Upload folder using huggingface_hub
Browse files
stage2/lightningdit-xl-pe-vit-l-bf16/checkpoints/0025000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f2b91578e11050726fee18d5cd5dfe06684b39e731960f9a3eaad403f1a2779
|
| 3 |
+
size 19243018610
|
stage2/lightningdit-xl-pe-vit-l-bf16/checkpoints/0050000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71c4520fd2b600f697dbafe5641a9148dd68f66aa626751f3095f585e300497e
|
| 3 |
+
size 19243018610
|
stage2/lightningdit-xl-pe-vit-l-bf16/checkpoints/0075000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c83a664c1fc2ae73dfa64a9e818f09eee25ba7114319de649e72d91527698399
|
| 3 |
+
size 19243018610
|
stage2/lightningdit-xl-pe-vit-l-bf16/log.txt
ADDED
|
@@ -0,0 +1,997 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[[34m2025-10-28 00:14:00[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-pe-vit-l-bf16
|
| 2 |
+
[[34m2025-10-28 00:14:07[0m] Missing keys for loading vision encoder: []
|
| 3 |
+
[[34m2025-10-28 00:14:07[0m] Unexpected keys for loading vision encoder: []
|
| 4 |
+
[[34m2025-10-28 00:14:22[0m] Model Parameters: 1202.82M
|
| 5 |
+
[[34m2025-10-28 00:14:26[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/train)
|
| 6 |
+
[[34m2025-10-28 00:14:26[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 7 |
+
[[34m2025-10-28 00:14:26[0m] Precision mode: bf16
|
| 8 |
+
[[34m2025-10-28 00:14:26[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 9 |
+
[[34m2025-10-28 00:14:26[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 00:14:26[0m] Training for 80 epochs...
|
| 12 |
+
[[34m2025-10-28 00:14:26[0m] Beginning epoch 0...
|
| 13 |
+
[[34m2025-10-28 00:46:27[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-pe-vit-l-bf16
|
| 14 |
+
[[34m2025-10-28 00:46:34[0m] Missing keys for loading vision encoder: []
|
| 15 |
+
[[34m2025-10-28 00:46:34[0m] Unexpected keys for loading vision encoder: []
|
| 16 |
+
[[34m2025-10-28 00:46:49[0m] Model Parameters: 1202.82M
|
| 17 |
+
[[34m2025-10-28 00:46:53[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/pe-vit-l_hfdataset_precentercrop_True_train_bfloat16)
|
| 18 |
+
[[34m2025-10-28 00:46:53[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 19 |
+
[[34m2025-10-28 00:46:53[0m] Precision mode: bf16
|
| 20 |
+
[[34m2025-10-28 00:46:53[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 21 |
+
[[34m2025-10-28 00:46:53[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 00:46:53[0m] Training for 80 epochs...
|
| 24 |
+
[[34m2025-10-28 00:46:53[0m] Beginning epoch 0...
|
| 25 |
+
[[34m2025-10-28 00:47:06[0m] Generating EMA samples...
|
| 26 |
+
[[34m2025-10-28 00:47:36[0m] Generating EMA samples done.
|
| 27 |
+
[[34m2025-10-28 00:49:03[0m] (step=0000100) Train Loss: 1.6644, Train Steps/Sec: 0.77
|
| 28 |
+
[[34m2025-10-28 00:50:31[0m] (step=0000200) Train Loss: 1.2154, Train Steps/Sec: 1.14
|
| 29 |
+
[[34m2025-10-28 00:51:59[0m] (step=0000300) Train Loss: 1.0384, Train Steps/Sec: 1.14
|
| 30 |
+
[[34m2025-10-28 00:53:27[0m] (step=0000400) Train Loss: 0.9517, Train Steps/Sec: 1.14
|
| 31 |
+
[[34m2025-10-28 00:54:54[0m] (step=0000500) Train Loss: 0.9050, Train Steps/Sec: 1.14
|
| 32 |
+
[[34m2025-10-28 00:56:22[0m] (step=0000600) Train Loss: 0.8704, Train Steps/Sec: 1.14
|
| 33 |
+
[[34m2025-10-28 00:57:50[0m] (step=0000700) Train Loss: 0.8443, Train Steps/Sec: 1.14
|
| 34 |
+
[[34m2025-10-28 00:59:18[0m] (step=0000800) Train Loss: 0.8232, Train Steps/Sec: 1.13
|
| 35 |
+
[[34m2025-10-28 01:00:46[0m] (step=0000900) Train Loss: 0.8078, Train Steps/Sec: 1.14
|
| 36 |
+
[[34m2025-10-28 01:02:15[0m] (step=0001000) Train Loss: 0.7977, Train Steps/Sec: 1.13
|
| 37 |
+
[[34m2025-10-28 01:03:43[0m] (step=0001100) Train Loss: 0.7881, Train Steps/Sec: 1.14
|
| 38 |
+
[[34m2025-10-28 01:05:10[0m] (step=0001200) Train Loss: 0.7801, Train Steps/Sec: 1.14
|
| 39 |
+
[[34m2025-10-28 01:05:56[0m] Beginning epoch 1...
|
| 40 |
+
[[34m2025-10-28 01:06:41[0m] (step=0001300) Train Loss: 0.7724, Train Steps/Sec: 1.10
|
| 41 |
+
[[34m2025-10-28 01:08:09[0m] (step=0001400) Train Loss: 0.7646, Train Steps/Sec: 1.14
|
| 42 |
+
[[34m2025-10-28 01:09:37[0m] (step=0001500) Train Loss: 0.7608, Train Steps/Sec: 1.14
|
| 43 |
+
[[34m2025-10-28 01:11:05[0m] (step=0001600) Train Loss: 0.7552, Train Steps/Sec: 1.14
|
| 44 |
+
[[34m2025-10-28 01:12:33[0m] (step=0001700) Train Loss: 0.7508, Train Steps/Sec: 1.14
|
| 45 |
+
[[34m2025-10-28 01:14:01[0m] (step=0001800) Train Loss: 0.7445, Train Steps/Sec: 1.13
|
| 46 |
+
[[34m2025-10-28 01:15:29[0m] (step=0001900) Train Loss: 0.7426, Train Steps/Sec: 1.14
|
| 47 |
+
[[34m2025-10-28 01:16:57[0m] (step=0002000) Train Loss: 0.7380, Train Steps/Sec: 1.14
|
| 48 |
+
[[34m2025-10-28 01:18:25[0m] (step=0002100) Train Loss: 0.7365, Train Steps/Sec: 1.14
|
| 49 |
+
[[34m2025-10-28 01:19:53[0m] (step=0002200) Train Loss: 0.7330, Train Steps/Sec: 1.14
|
| 50 |
+
[[34m2025-10-28 01:21:21[0m] (step=0002300) Train Loss: 0.7294, Train Steps/Sec: 1.14
|
| 51 |
+
[[34m2025-10-28 01:22:49[0m] (step=0002400) Train Loss: 0.7277, Train Steps/Sec: 1.14
|
| 52 |
+
[[34m2025-10-28 01:24:17[0m] (step=0002500) Train Loss: 0.7235, Train Steps/Sec: 1.14
|
| 53 |
+
[[34m2025-10-28 01:24:19[0m] Beginning epoch 2...
|
| 54 |
+
[[34m2025-10-28 01:25:48[0m] (step=0002600) Train Loss: 0.7213, Train Steps/Sec: 1.10
|
| 55 |
+
[[34m2025-10-28 01:27:16[0m] (step=0002700) Train Loss: 0.7193, Train Steps/Sec: 1.14
|
| 56 |
+
[[34m2025-10-28 01:28:44[0m] (step=0002800) Train Loss: 0.7172, Train Steps/Sec: 1.14
|
| 57 |
+
[[34m2025-10-28 01:30:12[0m] (step=0002900) Train Loss: 0.7148, Train Steps/Sec: 1.14
|
| 58 |
+
[[34m2025-10-28 01:31:40[0m] (step=0003000) Train Loss: 0.7144, Train Steps/Sec: 1.14
|
| 59 |
+
[[34m2025-10-28 01:33:08[0m] (step=0003100) Train Loss: 0.7124, Train Steps/Sec: 1.14
|
| 60 |
+
[[34m2025-10-28 01:34:36[0m] (step=0003200) Train Loss: 0.7108, Train Steps/Sec: 1.14
|
| 61 |
+
[[34m2025-10-28 01:36:04[0m] (step=0003300) Train Loss: 0.7094, Train Steps/Sec: 1.14
|
| 62 |
+
[[34m2025-10-28 01:37:32[0m] (step=0003400) Train Loss: 0.7075, Train Steps/Sec: 1.14
|
| 63 |
+
[[34m2025-10-28 01:39:00[0m] (step=0003500) Train Loss: 0.7055, Train Steps/Sec: 1.13
|
| 64 |
+
[[34m2025-10-28 01:40:28[0m] (step=0003600) Train Loss: 0.7026, Train Steps/Sec: 1.14
|
| 65 |
+
[[34m2025-10-28 01:41:56[0m] (step=0003700) Train Loss: 0.7039, Train Steps/Sec: 1.14
|
| 66 |
+
[[34m2025-10-28 01:42:43[0m] Beginning epoch 3...
|
| 67 |
+
[[34m2025-10-28 01:43:27[0m] (step=0003800) Train Loss: 0.7014, Train Steps/Sec: 1.10
|
| 68 |
+
[[34m2025-10-28 01:44:55[0m] (step=0003900) Train Loss: 0.6985, Train Steps/Sec: 1.14
|
| 69 |
+
[[34m2025-10-28 01:46:23[0m] (step=0004000) Train Loss: 0.6992, Train Steps/Sec: 1.14
|
| 70 |
+
[[34m2025-10-28 01:47:51[0m] (step=0004100) Train Loss: 0.6962, Train Steps/Sec: 1.14
|
| 71 |
+
[[34m2025-10-28 01:49:19[0m] (step=0004200) Train Loss: 0.6957, Train Steps/Sec: 1.14
|
| 72 |
+
[[34m2025-10-28 01:50:48[0m] (step=0004300) Train Loss: 0.6945, Train Steps/Sec: 1.13
|
| 73 |
+
[[34m2025-10-28 01:52:16[0m] (step=0004400) Train Loss: 0.6935, Train Steps/Sec: 1.14
|
| 74 |
+
[[34m2025-10-28 01:53:44[0m] (step=0004500) Train Loss: 0.6930, Train Steps/Sec: 1.14
|
| 75 |
+
[[34m2025-10-28 01:55:12[0m] (step=0004600) Train Loss: 0.6908, Train Steps/Sec: 1.14
|
| 76 |
+
[[34m2025-10-28 01:56:40[0m] (step=0004700) Train Loss: 0.6912, Train Steps/Sec: 1.14
|
| 77 |
+
[[34m2025-10-28 01:58:08[0m] (step=0004800) Train Loss: 0.6897, Train Steps/Sec: 1.14
|
| 78 |
+
[[34m2025-10-28 01:59:36[0m] (step=0004900) Train Loss: 0.6883, Train Steps/Sec: 1.14
|
| 79 |
+
[[34m2025-10-28 02:01:04[0m] (step=0005000) Train Loss: 0.6883, Train Steps/Sec: 1.14
|
| 80 |
+
[[34m2025-10-28 02:01:08[0m] Beginning epoch 4...
|
| 81 |
+
[[34m2025-10-28 02:02:34[0m] (step=0005100) Train Loss: 0.6863, Train Steps/Sec: 1.10
|
| 82 |
+
[[34m2025-10-28 02:04:03[0m] (step=0005200) Train Loss: 0.6865, Train Steps/Sec: 1.13
|
| 83 |
+
[[34m2025-10-28 02:05:31[0m] (step=0005300) Train Loss: 0.6854, Train Steps/Sec: 1.14
|
| 84 |
+
[[34m2025-10-28 02:06:59[0m] (step=0005400) Train Loss: 0.6827, Train Steps/Sec: 1.14
|
| 85 |
+
[[34m2025-10-28 02:08:27[0m] (step=0005500) Train Loss: 0.6820, Train Steps/Sec: 1.14
|
| 86 |
+
[[34m2025-10-28 02:09:55[0m] (step=0005600) Train Loss: 0.6827, Train Steps/Sec: 1.14
|
| 87 |
+
[[34m2025-10-28 02:11:23[0m] (step=0005700) Train Loss: 0.6819, Train Steps/Sec: 1.14
|
| 88 |
+
[[34m2025-10-28 02:12:51[0m] (step=0005800) Train Loss: 0.6814, Train Steps/Sec: 1.14
|
| 89 |
+
[[34m2025-10-28 02:14:19[0m] (step=0005900) Train Loss: 0.6801, Train Steps/Sec: 1.14
|
| 90 |
+
[[34m2025-10-28 02:15:47[0m] (step=0006000) Train Loss: 0.6791, Train Steps/Sec: 1.13
|
| 91 |
+
[[34m2025-10-28 02:17:15[0m] (step=0006100) Train Loss: 0.6779, Train Steps/Sec: 1.14
|
| 92 |
+
[[34m2025-10-28 02:18:43[0m] (step=0006200) Train Loss: 0.6766, Train Steps/Sec: 1.14
|
| 93 |
+
[[34m2025-10-28 02:19:32[0m] Beginning epoch 5...
|
| 94 |
+
[[34m2025-10-28 02:20:14[0m] (step=0006300) Train Loss: 0.6767, Train Steps/Sec: 1.10
|
| 95 |
+
[[34m2025-10-28 02:21:42[0m] (step=0006400) Train Loss: 0.6767, Train Steps/Sec: 1.14
|
| 96 |
+
[[34m2025-10-28 02:23:10[0m] (step=0006500) Train Loss: 0.6751, Train Steps/Sec: 1.14
|
| 97 |
+
[[34m2025-10-28 02:24:38[0m] (step=0006600) Train Loss: 0.6764, Train Steps/Sec: 1.14
|
| 98 |
+
[[34m2025-10-28 02:26:06[0m] (step=0006700) Train Loss: 0.6744, Train Steps/Sec: 1.14
|
| 99 |
+
[[34m2025-10-28 02:27:34[0m] (step=0006800) Train Loss: 0.6729, Train Steps/Sec: 1.14
|
| 100 |
+
[[34m2025-10-28 02:29:02[0m] (step=0006900) Train Loss: 0.6731, Train Steps/Sec: 1.13
|
| 101 |
+
[[34m2025-10-28 02:30:30[0m] (step=0007000) Train Loss: 0.6716, Train Steps/Sec: 1.14
|
| 102 |
+
[[34m2025-10-28 02:31:58[0m] (step=0007100) Train Loss: 0.6713, Train Steps/Sec: 1.14
|
| 103 |
+
[[34m2025-10-28 02:33:26[0m] (step=0007200) Train Loss: 0.6718, Train Steps/Sec: 1.14
|
| 104 |
+
[[34m2025-10-28 02:34:54[0m] (step=0007300) Train Loss: 0.6717, Train Steps/Sec: 1.14
|
| 105 |
+
[[34m2025-10-28 02:36:22[0m] (step=0007400) Train Loss: 0.6711, Train Steps/Sec: 1.14
|
| 106 |
+
[[34m2025-10-28 02:37:50[0m] (step=0007500) Train Loss: 0.6697, Train Steps/Sec: 1.14
|
| 107 |
+
[[34m2025-10-28 02:37:56[0m] Beginning epoch 6...
|
| 108 |
+
[[34m2025-10-28 02:39:21[0m] (step=0007600) Train Loss: 0.6699, Train Steps/Sec: 1.10
|
| 109 |
+
[[34m2025-10-28 02:40:49[0m] (step=0007700) Train Loss: 0.6693, Train Steps/Sec: 1.13
|
| 110 |
+
[[34m2025-10-28 02:42:17[0m] (step=0007800) Train Loss: 0.6679, Train Steps/Sec: 1.14
|
| 111 |
+
[[34m2025-10-28 02:43:45[0m] (step=0007900) Train Loss: 0.6673, Train Steps/Sec: 1.14
|
| 112 |
+
[[34m2025-10-28 02:45:13[0m] (step=0008000) Train Loss: 0.6676, Train Steps/Sec: 1.14
|
| 113 |
+
[[34m2025-10-28 02:46:41[0m] (step=0008100) Train Loss: 0.6668, Train Steps/Sec: 1.14
|
| 114 |
+
[[34m2025-10-28 02:48:09[0m] (step=0008200) Train Loss: 0.6671, Train Steps/Sec: 1.14
|
| 115 |
+
[[34m2025-10-28 02:49:37[0m] (step=0008300) Train Loss: 0.6658, Train Steps/Sec: 1.14
|
| 116 |
+
[[34m2025-10-28 02:51:05[0m] (step=0008400) Train Loss: 0.6653, Train Steps/Sec: 1.14
|
| 117 |
+
[[34m2025-10-28 02:52:33[0m] (step=0008500) Train Loss: 0.6646, Train Steps/Sec: 1.14
|
| 118 |
+
[[34m2025-10-28 02:54:01[0m] (step=0008600) Train Loss: 0.6641, Train Steps/Sec: 1.13
|
| 119 |
+
[[34m2025-10-28 02:55:29[0m] (step=0008700) Train Loss: 0.6652, Train Steps/Sec: 1.14
|
| 120 |
+
[[34m2025-10-28 02:56:20[0m] Beginning epoch 7...
|
| 121 |
+
[[34m2025-10-28 02:57:00[0m] (step=0008800) Train Loss: 0.6627, Train Steps/Sec: 1.10
|
| 122 |
+
[[34m2025-10-28 02:58:28[0m] (step=0008900) Train Loss: 0.6624, Train Steps/Sec: 1.14
|
| 123 |
+
[[34m2025-10-28 02:59:56[0m] (step=0009000) Train Loss: 0.6631, Train Steps/Sec: 1.14
|
| 124 |
+
[[34m2025-10-28 03:01:24[0m] (step=0009100) Train Loss: 0.6625, Train Steps/Sec: 1.14
|
| 125 |
+
[[34m2025-10-28 03:02:52[0m] (step=0009200) Train Loss: 0.6638, Train Steps/Sec: 1.14
|
| 126 |
+
[[34m2025-10-28 03:04:20[0m] (step=0009300) Train Loss: 0.6615, Train Steps/Sec: 1.14
|
| 127 |
+
[[34m2025-10-28 03:05:48[0m] (step=0009400) Train Loss: 0.6607, Train Steps/Sec: 1.13
|
| 128 |
+
[[34m2025-10-28 03:07:16[0m] (step=0009500) Train Loss: 0.6612, Train Steps/Sec: 1.13
|
| 129 |
+
[[34m2025-10-28 03:08:44[0m] (step=0009600) Train Loss: 0.6592, Train Steps/Sec: 1.14
|
| 130 |
+
[[34m2025-10-28 03:10:12[0m] (step=0009700) Train Loss: 0.6591, Train Steps/Sec: 1.14
|
| 131 |
+
[[34m2025-10-28 03:11:40[0m] (step=0009800) Train Loss: 0.6594, Train Steps/Sec: 1.14
|
| 132 |
+
[[34m2025-10-28 03:13:08[0m] (step=0009900) Train Loss: 0.6589, Train Steps/Sec: 1.14
|
| 133 |
+
[[34m2025-10-28 03:14:36[0m] (step=0010000) Train Loss: 0.6583, Train Steps/Sec: 1.14
|
| 134 |
+
[[34m2025-10-28 03:14:43[0m] Beginning epoch 8...
|
| 135 |
+
[[34m2025-10-28 03:16:07[0m] (step=0010100) Train Loss: 0.6575, Train Steps/Sec: 1.10
|
| 136 |
+
[[34m2025-10-28 03:17:35[0m] (step=0010200) Train Loss: 0.6577, Train Steps/Sec: 1.14
|
| 137 |
+
[[34m2025-10-28 03:19:03[0m] (step=0010300) Train Loss: 0.6581, Train Steps/Sec: 1.13
|
| 138 |
+
[[34m2025-10-28 03:20:31[0m] (step=0010400) Train Loss: 0.6574, Train Steps/Sec: 1.14
|
| 139 |
+
[[34m2025-10-28 03:21:59[0m] (step=0010500) Train Loss: 0.6576, Train Steps/Sec: 1.14
|
| 140 |
+
[[34m2025-10-28 03:23:27[0m] (step=0010600) Train Loss: 0.6565, Train Steps/Sec: 1.14
|
| 141 |
+
[[34m2025-10-28 03:24:55[0m] (step=0010700) Train Loss: 0.6569, Train Steps/Sec: 1.14
|
| 142 |
+
[[34m2025-10-28 03:26:23[0m] (step=0010800) Train Loss: 0.6560, Train Steps/Sec: 1.14
|
| 143 |
+
[[34m2025-10-28 03:27:51[0m] (step=0010900) Train Loss: 0.6561, Train Steps/Sec: 1.14
|
| 144 |
+
[[34m2025-10-28 03:29:19[0m] (step=0011000) Train Loss: 0.6567, Train Steps/Sec: 1.14
|
| 145 |
+
[[34m2025-10-28 03:30:47[0m] (step=0011100) Train Loss: 0.6549, Train Steps/Sec: 1.13
|
| 146 |
+
[[34m2025-10-28 03:32:15[0m] (step=0011200) Train Loss: 0.6546, Train Steps/Sec: 1.14
|
| 147 |
+
[[34m2025-10-28 03:33:07[0m] Beginning epoch 9...
|
| 148 |
+
[[34m2025-10-28 03:33:46[0m] (step=0011300) Train Loss: 0.6549, Train Steps/Sec: 1.10
|
| 149 |
+
[[34m2025-10-28 03:35:14[0m] (step=0011400) Train Loss: 0.6543, Train Steps/Sec: 1.14
|
| 150 |
+
[[34m2025-10-28 03:36:42[0m] (step=0011500) Train Loss: 0.6543, Train Steps/Sec: 1.14
|
| 151 |
+
[[34m2025-10-28 03:38:10[0m] (step=0011600) Train Loss: 0.6545, Train Steps/Sec: 1.14
|
| 152 |
+
[[34m2025-10-28 03:39:38[0m] (step=0011700) Train Loss: 0.6532, Train Steps/Sec: 1.14
|
| 153 |
+
[[34m2025-10-28 03:41:06[0m] (step=0011800) Train Loss: 0.6535, Train Steps/Sec: 1.14
|
| 154 |
+
[[34m2025-10-28 03:42:34[0m] (step=0011900) Train Loss: 0.6524, Train Steps/Sec: 1.14
|
| 155 |
+
[[34m2025-10-28 03:44:02[0m] (step=0012000) Train Loss: 0.6531, Train Steps/Sec: 1.13
|
| 156 |
+
[[34m2025-10-28 03:45:30[0m] (step=0012100) Train Loss: 0.6525, Train Steps/Sec: 1.14
|
| 157 |
+
[[34m2025-10-28 03:46:58[0m] (step=0012200) Train Loss: 0.6515, Train Steps/Sec: 1.14
|
| 158 |
+
[[34m2025-10-28 03:48:26[0m] (step=0012300) Train Loss: 0.6509, Train Steps/Sec: 1.14
|
| 159 |
+
[[34m2025-10-28 03:49:54[0m] (step=0012400) Train Loss: 0.6507, Train Steps/Sec: 1.14
|
| 160 |
+
[[34m2025-10-28 03:51:22[0m] (step=0012500) Train Loss: 0.6498, Train Steps/Sec: 1.14
|
| 161 |
+
[[34m2025-10-28 03:51:31[0m] Beginning epoch 10...
|
| 162 |
+
[[34m2025-10-28 03:52:53[0m] (step=0012600) Train Loss: 0.6506, Train Steps/Sec: 1.10
|
| 163 |
+
[[34m2025-10-28 03:54:21[0m] (step=0012700) Train Loss: 0.6509, Train Steps/Sec: 1.14
|
| 164 |
+
[[34m2025-10-28 03:55:49[0m] (step=0012800) Train Loss: 0.6494, Train Steps/Sec: 1.13
|
| 165 |
+
[[34m2025-10-28 03:57:17[0m] (step=0012900) Train Loss: 0.6500, Train Steps/Sec: 1.14
|
| 166 |
+
[[34m2025-10-28 03:58:45[0m] (step=0013000) Train Loss: 0.6493, Train Steps/Sec: 1.14
|
| 167 |
+
[[34m2025-10-28 04:00:13[0m] (step=0013100) Train Loss: 0.6491, Train Steps/Sec: 1.14
|
| 168 |
+
[[34m2025-10-28 04:01:41[0m] (step=0013200) Train Loss: 0.6487, Train Steps/Sec: 1.14
|
| 169 |
+
[[34m2025-10-28 04:03:09[0m] (step=0013300) Train Loss: 0.6484, Train Steps/Sec: 1.14
|
| 170 |
+
[[34m2025-10-28 04:04:37[0m] (step=0013400) Train Loss: 0.6495, Train Steps/Sec: 1.14
|
| 171 |
+
[[34m2025-10-28 04:06:05[0m] (step=0013500) Train Loss: 0.6476, Train Steps/Sec: 1.14
|
| 172 |
+
[[34m2025-10-28 04:07:33[0m] (step=0013600) Train Loss: 0.6499, Train Steps/Sec: 1.14
|
| 173 |
+
[[34m2025-10-28 04:09:01[0m] (step=0013700) Train Loss: 0.6458, Train Steps/Sec: 1.13
|
| 174 |
+
[[34m2025-10-28 04:09:55[0m] Beginning epoch 11...
|
| 175 |
+
[[34m2025-10-28 04:10:32[0m] (step=0013800) Train Loss: 0.6482, Train Steps/Sec: 1.10
|
| 176 |
+
[[34m2025-10-28 04:12:00[0m] (step=0013900) Train Loss: 0.6487, Train Steps/Sec: 1.14
|
| 177 |
+
[[34m2025-10-28 04:13:28[0m] (step=0014000) Train Loss: 0.6474, Train Steps/Sec: 1.14
|
| 178 |
+
[[34m2025-10-28 04:14:56[0m] (step=0014100) Train Loss: 0.6463, Train Steps/Sec: 1.14
|
| 179 |
+
[[34m2025-10-28 04:16:24[0m] (step=0014200) Train Loss: 0.6468, Train Steps/Sec: 1.14
|
| 180 |
+
[[34m2025-10-28 04:17:52[0m] (step=0014300) Train Loss: 0.6464, Train Steps/Sec: 1.14
|
| 181 |
+
[[34m2025-10-28 04:19:20[0m] (step=0014400) Train Loss: 0.6446, Train Steps/Sec: 1.14
|
| 182 |
+
[[34m2025-10-28 04:20:49[0m] (step=0014500) Train Loss: 0.6460, Train Steps/Sec: 1.13
|
| 183 |
+
[[34m2025-10-28 04:22:17[0m] (step=0014600) Train Loss: 0.6459, Train Steps/Sec: 1.14
|
| 184 |
+
[[34m2025-10-28 04:23:45[0m] (step=0014700) Train Loss: 0.6450, Train Steps/Sec: 1.14
|
| 185 |
+
[[34m2025-10-28 04:25:13[0m] (step=0014800) Train Loss: 0.6451, Train Steps/Sec: 1.14
|
| 186 |
+
[[34m2025-10-28 04:26:41[0m] (step=0014900) Train Loss: 0.6440, Train Steps/Sec: 1.14
|
| 187 |
+
[[34m2025-10-28 04:28:09[0m] (step=0015000) Train Loss: 0.6445, Train Steps/Sec: 1.14
|
| 188 |
+
[[34m2025-10-28 04:28:20[0m] Beginning epoch 12...
|
| 189 |
+
[[34m2025-10-28 04:29:39[0m] (step=0015100) Train Loss: 0.6463, Train Steps/Sec: 1.10
|
| 190 |
+
[[34m2025-10-28 04:31:07[0m] (step=0015200) Train Loss: 0.6443, Train Steps/Sec: 1.14
|
| 191 |
+
[[34m2025-10-28 04:32:35[0m] (step=0015300) Train Loss: 0.6442, Train Steps/Sec: 1.14
|
| 192 |
+
[[34m2025-10-28 04:34:04[0m] (step=0015400) Train Loss: 0.6437, Train Steps/Sec: 1.13
|
| 193 |
+
[[34m2025-10-28 04:35:32[0m] (step=0015500) Train Loss: 0.6429, Train Steps/Sec: 1.13
|
| 194 |
+
[[34m2025-10-28 04:37:00[0m] (step=0015600) Train Loss: 0.6425, Train Steps/Sec: 1.14
|
| 195 |
+
[[34m2025-10-28 04:38:28[0m] (step=0015700) Train Loss: 0.6434, Train Steps/Sec: 1.14
|
| 196 |
+
[[34m2025-10-28 04:39:56[0m] (step=0015800) Train Loss: 0.6427, Train Steps/Sec: 1.14
|
| 197 |
+
[[34m2025-10-28 04:41:24[0m] (step=0015900) Train Loss: 0.6446, Train Steps/Sec: 1.14
|
| 198 |
+
[[34m2025-10-28 04:42:52[0m] (step=0016000) Train Loss: 0.6443, Train Steps/Sec: 1.14
|
| 199 |
+
[[34m2025-10-28 04:44:20[0m] (step=0016100) Train Loss: 0.6426, Train Steps/Sec: 1.14
|
| 200 |
+
[[34m2025-10-28 04:45:48[0m] (step=0016200) Train Loss: 0.6434, Train Steps/Sec: 1.14
|
| 201 |
+
[[34m2025-10-28 04:46:44[0m] Beginning epoch 13...
|
| 202 |
+
[[34m2025-10-28 04:47:19[0m] (step=0016300) Train Loss: 0.6434, Train Steps/Sec: 1.10
|
| 203 |
+
[[34m2025-10-28 04:48:47[0m] (step=0016400) Train Loss: 0.6426, Train Steps/Sec: 1.14
|
| 204 |
+
[[34m2025-10-28 04:50:15[0m] (step=0016500) Train Loss: 0.6422, Train Steps/Sec: 1.14
|
| 205 |
+
[[34m2025-10-28 04:51:43[0m] (step=0016600) Train Loss: 0.6417, Train Steps/Sec: 1.14
|
| 206 |
+
[[34m2025-10-28 04:53:11[0m] (step=0016700) Train Loss: 0.6415, Train Steps/Sec: 1.14
|
| 207 |
+
[[34m2025-10-28 04:54:39[0m] (step=0016800) Train Loss: 0.6407, Train Steps/Sec: 1.14
|
| 208 |
+
[[34m2025-10-28 04:56:07[0m] (step=0016900) Train Loss: 0.6393, Train Steps/Sec: 1.14
|
| 209 |
+
[[34m2025-10-28 04:57:35[0m] (step=0017000) Train Loss: 0.6406, Train Steps/Sec: 1.14
|
| 210 |
+
[[34m2025-10-28 04:59:03[0m] (step=0017100) Train Loss: 0.6425, Train Steps/Sec: 1.13
|
| 211 |
+
[[34m2025-10-28 05:00:31[0m] (step=0017200) Train Loss: 0.6392, Train Steps/Sec: 1.14
|
| 212 |
+
[[34m2025-10-28 05:01:59[0m] (step=0017300) Train Loss: 0.6401, Train Steps/Sec: 1.14
|
| 213 |
+
[[34m2025-10-28 05:03:27[0m] (step=0017400) Train Loss: 0.6393, Train Steps/Sec: 1.14
|
| 214 |
+
[[34m2025-10-28 05:04:55[0m] (step=0017500) Train Loss: 0.6409, Train Steps/Sec: 1.14
|
| 215 |
+
[[34m2025-10-28 05:05:08[0m] Beginning epoch 14...
|
| 216 |
+
[[34m2025-10-28 05:06:26[0m] (step=0017600) Train Loss: 0.6399, Train Steps/Sec: 1.10
|
| 217 |
+
[[34m2025-10-28 05:07:54[0m] (step=0017700) Train Loss: 0.6390, Train Steps/Sec: 1.14
|
| 218 |
+
[[34m2025-10-28 05:09:22[0m] (step=0017800) Train Loss: 0.6394, Train Steps/Sec: 1.14
|
| 219 |
+
[[34m2025-10-28 05:10:50[0m] (step=0017900) Train Loss: 0.6396, Train Steps/Sec: 1.13
|
| 220 |
+
[[34m2025-10-28 05:12:18[0m] (step=0018000) Train Loss: 0.6392, Train Steps/Sec: 1.14
|
| 221 |
+
[[34m2025-10-28 05:13:46[0m] (step=0018100) Train Loss: 0.6395, Train Steps/Sec: 1.14
|
| 222 |
+
[[34m2025-10-28 05:15:14[0m] (step=0018200) Train Loss: 0.6380, Train Steps/Sec: 1.14
|
| 223 |
+
[[34m2025-10-28 05:16:42[0m] (step=0018300) Train Loss: 0.6399, Train Steps/Sec: 1.14
|
| 224 |
+
[[34m2025-10-28 05:18:10[0m] (step=0018400) Train Loss: 0.6391, Train Steps/Sec: 1.14
|
| 225 |
+
[[34m2025-10-28 05:19:38[0m] (step=0018500) Train Loss: 0.6381, Train Steps/Sec: 1.14
|
| 226 |
+
[[34m2025-10-28 05:21:06[0m] (step=0018600) Train Loss: 0.6369, Train Steps/Sec: 1.14
|
| 227 |
+
[[34m2025-10-28 05:22:34[0m] (step=0018700) Train Loss: 0.6382, Train Steps/Sec: 1.14
|
| 228 |
+
[[34m2025-10-28 05:23:32[0m] Beginning epoch 15...
|
| 229 |
+
[[34m2025-10-28 05:24:05[0m] (step=0018800) Train Loss: 0.6374, Train Steps/Sec: 1.10
|
| 230 |
+
[[34m2025-10-28 05:25:33[0m] (step=0018900) Train Loss: 0.6372, Train Steps/Sec: 1.14
|
| 231 |
+
[[34m2025-10-28 05:27:01[0m] (step=0019000) Train Loss: 0.6381, Train Steps/Sec: 1.14
|
| 232 |
+
[[34m2025-10-28 05:28:29[0m] (step=0019100) Train Loss: 0.6360, Train Steps/Sec: 1.14
|
| 233 |
+
[[34m2025-10-28 05:29:57[0m] (step=0019200) Train Loss: 0.6372, Train Steps/Sec: 1.14
|
| 234 |
+
[[34m2025-10-28 05:31:25[0m] (step=0019300) Train Loss: 0.6366, Train Steps/Sec: 1.14
|
| 235 |
+
[[34m2025-10-28 05:32:53[0m] (step=0019400) Train Loss: 0.6361, Train Steps/Sec: 1.14
|
| 236 |
+
[[34m2025-10-28 05:34:21[0m] (step=0019500) Train Loss: 0.6370, Train Steps/Sec: 1.14
|
| 237 |
+
[[34m2025-10-28 05:35:49[0m] (step=0019600) Train Loss: 0.6356, Train Steps/Sec: 1.13
|
| 238 |
+
[[34m2025-10-28 05:37:17[0m] (step=0019700) Train Loss: 0.6352, Train Steps/Sec: 1.14
|
| 239 |
+
[[34m2025-10-28 05:38:45[0m] (step=0019800) Train Loss: 0.6362, Train Steps/Sec: 1.14
|
| 240 |
+
[[34m2025-10-28 05:40:13[0m] (step=0019900) Train Loss: 0.6374, Train Steps/Sec: 1.14
|
| 241 |
+
[[34m2025-10-28 05:41:41[0m] (step=0020000) Train Loss: 0.6350, Train Steps/Sec: 1.14
|
| 242 |
+
[[34m2025-10-28 05:41:55[0m] Beginning epoch 16...
|
| 243 |
+
[[34m2025-10-28 05:43:11[0m] (step=0020100) Train Loss: 0.6363, Train Steps/Sec: 1.10
|
| 244 |
+
[[34m2025-10-28 05:44:39[0m] (step=0020200) Train Loss: 0.6343, Train Steps/Sec: 1.14
|
| 245 |
+
[[34m2025-10-28 05:46:07[0m] (step=0020300) Train Loss: 0.6360, Train Steps/Sec: 1.14
|
| 246 |
+
[[34m2025-10-28 05:47:35[0m] (step=0020400) Train Loss: 0.6334, Train Steps/Sec: 1.14
|
| 247 |
+
[[34m2025-10-28 05:49:04[0m] (step=0020500) Train Loss: 0.6353, Train Steps/Sec: 1.13
|
| 248 |
+
[[34m2025-10-28 05:50:32[0m] (step=0020600) Train Loss: 0.6343, Train Steps/Sec: 1.14
|
| 249 |
+
[[34m2025-10-28 05:52:00[0m] (step=0020700) Train Loss: 0.6348, Train Steps/Sec: 1.14
|
| 250 |
+
[[34m2025-10-28 05:53:28[0m] (step=0020800) Train Loss: 0.6345, Train Steps/Sec: 1.14
|
| 251 |
+
[[34m2025-10-28 05:54:56[0m] (step=0020900) Train Loss: 0.6349, Train Steps/Sec: 1.14
|
| 252 |
+
[[34m2025-10-28 05:56:24[0m] (step=0021000) Train Loss: 0.6349, Train Steps/Sec: 1.14
|
| 253 |
+
[[34m2025-10-28 05:57:52[0m] (step=0021100) Train Loss: 0.6327, Train Steps/Sec: 1.14
|
| 254 |
+
[[34m2025-10-28 05:59:20[0m] (step=0021200) Train Loss: 0.6339, Train Steps/Sec: 1.14
|
| 255 |
+
[[34m2025-10-28 06:00:19[0m] Beginning epoch 17...
|
| 256 |
+
[[34m2025-10-28 06:00:50[0m] (step=0021300) Train Loss: 0.6334, Train Steps/Sec: 1.10
|
| 257 |
+
[[34m2025-10-28 06:02:19[0m] (step=0021400) Train Loss: 0.6341, Train Steps/Sec: 1.14
|
| 258 |
+
[[34m2025-10-28 06:03:46[0m] (step=0021500) Train Loss: 0.6339, Train Steps/Sec: 1.14
|
| 259 |
+
[[34m2025-10-28 06:05:15[0m] (step=0021600) Train Loss: 0.6335, Train Steps/Sec: 1.13
|
| 260 |
+
[[34m2025-10-28 06:06:43[0m] (step=0021700) Train Loss: 0.6341, Train Steps/Sec: 1.14
|
| 261 |
+
[[34m2025-10-28 06:08:11[0m] (step=0021800) Train Loss: 0.6330, Train Steps/Sec: 1.14
|
| 262 |
+
[[34m2025-10-28 06:09:38[0m] (step=0021900) Train Loss: 0.6327, Train Steps/Sec: 1.14
|
| 263 |
+
[[34m2025-10-28 06:11:06[0m] (step=0022000) Train Loss: 0.6326, Train Steps/Sec: 1.14
|
| 264 |
+
[[34m2025-10-28 06:12:34[0m] (step=0022100) Train Loss: 0.6337, Train Steps/Sec: 1.14
|
| 265 |
+
[[34m2025-10-28 06:14:03[0m] (step=0022200) Train Loss: 0.6329, Train Steps/Sec: 1.13
|
| 266 |
+
[[34m2025-10-28 06:15:31[0m] (step=0022300) Train Loss: 0.6337, Train Steps/Sec: 1.14
|
| 267 |
+
[[34m2025-10-28 06:16:59[0m] (step=0022400) Train Loss: 0.6314, Train Steps/Sec: 1.14
|
| 268 |
+
[[34m2025-10-28 06:18:27[0m] (step=0022500) Train Loss: 0.6318, Train Steps/Sec: 1.14
|
| 269 |
+
[[34m2025-10-28 06:18:43[0m] Beginning epoch 18...
|
| 270 |
+
[[34m2025-10-28 06:19:58[0m] (step=0022600) Train Loss: 0.6312, Train Steps/Sec: 1.10
|
| 271 |
+
[[34m2025-10-28 06:21:26[0m] (step=0022700) Train Loss: 0.6324, Train Steps/Sec: 1.14
|
| 272 |
+
[[34m2025-10-28 06:22:53[0m] (step=0022800) Train Loss: 0.6324, Train Steps/Sec: 1.14
|
| 273 |
+
[[34m2025-10-28 06:24:21[0m] (step=0022900) Train Loss: 0.6312, Train Steps/Sec: 1.14
|
| 274 |
+
[[34m2025-10-28 06:25:50[0m] (step=0023000) Train Loss: 0.6323, Train Steps/Sec: 1.13
|
| 275 |
+
[[34m2025-10-28 06:27:18[0m] (step=0023100) Train Loss: 0.6309, Train Steps/Sec: 1.14
|
| 276 |
+
[[34m2025-10-28 06:28:46[0m] (step=0023200) Train Loss: 0.6314, Train Steps/Sec: 1.14
|
| 277 |
+
[[34m2025-10-28 06:30:14[0m] (step=0023300) Train Loss: 0.6296, Train Steps/Sec: 1.14
|
| 278 |
+
[[34m2025-10-28 06:31:42[0m] (step=0023400) Train Loss: 0.6317, Train Steps/Sec: 1.14
|
| 279 |
+
[[34m2025-10-28 06:33:10[0m] (step=0023500) Train Loss: 0.6327, Train Steps/Sec: 1.14
|
| 280 |
+
[[34m2025-10-28 06:34:38[0m] (step=0023600) Train Loss: 0.6318, Train Steps/Sec: 1.14
|
| 281 |
+
[[34m2025-10-28 06:36:06[0m] (step=0023700) Train Loss: 0.6311, Train Steps/Sec: 1.14
|
| 282 |
+
[[34m2025-10-28 06:37:07[0m] Beginning epoch 19...
|
| 283 |
+
[[34m2025-10-28 06:37:36[0m] (step=0023800) Train Loss: 0.6306, Train Steps/Sec: 1.10
|
| 284 |
+
[[34m2025-10-28 06:39:05[0m] (step=0023900) Train Loss: 0.6292, Train Steps/Sec: 1.13
|
| 285 |
+
[[34m2025-10-28 06:40:33[0m] (step=0024000) Train Loss: 0.6312, Train Steps/Sec: 1.13
|
| 286 |
+
[[34m2025-10-28 06:42:01[0m] (step=0024100) Train Loss: 0.6299, Train Steps/Sec: 1.14
|
| 287 |
+
[[34m2025-10-28 06:43:29[0m] (step=0024200) Train Loss: 0.6294, Train Steps/Sec: 1.14
|
| 288 |
+
[[34m2025-10-28 06:44:57[0m] (step=0024300) Train Loss: 0.6301, Train Steps/Sec: 1.14
|
| 289 |
+
[[34m2025-10-28 06:46:25[0m] (step=0024400) Train Loss: 0.6299, Train Steps/Sec: 1.14
|
| 290 |
+
[[34m2025-10-28 06:47:53[0m] (step=0024500) Train Loss: 0.6308, Train Steps/Sec: 1.14
|
| 291 |
+
[[34m2025-10-28 06:49:21[0m] (step=0024600) Train Loss: 0.6306, Train Steps/Sec: 1.14
|
| 292 |
+
[[34m2025-10-28 06:50:49[0m] (step=0024700) Train Loss: 0.6302, Train Steps/Sec: 1.13
|
| 293 |
+
[[34m2025-10-28 06:52:17[0m] (step=0024800) Train Loss: 0.6288, Train Steps/Sec: 1.14
|
| 294 |
+
[[34m2025-10-28 06:53:45[0m] (step=0024900) Train Loss: 0.6301, Train Steps/Sec: 1.14
|
| 295 |
+
[[34m2025-10-28 06:55:13[0m] (step=0025000) Train Loss: 0.6293, Train Steps/Sec: 1.14
|
| 296 |
+
[[34m2025-10-28 06:56:13[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-pe-vit-l-bf16/checkpoints/0025000.pt
|
| 297 |
+
[[34m2025-10-28 06:56:13[0m] Generating EMA samples...
|
| 298 |
+
[[34m2025-10-28 06:56:41[0m] Generating EMA samples done.
|
| 299 |
+
[[34m2025-10-28 06:56:59[0m] Beginning epoch 20...
|
| 300 |
+
[[34m2025-10-28 06:58:12[0m] (step=0025100) Train Loss: 0.6296, Train Steps/Sec: 0.56
|
| 301 |
+
[[34m2025-10-28 06:59:40[0m] (step=0025200) Train Loss: 0.6294, Train Steps/Sec: 1.14
|
| 302 |
+
[[34m2025-10-28 07:01:08[0m] (step=0025300) Train Loss: 0.6300, Train Steps/Sec: 1.14
|
| 303 |
+
[[34m2025-10-28 07:02:36[0m] (step=0025400) Train Loss: 0.6292, Train Steps/Sec: 1.14
|
| 304 |
+
[[34m2025-10-28 07:04:04[0m] (step=0025500) Train Loss: 0.6300, Train Steps/Sec: 1.14
|
| 305 |
+
[[34m2025-10-28 07:05:32[0m] (step=0025600) Train Loss: 0.6287, Train Steps/Sec: 1.13
|
| 306 |
+
[[34m2025-10-28 07:07:00[0m] (step=0025700) Train Loss: 0.6276, Train Steps/Sec: 1.14
|
| 307 |
+
[[34m2025-10-28 07:08:28[0m] (step=0025800) Train Loss: 0.6287, Train Steps/Sec: 1.14
|
| 308 |
+
[[34m2025-10-28 07:09:56[0m] (step=0025900) Train Loss: 0.6282, Train Steps/Sec: 1.14
|
| 309 |
+
[[34m2025-10-28 07:11:24[0m] (step=0026000) Train Loss: 0.6282, Train Steps/Sec: 1.14
|
| 310 |
+
[[34m2025-10-28 07:12:52[0m] (step=0026100) Train Loss: 0.6292, Train Steps/Sec: 1.14
|
| 311 |
+
[[34m2025-10-28 07:14:20[0m] (step=0026200) Train Loss: 0.6280, Train Steps/Sec: 1.14
|
| 312 |
+
[[34m2025-10-28 07:15:23[0m] Beginning epoch 21...
|
| 313 |
+
[[34m2025-10-28 07:15:52[0m] (step=0026300) Train Loss: 0.6276, Train Steps/Sec: 1.09
|
| 314 |
+
[[34m2025-10-28 07:17:20[0m] (step=0026400) Train Loss: 0.6274, Train Steps/Sec: 1.13
|
| 315 |
+
[[34m2025-10-28 07:18:48[0m] (step=0026500) Train Loss: 0.6270, Train Steps/Sec: 1.14
|
| 316 |
+
[[34m2025-10-28 07:20:16[0m] (step=0026600) Train Loss: 0.6286, Train Steps/Sec: 1.14
|
| 317 |
+
[[34m2025-10-28 07:21:44[0m] (step=0026700) Train Loss: 0.6275, Train Steps/Sec: 1.14
|
| 318 |
+
[[34m2025-10-28 07:23:12[0m] (step=0026800) Train Loss: 0.6276, Train Steps/Sec: 1.14
|
| 319 |
+
[[34m2025-10-28 07:24:40[0m] (step=0026900) Train Loss: 0.6266, Train Steps/Sec: 1.14
|
| 320 |
+
[[34m2025-10-28 07:26:08[0m] (step=0027000) Train Loss: 0.6263, Train Steps/Sec: 1.14
|
| 321 |
+
[[34m2025-10-28 07:27:36[0m] (step=0027100) Train Loss: 0.6293, Train Steps/Sec: 1.14
|
| 322 |
+
[[34m2025-10-28 07:29:04[0m] (step=0027200) Train Loss: 0.6273, Train Steps/Sec: 1.14
|
| 323 |
+
[[34m2025-10-28 07:30:32[0m] (step=0027300) Train Loss: 0.6275, Train Steps/Sec: 1.13
|
| 324 |
+
[[34m2025-10-28 07:32:00[0m] (step=0027400) Train Loss: 0.6280, Train Steps/Sec: 1.14
|
| 325 |
+
[[34m2025-10-28 07:33:28[0m] (step=0027500) Train Loss: 0.6268, Train Steps/Sec: 1.14
|
| 326 |
+
[[34m2025-10-28 07:33:48[0m] Beginning epoch 22...
|
| 327 |
+
[[34m2025-10-28 07:35:00[0m] (step=0027600) Train Loss: 0.6272, Train Steps/Sec: 1.09
|
| 328 |
+
[[34m2025-10-28 07:36:28[0m] (step=0027700) Train Loss: 0.6263, Train Steps/Sec: 1.14
|
| 329 |
+
[[34m2025-10-28 07:37:56[0m] (step=0027800) Train Loss: 0.6262, Train Steps/Sec: 1.14
|
| 330 |
+
[[34m2025-10-28 07:39:24[0m] (step=0027900) Train Loss: 0.6259, Train Steps/Sec: 1.14
|
| 331 |
+
[[34m2025-10-28 07:40:52[0m] (step=0028000) Train Loss: 0.6276, Train Steps/Sec: 1.14
|
| 332 |
+
[[34m2025-10-28 07:42:20[0m] (step=0028100) Train Loss: 0.6276, Train Steps/Sec: 1.13
|
| 333 |
+
[[34m2025-10-28 07:43:48[0m] (step=0028200) Train Loss: 0.6272, Train Steps/Sec: 1.14
|
| 334 |
+
[[34m2025-10-28 07:45:16[0m] (step=0028300) Train Loss: 0.6257, Train Steps/Sec: 1.14
|
| 335 |
+
[[34m2025-10-28 07:46:44[0m] (step=0028400) Train Loss: 0.6265, Train Steps/Sec: 1.14
|
| 336 |
+
[[34m2025-10-28 07:48:12[0m] (step=0028500) Train Loss: 0.6263, Train Steps/Sec: 1.14
|
| 337 |
+
[[34m2025-10-28 07:49:40[0m] (step=0028600) Train Loss: 0.6276, Train Steps/Sec: 1.14
|
| 338 |
+
[[34m2025-10-28 07:51:08[0m] (step=0028700) Train Loss: 0.6239, Train Steps/Sec: 1.14
|
| 339 |
+
[[34m2025-10-28 07:52:13[0m] Beginning epoch 23...
|
| 340 |
+
[[34m2025-10-28 07:52:40[0m] (step=0028800) Train Loss: 0.6259, Train Steps/Sec: 1.09
|
| 341 |
+
[[34m2025-10-28 07:54:07[0m] (step=0028900) Train Loss: 0.6249, Train Steps/Sec: 1.14
|
| 342 |
+
[[34m2025-10-28 07:55:36[0m] (step=0029000) Train Loss: 0.6258, Train Steps/Sec: 1.13
|
| 343 |
+
[[34m2025-10-28 07:57:04[0m] (step=0029100) Train Loss: 0.6256, Train Steps/Sec: 1.14
|
| 344 |
+
[[34m2025-10-28 07:58:32[0m] (step=0029200) Train Loss: 0.6256, Train Steps/Sec: 1.14
|
| 345 |
+
[[34m2025-10-28 08:00:00[0m] (step=0029300) Train Loss: 0.6237, Train Steps/Sec: 1.13
|
| 346 |
+
[[34m2025-10-28 08:01:28[0m] (step=0029400) Train Loss: 0.6248, Train Steps/Sec: 1.14
|
| 347 |
+
[[34m2025-10-28 08:02:56[0m] (step=0029500) Train Loss: 0.6260, Train Steps/Sec: 1.14
|
| 348 |
+
[[34m2025-10-28 08:04:24[0m] (step=0029600) Train Loss: 0.6253, Train Steps/Sec: 1.14
|
| 349 |
+
[[34m2025-10-28 08:05:52[0m] (step=0029700) Train Loss: 0.6262, Train Steps/Sec: 1.14
|
| 350 |
+
[[34m2025-10-28 08:07:20[0m] (step=0029800) Train Loss: 0.6248, Train Steps/Sec: 1.13
|
| 351 |
+
[[34m2025-10-28 08:08:48[0m] (step=0029900) Train Loss: 0.6253, Train Steps/Sec: 1.14
|
| 352 |
+
[[34m2025-10-28 08:10:16[0m] (step=0030000) Train Loss: 0.6255, Train Steps/Sec: 1.14
|
| 353 |
+
[[34m2025-10-28 08:10:38[0m] Beginning epoch 24...
|
| 354 |
+
[[34m2025-10-28 08:11:48[0m] (step=0030100) Train Loss: 0.6260, Train Steps/Sec: 1.09
|
| 355 |
+
[[34m2025-10-28 08:13:16[0m] (step=0030200) Train Loss: 0.6235, Train Steps/Sec: 1.14
|
| 356 |
+
[[34m2025-10-28 08:14:44[0m] (step=0030300) Train Loss: 0.6239, Train Steps/Sec: 1.14
|
| 357 |
+
[[34m2025-10-28 08:16:12[0m] (step=0030400) Train Loss: 0.6234, Train Steps/Sec: 1.14
|
| 358 |
+
[[34m2025-10-28 08:17:40[0m] (step=0030500) Train Loss: 0.6245, Train Steps/Sec: 1.14
|
| 359 |
+
[[34m2025-10-28 08:19:08[0m] (step=0030600) Train Loss: 0.6231, Train Steps/Sec: 1.14
|
| 360 |
+
[[34m2025-10-28 08:20:36[0m] (step=0030700) Train Loss: 0.6243, Train Steps/Sec: 1.13
|
| 361 |
+
[[34m2025-10-28 08:22:04[0m] (step=0030800) Train Loss: 0.6246, Train Steps/Sec: 1.14
|
| 362 |
+
[[34m2025-10-28 08:23:32[0m] (step=0030900) Train Loss: 0.6255, Train Steps/Sec: 1.14
|
| 363 |
+
[[34m2025-10-28 08:25:00[0m] (step=0031000) Train Loss: 0.6257, Train Steps/Sec: 1.14
|
| 364 |
+
[[34m2025-10-28 08:26:28[0m] (step=0031100) Train Loss: 0.6260, Train Steps/Sec: 1.14
|
| 365 |
+
[[34m2025-10-28 08:27:56[0m] (step=0031200) Train Loss: 0.6255, Train Steps/Sec: 1.14
|
| 366 |
+
[[34m2025-10-28 08:29:02[0m] Beginning epoch 25...
|
| 367 |
+
[[34m2025-10-28 08:29:27[0m] (step=0031300) Train Loss: 0.6222, Train Steps/Sec: 1.10
|
| 368 |
+
[[34m2025-10-28 08:30:55[0m] (step=0031400) Train Loss: 0.6243, Train Steps/Sec: 1.14
|
| 369 |
+
[[34m2025-10-28 08:32:23[0m] (step=0031500) Train Loss: 0.6246, Train Steps/Sec: 1.13
|
| 370 |
+
[[34m2025-10-28 08:33:51[0m] (step=0031600) Train Loss: 0.6227, Train Steps/Sec: 1.13
|
| 371 |
+
[[34m2025-10-28 08:35:19[0m] (step=0031700) Train Loss: 0.6232, Train Steps/Sec: 1.14
|
| 372 |
+
[[34m2025-10-28 08:36:47[0m] (step=0031800) Train Loss: 0.6223, Train Steps/Sec: 1.14
|
| 373 |
+
[[34m2025-10-28 08:38:15[0m] (step=0031900) Train Loss: 0.6234, Train Steps/Sec: 1.14
|
| 374 |
+
[[34m2025-10-28 08:39:43[0m] (step=0032000) Train Loss: 0.6231, Train Steps/Sec: 1.14
|
| 375 |
+
[[34m2025-10-28 08:41:11[0m] (step=0032100) Train Loss: 0.6235, Train Steps/Sec: 1.14
|
| 376 |
+
[[34m2025-10-28 08:42:39[0m] (step=0032200) Train Loss: 0.6226, Train Steps/Sec: 1.14
|
| 377 |
+
[[34m2025-10-28 08:44:07[0m] (step=0032300) Train Loss: 0.6230, Train Steps/Sec: 1.14
|
| 378 |
+
[[34m2025-10-28 08:45:35[0m] (step=0032400) Train Loss: 0.6229, Train Steps/Sec: 1.13
|
| 379 |
+
[[34m2025-10-28 08:47:03[0m] (step=0032500) Train Loss: 0.6237, Train Steps/Sec: 1.14
|
| 380 |
+
[[34m2025-10-28 08:47:27[0m] Beginning epoch 26...
|
| 381 |
+
[[34m2025-10-28 08:48:34[0m] (step=0032600) Train Loss: 0.6230, Train Steps/Sec: 1.10
|
| 382 |
+
[[34m2025-10-28 08:50:02[0m] (step=0032700) Train Loss: 0.6219, Train Steps/Sec: 1.14
|
| 383 |
+
[[34m2025-10-28 08:51:30[0m] (step=0032800) Train Loss: 0.6225, Train Steps/Sec: 1.14
|
| 384 |
+
[[34m2025-10-28 08:52:58[0m] (step=0032900) Train Loss: 0.6211, Train Steps/Sec: 1.14
|
| 385 |
+
[[34m2025-10-28 08:54:26[0m] (step=0033000) Train Loss: 0.6227, Train Steps/Sec: 1.14
|
| 386 |
+
[[34m2025-10-28 08:55:54[0m] (step=0033100) Train Loss: 0.6224, Train Steps/Sec: 1.14
|
| 387 |
+
[[34m2025-10-28 08:57:23[0m] (step=0033200) Train Loss: 0.6220, Train Steps/Sec: 1.13
|
| 388 |
+
[[34m2025-10-28 08:58:51[0m] (step=0033300) Train Loss: 0.6227, Train Steps/Sec: 1.14
|
| 389 |
+
[[34m2025-10-28 09:00:19[0m] (step=0033400) Train Loss: 0.6213, Train Steps/Sec: 1.14
|
| 390 |
+
[[34m2025-10-28 09:01:47[0m] (step=0033500) Train Loss: 0.6237, Train Steps/Sec: 1.14
|
| 391 |
+
[[34m2025-10-28 09:03:14[0m] (step=0033600) Train Loss: 0.6230, Train Steps/Sec: 1.14
|
| 392 |
+
[[34m2025-10-28 09:04:42[0m] (step=0033700) Train Loss: 0.6215, Train Steps/Sec: 1.14
|
| 393 |
+
[[34m2025-10-28 09:05:51[0m] Beginning epoch 27...
|
| 394 |
+
[[34m2025-10-28 09:06:13[0m] (step=0033800) Train Loss: 0.6211, Train Steps/Sec: 1.10
|
| 395 |
+
[[34m2025-10-28 09:07:41[0m] (step=0033900) Train Loss: 0.6204, Train Steps/Sec: 1.14
|
| 396 |
+
[[34m2025-10-28 09:09:09[0m] (step=0034000) Train Loss: 0.6215, Train Steps/Sec: 1.13
|
| 397 |
+
[[34m2025-10-28 09:10:38[0m] (step=0034100) Train Loss: 0.6207, Train Steps/Sec: 1.13
|
| 398 |
+
[[34m2025-10-28 09:12:06[0m] (step=0034200) Train Loss: 0.6213, Train Steps/Sec: 1.14
|
| 399 |
+
[[34m2025-10-28 09:13:34[0m] (step=0034300) Train Loss: 0.6206, Train Steps/Sec: 1.14
|
| 400 |
+
[[34m2025-10-28 09:15:01[0m] (step=0034400) Train Loss: 0.6206, Train Steps/Sec: 1.14
|
| 401 |
+
[[34m2025-10-28 09:16:29[0m] (step=0034500) Train Loss: 0.6213, Train Steps/Sec: 1.14
|
| 402 |
+
[[34m2025-10-28 09:17:57[0m] (step=0034600) Train Loss: 0.6225, Train Steps/Sec: 1.14
|
| 403 |
+
[[34m2025-10-28 09:19:25[0m] (step=0034700) Train Loss: 0.6212, Train Steps/Sec: 1.14
|
| 404 |
+
[[34m2025-10-28 09:20:53[0m] (step=0034800) Train Loss: 0.6206, Train Steps/Sec: 1.14
|
| 405 |
+
[[34m2025-10-28 09:22:22[0m] (step=0034900) Train Loss: 0.6217, Train Steps/Sec: 1.13
|
| 406 |
+
[[34m2025-10-28 09:23:50[0m] (step=0035000) Train Loss: 0.6211, Train Steps/Sec: 1.14
|
| 407 |
+
[[34m2025-10-28 09:24:15[0m] Beginning epoch 28...
|
| 408 |
+
[[34m2025-10-28 09:25:21[0m] (step=0035100) Train Loss: 0.6208, Train Steps/Sec: 1.10
|
| 409 |
+
[[34m2025-10-28 09:26:49[0m] (step=0035200) Train Loss: 0.6223, Train Steps/Sec: 1.14
|
| 410 |
+
[[34m2025-10-28 09:28:17[0m] (step=0035300) Train Loss: 0.6211, Train Steps/Sec: 1.14
|
| 411 |
+
[[34m2025-10-28 09:29:45[0m] (step=0035400) Train Loss: 0.6201, Train Steps/Sec: 1.14
|
| 412 |
+
[[34m2025-10-28 09:31:13[0m] (step=0035500) Train Loss: 0.6204, Train Steps/Sec: 1.14
|
| 413 |
+
[[34m2025-10-28 09:32:41[0m] (step=0035600) Train Loss: 0.6200, Train Steps/Sec: 1.14
|
| 414 |
+
[[34m2025-10-28 09:34:09[0m] (step=0035700) Train Loss: 0.6211, Train Steps/Sec: 1.14
|
| 415 |
+
[[34m2025-10-28 09:35:37[0m] (step=0035800) Train Loss: 0.6209, Train Steps/Sec: 1.13
|
| 416 |
+
[[34m2025-10-28 09:37:05[0m] (step=0035900) Train Loss: 0.6209, Train Steps/Sec: 1.14
|
| 417 |
+
[[34m2025-10-28 09:38:33[0m] (step=0036000) Train Loss: 0.6209, Train Steps/Sec: 1.14
|
| 418 |
+
[[34m2025-10-28 09:40:01[0m] (step=0036100) Train Loss: 0.6206, Train Steps/Sec: 1.14
|
| 419 |
+
[[34m2025-10-28 09:41:29[0m] (step=0036200) Train Loss: 0.6202, Train Steps/Sec: 1.14
|
| 420 |
+
[[34m2025-10-28 09:42:39[0m] Beginning epoch 29...
|
| 421 |
+
[[34m2025-10-28 09:43:00[0m] (step=0036300) Train Loss: 0.6189, Train Steps/Sec: 1.10
|
| 422 |
+
[[34m2025-10-28 09:44:28[0m] (step=0036400) Train Loss: 0.6199, Train Steps/Sec: 1.14
|
| 423 |
+
[[34m2025-10-28 09:45:56[0m] (step=0036500) Train Loss: 0.6203, Train Steps/Sec: 1.14
|
| 424 |
+
[[34m2025-10-28 09:47:24[0m] (step=0036600) Train Loss: 0.6198, Train Steps/Sec: 1.13
|
| 425 |
+
[[34m2025-10-28 09:48:52[0m] (step=0036700) Train Loss: 0.6204, Train Steps/Sec: 1.14
|
| 426 |
+
[[34m2025-10-28 09:50:20[0m] (step=0036800) Train Loss: 0.6197, Train Steps/Sec: 1.14
|
| 427 |
+
[[34m2025-10-28 09:51:48[0m] (step=0036900) Train Loss: 0.6193, Train Steps/Sec: 1.14
|
| 428 |
+
[[34m2025-10-28 09:53:16[0m] (step=0037000) Train Loss: 0.6197, Train Steps/Sec: 1.14
|
| 429 |
+
[[34m2025-10-28 09:54:44[0m] (step=0037100) Train Loss: 0.6191, Train Steps/Sec: 1.14
|
| 430 |
+
[[34m2025-10-28 09:56:12[0m] (step=0037200) Train Loss: 0.6185, Train Steps/Sec: 1.14
|
| 431 |
+
[[34m2025-10-28 09:57:40[0m] (step=0037300) Train Loss: 0.6193, Train Steps/Sec: 1.14
|
| 432 |
+
[[34m2025-10-28 09:59:08[0m] (step=0037400) Train Loss: 0.6200, Train Steps/Sec: 1.14
|
| 433 |
+
[[34m2025-10-28 10:00:36[0m] (step=0037500) Train Loss: 0.6199, Train Steps/Sec: 1.14
|
| 434 |
+
[[34m2025-10-28 10:01:03[0m] Beginning epoch 30...
|
| 435 |
+
[[34m2025-10-28 10:02:07[0m] (step=0037600) Train Loss: 0.6201, Train Steps/Sec: 1.10
|
| 436 |
+
[[34m2025-10-28 10:03:35[0m] (step=0037700) Train Loss: 0.6200, Train Steps/Sec: 1.14
|
| 437 |
+
[[34m2025-10-28 10:05:03[0m] (step=0037800) Train Loss: 0.6192, Train Steps/Sec: 1.14
|
| 438 |
+
[[34m2025-10-28 10:06:31[0m] (step=0037900) Train Loss: 0.6198, Train Steps/Sec: 1.14
|
| 439 |
+
[[34m2025-10-28 10:07:59[0m] (step=0038000) Train Loss: 0.6176, Train Steps/Sec: 1.14
|
| 440 |
+
[[34m2025-10-28 10:09:27[0m] (step=0038100) Train Loss: 0.6174, Train Steps/Sec: 1.14
|
| 441 |
+
[[34m2025-10-28 10:10:55[0m] (step=0038200) Train Loss: 0.6193, Train Steps/Sec: 1.14
|
| 442 |
+
[[34m2025-10-28 10:12:23[0m] (step=0038300) Train Loss: 0.6195, Train Steps/Sec: 1.13
|
| 443 |
+
[[34m2025-10-28 10:13:51[0m] (step=0038400) Train Loss: 0.6191, Train Steps/Sec: 1.14
|
| 444 |
+
[[34m2025-10-28 10:15:19[0m] (step=0038500) Train Loss: 0.6191, Train Steps/Sec: 1.14
|
| 445 |
+
[[34m2025-10-28 10:16:47[0m] (step=0038600) Train Loss: 0.6177, Train Steps/Sec: 1.14
|
| 446 |
+
[[34m2025-10-28 10:18:15[0m] (step=0038700) Train Loss: 0.6191, Train Steps/Sec: 1.14
|
| 447 |
+
[[34m2025-10-28 10:19:27[0m] Beginning epoch 31...
|
| 448 |
+
[[34m2025-10-28 10:19:46[0m] (step=0038800) Train Loss: 0.6188, Train Steps/Sec: 1.10
|
| 449 |
+
[[34m2025-10-28 10:21:14[0m] (step=0038900) Train Loss: 0.6189, Train Steps/Sec: 1.14
|
| 450 |
+
[[34m2025-10-28 10:22:42[0m] (step=0039000) Train Loss: 0.6197, Train Steps/Sec: 1.14
|
| 451 |
+
[[34m2025-10-28 10:24:10[0m] (step=0039100) Train Loss: 0.6188, Train Steps/Sec: 1.13
|
| 452 |
+
[[34m2025-10-28 10:25:39[0m] (step=0039200) Train Loss: 0.6175, Train Steps/Sec: 1.13
|
| 453 |
+
[[34m2025-10-28 10:27:07[0m] (step=0039300) Train Loss: 0.6188, Train Steps/Sec: 1.14
|
| 454 |
+
[[34m2025-10-28 10:28:35[0m] (step=0039400) Train Loss: 0.6185, Train Steps/Sec: 1.14
|
| 455 |
+
[[34m2025-10-28 10:30:02[0m] (step=0039500) Train Loss: 0.6194, Train Steps/Sec: 1.14
|
| 456 |
+
[[34m2025-10-28 10:31:30[0m] (step=0039600) Train Loss: 0.6195, Train Steps/Sec: 1.14
|
| 457 |
+
[[34m2025-10-28 10:32:58[0m] (step=0039700) Train Loss: 0.6175, Train Steps/Sec: 1.14
|
| 458 |
+
[[34m2025-10-28 10:34:26[0m] (step=0039800) Train Loss: 0.6181, Train Steps/Sec: 1.14
|
| 459 |
+
[[34m2025-10-28 10:35:54[0m] (step=0039900) Train Loss: 0.6192, Train Steps/Sec: 1.14
|
| 460 |
+
[[34m2025-10-28 10:37:22[0m] (step=0040000) Train Loss: 0.6186, Train Steps/Sec: 1.13
|
| 461 |
+
[[34m2025-10-28 10:37:51[0m] Beginning epoch 32...
|
| 462 |
+
[[34m2025-10-28 10:38:54[0m] (step=0040100) Train Loss: 0.6176, Train Steps/Sec: 1.10
|
| 463 |
+
[[34m2025-10-28 10:40:22[0m] (step=0040200) Train Loss: 0.6176, Train Steps/Sec: 1.14
|
| 464 |
+
[[34m2025-10-28 10:41:49[0m] (step=0040300) Train Loss: 0.6177, Train Steps/Sec: 1.14
|
| 465 |
+
[[34m2025-10-28 10:43:17[0m] (step=0040400) Train Loss: 0.6189, Train Steps/Sec: 1.14
|
| 466 |
+
[[34m2025-10-28 10:44:45[0m] (step=0040500) Train Loss: 0.6188, Train Steps/Sec: 1.14
|
| 467 |
+
[[34m2025-10-28 10:46:13[0m] (step=0040600) Train Loss: 0.6188, Train Steps/Sec: 1.14
|
| 468 |
+
[[34m2025-10-28 10:47:41[0m] (step=0040700) Train Loss: 0.6191, Train Steps/Sec: 1.14
|
| 469 |
+
[[34m2025-10-28 10:49:09[0m] (step=0040800) Train Loss: 0.6183, Train Steps/Sec: 1.14
|
| 470 |
+
[[34m2025-10-28 10:50:38[0m] (step=0040900) Train Loss: 0.6171, Train Steps/Sec: 1.13
|
| 471 |
+
[[34m2025-10-28 10:52:06[0m] (step=0041000) Train Loss: 0.6176, Train Steps/Sec: 1.14
|
| 472 |
+
[[34m2025-10-28 10:53:34[0m] (step=0041100) Train Loss: 0.6168, Train Steps/Sec: 1.14
|
| 473 |
+
[[34m2025-10-28 10:55:02[0m] (step=0041200) Train Loss: 0.6161, Train Steps/Sec: 1.14
|
| 474 |
+
[[34m2025-10-28 10:56:15[0m] Beginning epoch 33...
|
| 475 |
+
[[34m2025-10-28 10:56:33[0m] (step=0041300) Train Loss: 0.6171, Train Steps/Sec: 1.10
|
| 476 |
+
[[34m2025-10-28 10:58:01[0m] (step=0041400) Train Loss: 0.6169, Train Steps/Sec: 1.14
|
| 477 |
+
[[34m2025-10-28 10:59:28[0m] (step=0041500) Train Loss: 0.6167, Train Steps/Sec: 1.14
|
| 478 |
+
[[34m2025-10-28 11:00:56[0m] (step=0041600) Train Loss: 0.6170, Train Steps/Sec: 1.14
|
| 479 |
+
[[34m2025-10-28 11:02:25[0m] (step=0041700) Train Loss: 0.6165, Train Steps/Sec: 1.13
|
| 480 |
+
[[34m2025-10-28 11:03:53[0m] (step=0041800) Train Loss: 0.6176, Train Steps/Sec: 1.13
|
| 481 |
+
[[34m2025-10-28 11:05:21[0m] (step=0041900) Train Loss: 0.6174, Train Steps/Sec: 1.14
|
| 482 |
+
[[34m2025-10-28 11:06:49[0m] (step=0042000) Train Loss: 0.6179, Train Steps/Sec: 1.14
|
| 483 |
+
[[34m2025-10-28 11:08:17[0m] (step=0042100) Train Loss: 0.6173, Train Steps/Sec: 1.14
|
| 484 |
+
[[34m2025-10-28 11:09:45[0m] (step=0042200) Train Loss: 0.6177, Train Steps/Sec: 1.14
|
| 485 |
+
[[34m2025-10-28 11:11:13[0m] (step=0042300) Train Loss: 0.6158, Train Steps/Sec: 1.14
|
| 486 |
+
[[34m2025-10-28 11:12:41[0m] (step=0042400) Train Loss: 0.6165, Train Steps/Sec: 1.14
|
| 487 |
+
[[34m2025-10-28 11:14:09[0m] (step=0042500) Train Loss: 0.6169, Train Steps/Sec: 1.14
|
| 488 |
+
[[34m2025-10-28 11:14:40[0m] Beginning epoch 34...
|
| 489 |
+
[[34m2025-10-28 11:15:40[0m] (step=0042600) Train Loss: 0.6165, Train Steps/Sec: 1.10
|
| 490 |
+
[[34m2025-10-28 11:17:08[0m] (step=0042700) Train Loss: 0.6170, Train Steps/Sec: 1.14
|
| 491 |
+
[[34m2025-10-28 11:18:36[0m] (step=0042800) Train Loss: 0.6158, Train Steps/Sec: 1.14
|
| 492 |
+
[[34m2025-10-28 11:20:04[0m] (step=0042900) Train Loss: 0.6160, Train Steps/Sec: 1.14
|
| 493 |
+
[[34m2025-10-28 11:21:32[0m] (step=0043000) Train Loss: 0.6167, Train Steps/Sec: 1.14
|
| 494 |
+
[[34m2025-10-28 11:23:00[0m] (step=0043100) Train Loss: 0.6158, Train Steps/Sec: 1.14
|
| 495 |
+
[[34m2025-10-28 11:24:28[0m] (step=0043200) Train Loss: 0.6154, Train Steps/Sec: 1.14
|
| 496 |
+
[[34m2025-10-28 11:25:56[0m] (step=0043300) Train Loss: 0.6171, Train Steps/Sec: 1.14
|
| 497 |
+
[[34m2025-10-28 11:27:24[0m] (step=0043400) Train Loss: 0.6181, Train Steps/Sec: 1.13
|
| 498 |
+
[[34m2025-10-28 11:28:52[0m] (step=0043500) Train Loss: 0.6149, Train Steps/Sec: 1.14
|
| 499 |
+
[[34m2025-10-28 11:30:20[0m] (step=0043600) Train Loss: 0.6155, Train Steps/Sec: 1.14
|
| 500 |
+
[[34m2025-10-28 11:31:48[0m] (step=0043700) Train Loss: 0.6163, Train Steps/Sec: 1.14
|
| 501 |
+
[[34m2025-10-28 11:33:03[0m] Beginning epoch 35...
|
| 502 |
+
[[34m2025-10-28 11:33:20[0m] (step=0043800) Train Loss: 0.6175, Train Steps/Sec: 1.09
|
| 503 |
+
[[34m2025-10-28 11:34:48[0m] (step=0043900) Train Loss: 0.6174, Train Steps/Sec: 1.14
|
| 504 |
+
[[34m2025-10-28 11:36:16[0m] (step=0044000) Train Loss: 0.6172, Train Steps/Sec: 1.14
|
| 505 |
+
[[34m2025-10-28 11:37:44[0m] (step=0044100) Train Loss: 0.6148, Train Steps/Sec: 1.14
|
| 506 |
+
[[34m2025-10-28 11:39:12[0m] (step=0044200) Train Loss: 0.6157, Train Steps/Sec: 1.13
|
| 507 |
+
[[34m2025-10-28 11:40:40[0m] (step=0044300) Train Loss: 0.6160, Train Steps/Sec: 1.13
|
| 508 |
+
[[34m2025-10-28 11:42:08[0m] (step=0044400) Train Loss: 0.6152, Train Steps/Sec: 1.14
|
| 509 |
+
[[34m2025-10-28 11:43:36[0m] (step=0044500) Train Loss: 0.6157, Train Steps/Sec: 1.14
|
| 510 |
+
[[34m2025-10-28 11:45:04[0m] (step=0044600) Train Loss: 0.6157, Train Steps/Sec: 1.14
|
| 511 |
+
[[34m2025-10-28 11:46:32[0m] (step=0044700) Train Loss: 0.6156, Train Steps/Sec: 1.14
|
| 512 |
+
[[34m2025-10-28 11:48:00[0m] (step=0044800) Train Loss: 0.6162, Train Steps/Sec: 1.14
|
| 513 |
+
[[34m2025-10-28 11:49:28[0m] (step=0044900) Train Loss: 0.6156, Train Steps/Sec: 1.14
|
| 514 |
+
[[34m2025-10-28 11:50:56[0m] (step=0045000) Train Loss: 0.6160, Train Steps/Sec: 1.14
|
| 515 |
+
[[34m2025-10-28 11:51:28[0m] Beginning epoch 36...
|
| 516 |
+
[[34m2025-10-28 11:52:28[0m] (step=0045100) Train Loss: 0.6170, Train Steps/Sec: 1.09
|
| 517 |
+
[[34m2025-10-28 11:53:56[0m] (step=0045200) Train Loss: 0.6164, Train Steps/Sec: 1.13
|
| 518 |
+
[[34m2025-10-28 11:55:24[0m] (step=0045300) Train Loss: 0.6152, Train Steps/Sec: 1.14
|
| 519 |
+
[[34m2025-10-28 11:56:52[0m] (step=0045400) Train Loss: 0.6163, Train Steps/Sec: 1.14
|
| 520 |
+
[[34m2025-10-28 11:58:20[0m] (step=0045500) Train Loss: 0.6159, Train Steps/Sec: 1.14
|
| 521 |
+
[[34m2025-10-28 11:59:48[0m] (step=0045600) Train Loss: 0.6159, Train Steps/Sec: 1.14
|
| 522 |
+
[[34m2025-10-28 12:01:16[0m] (step=0045700) Train Loss: 0.6156, Train Steps/Sec: 1.14
|
| 523 |
+
[[34m2025-10-28 12:02:43[0m] (step=0045800) Train Loss: 0.6155, Train Steps/Sec: 1.14
|
| 524 |
+
[[34m2025-10-28 12:04:12[0m] (step=0045900) Train Loss: 0.6154, Train Steps/Sec: 1.14
|
| 525 |
+
[[34m2025-10-28 12:05:40[0m] (step=0046000) Train Loss: 0.6150, Train Steps/Sec: 1.13
|
| 526 |
+
[[34m2025-10-28 12:07:08[0m] (step=0046100) Train Loss: 0.6145, Train Steps/Sec: 1.14
|
| 527 |
+
[[34m2025-10-28 12:08:36[0m] (step=0046200) Train Loss: 0.6154, Train Steps/Sec: 1.14
|
| 528 |
+
[[34m2025-10-28 12:09:53[0m] Beginning epoch 37...
|
| 529 |
+
[[34m2025-10-28 12:10:07[0m] (step=0046300) Train Loss: 0.6146, Train Steps/Sec: 1.10
|
| 530 |
+
[[34m2025-10-28 12:11:35[0m] (step=0046400) Train Loss: 0.6148, Train Steps/Sec: 1.14
|
| 531 |
+
[[34m2025-10-28 12:13:03[0m] (step=0046500) Train Loss: 0.6161, Train Steps/Sec: 1.14
|
| 532 |
+
[[34m2025-10-28 12:14:31[0m] (step=0046600) Train Loss: 0.6150, Train Steps/Sec: 1.14
|
| 533 |
+
[[34m2025-10-28 12:15:59[0m] (step=0046700) Train Loss: 0.6142, Train Steps/Sec: 1.14
|
| 534 |
+
[[34m2025-10-28 12:17:27[0m] (step=0046800) Train Loss: 0.6150, Train Steps/Sec: 1.13
|
| 535 |
+
[[34m2025-10-28 12:18:55[0m] (step=0046900) Train Loss: 0.6136, Train Steps/Sec: 1.14
|
| 536 |
+
[[34m2025-10-28 12:20:23[0m] (step=0047000) Train Loss: 0.6157, Train Steps/Sec: 1.14
|
| 537 |
+
[[34m2025-10-28 12:21:51[0m] (step=0047100) Train Loss: 0.6150, Train Steps/Sec: 1.14
|
| 538 |
+
[[34m2025-10-28 12:23:19[0m] (step=0047200) Train Loss: 0.6138, Train Steps/Sec: 1.14
|
| 539 |
+
[[34m2025-10-28 12:24:47[0m] (step=0047300) Train Loss: 0.6150, Train Steps/Sec: 1.14
|
| 540 |
+
[[34m2025-10-28 12:26:15[0m] (step=0047400) Train Loss: 0.6148, Train Steps/Sec: 1.14
|
| 541 |
+
[[34m2025-10-28 12:27:43[0m] (step=0047500) Train Loss: 0.6153, Train Steps/Sec: 1.14
|
| 542 |
+
[[34m2025-10-28 12:28:17[0m] Beginning epoch 38...
|
| 543 |
+
[[34m2025-10-28 12:29:14[0m] (step=0047600) Train Loss: 0.6161, Train Steps/Sec: 1.10
|
| 544 |
+
[[34m2025-10-28 12:30:42[0m] (step=0047700) Train Loss: 0.6149, Train Steps/Sec: 1.13
|
| 545 |
+
[[34m2025-10-28 12:32:10[0m] (step=0047800) Train Loss: 0.6131, Train Steps/Sec: 1.14
|
| 546 |
+
[[34m2025-10-28 12:33:38[0m] (step=0047900) Train Loss: 0.6139, Train Steps/Sec: 1.14
|
| 547 |
+
[[34m2025-10-28 12:35:06[0m] (step=0048000) Train Loss: 0.6138, Train Steps/Sec: 1.14
|
| 548 |
+
[[34m2025-10-28 12:36:34[0m] (step=0048100) Train Loss: 0.6140, Train Steps/Sec: 1.14
|
| 549 |
+
[[34m2025-10-28 12:38:02[0m] (step=0048200) Train Loss: 0.6155, Train Steps/Sec: 1.14
|
| 550 |
+
[[34m2025-10-28 12:39:30[0m] (step=0048300) Train Loss: 0.6133, Train Steps/Sec: 1.14
|
| 551 |
+
[[34m2025-10-28 12:40:58[0m] (step=0048400) Train Loss: 0.6139, Train Steps/Sec: 1.14
|
| 552 |
+
[[34m2025-10-28 12:42:26[0m] (step=0048500) Train Loss: 0.6149, Train Steps/Sec: 1.13
|
| 553 |
+
[[34m2025-10-28 12:43:54[0m] (step=0048600) Train Loss: 0.6140, Train Steps/Sec: 1.14
|
| 554 |
+
[[34m2025-10-28 12:45:22[0m] (step=0048700) Train Loss: 0.6136, Train Steps/Sec: 1.14
|
| 555 |
+
[[34m2025-10-28 12:46:41[0m] Beginning epoch 39...
|
| 556 |
+
[[34m2025-10-28 12:46:53[0m] (step=0048800) Train Loss: 0.6138, Train Steps/Sec: 1.10
|
| 557 |
+
[[34m2025-10-28 12:48:21[0m] (step=0048900) Train Loss: 0.6138, Train Steps/Sec: 1.14
|
| 558 |
+
[[34m2025-10-28 12:49:49[0m] (step=0049000) Train Loss: 0.6146, Train Steps/Sec: 1.14
|
| 559 |
+
[[34m2025-10-28 12:51:17[0m] (step=0049100) Train Loss: 0.6136, Train Steps/Sec: 1.14
|
| 560 |
+
[[34m2025-10-28 12:52:45[0m] (step=0049200) Train Loss: 0.6126, Train Steps/Sec: 1.14
|
| 561 |
+
[[34m2025-10-28 12:54:13[0m] (step=0049300) Train Loss: 0.6148, Train Steps/Sec: 1.14
|
| 562 |
+
[[34m2025-10-28 12:55:41[0m] (step=0049400) Train Loss: 0.6139, Train Steps/Sec: 1.13
|
| 563 |
+
[[34m2025-10-28 12:57:10[0m] (step=0049500) Train Loss: 0.6145, Train Steps/Sec: 1.13
|
| 564 |
+
[[34m2025-10-28 12:58:38[0m] (step=0049600) Train Loss: 0.6138, Train Steps/Sec: 1.14
|
| 565 |
+
[[34m2025-10-28 13:00:05[0m] (step=0049700) Train Loss: 0.6149, Train Steps/Sec: 1.14
|
| 566 |
+
[[34m2025-10-28 13:01:33[0m] (step=0049800) Train Loss: 0.6132, Train Steps/Sec: 1.14
|
| 567 |
+
[[34m2025-10-28 13:03:01[0m] (step=0049900) Train Loss: 0.6148, Train Steps/Sec: 1.14
|
| 568 |
+
[[34m2025-10-28 13:04:29[0m] (step=0050000) Train Loss: 0.6135, Train Steps/Sec: 1.14
|
| 569 |
+
[[34m2025-10-28 13:05:28[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-pe-vit-l-bf16/checkpoints/0050000.pt
|
| 570 |
+
[[34m2025-10-28 13:05:28[0m] Generating EMA samples...
|
| 571 |
+
[[34m2025-10-28 13:05:57[0m] Generating EMA samples done.
|
| 572 |
+
[[34m2025-10-28 13:06:32[0m] Beginning epoch 40...
|
| 573 |
+
[[34m2025-10-28 13:07:27[0m] (step=0050100) Train Loss: 0.6133, Train Steps/Sec: 0.56
|
| 574 |
+
[[34m2025-10-28 13:08:55[0m] (step=0050200) Train Loss: 0.6151, Train Steps/Sec: 1.13
|
| 575 |
+
[[34m2025-10-28 13:10:23[0m] (step=0050300) Train Loss: 0.6130, Train Steps/Sec: 1.14
|
| 576 |
+
[[34m2025-10-28 13:11:51[0m] (step=0050400) Train Loss: 0.6132, Train Steps/Sec: 1.14
|
| 577 |
+
[[34m2025-10-28 13:13:19[0m] (step=0050500) Train Loss: 0.6130, Train Steps/Sec: 1.14
|
| 578 |
+
[[34m2025-10-28 13:14:47[0m] (step=0050600) Train Loss: 0.6129, Train Steps/Sec: 1.14
|
| 579 |
+
[[34m2025-10-28 13:16:15[0m] (step=0050700) Train Loss: 0.6135, Train Steps/Sec: 1.14
|
| 580 |
+
[[34m2025-10-28 13:17:43[0m] (step=0050800) Train Loss: 0.6135, Train Steps/Sec: 1.14
|
| 581 |
+
[[34m2025-10-28 13:19:11[0m] (step=0050900) Train Loss: 0.6128, Train Steps/Sec: 1.14
|
| 582 |
+
[[34m2025-10-28 13:20:39[0m] (step=0051000) Train Loss: 0.6128, Train Steps/Sec: 1.13
|
| 583 |
+
[[34m2025-10-28 13:22:07[0m] (step=0051100) Train Loss: 0.6128, Train Steps/Sec: 1.13
|
| 584 |
+
[[34m2025-10-28 13:23:35[0m] (step=0051200) Train Loss: 0.6122, Train Steps/Sec: 1.14
|
| 585 |
+
[[34m2025-10-28 13:24:56[0m] Beginning epoch 41...
|
| 586 |
+
[[34m2025-10-28 13:25:06[0m] (step=0051300) Train Loss: 0.6129, Train Steps/Sec: 1.10
|
| 587 |
+
[[34m2025-10-28 13:26:34[0m] (step=0051400) Train Loss: 0.6136, Train Steps/Sec: 1.14
|
| 588 |
+
[[34m2025-10-28 13:28:02[0m] (step=0051500) Train Loss: 0.6120, Train Steps/Sec: 1.14
|
| 589 |
+
[[34m2025-10-28 13:29:30[0m] (step=0051600) Train Loss: 0.6130, Train Steps/Sec: 1.14
|
| 590 |
+
[[34m2025-10-28 13:30:58[0m] (step=0051700) Train Loss: 0.6119, Train Steps/Sec: 1.13
|
| 591 |
+
[[34m2025-10-28 13:32:26[0m] (step=0051800) Train Loss: 0.6129, Train Steps/Sec: 1.14
|
| 592 |
+
[[34m2025-10-28 13:33:54[0m] (step=0051900) Train Loss: 0.6130, Train Steps/Sec: 1.13
|
| 593 |
+
[[34m2025-10-28 13:35:23[0m] (step=0052000) Train Loss: 0.6127, Train Steps/Sec: 1.13
|
| 594 |
+
[[34m2025-10-28 13:36:51[0m] (step=0052100) Train Loss: 0.6117, Train Steps/Sec: 1.14
|
| 595 |
+
[[34m2025-10-28 13:38:19[0m] (step=0052200) Train Loss: 0.6121, Train Steps/Sec: 1.14
|
| 596 |
+
[[34m2025-10-28 13:39:46[0m] (step=0052300) Train Loss: 0.6129, Train Steps/Sec: 1.14
|
| 597 |
+
[[34m2025-10-28 13:41:14[0m] (step=0052400) Train Loss: 0.6135, Train Steps/Sec: 1.14
|
| 598 |
+
[[34m2025-10-28 13:42:42[0m] (step=0052500) Train Loss: 0.6132, Train Steps/Sec: 1.14
|
| 599 |
+
[[34m2025-10-28 13:43:20[0m] Beginning epoch 42...
|
| 600 |
+
[[34m2025-10-28 13:44:13[0m] (step=0052600) Train Loss: 0.6123, Train Steps/Sec: 1.10
|
| 601 |
+
[[34m2025-10-28 13:45:41[0m] (step=0052700) Train Loss: 0.6126, Train Steps/Sec: 1.13
|
| 602 |
+
[[34m2025-10-28 13:47:10[0m] (step=0052800) Train Loss: 0.6127, Train Steps/Sec: 1.13
|
| 603 |
+
[[34m2025-10-28 13:48:38[0m] (step=0052900) Train Loss: 0.6121, Train Steps/Sec: 1.14
|
| 604 |
+
[[34m2025-10-28 13:50:06[0m] (step=0053000) Train Loss: 0.6128, Train Steps/Sec: 1.14
|
| 605 |
+
[[34m2025-10-28 13:51:34[0m] (step=0053100) Train Loss: 0.6114, Train Steps/Sec: 1.14
|
| 606 |
+
[[34m2025-10-28 13:53:01[0m] (step=0053200) Train Loss: 0.6134, Train Steps/Sec: 1.14
|
| 607 |
+
[[34m2025-10-28 13:54:29[0m] (step=0053300) Train Loss: 0.6123, Train Steps/Sec: 1.14
|
| 608 |
+
[[34m2025-10-28 13:55:57[0m] (step=0053400) Train Loss: 0.6128, Train Steps/Sec: 1.14
|
| 609 |
+
[[34m2025-10-28 13:57:25[0m] (step=0053500) Train Loss: 0.6110, Train Steps/Sec: 1.14
|
| 610 |
+
[[34m2025-10-28 13:58:54[0m] (step=0053600) Train Loss: 0.6140, Train Steps/Sec: 1.13
|
| 611 |
+
[[34m2025-10-28 14:00:22[0m] (step=0053700) Train Loss: 0.6109, Train Steps/Sec: 1.14
|
| 612 |
+
[[34m2025-10-28 14:01:44[0m] Beginning epoch 43...
|
| 613 |
+
[[34m2025-10-28 14:01:52[0m] (step=0053800) Train Loss: 0.6118, Train Steps/Sec: 1.11
|
| 614 |
+
[[34m2025-10-28 14:03:20[0m] (step=0053900) Train Loss: 0.6114, Train Steps/Sec: 1.14
|
| 615 |
+
[[34m2025-10-28 14:04:48[0m] (step=0054000) Train Loss: 0.6118, Train Steps/Sec: 1.14
|
| 616 |
+
[[34m2025-10-28 14:06:16[0m] (step=0054100) Train Loss: 0.6136, Train Steps/Sec: 1.14
|
| 617 |
+
[[34m2025-10-28 14:07:44[0m] (step=0054200) Train Loss: 0.6113, Train Steps/Sec: 1.14
|
| 618 |
+
[[34m2025-10-28 14:09:12[0m] (step=0054300) Train Loss: 0.6112, Train Steps/Sec: 1.14
|
| 619 |
+
[[34m2025-10-28 14:10:40[0m] (step=0054400) Train Loss: 0.6124, Train Steps/Sec: 1.13
|
| 620 |
+
[[34m2025-10-28 14:12:08[0m] (step=0054500) Train Loss: 0.6129, Train Steps/Sec: 1.14
|
| 621 |
+
[[34m2025-10-28 14:13:36[0m] (step=0054600) Train Loss: 0.6126, Train Steps/Sec: 1.14
|
| 622 |
+
[[34m2025-10-28 14:15:04[0m] (step=0054700) Train Loss: 0.6115, Train Steps/Sec: 1.14
|
| 623 |
+
[[34m2025-10-28 14:16:32[0m] (step=0054800) Train Loss: 0.6120, Train Steps/Sec: 1.14
|
| 624 |
+
[[34m2025-10-28 14:18:00[0m] (step=0054900) Train Loss: 0.6121, Train Steps/Sec: 1.14
|
| 625 |
+
[[34m2025-10-28 14:19:28[0m] (step=0055000) Train Loss: 0.6121, Train Steps/Sec: 1.14
|
| 626 |
+
[[34m2025-10-28 14:20:07[0m] Beginning epoch 44...
|
| 627 |
+
[[34m2025-10-28 14:20:59[0m] (step=0055100) Train Loss: 0.6118, Train Steps/Sec: 1.10
|
| 628 |
+
[[34m2025-10-28 14:22:27[0m] (step=0055200) Train Loss: 0.6127, Train Steps/Sec: 1.14
|
| 629 |
+
[[34m2025-10-28 14:23:55[0m] (step=0055300) Train Loss: 0.6120, Train Steps/Sec: 1.13
|
| 630 |
+
[[34m2025-10-28 14:25:23[0m] (step=0055400) Train Loss: 0.6126, Train Steps/Sec: 1.14
|
| 631 |
+
[[34m2025-10-28 14:26:51[0m] (step=0055500) Train Loss: 0.6119, Train Steps/Sec: 1.14
|
| 632 |
+
[[34m2025-10-28 14:28:20[0m] (step=0055600) Train Loss: 0.6119, Train Steps/Sec: 1.14
|
| 633 |
+
[[34m2025-10-28 14:29:47[0m] (step=0055700) Train Loss: 0.6120, Train Steps/Sec: 1.14
|
| 634 |
+
[[34m2025-10-28 14:31:15[0m] (step=0055800) Train Loss: 0.6111, Train Steps/Sec: 1.14
|
| 635 |
+
[[34m2025-10-28 14:32:43[0m] (step=0055900) Train Loss: 0.6133, Train Steps/Sec: 1.14
|
| 636 |
+
[[34m2025-10-28 14:34:11[0m] (step=0056000) Train Loss: 0.6099, Train Steps/Sec: 1.14
|
| 637 |
+
[[34m2025-10-28 14:35:39[0m] (step=0056100) Train Loss: 0.6117, Train Steps/Sec: 1.13
|
| 638 |
+
[[34m2025-10-28 14:37:07[0m] (step=0056200) Train Loss: 0.6109, Train Steps/Sec: 1.14
|
| 639 |
+
[[34m2025-10-28 14:38:31[0m] Beginning epoch 45...
|
| 640 |
+
[[34m2025-10-28 14:38:38[0m] (step=0056300) Train Loss: 0.6118, Train Steps/Sec: 1.10
|
| 641 |
+
[[34m2025-10-28 14:40:06[0m] (step=0056400) Train Loss: 0.6109, Train Steps/Sec: 1.14
|
| 642 |
+
[[34m2025-10-28 14:41:34[0m] (step=0056500) Train Loss: 0.6098, Train Steps/Sec: 1.14
|
| 643 |
+
[[34m2025-10-28 14:43:02[0m] (step=0056600) Train Loss: 0.6105, Train Steps/Sec: 1.14
|
| 644 |
+
[[34m2025-10-28 14:44:30[0m] (step=0056700) Train Loss: 0.6111, Train Steps/Sec: 1.14
|
| 645 |
+
[[34m2025-10-28 14:45:58[0m] (step=0056800) Train Loss: 0.6123, Train Steps/Sec: 1.14
|
| 646 |
+
[[34m2025-10-28 14:47:26[0m] (step=0056900) Train Loss: 0.6109, Train Steps/Sec: 1.14
|
| 647 |
+
[[34m2025-10-28 14:48:54[0m] (step=0057000) Train Loss: 0.6121, Train Steps/Sec: 1.13
|
| 648 |
+
[[34m2025-10-28 14:50:22[0m] (step=0057100) Train Loss: 0.6112, Train Steps/Sec: 1.14
|
| 649 |
+
[[34m2025-10-28 14:51:50[0m] (step=0057200) Train Loss: 0.6122, Train Steps/Sec: 1.14
|
| 650 |
+
[[34m2025-10-28 14:53:18[0m] (step=0057300) Train Loss: 0.6103, Train Steps/Sec: 1.14
|
| 651 |
+
[[34m2025-10-28 14:54:46[0m] (step=0057400) Train Loss: 0.6112, Train Steps/Sec: 1.14
|
| 652 |
+
[[34m2025-10-28 14:56:14[0m] (step=0057500) Train Loss: 0.6116, Train Steps/Sec: 1.14
|
| 653 |
+
[[34m2025-10-28 14:56:55[0m] Beginning epoch 46...
|
| 654 |
+
[[34m2025-10-28 14:57:45[0m] (step=0057600) Train Loss: 0.6124, Train Steps/Sec: 1.10
|
| 655 |
+
[[34m2025-10-28 14:59:13[0m] (step=0057700) Train Loss: 0.6112, Train Steps/Sec: 1.14
|
| 656 |
+
[[34m2025-10-28 15:00:41[0m] (step=0057800) Train Loss: 0.6110, Train Steps/Sec: 1.13
|
| 657 |
+
[[34m2025-10-28 15:02:09[0m] (step=0057900) Train Loss: 0.6119, Train Steps/Sec: 1.13
|
| 658 |
+
[[34m2025-10-28 15:03:37[0m] (step=0058000) Train Loss: 0.6114, Train Steps/Sec: 1.13
|
| 659 |
+
[[34m2025-10-28 15:05:05[0m] (step=0058100) Train Loss: 0.6101, Train Steps/Sec: 1.14
|
| 660 |
+
[[34m2025-10-28 15:06:33[0m] (step=0058200) Train Loss: 0.6121, Train Steps/Sec: 1.14
|
| 661 |
+
[[34m2025-10-28 15:08:01[0m] (step=0058300) Train Loss: 0.6109, Train Steps/Sec: 1.14
|
| 662 |
+
[[34m2025-10-28 15:09:29[0m] (step=0058400) Train Loss: 0.6101, Train Steps/Sec: 1.14
|
| 663 |
+
[[34m2025-10-28 15:10:57[0m] (step=0058500) Train Loss: 0.6115, Train Steps/Sec: 1.14
|
| 664 |
+
[[34m2025-10-28 15:12:25[0m] (step=0058600) Train Loss: 0.6107, Train Steps/Sec: 1.14
|
| 665 |
+
[[34m2025-10-28 15:13:53[0m] (step=0058700) Train Loss: 0.6116, Train Steps/Sec: 1.13
|
| 666 |
+
[[34m2025-10-28 15:15:20[0m] Beginning epoch 47...
|
| 667 |
+
[[34m2025-10-28 15:15:25[0m] (step=0058800) Train Loss: 0.6100, Train Steps/Sec: 1.10
|
| 668 |
+
[[34m2025-10-28 15:16:53[0m] (step=0058900) Train Loss: 0.6108, Train Steps/Sec: 1.14
|
| 669 |
+
[[34m2025-10-28 15:18:21[0m] (step=0059000) Train Loss: 0.6098, Train Steps/Sec: 1.14
|
| 670 |
+
[[34m2025-10-28 15:19:49[0m] (step=0059100) Train Loss: 0.6099, Train Steps/Sec: 1.14
|
| 671 |
+
[[34m2025-10-28 15:21:17[0m] (step=0059200) Train Loss: 0.6109, Train Steps/Sec: 1.14
|
| 672 |
+
[[34m2025-10-28 15:22:45[0m] (step=0059300) Train Loss: 0.6110, Train Steps/Sec: 1.14
|
| 673 |
+
[[34m2025-10-28 15:24:13[0m] (step=0059400) Train Loss: 0.6101, Train Steps/Sec: 1.14
|
| 674 |
+
[[34m2025-10-28 15:25:41[0m] (step=0059500) Train Loss: 0.6099, Train Steps/Sec: 1.13
|
| 675 |
+
[[34m2025-10-28 15:27:09[0m] (step=0059600) Train Loss: 0.6098, Train Steps/Sec: 1.14
|
| 676 |
+
[[34m2025-10-28 15:28:37[0m] (step=0059700) Train Loss: 0.6114, Train Steps/Sec: 1.14
|
| 677 |
+
[[34m2025-10-28 15:30:05[0m] (step=0059800) Train Loss: 0.6111, Train Steps/Sec: 1.14
|
| 678 |
+
[[34m2025-10-28 15:31:33[0m] (step=0059900) Train Loss: 0.6102, Train Steps/Sec: 1.14
|
| 679 |
+
[[34m2025-10-28 15:33:01[0m] (step=0060000) Train Loss: 0.6098, Train Steps/Sec: 1.14
|
| 680 |
+
[[34m2025-10-28 15:33:44[0m] Beginning epoch 48...
|
| 681 |
+
[[34m2025-10-28 15:34:32[0m] (step=0060100) Train Loss: 0.6091, Train Steps/Sec: 1.10
|
| 682 |
+
[[34m2025-10-28 15:36:00[0m] (step=0060200) Train Loss: 0.6102, Train Steps/Sec: 1.14
|
| 683 |
+
[[34m2025-10-28 15:37:28[0m] (step=0060300) Train Loss: 0.6104, Train Steps/Sec: 1.14
|
| 684 |
+
[[34m2025-10-28 15:38:56[0m] (step=0060400) Train Loss: 0.6100, Train Steps/Sec: 1.13
|
| 685 |
+
[[34m2025-10-28 15:40:24[0m] (step=0060500) Train Loss: 0.6102, Train Steps/Sec: 1.14
|
| 686 |
+
[[34m2025-10-28 15:41:52[0m] (step=0060600) Train Loss: 0.6111, Train Steps/Sec: 1.14
|
| 687 |
+
[[34m2025-10-28 15:43:20[0m] (step=0060700) Train Loss: 0.6100, Train Steps/Sec: 1.14
|
| 688 |
+
[[34m2025-10-28 15:44:48[0m] (step=0060800) Train Loss: 0.6112, Train Steps/Sec: 1.14
|
| 689 |
+
[[34m2025-10-28 15:46:16[0m] (step=0060900) Train Loss: 0.6088, Train Steps/Sec: 1.14
|
| 690 |
+
[[34m2025-10-28 15:47:44[0m] (step=0061000) Train Loss: 0.6099, Train Steps/Sec: 1.14
|
| 691 |
+
[[34m2025-10-28 15:49:12[0m] (step=0061100) Train Loss: 0.6101, Train Steps/Sec: 1.14
|
| 692 |
+
[[34m2025-10-28 15:50:40[0m] (step=0061200) Train Loss: 0.6097, Train Steps/Sec: 1.14
|
| 693 |
+
[[34m2025-10-28 15:52:08[0m] Beginning epoch 49...
|
| 694 |
+
[[34m2025-10-28 15:52:11[0m] (step=0061300) Train Loss: 0.6098, Train Steps/Sec: 1.10
|
| 695 |
+
[[34m2025-10-28 15:53:39[0m] (step=0061400) Train Loss: 0.6099, Train Steps/Sec: 1.14
|
| 696 |
+
[[34m2025-10-28 15:55:07[0m] (step=0061500) Train Loss: 0.6106, Train Steps/Sec: 1.14
|
| 697 |
+
[[34m2025-10-28 15:56:35[0m] (step=0061600) Train Loss: 0.6088, Train Steps/Sec: 1.14
|
| 698 |
+
[[34m2025-10-28 15:58:03[0m] (step=0061700) Train Loss: 0.6089, Train Steps/Sec: 1.14
|
| 699 |
+
[[34m2025-10-28 15:59:31[0m] (step=0061800) Train Loss: 0.6097, Train Steps/Sec: 1.14
|
| 700 |
+
[[34m2025-10-28 16:00:58[0m] (step=0061900) Train Loss: 0.6097, Train Steps/Sec: 1.14
|
| 701 |
+
[[34m2025-10-28 16:02:26[0m] (step=0062000) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 702 |
+
[[34m2025-10-28 16:03:55[0m] (step=0062100) Train Loss: 0.6094, Train Steps/Sec: 1.13
|
| 703 |
+
[[34m2025-10-28 16:05:23[0m] (step=0062200) Train Loss: 0.6096, Train Steps/Sec: 1.14
|
| 704 |
+
[[34m2025-10-28 16:06:51[0m] (step=0062300) Train Loss: 0.6091, Train Steps/Sec: 1.14
|
| 705 |
+
[[34m2025-10-28 16:08:19[0m] (step=0062400) Train Loss: 0.6106, Train Steps/Sec: 1.14
|
| 706 |
+
[[34m2025-10-28 16:09:47[0m] (step=0062500) Train Loss: 0.6098, Train Steps/Sec: 1.14
|
| 707 |
+
[[34m2025-10-28 16:10:31[0m] Beginning epoch 50...
|
| 708 |
+
[[34m2025-10-28 16:11:18[0m] (step=0062600) Train Loss: 0.6098, Train Steps/Sec: 1.10
|
| 709 |
+
[[34m2025-10-28 16:12:46[0m] (step=0062700) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 710 |
+
[[34m2025-10-28 16:14:13[0m] (step=0062800) Train Loss: 0.6074, Train Steps/Sec: 1.14
|
| 711 |
+
[[34m2025-10-28 16:15:42[0m] (step=0062900) Train Loss: 0.6098, Train Steps/Sec: 1.13
|
| 712 |
+
[[34m2025-10-28 16:17:10[0m] (step=0063000) Train Loss: 0.6093, Train Steps/Sec: 1.14
|
| 713 |
+
[[34m2025-10-28 16:18:38[0m] (step=0063100) Train Loss: 0.6090, Train Steps/Sec: 1.14
|
| 714 |
+
[[34m2025-10-28 16:20:06[0m] (step=0063200) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 715 |
+
[[34m2025-10-28 16:21:34[0m] (step=0063300) Train Loss: 0.6093, Train Steps/Sec: 1.14
|
| 716 |
+
[[34m2025-10-28 16:23:02[0m] (step=0063400) Train Loss: 0.6094, Train Steps/Sec: 1.14
|
| 717 |
+
[[34m2025-10-28 16:24:30[0m] (step=0063500) Train Loss: 0.6098, Train Steps/Sec: 1.14
|
| 718 |
+
[[34m2025-10-28 16:25:58[0m] (step=0063600) Train Loss: 0.6096, Train Steps/Sec: 1.14
|
| 719 |
+
[[34m2025-10-28 16:27:26[0m] (step=0063700) Train Loss: 0.6092, Train Steps/Sec: 1.14
|
| 720 |
+
[[34m2025-10-28 16:28:54[0m] (step=0063800) Train Loss: 0.6090, Train Steps/Sec: 1.13
|
| 721 |
+
[[34m2025-10-28 16:28:55[0m] Beginning epoch 51...
|
| 722 |
+
[[34m2025-10-28 16:30:25[0m] (step=0063900) Train Loss: 0.6090, Train Steps/Sec: 1.10
|
| 723 |
+
[[34m2025-10-28 16:31:53[0m] (step=0064000) Train Loss: 0.6102, Train Steps/Sec: 1.14
|
| 724 |
+
[[34m2025-10-28 16:33:21[0m] (step=0064100) Train Loss: 0.6089, Train Steps/Sec: 1.14
|
| 725 |
+
[[34m2025-10-28 16:34:49[0m] (step=0064200) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 726 |
+
[[34m2025-10-28 16:36:17[0m] (step=0064300) Train Loss: 0.6092, Train Steps/Sec: 1.14
|
| 727 |
+
[[34m2025-10-28 16:37:45[0m] (step=0064400) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 728 |
+
[[34m2025-10-28 16:39:13[0m] (step=0064500) Train Loss: 0.6082, Train Steps/Sec: 1.14
|
| 729 |
+
[[34m2025-10-28 16:40:41[0m] (step=0064600) Train Loss: 0.6093, Train Steps/Sec: 1.13
|
| 730 |
+
[[34m2025-10-28 16:42:09[0m] (step=0064700) Train Loss: 0.6090, Train Steps/Sec: 1.14
|
| 731 |
+
[[34m2025-10-28 16:43:37[0m] (step=0064800) Train Loss: 0.6090, Train Steps/Sec: 1.13
|
| 732 |
+
[[34m2025-10-28 16:45:05[0m] (step=0064900) Train Loss: 0.6082, Train Steps/Sec: 1.14
|
| 733 |
+
[[34m2025-10-28 16:46:33[0m] (step=0065000) Train Loss: 0.6083, Train Steps/Sec: 1.14
|
| 734 |
+
[[34m2025-10-28 16:47:19[0m] Beginning epoch 52...
|
| 735 |
+
[[34m2025-10-28 16:48:04[0m] (step=0065100) Train Loss: 0.6094, Train Steps/Sec: 1.10
|
| 736 |
+
[[34m2025-10-28 16:49:32[0m] (step=0065200) Train Loss: 0.6101, Train Steps/Sec: 1.14
|
| 737 |
+
[[34m2025-10-28 16:51:00[0m] (step=0065300) Train Loss: 0.6093, Train Steps/Sec: 1.14
|
| 738 |
+
[[34m2025-10-28 16:52:28[0m] (step=0065400) Train Loss: 0.6093, Train Steps/Sec: 1.14
|
| 739 |
+
[[34m2025-10-28 16:53:56[0m] (step=0065500) Train Loss: 0.6083, Train Steps/Sec: 1.13
|
| 740 |
+
[[34m2025-10-28 16:55:24[0m] (step=0065600) Train Loss: 0.6075, Train Steps/Sec: 1.13
|
| 741 |
+
[[34m2025-10-28 16:56:52[0m] (step=0065700) Train Loss: 0.6075, Train Steps/Sec: 1.14
|
| 742 |
+
[[34m2025-10-28 16:58:20[0m] (step=0065800) Train Loss: 0.6082, Train Steps/Sec: 1.14
|
| 743 |
+
[[34m2025-10-28 16:59:48[0m] (step=0065900) Train Loss: 0.6080, Train Steps/Sec: 1.14
|
| 744 |
+
[[34m2025-10-28 17:01:16[0m] (step=0066000) Train Loss: 0.6062, Train Steps/Sec: 1.14
|
| 745 |
+
[[34m2025-10-28 17:02:44[0m] (step=0066100) Train Loss: 0.6086, Train Steps/Sec: 1.14
|
| 746 |
+
[[34m2025-10-28 17:04:12[0m] (step=0066200) Train Loss: 0.6085, Train Steps/Sec: 1.14
|
| 747 |
+
[[34m2025-10-28 17:05:40[0m] (step=0066300) Train Loss: 0.6089, Train Steps/Sec: 1.14
|
| 748 |
+
[[34m2025-10-28 17:05:43[0m] Beginning epoch 53...
|
| 749 |
+
[[34m2025-10-28 17:07:12[0m] (step=0066400) Train Loss: 0.6081, Train Steps/Sec: 1.09
|
| 750 |
+
[[34m2025-10-28 17:08:40[0m] (step=0066500) Train Loss: 0.6083, Train Steps/Sec: 1.14
|
| 751 |
+
[[34m2025-10-28 17:10:08[0m] (step=0066600) Train Loss: 0.6085, Train Steps/Sec: 1.14
|
| 752 |
+
[[34m2025-10-28 17:11:36[0m] (step=0066700) Train Loss: 0.6078, Train Steps/Sec: 1.14
|
| 753 |
+
[[34m2025-10-28 17:13:03[0m] (step=0066800) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 754 |
+
[[34m2025-10-28 17:14:31[0m] (step=0066900) Train Loss: 0.6065, Train Steps/Sec: 1.14
|
| 755 |
+
[[34m2025-10-28 17:15:59[0m] (step=0067000) Train Loss: 0.6085, Train Steps/Sec: 1.14
|
| 756 |
+
[[34m2025-10-28 17:17:27[0m] (step=0067100) Train Loss: 0.6096, Train Steps/Sec: 1.14
|
| 757 |
+
[[34m2025-10-28 17:18:56[0m] (step=0067200) Train Loss: 0.6076, Train Steps/Sec: 1.13
|
| 758 |
+
[[34m2025-10-28 17:20:24[0m] (step=0067300) Train Loss: 0.6083, Train Steps/Sec: 1.14
|
| 759 |
+
[[34m2025-10-28 17:21:52[0m] (step=0067400) Train Loss: 0.6092, Train Steps/Sec: 1.14
|
| 760 |
+
[[34m2025-10-28 17:23:19[0m] (step=0067500) Train Loss: 0.6092, Train Steps/Sec: 1.14
|
| 761 |
+
[[34m2025-10-28 17:24:07[0m] Beginning epoch 54...
|
| 762 |
+
[[34m2025-10-28 17:24:50[0m] (step=0067600) Train Loss: 0.6089, Train Steps/Sec: 1.10
|
| 763 |
+
[[34m2025-10-28 17:26:18[0m] (step=0067700) Train Loss: 0.6085, Train Steps/Sec: 1.14
|
| 764 |
+
[[34m2025-10-28 17:27:46[0m] (step=0067800) Train Loss: 0.6083, Train Steps/Sec: 1.14
|
| 765 |
+
[[34m2025-10-28 17:29:14[0m] (step=0067900) Train Loss: 0.6079, Train Steps/Sec: 1.14
|
| 766 |
+
[[34m2025-10-28 17:30:42[0m] (step=0068000) Train Loss: 0.6078, Train Steps/Sec: 1.13
|
| 767 |
+
[[34m2025-10-28 17:32:11[0m] (step=0068100) Train Loss: 0.6069, Train Steps/Sec: 1.13
|
| 768 |
+
[[34m2025-10-28 17:33:39[0m] (step=0068200) Train Loss: 0.6088, Train Steps/Sec: 1.14
|
| 769 |
+
[[34m2025-10-28 17:35:07[0m] (step=0068300) Train Loss: 0.6077, Train Steps/Sec: 1.14
|
| 770 |
+
[[34m2025-10-28 17:36:34[0m] (step=0068400) Train Loss: 0.6080, Train Steps/Sec: 1.14
|
| 771 |
+
[[34m2025-10-28 17:38:02[0m] (step=0068500) Train Loss: 0.6082, Train Steps/Sec: 1.14
|
| 772 |
+
[[34m2025-10-28 17:39:30[0m] (step=0068600) Train Loss: 0.6063, Train Steps/Sec: 1.14
|
| 773 |
+
[[34m2025-10-28 17:40:58[0m] (step=0068700) Train Loss: 0.6069, Train Steps/Sec: 1.14
|
| 774 |
+
[[34m2025-10-28 17:42:26[0m] (step=0068800) Train Loss: 0.6076, Train Steps/Sec: 1.14
|
| 775 |
+
[[34m2025-10-28 17:42:31[0m] Beginning epoch 55...
|
| 776 |
+
[[34m2025-10-28 17:43:58[0m] (step=0068900) Train Loss: 0.6070, Train Steps/Sec: 1.09
|
| 777 |
+
[[34m2025-10-28 17:45:26[0m] (step=0069000) Train Loss: 0.6093, Train Steps/Sec: 1.14
|
| 778 |
+
[[34m2025-10-28 17:46:54[0m] (step=0069100) Train Loss: 0.6079, Train Steps/Sec: 1.14
|
| 779 |
+
[[34m2025-10-28 17:48:22[0m] (step=0069200) Train Loss: 0.6080, Train Steps/Sec: 1.14
|
| 780 |
+
[[34m2025-10-28 17:49:50[0m] (step=0069300) Train Loss: 0.6076, Train Steps/Sec: 1.14
|
| 781 |
+
[[34m2025-10-28 17:51:18[0m] (step=0069400) Train Loss: 0.6079, Train Steps/Sec: 1.14
|
| 782 |
+
[[34m2025-10-28 17:52:46[0m] (step=0069500) Train Loss: 0.6078, Train Steps/Sec: 1.14
|
| 783 |
+
[[34m2025-10-28 17:54:14[0m] (step=0069600) Train Loss: 0.6073, Train Steps/Sec: 1.14
|
| 784 |
+
[[34m2025-10-28 17:55:42[0m] (step=0069700) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 785 |
+
[[34m2025-10-28 17:57:10[0m] (step=0069800) Train Loss: 0.6081, Train Steps/Sec: 1.13
|
| 786 |
+
[[34m2025-10-28 17:58:38[0m] (step=0069900) Train Loss: 0.6084, Train Steps/Sec: 1.14
|
| 787 |
+
[[34m2025-10-28 18:00:06[0m] (step=0070000) Train Loss: 0.6069, Train Steps/Sec: 1.14
|
| 788 |
+
[[34m2025-10-28 18:00:56[0m] Beginning epoch 56...
|
| 789 |
+
[[34m2025-10-28 18:01:37[0m] (step=0070100) Train Loss: 0.6065, Train Steps/Sec: 1.10
|
| 790 |
+
[[34m2025-10-28 18:03:05[0m] (step=0070200) Train Loss: 0.6083, Train Steps/Sec: 1.14
|
| 791 |
+
[[34m2025-10-28 18:04:33[0m] (step=0070300) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 792 |
+
[[34m2025-10-28 18:06:01[0m] (step=0070400) Train Loss: 0.6073, Train Steps/Sec: 1.14
|
| 793 |
+
[[34m2025-10-28 18:07:29[0m] (step=0070500) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 794 |
+
[[34m2025-10-28 18:08:57[0m] (step=0070600) Train Loss: 0.6065, Train Steps/Sec: 1.13
|
| 795 |
+
[[34m2025-10-28 18:10:25[0m] (step=0070700) Train Loss: 0.6081, Train Steps/Sec: 1.14
|
| 796 |
+
[[34m2025-10-28 18:11:53[0m] (step=0070800) Train Loss: 0.6079, Train Steps/Sec: 1.14
|
| 797 |
+
[[34m2025-10-28 18:13:21[0m] (step=0070900) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 798 |
+
[[34m2025-10-28 18:14:49[0m] (step=0071000) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 799 |
+
[[34m2025-10-28 18:16:17[0m] (step=0071100) Train Loss: 0.6064, Train Steps/Sec: 1.14
|
| 800 |
+
[[34m2025-10-28 18:17:45[0m] (step=0071200) Train Loss: 0.6076, Train Steps/Sec: 1.14
|
| 801 |
+
[[34m2025-10-28 18:19:13[0m] (step=0071300) Train Loss: 0.6075, Train Steps/Sec: 1.14
|
| 802 |
+
[[34m2025-10-28 18:19:20[0m] Beginning epoch 57...
|
| 803 |
+
[[34m2025-10-28 18:20:45[0m] (step=0071400) Train Loss: 0.6076, Train Steps/Sec: 1.09
|
| 804 |
+
[[34m2025-10-28 18:22:13[0m] (step=0071500) Train Loss: 0.6067, Train Steps/Sec: 1.13
|
| 805 |
+
[[34m2025-10-28 18:23:41[0m] (step=0071600) Train Loss: 0.6069, Train Steps/Sec: 1.14
|
| 806 |
+
[[34m2025-10-28 18:25:09[0m] (step=0071700) Train Loss: 0.6078, Train Steps/Sec: 1.14
|
| 807 |
+
[[34m2025-10-28 18:26:37[0m] (step=0071800) Train Loss: 0.6068, Train Steps/Sec: 1.14
|
| 808 |
+
[[34m2025-10-28 18:28:05[0m] (step=0071900) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 809 |
+
[[34m2025-10-28 18:29:33[0m] (step=0072000) Train Loss: 0.6063, Train Steps/Sec: 1.14
|
| 810 |
+
[[34m2025-10-28 18:31:01[0m] (step=0072100) Train Loss: 0.6069, Train Steps/Sec: 1.14
|
| 811 |
+
[[34m2025-10-28 18:32:29[0m] (step=0072200) Train Loss: 0.6074, Train Steps/Sec: 1.14
|
| 812 |
+
[[34m2025-10-28 18:33:57[0m] (step=0072300) Train Loss: 0.6070, Train Steps/Sec: 1.13
|
| 813 |
+
[[34m2025-10-28 18:35:25[0m] (step=0072400) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 814 |
+
[[34m2025-10-28 18:36:53[0m] (step=0072500) Train Loss: 0.6069, Train Steps/Sec: 1.14
|
| 815 |
+
[[34m2025-10-28 18:37:45[0m] Beginning epoch 58...
|
| 816 |
+
[[34m2025-10-28 18:38:24[0m] (step=0072600) Train Loss: 0.6070, Train Steps/Sec: 1.10
|
| 817 |
+
[[34m2025-10-28 18:39:52[0m] (step=0072700) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 818 |
+
[[34m2025-10-28 18:41:20[0m] (step=0072800) Train Loss: 0.6075, Train Steps/Sec: 1.14
|
| 819 |
+
[[34m2025-10-28 18:42:48[0m] (step=0072900) Train Loss: 0.6065, Train Steps/Sec: 1.14
|
| 820 |
+
[[34m2025-10-28 18:44:16[0m] (step=0073000) Train Loss: 0.6059, Train Steps/Sec: 1.14
|
| 821 |
+
[[34m2025-10-28 18:45:44[0m] (step=0073100) Train Loss: 0.6057, Train Steps/Sec: 1.13
|
| 822 |
+
[[34m2025-10-28 18:47:13[0m] (step=0073200) Train Loss: 0.6082, Train Steps/Sec: 1.13
|
| 823 |
+
[[34m2025-10-28 18:48:41[0m] (step=0073300) Train Loss: 0.6064, Train Steps/Sec: 1.14
|
| 824 |
+
[[34m2025-10-28 18:50:09[0m] (step=0073400) Train Loss: 0.6073, Train Steps/Sec: 1.14
|
| 825 |
+
[[34m2025-10-28 18:51:37[0m] (step=0073500) Train Loss: 0.6072, Train Steps/Sec: 1.14
|
| 826 |
+
[[34m2025-10-28 18:53:05[0m] (step=0073600) Train Loss: 0.6068, Train Steps/Sec: 1.14
|
| 827 |
+
[[34m2025-10-28 18:54:33[0m] (step=0073700) Train Loss: 0.6065, Train Steps/Sec: 1.14
|
| 828 |
+
[[34m2025-10-28 18:56:00[0m] (step=0073800) Train Loss: 0.6068, Train Steps/Sec: 1.14
|
| 829 |
+
[[34m2025-10-28 18:56:09[0m] Beginning epoch 59...
|
| 830 |
+
[[34m2025-10-28 18:57:31[0m] (step=0073900) Train Loss: 0.6060, Train Steps/Sec: 1.10
|
| 831 |
+
[[34m2025-10-28 18:59:00[0m] (step=0074000) Train Loss: 0.6071, Train Steps/Sec: 1.13
|
| 832 |
+
[[34m2025-10-28 19:00:28[0m] (step=0074100) Train Loss: 0.6063, Train Steps/Sec: 1.13
|
| 833 |
+
[[34m2025-10-28 19:01:56[0m] (step=0074200) Train Loss: 0.6073, Train Steps/Sec: 1.14
|
| 834 |
+
[[34m2025-10-28 19:03:24[0m] (step=0074300) Train Loss: 0.6060, Train Steps/Sec: 1.14
|
| 835 |
+
[[34m2025-10-28 19:04:52[0m] (step=0074400) Train Loss: 0.6061, Train Steps/Sec: 1.14
|
| 836 |
+
[[34m2025-10-28 19:06:20[0m] (step=0074500) Train Loss: 0.6073, Train Steps/Sec: 1.14
|
| 837 |
+
[[34m2025-10-28 19:07:48[0m] (step=0074600) Train Loss: 0.6072, Train Steps/Sec: 1.14
|
| 838 |
+
[[34m2025-10-28 19:09:16[0m] (step=0074700) Train Loss: 0.6058, Train Steps/Sec: 1.14
|
| 839 |
+
[[34m2025-10-28 19:10:44[0m] (step=0074800) Train Loss: 0.6073, Train Steps/Sec: 1.14
|
| 840 |
+
[[34m2025-10-28 19:12:12[0m] (step=0074900) Train Loss: 0.6079, Train Steps/Sec: 1.14
|
| 841 |
+
[[34m2025-10-28 19:13:40[0m] (step=0075000) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 842 |
+
[[34m2025-10-28 19:14:38[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-pe-vit-l-bf16/checkpoints/0075000.pt
|
| 843 |
+
[[34m2025-10-28 19:14:38[0m] Generating EMA samples...
|
| 844 |
+
[[34m2025-10-28 19:15:07[0m] Generating EMA samples done.
|
| 845 |
+
[[34m2025-10-28 19:15:59[0m] Beginning epoch 60...
|
| 846 |
+
[[34m2025-10-28 19:16:37[0m] (step=0075100) Train Loss: 0.6060, Train Steps/Sec: 0.56
|
| 847 |
+
[[34m2025-10-28 19:18:05[0m] (step=0075200) Train Loss: 0.6075, Train Steps/Sec: 1.14
|
| 848 |
+
[[34m2025-10-28 19:19:33[0m] (step=0075300) Train Loss: 0.6061, Train Steps/Sec: 1.14
|
| 849 |
+
[[34m2025-10-28 19:21:00[0m] (step=0075400) Train Loss: 0.6056, Train Steps/Sec: 1.14
|
| 850 |
+
[[34m2025-10-28 19:22:28[0m] (step=0075500) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 851 |
+
[[34m2025-10-28 19:23:56[0m] (step=0075600) Train Loss: 0.6056, Train Steps/Sec: 1.14
|
| 852 |
+
[[34m2025-10-28 19:25:25[0m] (step=0075700) Train Loss: 0.6071, Train Steps/Sec: 1.13
|
| 853 |
+
[[34m2025-10-28 19:26:53[0m] (step=0075800) Train Loss: 0.6058, Train Steps/Sec: 1.13
|
| 854 |
+
[[34m2025-10-28 19:28:21[0m] (step=0075900) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 855 |
+
[[34m2025-10-28 19:29:49[0m] (step=0076000) Train Loss: 0.6056, Train Steps/Sec: 1.14
|
| 856 |
+
[[34m2025-10-28 19:31:17[0m] (step=0076100) Train Loss: 0.6062, Train Steps/Sec: 1.14
|
| 857 |
+
[[34m2025-10-28 19:32:45[0m] (step=0076200) Train Loss: 0.6062, Train Steps/Sec: 1.14
|
| 858 |
+
[[34m2025-10-28 19:34:13[0m] (step=0076300) Train Loss: 0.6062, Train Steps/Sec: 1.14
|
| 859 |
+
[[34m2025-10-28 19:34:23[0m] Beginning epoch 61...
|
| 860 |
+
[[34m2025-10-28 19:35:44[0m] (step=0076400) Train Loss: 0.6080, Train Steps/Sec: 1.10
|
| 861 |
+
[[34m2025-10-28 19:37:12[0m] (step=0076500) Train Loss: 0.6061, Train Steps/Sec: 1.13
|
| 862 |
+
[[34m2025-10-28 19:38:41[0m] (step=0076600) Train Loss: 0.6069, Train Steps/Sec: 1.13
|
| 863 |
+
[[34m2025-10-28 19:40:08[0m] (step=0076700) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 864 |
+
[[34m2025-10-28 19:41:36[0m] (step=0076800) Train Loss: 0.6062, Train Steps/Sec: 1.14
|
| 865 |
+
[[34m2025-10-28 19:43:04[0m] (step=0076900) Train Loss: 0.6058, Train Steps/Sec: 1.14
|
| 866 |
+
[[34m2025-10-28 19:44:32[0m] (step=0077000) Train Loss: 0.6060, Train Steps/Sec: 1.14
|
| 867 |
+
[[34m2025-10-28 19:46:00[0m] (step=0077100) Train Loss: 0.6064, Train Steps/Sec: 1.14
|
| 868 |
+
[[34m2025-10-28 19:47:28[0m] (step=0077200) Train Loss: 0.6065, Train Steps/Sec: 1.14
|
| 869 |
+
[[34m2025-10-28 19:48:56[0m] (step=0077300) Train Loss: 0.6055, Train Steps/Sec: 1.14
|
| 870 |
+
[[34m2025-10-28 19:50:24[0m] (step=0077400) Train Loss: 0.6063, Train Steps/Sec: 1.13
|
| 871 |
+
[[34m2025-10-28 19:51:52[0m] (step=0077500) Train Loss: 0.6063, Train Steps/Sec: 1.14
|
| 872 |
+
[[34m2025-10-28 19:52:47[0m] Beginning epoch 62...
|
| 873 |
+
[[34m2025-10-28 19:53:23[0m] (step=0077600) Train Loss: 0.6052, Train Steps/Sec: 1.10
|
| 874 |
+
[[34m2025-10-28 19:54:51[0m] (step=0077700) Train Loss: 0.6060, Train Steps/Sec: 1.14
|
| 875 |
+
[[34m2025-10-28 19:56:19[0m] (step=0077800) Train Loss: 0.6050, Train Steps/Sec: 1.14
|
| 876 |
+
[[34m2025-10-28 19:57:47[0m] (step=0077900) Train Loss: 0.6059, Train Steps/Sec: 1.14
|
| 877 |
+
[[34m2025-10-28 19:59:15[0m] (step=0078000) Train Loss: 0.6055, Train Steps/Sec: 1.14
|
| 878 |
+
[[34m2025-10-28 20:00:43[0m] (step=0078100) Train Loss: 0.6055, Train Steps/Sec: 1.14
|
| 879 |
+
[[34m2025-10-28 20:02:11[0m] (step=0078200) Train Loss: 0.6059, Train Steps/Sec: 1.13
|
| 880 |
+
[[34m2025-10-28 20:03:39[0m] (step=0078300) Train Loss: 0.6048, Train Steps/Sec: 1.13
|
| 881 |
+
[[34m2025-10-28 20:05:07[0m] (step=0078400) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 882 |
+
[[34m2025-10-28 20:06:35[0m] (step=0078500) Train Loss: 0.6064, Train Steps/Sec: 1.14
|
| 883 |
+
[[34m2025-10-28 20:08:03[0m] (step=0078600) Train Loss: 0.6062, Train Steps/Sec: 1.14
|
| 884 |
+
[[34m2025-10-28 20:09:31[0m] (step=0078700) Train Loss: 0.6048, Train Steps/Sec: 1.14
|
| 885 |
+
[[34m2025-10-28 20:10:59[0m] (step=0078800) Train Loss: 0.6054, Train Steps/Sec: 1.14
|
| 886 |
+
[[34m2025-10-28 20:11:11[0m] Beginning epoch 63...
|
| 887 |
+
[[34m2025-10-28 20:12:30[0m] (step=0078900) Train Loss: 0.6058, Train Steps/Sec: 1.10
|
| 888 |
+
[[34m2025-10-28 20:13:58[0m] (step=0079000) Train Loss: 0.6040, Train Steps/Sec: 1.14
|
| 889 |
+
[[34m2025-10-28 20:15:26[0m] (step=0079100) Train Loss: 0.6064, Train Steps/Sec: 1.13
|
| 890 |
+
[[34m2025-10-28 20:16:54[0m] (step=0079200) Train Loss: 0.6069, Train Steps/Sec: 1.14
|
| 891 |
+
[[34m2025-10-28 20:18:22[0m] (step=0079300) Train Loss: 0.6051, Train Steps/Sec: 1.14
|
| 892 |
+
[[34m2025-10-28 20:19:50[0m] (step=0079400) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 893 |
+
[[34m2025-10-28 20:21:18[0m] (step=0079500) Train Loss: 0.6045, Train Steps/Sec: 1.14
|
| 894 |
+
[[34m2025-10-28 20:22:46[0m] (step=0079600) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 895 |
+
[[34m2025-10-28 20:24:14[0m] (step=0079700) Train Loss: 0.6054, Train Steps/Sec: 1.14
|
| 896 |
+
[[34m2025-10-28 20:25:42[0m] (step=0079800) Train Loss: 0.6054, Train Steps/Sec: 1.14
|
| 897 |
+
[[34m2025-10-28 20:27:10[0m] (step=0079900) Train Loss: 0.6054, Train Steps/Sec: 1.14
|
| 898 |
+
[[34m2025-10-28 20:28:38[0m] (step=0080000) Train Loss: 0.6048, Train Steps/Sec: 1.14
|
| 899 |
+
[[34m2025-10-28 20:29:35[0m] Beginning epoch 64...
|
| 900 |
+
[[34m2025-10-28 20:30:09[0m] (step=0080100) Train Loss: 0.6051, Train Steps/Sec: 1.10
|
| 901 |
+
[[34m2025-10-28 20:31:37[0m] (step=0080200) Train Loss: 0.6051, Train Steps/Sec: 1.14
|
| 902 |
+
[[34m2025-10-28 20:33:05[0m] (step=0080300) Train Loss: 0.6055, Train Steps/Sec: 1.14
|
| 903 |
+
[[34m2025-10-28 20:34:33[0m] (step=0080400) Train Loss: 0.6057, Train Steps/Sec: 1.14
|
| 904 |
+
[[34m2025-10-28 20:36:01[0m] (step=0080500) Train Loss: 0.6055, Train Steps/Sec: 1.14
|
| 905 |
+
[[34m2025-10-28 20:37:29[0m] (step=0080600) Train Loss: 0.6034, Train Steps/Sec: 1.14
|
| 906 |
+
[[34m2025-10-28 20:38:56[0m] (step=0080700) Train Loss: 0.6056, Train Steps/Sec: 1.14
|
| 907 |
+
[[34m2025-10-28 20:40:25[0m] (step=0080800) Train Loss: 0.6051, Train Steps/Sec: 1.13
|
| 908 |
+
[[34m2025-10-28 20:41:53[0m] (step=0080900) Train Loss: 0.6052, Train Steps/Sec: 1.14
|
| 909 |
+
[[34m2025-10-28 20:43:21[0m] (step=0081000) Train Loss: 0.6061, Train Steps/Sec: 1.14
|
| 910 |
+
[[34m2025-10-28 20:44:49[0m] (step=0081100) Train Loss: 0.6052, Train Steps/Sec: 1.14
|
| 911 |
+
[[34m2025-10-28 20:46:17[0m] (step=0081200) Train Loss: 0.6043, Train Steps/Sec: 1.14
|
| 912 |
+
[[34m2025-10-28 20:47:45[0m] (step=0081300) Train Loss: 0.6047, Train Steps/Sec: 1.14
|
| 913 |
+
[[34m2025-10-28 20:47:58[0m] Beginning epoch 65...
|
| 914 |
+
[[34m2025-10-28 20:49:15[0m] (step=0081400) Train Loss: 0.6051, Train Steps/Sec: 1.10
|
| 915 |
+
[[34m2025-10-28 20:50:43[0m] (step=0081500) Train Loss: 0.6055, Train Steps/Sec: 1.14
|
| 916 |
+
[[34m2025-10-28 20:52:12[0m] (step=0081600) Train Loss: 0.6054, Train Steps/Sec: 1.13
|
| 917 |
+
[[34m2025-10-28 20:53:40[0m] (step=0081700) Train Loss: 0.6051, Train Steps/Sec: 1.13
|
| 918 |
+
[[34m2025-10-28 20:55:08[0m] (step=0081800) Train Loss: 0.6049, Train Steps/Sec: 1.14
|
| 919 |
+
[[34m2025-10-28 20:56:36[0m] (step=0081900) Train Loss: 0.6050, Train Steps/Sec: 1.14
|
| 920 |
+
[[34m2025-10-28 20:58:04[0m] (step=0082000) Train Loss: 0.6044, Train Steps/Sec: 1.14
|
| 921 |
+
[[34m2025-10-28 20:59:32[0m] (step=0082100) Train Loss: 0.6047, Train Steps/Sec: 1.14
|
| 922 |
+
[[34m2025-10-28 21:01:00[0m] (step=0082200) Train Loss: 0.6050, Train Steps/Sec: 1.14
|
| 923 |
+
[[34m2025-10-28 21:02:28[0m] (step=0082300) Train Loss: 0.6044, Train Steps/Sec: 1.14
|
| 924 |
+
[[34m2025-10-28 21:03:56[0m] (step=0082400) Train Loss: 0.6048, Train Steps/Sec: 1.14
|
| 925 |
+
[[34m2025-10-28 21:05:24[0m] (step=0082500) Train Loss: 0.6044, Train Steps/Sec: 1.13
|
| 926 |
+
[[34m2025-10-28 21:06:22[0m] Beginning epoch 66...
|
| 927 |
+
[[34m2025-10-28 21:06:55[0m] (step=0082600) Train Loss: 0.6052, Train Steps/Sec: 1.10
|
| 928 |
+
[[34m2025-10-28 21:08:23[0m] (step=0082700) Train Loss: 0.6044, Train Steps/Sec: 1.14
|
| 929 |
+
[[34m2025-10-28 21:09:51[0m] (step=0082800) Train Loss: 0.6039, Train Steps/Sec: 1.14
|
| 930 |
+
[[34m2025-10-28 21:11:19[0m] (step=0082900) Train Loss: 0.6047, Train Steps/Sec: 1.14
|
| 931 |
+
[[34m2025-10-28 21:12:47[0m] (step=0083000) Train Loss: 0.6044, Train Steps/Sec: 1.14
|
| 932 |
+
[[34m2025-10-28 21:14:15[0m] (step=0083100) Train Loss: 0.6052, Train Steps/Sec: 1.14
|
| 933 |
+
[[34m2025-10-28 21:15:43[0m] (step=0083200) Train Loss: 0.6031, Train Steps/Sec: 1.14
|
| 934 |
+
[[34m2025-10-28 21:17:11[0m] (step=0083300) Train Loss: 0.6053, Train Steps/Sec: 1.13
|
| 935 |
+
[[34m2025-10-28 21:18:39[0m] (step=0083400) Train Loss: 0.6033, Train Steps/Sec: 1.13
|
| 936 |
+
[[34m2025-10-28 21:20:07[0m] (step=0083500) Train Loss: 0.6041, Train Steps/Sec: 1.14
|
| 937 |
+
[[34m2025-10-28 21:21:35[0m] (step=0083600) Train Loss: 0.6041, Train Steps/Sec: 1.14
|
| 938 |
+
[[34m2025-10-28 21:23:03[0m] (step=0083700) Train Loss: 0.6056, Train Steps/Sec: 1.14
|
| 939 |
+
[[34m2025-10-28 21:24:31[0m] (step=0083800) Train Loss: 0.6051, Train Steps/Sec: 1.14
|
| 940 |
+
[[34m2025-10-28 21:24:46[0m] Beginning epoch 67...
|
| 941 |
+
[[34m2025-10-28 21:26:02[0m] (step=0083900) Train Loss: 0.6048, Train Steps/Sec: 1.10
|
| 942 |
+
[[34m2025-10-28 21:27:30[0m] (step=0084000) Train Loss: 0.6039, Train Steps/Sec: 1.14
|
| 943 |
+
[[34m2025-10-28 21:28:58[0m] (step=0084100) Train Loss: 0.6039, Train Steps/Sec: 1.14
|
| 944 |
+
[[34m2025-10-28 21:30:26[0m] (step=0084200) Train Loss: 0.6027, Train Steps/Sec: 1.13
|
| 945 |
+
[[34m2025-10-28 21:31:54[0m] (step=0084300) Train Loss: 0.6042, Train Steps/Sec: 1.14
|
| 946 |
+
[[34m2025-10-28 21:33:22[0m] (step=0084400) Train Loss: 0.6034, Train Steps/Sec: 1.14
|
| 947 |
+
[[34m2025-10-28 21:34:50[0m] (step=0084500) Train Loss: 0.6069, Train Steps/Sec: 1.14
|
| 948 |
+
[[34m2025-10-28 21:36:18[0m] (step=0084600) Train Loss: 0.6045, Train Steps/Sec: 1.14
|
| 949 |
+
[[34m2025-10-28 21:37:46[0m] (step=0084700) Train Loss: 0.6050, Train Steps/Sec: 1.14
|
| 950 |
+
[[34m2025-10-28 21:39:14[0m] (step=0084800) Train Loss: 0.6046, Train Steps/Sec: 1.14
|
| 951 |
+
[[34m2025-10-28 21:40:42[0m] (step=0084900) Train Loss: 0.6044, Train Steps/Sec: 1.14
|
| 952 |
+
[[34m2025-10-28 21:42:10[0m] (step=0085000) Train Loss: 0.6053, Train Steps/Sec: 1.13
|
| 953 |
+
[[34m2025-10-28 21:43:10[0m] Beginning epoch 68...
|
| 954 |
+
[[34m2025-10-28 21:43:41[0m] (step=0085100) Train Loss: 0.6045, Train Steps/Sec: 1.10
|
| 955 |
+
[[34m2025-10-28 21:45:09[0m] (step=0085200) Train Loss: 0.6046, Train Steps/Sec: 1.14
|
| 956 |
+
[[34m2025-10-28 21:46:37[0m] (step=0085300) Train Loss: 0.6035, Train Steps/Sec: 1.14
|
| 957 |
+
[[34m2025-10-28 21:48:05[0m] (step=0085400) Train Loss: 0.6037, Train Steps/Sec: 1.14
|
| 958 |
+
[[34m2025-10-28 21:49:33[0m] (step=0085500) Train Loss: 0.6053, Train Steps/Sec: 1.14
|
| 959 |
+
[[34m2025-10-28 21:51:01[0m] (step=0085600) Train Loss: 0.6042, Train Steps/Sec: 1.14
|
| 960 |
+
[[34m2025-10-28 21:52:29[0m] (step=0085700) Train Loss: 0.6048, Train Steps/Sec: 1.14
|
| 961 |
+
[[34m2025-10-28 21:53:57[0m] (step=0085800) Train Loss: 0.6046, Train Steps/Sec: 1.14
|
| 962 |
+
[[34m2025-10-28 21:55:25[0m] (step=0085900) Train Loss: 0.6044, Train Steps/Sec: 1.13
|
| 963 |
+
[[34m2025-10-28 21:56:53[0m] (step=0086000) Train Loss: 0.6052, Train Steps/Sec: 1.14
|
| 964 |
+
[[34m2025-10-28 21:58:21[0m] (step=0086100) Train Loss: 0.6034, Train Steps/Sec: 1.14
|
| 965 |
+
[[34m2025-10-28 21:59:49[0m] (step=0086200) Train Loss: 0.6035, Train Steps/Sec: 1.14
|
| 966 |
+
[[34m2025-10-28 22:01:17[0m] (step=0086300) Train Loss: 0.6037, Train Steps/Sec: 1.14
|
| 967 |
+
[[34m2025-10-28 22:01:34[0m] Beginning epoch 69...
|
| 968 |
+
[[34m2025-10-28 22:02:48[0m] (step=0086400) Train Loss: 0.6043, Train Steps/Sec: 1.10
|
| 969 |
+
[[34m2025-10-28 22:04:15[0m] (step=0086500) Train Loss: 0.6049, Train Steps/Sec: 1.14
|
| 970 |
+
[[34m2025-10-28 22:05:43[0m] (step=0086600) Train Loss: 0.6031, Train Steps/Sec: 1.14
|
| 971 |
+
[[34m2025-10-28 22:07:12[0m] (step=0086700) Train Loss: 0.6037, Train Steps/Sec: 1.13
|
| 972 |
+
[[34m2025-10-28 22:08:40[0m] (step=0086800) Train Loss: 0.6040, Train Steps/Sec: 1.14
|
| 973 |
+
[[34m2025-10-28 22:10:08[0m] (step=0086900) Train Loss: 0.6031, Train Steps/Sec: 1.14
|
| 974 |
+
[[34m2025-10-28 22:11:36[0m] (step=0087000) Train Loss: 0.6047, Train Steps/Sec: 1.14
|
| 975 |
+
[[34m2025-10-28 22:13:04[0m] (step=0087100) Train Loss: 0.6053, Train Steps/Sec: 1.14
|
| 976 |
+
[[34m2025-10-28 22:14:32[0m] (step=0087200) Train Loss: 0.6035, Train Steps/Sec: 1.14
|
| 977 |
+
[[34m2025-10-28 22:16:00[0m] (step=0087300) Train Loss: 0.6041, Train Steps/Sec: 1.14
|
| 978 |
+
[[34m2025-10-28 22:17:28[0m] (step=0087400) Train Loss: 0.6037, Train Steps/Sec: 1.14
|
| 979 |
+
[[34m2025-10-28 22:18:56[0m] (step=0087500) Train Loss: 0.6044, Train Steps/Sec: 1.14
|
| 980 |
+
[[34m2025-10-28 22:19:58[0m] Beginning epoch 70...
|
| 981 |
+
[[34m2025-10-28 22:20:26[0m] (step=0087600) Train Loss: 0.6040, Train Steps/Sec: 1.10
|
| 982 |
+
[[34m2025-10-28 22:21:55[0m] (step=0087700) Train Loss: 0.6021, Train Steps/Sec: 1.14
|
| 983 |
+
[[34m2025-10-28 22:23:22[0m] (step=0087800) Train Loss: 0.6029, Train Steps/Sec: 1.14
|
| 984 |
+
[[34m2025-10-28 22:24:50[0m] (step=0087900) Train Loss: 0.6042, Train Steps/Sec: 1.14
|
| 985 |
+
[[34m2025-10-28 22:26:18[0m] (step=0088000) Train Loss: 0.6038, Train Steps/Sec: 1.14
|
| 986 |
+
[[34m2025-10-28 22:27:46[0m] (step=0088100) Train Loss: 0.6041, Train Steps/Sec: 1.14
|
| 987 |
+
[[34m2025-10-28 22:29:14[0m] (step=0088200) Train Loss: 0.6032, Train Steps/Sec: 1.14
|
| 988 |
+
[[34m2025-10-28 22:30:42[0m] (step=0088300) Train Loss: 0.6040, Train Steps/Sec: 1.14
|
| 989 |
+
[[34m2025-10-28 22:32:11[0m] (step=0088400) Train Loss: 0.6037, Train Steps/Sec: 1.13
|
| 990 |
+
[[34m2025-10-28 22:33:39[0m] (step=0088500) Train Loss: 0.6031, Train Steps/Sec: 1.14
|
| 991 |
+
[[34m2025-10-28 22:35:07[0m] (step=0088600) Train Loss: 0.6029, Train Steps/Sec: 1.14
|
| 992 |
+
[[34m2025-10-28 22:36:35[0m] (step=0088700) Train Loss: 0.6031, Train Steps/Sec: 1.14
|
| 993 |
+
[[34m2025-10-28 22:38:03[0m] (step=0088800) Train Loss: 0.6040, Train Steps/Sec: 1.14
|
| 994 |
+
[[34m2025-10-28 22:38:22[0m] Beginning epoch 71...
|
| 995 |
+
[[34m2025-10-28 22:39:33[0m] (step=0088900) Train Loss: 0.6051, Train Steps/Sec: 1.10
|
| 996 |
+
[[34m2025-10-28 22:41:01[0m] (step=0089000) Train Loss: 0.6044, Train Steps/Sec: 1.14
|
| 997 |
+
[[34m2025-10-28 22:42:29[0m] (step=0089100) Train Loss: 0.6033, Train Steps/Sec: 1.14
|