34m2025-10-28 16:50:11[0m] (step=0064500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 729 |
+
[[34m2025-10-28 16:51:36[0m] (step=0064600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 730 |
+
[[34m2025-10-28 16:53:00[0m] (step=0064700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 731 |
+
[[34m2025-10-28 16:54:25[0m] (step=0064800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 732 |
+
[[34m2025-10-28 16:55:50[0m] (step=0064900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 733 |
+
[[34m2025-10-28 16:57:14[0m] (step=0065000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 734 |
+
[[34m2025-10-28 16:57:59[0m] Beginning epoch 52...
|
| 735 |
+
[[34m2025-10-28 16:58:45[0m] (step=0065100) Train Loss: nan, Train Steps/Sec: 1.10
|
| 736 |
+
[[34m2025-10-28 17:00:10[0m] (step=0065200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 737 |
+
[[34m2025-10-28 17:01:34[0m] (step=0065300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 738 |
+
[[34m2025-10-28 17:02:59[0m] (step=0065400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 739 |
+
[[34m2025-10-28 17:04:23[0m] (step=0065500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 740 |
+
[[34m2025-10-28 17:05:47[0m] (step=0065600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 741 |
+
[[34m2025-10-28 17:07:12[0m] (step=0065700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 742 |
+
[[34m2025-10-28 17:08:37[0m] (step=0065800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 743 |
+
[[34m2025-10-28 17:10:01[0m] (step=0065900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 744 |
+
[[34m2025-10-28 17:11:26[0m] (step=0066000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 745 |
+
[[34m2025-10-28 17:12:50[0m] (step=0066100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 746 |
+
[[34m2025-10-28 17:14:14[0m] (step=0066200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 747 |
+
[[34m2025-10-28 17:15:39[0m] (step=0066300) Train Loss: nan, Train Steps/Sec: 1.19
|
| 748 |
+
[[34m2025-10-28 17:15:42[0m] Beginning epoch 53...
|
| 749 |
+
[[34m2025-10-28 17:17:10[0m] (step=0066400) Train Loss: nan, Train Steps/Sec: 1.10
|
| 750 |
+
[[34m2025-10-28 17:18:35[0m] (step=0066500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 751 |
+
[[34m2025-10-28 17:20:00[0m] (step=0066600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 752 |
+
[[34m2025-10-28 17:21:24[0m] (step=0066700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 753 |
+
[[34m2025-10-28 17:22:49[0m] (step=0066800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 754 |
+
[[34m2025-10-28 17:24:13[0m] (step=0066900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 755 |
+
[[34m2025-10-28 17:25:37[0m] (step=0067000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 756 |
+
[[34m2025-10-28 17:27:02[0m] (step=0067100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 757 |
+
[[34m2025-10-28 17:28:26[0m] (step=0067200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 758 |
+
[[34m2025-10-28 17:29:51[0m] (step=0067300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 759 |
+
[[34m2025-10-28 17:31:16[0m] (step=0067400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 760 |
+
[[34m2025-10-28 17:32:40[0m] (step=0067500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 761 |
+
[[34m2025-10-28 17:33:26[0m] Beginning epoch 54...
|
| 762 |
+
[[34m2025-10-28 17:34:11[0m] (step=0067600) Train Loss: nan, Train Steps/Sec: 1.10
|
| 763 |
+
[[34m2025-10-28 17:35:36[0m] (step=0067700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 764 |
+
[[34m2025-10-28 17:37:00[0m] (step=0067800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 765 |
+
[[34m2025-10-28 17:38:25[0m] (step=0067900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 766 |
+
[[34m2025-10-28 17:39:49[0m] (step=0068000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 767 |
+
[[34m2025-10-28 17:41:13[0m] (step=0068100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 768 |
+
[[34m2025-10-28 17:42:38[0m] (step=0068200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 769 |
+
[[34m2025-10-28 17:44:03[0m] (step=0068300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 770 |
+
[[34m2025-10-28 17:45:27[0m] (step=0068400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 771 |
+
[[34m2025-10-28 17:46:52[0m] (step=0068500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 772 |
+
[[34m2025-10-28 17:48:16[0m] (step=0068600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 773 |
+
[[34m2025-10-28 17:49:41[0m] (step=0068700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 774 |
+
[[34m2025-10-28 17:51:05[0m] (step=0068800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 775 |
+
[[34m2025-10-28 17:51:10[0m] Beginning epoch 55...
|
| 776 |
+
[[34m2025-10-28 17:52:35[0m] (step=0068900) Train Loss: nan, Train Steps/Sec: 1.11
|
| 777 |
+
[[34m2025-10-28 17:54:00[0m] (step=0069000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 778 |
+
[[34m2025-10-28 17:55:25[0m] (step=0069100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 779 |
+
[[34m2025-10-28 17:56:50[0m] (step=0069200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 780 |
+
[[34m2025-10-28 17:58:14[0m] (step=0069300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 781 |
+
[[34m2025-10-28 17:59:39[0m] (step=0069400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 782 |
+
[[34m2025-10-28 18:01:03[0m] (step=0069500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 783 |
+
[[34m2025-10-28 18:02:27[0m] (step=0069600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 784 |
+
[[34m2025-10-28 18:03:52[0m] (step=0069700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 785 |
+
[[34m2025-10-28 18:05:16[0m] (step=0069800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 786 |
+
[[34m2025-10-28 18:06:41[0m] (step=0069900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 787 |
+
[[34m2025-10-28 18:08:06[0m] (step=0070000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 788 |
+
[[34m2025-10-28 18:08:54[0m] Beginning epoch 56...
|
| 789 |
+
[[34m2025-10-28 18:09:36[0m] (step=0070100) Train Loss: nan, Train Steps/Sec: 1.11
|
| 790 |
+
[[34m2025-10-28 18:11:00[0m] (step=0070200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 791 |
+
[[34m2025-10-28 18:12:25[0m] (step=0070300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 792 |
+
[[34m2025-10-28 18:13:49[0m] (step=0070400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 793 |
+
[[34m2025-10-28 18:15:14[0m] (step=0070500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 794 |
+
[[34m2025-10-28 18:16:38[0m] (step=0070600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 795 |
+
[[34m2025-10-28 18:18:03[0m] (step=0070700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 796 |
+
[[34m2025-10-28 18:19:27[0m] (step=0070800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 797 |
+
[[34m2025-10-28 18:20:52[0m] (step=0070900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 798 |
+
[[34m2025-10-28 18:22:17[0m] (step=0071000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 799 |
+
[[34m2025-10-28 18:23:41[0m] (step=0071100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 800 |
+
[[34m2025-10-28 18:25:06[0m] (step=0071200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 801 |
+
[[34m2025-10-28 18:26:30[0m] (step=0071300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 802 |
+
[[34m2025-10-28 18:26:37[0m] Beginning epoch 57...
|
| 803 |
+
[[34m2025-10-28 18:28:00[0m] (step=0071400) Train Loss: nan, Train Steps/Sec: 1.11
|
| 804 |
+
[[34m2025-10-28 18:29:25[0m] (step=0071500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 805 |
+
[[34m2025-10-28 18:30:49[0m] (step=0071600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 806 |
+
[[34m2025-10-28 18:32:14[0m] (step=0071700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 807 |
+
[[34m2025-10-28 18:33:39[0m] (step=0071800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 808 |
+
[[34m2025-10-28 18:35:03[0m] (step=0071900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 809 |
+
[[34m2025-10-28 18:36:27[0m] (step=0072000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 810 |
+
[[34m2025-10-28 18:37:52[0m] (step=0072100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 811 |
+
[[34m2025-10-28 18:39:16[0m] (step=0072200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 812 |
+
[[34m2025-10-28 18:40:41[0m] (step=0072300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 813 |
+
[[34m2025-10-28 18:42:05[0m] (step=0072400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 814 |
+
[[34m2025-10-28 18:43:30[0m] (step=0072500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 815 |
+
[[34m2025-10-28 18:44:20[0m] Beginning epoch 58...
|
| 816 |
+
[[34m2025-10-28 18:45:02[0m] (step=0072600) Train Loss: nan, Train Steps/Sec: 1.09
|
| 817 |
+
[[34m2025-10-28 18:46:26[0m] (step=0072700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 818 |
+
[[34m2025-10-28 18:47:50[0m] (step=0072800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 819 |
+
[[34m2025-10-28 18:49:15[0m] (step=0072900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 820 |
+
[[34m2025-10-28 18:50:40[0m] (step=0073000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 821 |
+
[[34m2025-10-28 18:52:04[0m] (step=0073100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 822 |
+
[[34m2025-10-28 18:53:28[0m] (step=0073200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 823 |
+
[[34m2025-10-28 18:54:53[0m] (step=0073300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 824 |
+
[[34m2025-10-28 18:56:17[0m] (step=0073400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 825 |
+
[[34m2025-10-28 18:57:42[0m] (step=0073500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 826 |
+
[[34m2025-10-28 18:59:07[0m] (step=0073600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 827 |
+
[[34m2025-10-28 19:00:31[0m] (step=0073700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 828 |
+
[[34m2025-10-28 19:01:55[0m] (step=0073800) Train Loss: nan, Train Steps/Sec: 1.19
|
| 829 |
+
[[34m2025-10-28 19:02:04[0m] Beginning epoch 59...
|
| 830 |
+
[[34m2025-10-28 19:03:25[0m] (step=0073900) Train Loss: nan, Train Steps/Sec: 1.11
|
| 831 |
+
[[34m2025-10-28 19:04:50[0m] (step=0074000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 832 |
+
[[34m2025-10-28 19:06:14[0m] (step=0074100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 833 |
+
[[34m2025-10-28 19:07:39[0m] (step=0074200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 834 |
+
[[34m2025-10-28 19:09:04[0m] (step=0074300) Train Loss: nan, Train Steps/Sec: 1.17
|
| 835 |
+
[[34m2025-10-28 19:10:29[0m] (step=0074400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 836 |
+
[[34m2025-10-28 19:11:53[0m] (step=0074500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 837 |
+
[[34m2025-10-28 19:13:18[0m] (step=0074600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 838 |
+
[[34m2025-10-28 19:14:42[0m] (step=0074700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 839 |
+
[[34m2025-10-28 19:16:06[0m] (step=0074800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 840 |
+
[[34m2025-10-28 19:17:31[0m] (step=0074900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 841 |
+
[[34m2025-10-28 19:18:55[0m] (step=0075000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 842 |
+
[[34m2025-10-28 19:19:49[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-spatialpe-vit-g-bf16/checkpoints/0075000.pt
|
| 843 |
+
[[34m2025-10-28 19:19:49[0m] Generating EMA samples...
|
| 844 |
+
[[34m2025-10-28 19:20:03[0m] Generating EMA samples done.
|
| 845 |
+
[[34m2025-10-28 19:20:54[0m] Beginning epoch 60...
|
| 846 |
+
[[34m2025-10-28 19:21:33[0m] (step=0075100) Train Loss: nan, Train Steps/Sec: 0.63
|
| 847 |
+
[[34m2025-10-28 19:22:59[0m] (step=0075200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 848 |
+
[[34m2025-10-28 19:24:23[0m] (step=0075300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 849 |
+
[[34m2025-10-28 19:25:47[0m] (step=0075400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 850 |
+
[[34m2025-10-28 19:27:12[0m] (step=0075500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 851 |
+
[[34m2025-10-28 19:28:36[0m] (step=0075600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 852 |
+
[[34m2025-10-28 19:30:01[0m] (step=0075700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 853 |
+
[[34m2025-10-28 19:31:25[0m] (step=0075800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 854 |
+
[[34m2025-10-28 19:32:50[0m] (step=0075900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 855 |
+
[[34m2025-10-28 19:34:15[0m] (step=0076000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 856 |
+
[[34m2025-10-28 19:35:39[0m] (step=0076100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 857 |
+
[[34m2025-10-28 19:37:04[0m] (step=0076200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 858 |
+
[[34m2025-10-28 19:38:28[0m] (step=0076300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 859 |
+
[[34m2025-10-28 19:38:38[0m] Beginning epoch 61...
|
| 860 |
+
[[34m2025-10-28 19:39:59[0m] (step=0076400) Train Loss: nan, Train Steps/Sec: 1.10
|
| 861 |
+
[[34m2025-10-28 19:41:24[0m] (step=0076500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 862 |
+
[[34m2025-10-28 19:42:48[0m] (step=0076600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 863 |
+
[[34m2025-10-28 19:44:13[0m] (step=0076700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 864 |
+
[[34m2025-10-28 19:45:37[0m] (step=0076800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 865 |
+
[[34m2025-10-28 19:47:02[0m] (step=0076900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 866 |
+
[[34m2025-10-28 19:48:27[0m] (step=0077000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 867 |
+
[[34m2025-10-28 19:49:51[0m] (step=0077100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 868 |
+
[[34m2025-10-28 19:51:15[0m] (step=0077200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 869 |
+
[[34m2025-10-28 19:52:40[0m] (step=0077300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 870 |
+
[[34m2025-10-28 19:54:04[0m] (step=0077400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 871 |
+
[[34m2025-10-28 19:55:29[0m] (step=0077500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 872 |
+
[[34m2025-10-28 19:56:22[0m] Beginning epoch 62...
|
| 873 |
+
[[34m2025-10-28 19:56:59[0m] (step=0077600) Train Loss: nan, Train Steps/Sec: 1.11
|
| 874 |
+
[[34m2025-10-28 19:58:24[0m] (step=0077700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 875 |
+
[[34m2025-10-28 19:59:49[0m] (step=0077800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 876 |
+
[[34m2025-10-28 20:01:13[0m] (step=0077900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 877 |
+
[[34m2025-10-28 20:02:38[0m] (step=0078000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 878 |
+
[[34m2025-10-28 20:04:02[0m] (step=0078100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 879 |
+
[[34m2025-10-28 20:05:27[0m] (step=0078200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 880 |
+
[[34m2025-10-28 20:06:51[0m] (step=0078300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 881 |
+
[[34m2025-10-28 20:08:16[0m] (step=0078400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 882 |
+
[[34m2025-10-28 20:09:40[0m] (step=0078500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 883 |
+
[[34m2025-10-28 20:11:05[0m] (step=0078600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 884 |
+
[[34m2025-10-28 20:12:29[0m] (step=0078700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 885 |
+
[[34m2025-10-28 20:13:54[0m] (step=0078800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 886 |
+
[[34m2025-10-28 20:14:06[0m] Beginning epoch 63...
|
| 887 |
+
[[34m2025-10-28 20:15:25[0m] (step=0078900) Train Loss: nan, Train Steps/Sec: 1.10
|
| 888 |
+
[[34m2025-10-28 20:16:49[0m] (step=0079000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 889 |
+
[[34m2025-10-28 20:18:13[0m] (step=0079100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 890 |
+
[[34m2025-10-28 20:19:38[0m] (step=0079200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 891 |
+
[[34m2025-10-28 20:21:03[0m] (step=0079300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 892 |
+
[[34m2025-10-28 20:22:27[0m] (step=0079400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 893 |
+
[[34m2025-10-28 20:23:52[0m] (step=0079500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 894 |
+
[[34m2025-10-28 20:25:17[0m] (step=0079600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 895 |
+
[[34m2025-10-28 20:26:41[0m] (step=0079700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 896 |
+
[[34m2025-10-28 20:28:06[0m] (step=0079800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 897 |
+
[[34m2025-10-28 20:29:30[0m] (step=0079900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 898 |
+
[[34m2025-10-28 20:30:55[0m] (step=0080000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 899 |
+
[[34m2025-10-28 20:31:49[0m] Beginning epoch 64...
|
| 900 |
+
[[34m2025-10-28 20:32:25[0m] (step=0080100) Train Loss: nan, Train Steps/Sec: 1.11
|
| 901 |
+
[[34m2025-10-28 20:33:49[0m] (step=0080200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 902 |
+
[[34m2025-10-28 20:35:14[0m] (step=0080300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 903 |
+
[[34m2025-10-28 20:36:39[0m] (step=0080400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 904 |
+
[[34m2025-10-28 20:38:03[0m] (step=0080500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 905 |
+
[[34m2025-10-28 20:39:28[0m] (step=0080600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 906 |
+
[[34m2025-10-28 20:40:52[0m] (step=0080700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 907 |
+
[[34m2025-10-28 20:42:17[0m] (step=0080800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 908 |
+
[[34m2025-10-28 20:43:41[0m] (step=0080900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 909 |
+
[[34m2025-10-28 20:45:06[0m] (step=0081000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 910 |
+
[[34m2025-10-28 20:46:30[0m] (step=0081100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 911 |
+
[[34m2025-10-28 20:47:55[0m] (step=0081200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 912 |
+
[[34m2025-10-28 20:49:19[0m] (step=0081300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 913 |
+
[[34m2025-10-28 20:49:33[0m] Beginning epoch 65...
|
| 914 |
+
[[34m2025-10-28 20:50:50[0m] (step=0081400) Train Loss: nan, Train Steps/Sec: 1.11
|
| 915 |
+
[[34m2025-10-28 20:52:14[0m] (step=0081500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 916 |
+
[[34m2025-10-28 20:53:39[0m] (step=0081600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 917 |
+
[[34m2025-10-28 20:55:03[0m] (step=0081700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 918 |
+
[[34m2025-10-28 20:56:28[0m] (step=0081800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 919 |
+
[[34m2025-10-28 20:57:52[0m] (step=0081900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 920 |
+
[[34m2025-10-28 20:59:17[0m] (step=0082000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 921 |
+
[[34m2025-10-28 21:00:42[0m] (step=0082100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 922 |
+
[[34m2025-10-28 21:02:06[0m] (step=0082200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 923 |
+
[[34m2025-10-28 21:03:31[0m] (step=0082300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 924 |
+
[[34m2025-10-28 21:04:55[0m] (step=0082400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 925 |
+
[[34m2025-10-28 21:06:20[0m] (step=0082500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 926 |
+
[[34m2025-10-28 21:07:16[0m] Beginning epoch 66...
|
| 927 |
+
[[34m2025-10-28 21:07:50[0m] (step=0082600) Train Loss: nan, Train Steps/Sec: 1.11
|
| 928 |
+
[[34m2025-10-28 21:09:14[0m] (step=0082700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 929 |
+
[[34m2025-10-28 21:10:39[0m] (step=0082800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 930 |
+
[[34m2025-10-28 21:12:03[0m] (step=0082900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 931 |
+
[[34m2025-10-28 21:13:28[0m] (step=0083000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 932 |
+
[[34m2025-10-28 21:14:53[0m] (step=0083100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 933 |
+
[[34m2025-10-28 21:16:17[0m] (step=0083200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 934 |
+
[[34m2025-10-28 21:17:42[0m] (step=0083300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 935 |
+
[[34m2025-10-28 21:19:06[0m] (step=0083400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 936 |
+
[[34m2025-10-28 21:20:30[0m] (step=0083500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 937 |
+
[[34m2025-10-28 21:21:55[0m] (step=0083600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 938 |
+
[[34m2025-10-28 21:23:19[0m] (step=0083700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 939 |
+
[[34m2025-10-28 21:24:44[0m] (step=0083800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 940 |
+
[[34m2025-10-28 21:24:59[0m] Beginning epoch 67...
|
| 941 |
+
[[34m2025-10-28 21:26:15[0m] (step=0083900) Train Loss: nan, Train Steps/Sec: 1.10
|
| 942 |
+
[[34m2025-10-28 21:27:40[0m] (step=0084000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 943 |
+
[[34m2025-10-28 21:29:04[0m] (step=0084100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 944 |
+
[[34m2025-10-28 21:30:28[0m] (step=0084200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 945 |
+
[[34m2025-10-28 21:31:53[0m] (step=0084300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 946 |
+
[[34m2025-10-28 21:33:17[0m] (step=0084400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 947 |
+
[[34m2025-10-28 21:34:42[0m] (step=0084500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 948 |
+
[[34m2025-10-28 21:36:06[0m] (step=0084600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 949 |
+
[[34m2025-10-28 21:37:31[0m] (step=0084700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 950 |
+
[[34m2025-10-28 21:38:56[0m] (step=0084800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 951 |
+
[[34m2025-10-28 21:40:20[0m] (step=0084900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 952 |
+
[[34m2025-10-28 21:41:45[0m] (step=0085000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 953 |
+
[[34m2025-10-28 21:42:43[0m] Beginning epoch 68...
|
| 954 |
+
[[34m2025-10-28 21:43:16[0m] (step=0085100) Train Loss: nan, Train Steps/Sec: 1.09
|
| 955 |
+
[[34m2025-10-28 21:44:41[0m] (step=0085200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 956 |
+
[[34m2025-10-28 21:46:05[0m] (step=0085300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 957 |
+
[[34m2025-10-28 21:47:30[0m] (step=0085400) Train Loss: nan, Train Steps/Sec: 1.18
|
| 958 |
+
[[34m2025-10-28 21:48:55[0m] (step=0085500) Train Loss: nan, Train Steps/Sec: 1.18
|
| 959 |
+
[[34m2025-10-28 21:50:19[0m] (step=0085600) Train Loss: nan, Train Steps/Sec: 1.18
|
| 960 |
+
[[34m2025-10-28 21:51:44[0m] (step=0085700) Train Loss: nan, Train Steps/Sec: 1.18
|
| 961 |
+
[[34m2025-10-28 21:53:08[0m] (step=0085800) Train Loss: nan, Train Steps/Sec: 1.18
|
| 962 |
+
[[34m2025-10-28 21:54:33[0m] (step=0085900) Train Loss: nan, Train Steps/Sec: 1.18
|
| 963 |
+
[[34m2025-10-28 21:55:57[0m] (step=0086000) Train Loss: nan, Train Steps/Sec: 1.18
|
| 964 |
+
[[34m2025-10-28 21:57:22[0m] (step=0086100) Train Loss: nan, Train Steps/Sec: 1.18
|
| 965 |
+
[[34m2025-10-28 21:58:46[0m] (step=0086200) Train Loss: nan, Train Steps/Sec: 1.18
|
| 966 |
+
[[34m2025-10-28 22:00:10[0m] (step=0086300) Train Loss: nan, Train Steps/Sec: 1.18
|
| 967 |
+
[[34m2025-10-28 22:00:27[0m] Beginning epoch 69...
|