Upload folder using huggingface_hub
Browse files- stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0025000.pt +3 -0
- stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0050000.pt +3 -0
- stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0075000.pt +3 -0
- stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0100000.pt +3 -0
- stage2/lightningdit-xl-dinov2-vit-b-bf16/log.txt +1105 -0
stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0025000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1000f0fcfb4a208a3a8af3b7c278b2f96282686a236b7f496ec4c5faeb87c908
|
| 3 |
+
size 19230431602
|
stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0050000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eff578b48d343e9e93a6fd80983bfd8c14fa282efa0d61bec63a14491a91836d
|
| 3 |
+
size 19230431602
|
stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0075000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d190330e94ceae9c0ad9eb5acb5b3330828c71758a6b68ed4c41b6a642ec0318
|
| 3 |
+
size 19230431602
|
stage2/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0100000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ccbeb08595d21ae4bf2c2ae5a9fefba0b76a6a94dd7747108bd1f316acb826a
|
| 3 |
+
size 19230431602
|
stage2/lightningdit-xl-dinov2-vit-b-bf16/log.txt
ADDED
|
@@ -0,0 +1,1105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[[34m2025-10-29 05:36:42[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-bf16
|
| 2 |
+
[[34m2025-10-29 05:36:44[0m] using MLP layer as FFN
|
| 3 |
+
[[34m2025-10-29 05:37:00[0m] Model Parameters: 1202.04M
|
| 4 |
+
[[34m2025-10-29 05:37:03[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/train)
|
| 5 |
+
[[34m2025-10-29 05:37:03[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 6 |
+
[[34m2025-10-29 05:37:03[0m] Precision mode: bf16
|
| 7 |
+
[[34m2025-10-29 05:37:03[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 8 |
+
[[34m2025-10-29 05:37:03[0m] Optimizer: ADAMW with lr=0.0002, betas=(0.9, 0.95), weight_decay=0.0, eps=1e-08
|
| 9 |
+
Scheduler: linear with warmup_steps=0, decay_end_steps=0, final_lr=0.0002
|
| 10 |
+
[[34m2025-10-29 05:37:03[0m] Training for 80 epochs...
|
| 11 |
+
[[34m2025-10-29 05:37:03[0m] Beginning epoch 0...
|
| 12 |
+
[[34m2025-10-29 05:37:09[0m] Generating EMA samples...
|
| 13 |
+
[[34m2025-10-29 05:37:37[0m] Generating EMA samples done.
|
| 14 |
+
[[34m2025-10-29 05:38:57[0m] (step=0000100) Train Loss: 1.6175, Train Steps/Sec: 0.88
|
| 15 |
+
[[34m2025-10-29 05:40:17[0m] (step=0000200) Train Loss: 1.2188, Train Steps/Sec: 1.24
|
| 16 |
+
[[34m2025-10-29 05:41:38[0m] (step=0000300) Train Loss: 1.0074, Train Steps/Sec: 1.24
|
| 17 |
+
[[34m2025-10-29 05:42:59[0m] (step=0000400) Train Loss: 0.8993, Train Steps/Sec: 1.24
|
| 18 |
+
[[34m2025-10-29 05:44:19[0m] (step=0000500) Train Loss: 0.8367, Train Steps/Sec: 1.24
|
| 19 |
+
[[34m2025-10-29 05:45:40[0m] (step=0000600) Train Loss: 0.7966, Train Steps/Sec: 1.24
|
| 20 |
+
[[34m2025-10-29 05:47:01[0m] (step=0000700) Train Loss: 0.7646, Train Steps/Sec: 1.24
|
| 21 |
+
[[34m2025-10-29 05:48:22[0m] (step=0000800) Train Loss: 0.7402, Train Steps/Sec: 1.24
|
| 22 |
+
[[34m2025-10-29 05:49:42[0m] (step=0000900) Train Loss: 0.7223, Train Steps/Sec: 1.24
|
| 23 |
+
[[34m2025-10-29 05:51:04[0m] (step=0001000) Train Loss: 0.7073, Train Steps/Sec: 1.23
|
| 24 |
+
[[34m2025-10-29 05:52:24[0m] (step=0001100) Train Loss: 0.6949, Train Steps/Sec: 1.24
|
| 25 |
+
[[34m2025-10-29 05:53:45[0m] (step=0001200) Train Loss: 0.6842, Train Steps/Sec: 1.24
|
| 26 |
+
[[34m2025-10-29 05:54:26[0m] Beginning epoch 1...
|
| 27 |
+
[[34m2025-10-29 05:55:08[0m] (step=0001300) Train Loss: 0.6755, Train Steps/Sec: 1.21
|
| 28 |
+
[[34m2025-10-29 05:56:28[0m] (step=0001400) Train Loss: 0.6679, Train Steps/Sec: 1.24
|
| 29 |
+
[[34m2025-10-29 05:57:49[0m] (step=0001500) Train Loss: 0.6589, Train Steps/Sec: 1.24
|
| 30 |
+
[[34m2025-10-29 05:59:10[0m] (step=0001600) Train Loss: 0.6533, Train Steps/Sec: 1.24
|
| 31 |
+
[[34m2025-10-29 06:00:31[0m] (step=0001700) Train Loss: 0.6480, Train Steps/Sec: 1.24
|
| 32 |
+
[[34m2025-10-29 06:01:51[0m] (step=0001800) Train Loss: 0.6431, Train Steps/Sec: 1.24
|
| 33 |
+
[[34m2025-10-29 06:03:12[0m] (step=0001900) Train Loss: 0.6386, Train Steps/Sec: 1.24
|
| 34 |
+
[[34m2025-10-29 06:04:33[0m] (step=0002000) Train Loss: 0.6349, Train Steps/Sec: 1.24
|
| 35 |
+
[[34m2025-10-29 06:05:54[0m] (step=0002100) Train Loss: 0.6292, Train Steps/Sec: 1.24
|
| 36 |
+
[[34m2025-10-29 06:07:14[0m] (step=0002200) Train Loss: 0.6266, Train Steps/Sec: 1.24
|
| 37 |
+
[[34m2025-10-29 06:08:35[0m] (step=0002300) Train Loss: 0.6230, Train Steps/Sec: 1.24
|
| 38 |
+
[[34m2025-10-29 06:09:56[0m] (step=0002400) Train Loss: 0.6207, Train Steps/Sec: 1.24
|
| 39 |
+
[[34m2025-10-29 06:11:17[0m] (step=0002500) Train Loss: 0.6161, Train Steps/Sec: 1.24
|
| 40 |
+
[[34m2025-10-29 06:11:19[0m] Beginning epoch 2...
|
| 41 |
+
[[34m2025-10-29 06:12:40[0m] (step=0002600) Train Loss: 0.6125, Train Steps/Sec: 1.20
|
| 42 |
+
[[34m2025-10-29 06:14:01[0m] (step=0002700) Train Loss: 0.6106, Train Steps/Sec: 1.24
|
| 43 |
+
[[34m2025-10-29 06:15:22[0m] (step=0002800) Train Loss: 0.6096, Train Steps/Sec: 1.24
|
| 44 |
+
[[34m2025-10-29 06:16:43[0m] (step=0002900) Train Loss: 0.6065, Train Steps/Sec: 1.24
|
| 45 |
+
[[34m2025-10-29 06:18:03[0m] (step=0003000) Train Loss: 0.6031, Train Steps/Sec: 1.24
|
| 46 |
+
[[34m2025-10-29 06:19:24[0m] (step=0003100) Train Loss: 0.6027, Train Steps/Sec: 1.24
|
| 47 |
+
[[34m2025-10-29 06:20:45[0m] (step=0003200) Train Loss: 0.6002, Train Steps/Sec: 1.24
|
| 48 |
+
[[34m2025-10-29 06:22:05[0m] (step=0003300) Train Loss: 0.5983, Train Steps/Sec: 1.24
|
| 49 |
+
[[34m2025-10-29 06:23:26[0m] (step=0003400) Train Loss: 0.5953, Train Steps/Sec: 1.24
|
| 50 |
+
[[34m2025-10-29 06:24:47[0m] (step=0003500) Train Loss: 0.5952, Train Steps/Sec: 1.24
|
| 51 |
+
[[34m2025-10-29 06:26:08[0m] (step=0003600) Train Loss: 0.5926, Train Steps/Sec: 1.24
|
| 52 |
+
[[34m2025-10-29 06:27:28[0m] (step=0003700) Train Loss: 0.5909, Train Steps/Sec: 1.24
|
| 53 |
+
[[34m2025-10-29 06:28:12[0m] Beginning epoch 3...
|
| 54 |
+
[[34m2025-10-29 06:28:51[0m] (step=0003800) Train Loss: 0.5897, Train Steps/Sec: 1.20
|
| 55 |
+
[[34m2025-10-29 06:30:12[0m] (step=0003900) Train Loss: 0.5872, Train Steps/Sec: 1.24
|
| 56 |
+
[[34m2025-10-29 06:31:33[0m] (step=0004000) Train Loss: 0.5865, Train Steps/Sec: 1.24
|
| 57 |
+
[[34m2025-10-29 06:32:53[0m] (step=0004100) Train Loss: 0.5865, Train Steps/Sec: 1.24
|
| 58 |
+
[[34m2025-10-29 06:34:14[0m] (step=0004200) Train Loss: 0.5842, Train Steps/Sec: 1.24
|
| 59 |
+
[[34m2025-10-29 06:35:35[0m] (step=0004300) Train Loss: 0.5824, Train Steps/Sec: 1.23
|
| 60 |
+
[[34m2025-10-29 06:36:56[0m] (step=0004400) Train Loss: 0.5808, Train Steps/Sec: 1.24
|
| 61 |
+
[[34m2025-10-29 06:38:17[0m] (step=0004500) Train Loss: 0.5804, Train Steps/Sec: 1.24
|
| 62 |
+
[[34m2025-10-29 06:39:37[0m] (step=0004600) Train Loss: 0.5791, Train Steps/Sec: 1.24
|
| 63 |
+
[[34m2025-10-29 06:40:58[0m] (step=0004700) Train Loss: 0.5782, Train Steps/Sec: 1.24
|
| 64 |
+
[[34m2025-10-29 06:42:19[0m] (step=0004800) Train Loss: 0.5766, Train Steps/Sec: 1.24
|
| 65 |
+
[[34m2025-10-29 06:43:40[0m] (step=0004900) Train Loss: 0.5752, Train Steps/Sec: 1.24
|
| 66 |
+
[[34m2025-10-29 06:45:00[0m] (step=0005000) Train Loss: 0.5752, Train Steps/Sec: 1.24
|
| 67 |
+
[[34m2025-10-29 06:45:04[0m] Beginning epoch 4...
|
| 68 |
+
[[34m2025-10-29 06:46:23[0m] (step=0005100) Train Loss: 0.5731, Train Steps/Sec: 1.21
|
| 69 |
+
[[34m2025-10-29 06:47:44[0m] (step=0005200) Train Loss: 0.5728, Train Steps/Sec: 1.24
|
| 70 |
+
[[34m2025-10-29 06:49:05[0m] (step=0005300) Train Loss: 0.5723, Train Steps/Sec: 1.24
|
| 71 |
+
[[34m2025-10-29 06:50:25[0m] (step=0005400) Train Loss: 0.5700, Train Steps/Sec: 1.24
|
| 72 |
+
[[34m2025-10-29 06:51:46[0m] (step=0005500) Train Loss: 0.5695, Train Steps/Sec: 1.24
|
| 73 |
+
[[34m2025-10-29 06:53:07[0m] (step=0005600) Train Loss: 0.5686, Train Steps/Sec: 1.24
|
| 74 |
+
[[34m2025-10-29 06:54:27[0m] (step=0005700) Train Loss: 0.5670, Train Steps/Sec: 1.24
|
| 75 |
+
[[34m2025-10-29 06:55:48[0m] (step=0005800) Train Loss: 0.5684, Train Steps/Sec: 1.24
|
| 76 |
+
[[34m2025-10-29 06:57:09[0m] (step=0005900) Train Loss: 0.5663, Train Steps/Sec: 1.24
|
| 77 |
+
[[34m2025-10-29 06:58:30[0m] (step=0006000) Train Loss: 0.5658, Train Steps/Sec: 1.23
|
| 78 |
+
[[34m2025-10-29 06:59:51[0m] (step=0006100) Train Loss: 0.5650, Train Steps/Sec: 1.24
|
| 79 |
+
[[34m2025-10-29 07:01:11[0m] (step=0006200) Train Loss: 0.5642, Train Steps/Sec: 1.24
|
| 80 |
+
[[34m2025-10-29 07:01:56[0m] Beginning epoch 5...
|
| 81 |
+
[[34m2025-10-29 07:02:35[0m] (step=0006300) Train Loss: 0.5636, Train Steps/Sec: 1.20
|
| 82 |
+
[[34m2025-10-29 07:03:55[0m] (step=0006400) Train Loss: 0.5617, Train Steps/Sec: 1.24
|
| 83 |
+
[[34m2025-10-29 07:05:16[0m] (step=0006500) Train Loss: 0.5601, Train Steps/Sec: 1.24
|
| 84 |
+
[[34m2025-10-29 07:06:37[0m] (step=0006600) Train Loss: 0.5609, Train Steps/Sec: 1.24
|
| 85 |
+
[[34m2025-10-29 07:07:57[0m] (step=0006700) Train Loss: 0.5600, Train Steps/Sec: 1.24
|
| 86 |
+
[[34m2025-10-29 07:09:18[0m] (step=0006800) Train Loss: 0.5588, Train Steps/Sec: 1.24
|
| 87 |
+
[[34m2025-10-29 07:10:39[0m] (step=0006900) Train Loss: 0.5591, Train Steps/Sec: 1.24
|
| 88 |
+
[[34m2025-10-29 07:11:59[0m] (step=0007000) Train Loss: 0.5591, Train Steps/Sec: 1.24
|
| 89 |
+
[[34m2025-10-29 07:13:20[0m] (step=0007100) Train Loss: 0.5578, Train Steps/Sec: 1.24
|
| 90 |
+
[[34m2025-10-29 07:14:41[0m] (step=0007200) Train Loss: 0.5574, Train Steps/Sec: 1.24
|
| 91 |
+
[[34m2025-10-29 07:16:02[0m] (step=0007300) Train Loss: 0.5549, Train Steps/Sec: 1.24
|
| 92 |
+
[[34m2025-10-29 07:17:22[0m] (step=0007400) Train Loss: 0.5566, Train Steps/Sec: 1.24
|
| 93 |
+
[[34m2025-10-29 07:18:43[0m] (step=0007500) Train Loss: 0.5547, Train Steps/Sec: 1.24
|
| 94 |
+
[[34m2025-10-29 07:18:48[0m] Beginning epoch 6...
|
| 95 |
+
[[34m2025-10-29 07:20:06[0m] (step=0007600) Train Loss: 0.5547, Train Steps/Sec: 1.20
|
| 96 |
+
[[34m2025-10-29 07:21:28[0m] (step=0007700) Train Loss: 0.5538, Train Steps/Sec: 1.23
|
| 97 |
+
[[34m2025-10-29 07:22:48[0m] (step=0007800) Train Loss: 0.5537, Train Steps/Sec: 1.24
|
| 98 |
+
[[34m2025-10-29 07:24:09[0m] (step=0007900) Train Loss: 0.5538, Train Steps/Sec: 1.24
|
| 99 |
+
[[34m2025-10-29 07:25:30[0m] (step=0008000) Train Loss: 0.5524, Train Steps/Sec: 1.24
|
| 100 |
+
[[34m2025-10-29 07:26:51[0m] (step=0008100) Train Loss: 0.5516, Train Steps/Sec: 1.24
|
| 101 |
+
[[34m2025-10-29 07:28:11[0m] (step=0008200) Train Loss: 0.5504, Train Steps/Sec: 1.24
|
| 102 |
+
[[34m2025-10-29 07:29:32[0m] (step=0008300) Train Loss: 0.5505, Train Steps/Sec: 1.24
|
| 103 |
+
[[34m2025-10-29 07:30:53[0m] (step=0008400) Train Loss: 0.5493, Train Steps/Sec: 1.24
|
| 104 |
+
[[34m2025-10-29 07:32:13[0m] (step=0008500) Train Loss: 0.5492, Train Steps/Sec: 1.24
|
| 105 |
+
[[34m2025-10-29 07:33:34[0m] (step=0008600) Train Loss: 0.5493, Train Steps/Sec: 1.24
|
| 106 |
+
[[34m2025-10-29 07:34:55[0m] (step=0008700) Train Loss: 0.5496, Train Steps/Sec: 1.24
|
| 107 |
+
[[34m2025-10-29 07:35:41[0m] Beginning epoch 7...
|
| 108 |
+
[[34m2025-10-29 07:36:18[0m] (step=0008800) Train Loss: 0.5484, Train Steps/Sec: 1.20
|
| 109 |
+
[[34m2025-10-29 07:37:39[0m] (step=0008900) Train Loss: 0.5473, Train Steps/Sec: 1.24
|
| 110 |
+
[[34m2025-10-29 07:38:59[0m] (step=0009000) Train Loss: 0.5460, Train Steps/Sec: 1.24
|
| 111 |
+
[[34m2025-10-29 07:40:20[0m] (step=0009100) Train Loss: 0.5468, Train Steps/Sec: 1.24
|
| 112 |
+
[[34m2025-10-29 07:41:41[0m] (step=0009200) Train Loss: 0.5471, Train Steps/Sec: 1.24
|
| 113 |
+
[[34m2025-10-29 07:43:02[0m] (step=0009300) Train Loss: 0.5462, Train Steps/Sec: 1.23
|
| 114 |
+
[[34m2025-10-29 07:44:23[0m] (step=0009400) Train Loss: 0.5463, Train Steps/Sec: 1.23
|
| 115 |
+
[[34m2025-10-29 07:45:44[0m] (step=0009500) Train Loss: 0.5444, Train Steps/Sec: 1.24
|
| 116 |
+
[[34m2025-10-29 07:47:05[0m] (step=0009600) Train Loss: 0.5439, Train Steps/Sec: 1.24
|
| 117 |
+
[[34m2025-10-29 07:48:25[0m] (step=0009700) Train Loss: 0.5447, Train Steps/Sec: 1.24
|
| 118 |
+
[[34m2025-10-29 07:49:46[0m] (step=0009800) Train Loss: 0.5435, Train Steps/Sec: 1.24
|
| 119 |
+
[[34m2025-10-29 07:51:07[0m] (step=0009900) Train Loss: 0.5439, Train Steps/Sec: 1.24
|
| 120 |
+
[[34m2025-10-29 07:52:27[0m] (step=0010000) Train Loss: 0.5426, Train Steps/Sec: 1.24
|
| 121 |
+
[[34m2025-10-29 07:52:34[0m] Beginning epoch 8...
|
| 122 |
+
[[34m2025-10-29 07:53:50[0m] (step=0010100) Train Loss: 0.5417, Train Steps/Sec: 1.21
|
| 123 |
+
[[34m2025-10-29 07:55:11[0m] (step=0010200) Train Loss: 0.5415, Train Steps/Sec: 1.24
|
| 124 |
+
[[34m2025-10-29 07:56:32[0m] (step=0010300) Train Loss: 0.5405, Train Steps/Sec: 1.24
|
| 125 |
+
[[34m2025-10-29 07:57:52[0m] (step=0010400) Train Loss: 0.5415, Train Steps/Sec: 1.24
|
| 126 |
+
[[34m2025-10-29 07:59:13[0m] (step=0010500) Train Loss: 0.5399, Train Steps/Sec: 1.24
|
| 127 |
+
[[34m2025-10-29 08:00:34[0m] (step=0010600) Train Loss: 0.5401, Train Steps/Sec: 1.24
|
| 128 |
+
[[34m2025-10-29 08:01:55[0m] (step=0010700) Train Loss: 0.5386, Train Steps/Sec: 1.24
|
| 129 |
+
[[34m2025-10-29 08:03:15[0m] (step=0010800) Train Loss: 0.5396, Train Steps/Sec: 1.24
|
| 130 |
+
[[34m2025-10-29 08:04:36[0m] (step=0010900) Train Loss: 0.5394, Train Steps/Sec: 1.24
|
| 131 |
+
[[34m2025-10-29 08:05:58[0m] (step=0011000) Train Loss: 0.5381, Train Steps/Sec: 1.23
|
| 132 |
+
[[34m2025-10-29 08:07:18[0m] (step=0011100) Train Loss: 0.5389, Train Steps/Sec: 1.24
|
| 133 |
+
[[34m2025-10-29 08:08:39[0m] (step=0011200) Train Loss: 0.5391, Train Steps/Sec: 1.24
|
| 134 |
+
[[34m2025-10-29 08:09:27[0m] Beginning epoch 9...
|
| 135 |
+
[[34m2025-10-29 08:10:02[0m] (step=0011300) Train Loss: 0.5372, Train Steps/Sec: 1.20
|
| 136 |
+
[[34m2025-10-29 08:11:23[0m] (step=0011400) Train Loss: 0.5380, Train Steps/Sec: 1.24
|
| 137 |
+
[[34m2025-10-29 08:12:44[0m] (step=0011500) Train Loss: 0.5365, Train Steps/Sec: 1.24
|
| 138 |
+
[[34m2025-10-29 08:14:04[0m] (step=0011600) Train Loss: 0.5358, Train Steps/Sec: 1.24
|
| 139 |
+
[[34m2025-10-29 08:15:25[0m] (step=0011700) Train Loss: 0.5369, Train Steps/Sec: 1.24
|
| 140 |
+
[[34m2025-10-29 08:16:46[0m] (step=0011800) Train Loss: 0.5358, Train Steps/Sec: 1.24
|
| 141 |
+
[[34m2025-10-29 08:18:06[0m] (step=0011900) Train Loss: 0.5360, Train Steps/Sec: 1.24
|
| 142 |
+
[[34m2025-10-29 08:19:27[0m] (step=0012000) Train Loss: 0.5345, Train Steps/Sec: 1.24
|
| 143 |
+
[[34m2025-10-29 08:20:48[0m] (step=0012100) Train Loss: 0.5347, Train Steps/Sec: 1.24
|
| 144 |
+
[[34m2025-10-29 08:22:09[0m] (step=0012200) Train Loss: 0.5348, Train Steps/Sec: 1.24
|
| 145 |
+
[[34m2025-10-29 08:23:29[0m] (step=0012300) Train Loss: 0.5329, Train Steps/Sec: 1.24
|
| 146 |
+
[[34m2025-10-29 08:24:50[0m] (step=0012400) Train Loss: 0.5334, Train Steps/Sec: 1.24
|
| 147 |
+
[[34m2025-10-29 08:26:11[0m] (step=0012500) Train Loss: 0.5334, Train Steps/Sec: 1.24
|
| 148 |
+
[[34m2025-10-29 08:26:19[0m] Beginning epoch 10...
|
| 149 |
+
[[34m2025-10-29 08:27:34[0m] (step=0012600) Train Loss: 0.5321, Train Steps/Sec: 1.20
|
| 150 |
+
[[34m2025-10-29 08:28:55[0m] (step=0012700) Train Loss: 0.5326, Train Steps/Sec: 1.23
|
| 151 |
+
[[34m2025-10-29 08:30:16[0m] (step=0012800) Train Loss: 0.5328, Train Steps/Sec: 1.24
|
| 152 |
+
[[34m2025-10-29 08:31:37[0m] (step=0012900) Train Loss: 0.5322, Train Steps/Sec: 1.24
|
| 153 |
+
[[34m2025-10-29 08:32:57[0m] (step=0013000) Train Loss: 0.5311, Train Steps/Sec: 1.24
|
| 154 |
+
[[34m2025-10-29 08:34:18[0m] (step=0013100) Train Loss: 0.5316, Train Steps/Sec: 1.24
|
| 155 |
+
[[34m2025-10-29 08:35:39[0m] (step=0013200) Train Loss: 0.5315, Train Steps/Sec: 1.24
|
| 156 |
+
[[34m2025-10-29 08:36:59[0m] (step=0013300) Train Loss: 0.5320, Train Steps/Sec: 1.24
|
| 157 |
+
[[34m2025-10-29 08:38:20[0m] (step=0013400) Train Loss: 0.5307, Train Steps/Sec: 1.24
|
| 158 |
+
[[34m2025-10-29 08:39:41[0m] (step=0013500) Train Loss: 0.5301, Train Steps/Sec: 1.24
|
| 159 |
+
[[34m2025-10-29 08:41:02[0m] (step=0013600) Train Loss: 0.5290, Train Steps/Sec: 1.24
|
| 160 |
+
[[34m2025-10-29 08:42:22[0m] (step=0013700) Train Loss: 0.5299, Train Steps/Sec: 1.24
|
| 161 |
+
[[34m2025-10-29 08:43:12[0m] Beginning epoch 11...
|
| 162 |
+
[[34m2025-10-29 08:43:45[0m] (step=0013800) Train Loss: 0.5288, Train Steps/Sec: 1.21
|
| 163 |
+
[[34m2025-10-29 08:45:06[0m] (step=0013900) Train Loss: 0.5289, Train Steps/Sec: 1.24
|
| 164 |
+
[[34m2025-10-29 08:46:26[0m] (step=0014000) Train Loss: 0.5277, Train Steps/Sec: 1.24
|
| 165 |
+
[[34m2025-10-29 08:47:47[0m] (step=0014100) Train Loss: 0.5288, Train Steps/Sec: 1.24
|
| 166 |
+
[[34m2025-10-29 08:49:08[0m] (step=0014200) Train Loss: 0.5289, Train Steps/Sec: 1.24
|
| 167 |
+
[[34m2025-10-29 08:50:28[0m] (step=0014300) Train Loss: 0.5272, Train Steps/Sec: 1.24
|
| 168 |
+
[[34m2025-10-29 08:51:50[0m] (step=0014400) Train Loss: 0.5271, Train Steps/Sec: 1.23
|
| 169 |
+
[[34m2025-10-29 08:53:10[0m] (step=0014500) Train Loss: 0.5260, Train Steps/Sec: 1.24
|
| 170 |
+
[[34m2025-10-29 08:54:31[0m] (step=0014600) Train Loss: 0.5267, Train Steps/Sec: 1.24
|
| 171 |
+
[[34m2025-10-29 08:55:52[0m] (step=0014700) Train Loss: 0.5279, Train Steps/Sec: 1.24
|
| 172 |
+
[[34m2025-10-29 08:57:12[0m] (step=0014800) Train Loss: 0.5260, Train Steps/Sec: 1.24
|
| 173 |
+
[[34m2025-10-29 08:58:33[0m] (step=0014900) Train Loss: 0.5250, Train Steps/Sec: 1.24
|
| 174 |
+
[[34m2025-10-29 08:59:54[0m] (step=0015000) Train Loss: 0.5270, Train Steps/Sec: 1.24
|
| 175 |
+
[[34m2025-10-29 09:00:04[0m] Beginning epoch 12...
|
| 176 |
+
[[34m2025-10-29 09:01:17[0m] (step=0015100) Train Loss: 0.5254, Train Steps/Sec: 1.20
|
| 177 |
+
[[34m2025-10-29 09:02:38[0m] (step=0015200) Train Loss: 0.5235, Train Steps/Sec: 1.24
|
| 178 |
+
[[34m2025-10-29 09:03:58[0m] (step=0015300) Train Loss: 0.5258, Train Steps/Sec: 1.24
|
| 179 |
+
[[34m2025-10-29 09:05:19[0m] (step=0015400) Train Loss: 0.5250, Train Steps/Sec: 1.24
|
| 180 |
+
[[34m2025-10-29 09:06:40[0m] (step=0015500) Train Loss: 0.5249, Train Steps/Sec: 1.24
|
| 181 |
+
[[34m2025-10-29 09:08:00[0m] (step=0015600) Train Loss: 0.5241, Train Steps/Sec: 1.24
|
| 182 |
+
[[34m2025-10-29 09:09:21[0m] (step=0015700) Train Loss: 0.5236, Train Steps/Sec: 1.24
|
| 183 |
+
[[34m2025-10-29 09:10:41[0m] (step=0015800) Train Loss: 0.5243, Train Steps/Sec: 1.24
|
| 184 |
+
[[34m2025-10-29 09:12:02[0m] (step=0015900) Train Loss: 0.5236, Train Steps/Sec: 1.24
|
| 185 |
+
[[34m2025-10-29 09:13:23[0m] (step=0016000) Train Loss: 0.5236, Train Steps/Sec: 1.23
|
| 186 |
+
[[34m2025-10-29 09:14:44[0m] (step=0016100) Train Loss: 0.5242, Train Steps/Sec: 1.24
|
| 187 |
+
[[34m2025-10-29 09:16:05[0m] (step=0016200) Train Loss: 0.5234, Train Steps/Sec: 1.24
|
| 188 |
+
[[34m2025-10-29 09:16:56[0m] Beginning epoch 13...
|
| 189 |
+
[[34m2025-10-29 09:17:28[0m] (step=0016300) Train Loss: 0.5214, Train Steps/Sec: 1.20
|
| 190 |
+
[[34m2025-10-29 09:18:49[0m] (step=0016400) Train Loss: 0.5216, Train Steps/Sec: 1.24
|
| 191 |
+
[[34m2025-10-29 09:20:09[0m] (step=0016500) Train Loss: 0.5206, Train Steps/Sec: 1.24
|
| 192 |
+
[[34m2025-10-29 09:21:30[0m] (step=0016600) Train Loss: 0.5212, Train Steps/Sec: 1.24
|
| 193 |
+
[[34m2025-10-29 09:22:51[0m] (step=0016700) Train Loss: 0.5227, Train Steps/Sec: 1.24
|
| 194 |
+
[[34m2025-10-29 09:24:11[0m] (step=0016800) Train Loss: 0.5215, Train Steps/Sec: 1.24
|
| 195 |
+
[[34m2025-10-29 09:25:32[0m] (step=0016900) Train Loss: 0.5210, Train Steps/Sec: 1.24
|
| 196 |
+
[[34m2025-10-29 09:26:53[0m] (step=0017000) Train Loss: 0.5197, Train Steps/Sec: 1.24
|
| 197 |
+
[[34m2025-10-29 09:28:13[0m] (step=0017100) Train Loss: 0.5215, Train Steps/Sec: 1.24
|
| 198 |
+
[[34m2025-10-29 09:29:34[0m] (step=0017200) Train Loss: 0.5207, Train Steps/Sec: 1.24
|
| 199 |
+
[[34m2025-10-29 09:30:55[0m] (step=0017300) Train Loss: 0.5196, Train Steps/Sec: 1.24
|
| 200 |
+
[[34m2025-10-29 09:32:15[0m] (step=0017400) Train Loss: 0.5195, Train Steps/Sec: 1.24
|
| 201 |
+
[[34m2025-10-29 09:33:36[0m] (step=0017500) Train Loss: 0.5203, Train Steps/Sec: 1.24
|
| 202 |
+
[[34m2025-10-29 09:33:48[0m] Beginning epoch 14...
|
| 203 |
+
[[34m2025-10-29 09:34:59[0m] (step=0017600) Train Loss: 0.5180, Train Steps/Sec: 1.20
|
| 204 |
+
[[34m2025-10-29 09:36:21[0m] (step=0017700) Train Loss: 0.5177, Train Steps/Sec: 1.23
|
| 205 |
+
[[34m2025-10-29 09:37:41[0m] (step=0017800) Train Loss: 0.5177, Train Steps/Sec: 1.24
|
| 206 |
+
[[34m2025-10-29 09:39:02[0m] (step=0017900) Train Loss: 0.5189, Train Steps/Sec: 1.24
|
| 207 |
+
[[34m2025-10-29 09:40:23[0m] (step=0018000) Train Loss: 0.5192, Train Steps/Sec: 1.24
|
| 208 |
+
[[34m2025-10-29 09:41:43[0m] (step=0018100) Train Loss: 0.5172, Train Steps/Sec: 1.24
|
| 209 |
+
[[34m2025-10-29 09:43:04[0m] (step=0018200) Train Loss: 0.5174, Train Steps/Sec: 1.24
|
| 210 |
+
[[34m2025-10-29 09:44:25[0m] (step=0018300) Train Loss: 0.5178, Train Steps/Sec: 1.24
|
| 211 |
+
[[34m2025-10-29 09:45:45[0m] (step=0018400) Train Loss: 0.5176, Train Steps/Sec: 1.24
|
| 212 |
+
[[34m2025-10-29 09:47:06[0m] (step=0018500) Train Loss: 0.5170, Train Steps/Sec: 1.24
|
| 213 |
+
[[34m2025-10-29 09:48:27[0m] (step=0018600) Train Loss: 0.5177, Train Steps/Sec: 1.24
|
| 214 |
+
[[34m2025-10-29 09:49:47[0m] (step=0018700) Train Loss: 0.5170, Train Steps/Sec: 1.24
|
| 215 |
+
[[34m2025-10-29 09:50:40[0m] Beginning epoch 15...
|
| 216 |
+
[[34m2025-10-29 09:51:11[0m] (step=0018800) Train Loss: 0.5169, Train Steps/Sec: 1.20
|
| 217 |
+
[[34m2025-10-29 09:52:31[0m] (step=0018900) Train Loss: 0.5158, Train Steps/Sec: 1.24
|
| 218 |
+
[[34m2025-10-29 09:53:52[0m] (step=0019000) Train Loss: 0.5138, Train Steps/Sec: 1.24
|
| 219 |
+
[[34m2025-10-29 09:55:13[0m] (step=0019100) Train Loss: 0.5151, Train Steps/Sec: 1.24
|
| 220 |
+
[[34m2025-10-29 09:56:34[0m] (step=0019200) Train Loss: 0.5151, Train Steps/Sec: 1.24
|
| 221 |
+
[[34m2025-10-29 09:57:54[0m] (step=0019300) Train Loss: 0.5155, Train Steps/Sec: 1.24
|
| 222 |
+
[[34m2025-10-29 09:59:16[0m] (step=0019400) Train Loss: 0.5156, Train Steps/Sec: 1.23
|
| 223 |
+
[[34m2025-10-29 10:00:36[0m] (step=0019500) Train Loss: 0.5152, Train Steps/Sec: 1.24
|
| 224 |
+
[[34m2025-10-29 10:01:57[0m] (step=0019600) Train Loss: 0.5160, Train Steps/Sec: 1.24
|
| 225 |
+
[[34m2025-10-29 10:03:18[0m] (step=0019700) Train Loss: 0.5146, Train Steps/Sec: 1.24
|
| 226 |
+
[[34m2025-10-29 10:04:38[0m] (step=0019800) Train Loss: 0.5141, Train Steps/Sec: 1.24
|
| 227 |
+
[[34m2025-10-29 10:05:59[0m] (step=0019900) Train Loss: 0.5139, Train Steps/Sec: 1.24
|
| 228 |
+
[[34m2025-10-29 10:07:20[0m] (step=0020000) Train Loss: 0.5142, Train Steps/Sec: 1.24
|
| 229 |
+
[[34m2025-10-29 10:07:33[0m] Beginning epoch 16...
|
| 230 |
+
[[34m2025-10-29 10:08:43[0m] (step=0020100) Train Loss: 0.5137, Train Steps/Sec: 1.20
|
| 231 |
+
[[34m2025-10-29 10:10:04[0m] (step=0020200) Train Loss: 0.5133, Train Steps/Sec: 1.24
|
| 232 |
+
[[34m2025-10-29 10:11:24[0m] (step=0020300) Train Loss: 0.5139, Train Steps/Sec: 1.24
|
| 233 |
+
[[34m2025-10-29 10:12:45[0m] (step=0020400) Train Loss: 0.5136, Train Steps/Sec: 1.24
|
| 234 |
+
[[34m2025-10-29 10:14:06[0m] (step=0020500) Train Loss: 0.5129, Train Steps/Sec: 1.24
|
| 235 |
+
[[34m2025-10-29 10:15:26[0m] (step=0020600) Train Loss: 0.5107, Train Steps/Sec: 1.24
|
| 236 |
+
[[34m2025-10-29 10:16:47[0m] (step=0020700) Train Loss: 0.5119, Train Steps/Sec: 1.24
|
| 237 |
+
[[34m2025-10-29 10:18:08[0m] (step=0020800) Train Loss: 0.5129, Train Steps/Sec: 1.24
|
| 238 |
+
[[34m2025-10-29 10:19:28[0m] (step=0020900) Train Loss: 0.5115, Train Steps/Sec: 1.24
|
| 239 |
+
[[34m2025-10-29 10:20:49[0m] (step=0021000) Train Loss: 0.5128, Train Steps/Sec: 1.24
|
| 240 |
+
[[34m2025-10-29 10:22:11[0m] (step=0021100) Train Loss: 0.5117, Train Steps/Sec: 1.23
|
| 241 |
+
[[34m2025-10-29 10:23:31[0m] (step=0021200) Train Loss: 0.5112, Train Steps/Sec: 1.24
|
| 242 |
+
[[34m2025-10-29 10:24:26[0m] Beginning epoch 17...
|
| 243 |
+
[[34m2025-10-29 10:24:54[0m] (step=0021300) Train Loss: 0.5115, Train Steps/Sec: 1.21
|
| 244 |
+
[[34m2025-10-29 10:26:15[0m] (step=0021400) Train Loss: 0.5117, Train Steps/Sec: 1.24
|
| 245 |
+
[[34m2025-10-29 10:27:35[0m] (step=0021500) Train Loss: 0.5101, Train Steps/Sec: 1.24
|
| 246 |
+
[[34m2025-10-29 10:28:56[0m] (step=0021600) Train Loss: 0.5106, Train Steps/Sec: 1.24
|
| 247 |
+
[[34m2025-10-29 10:30:17[0m] (step=0021700) Train Loss: 0.5116, Train Steps/Sec: 1.24
|
| 248 |
+
[[34m2025-10-29 10:31:37[0m] (step=0021800) Train Loss: 0.5101, Train Steps/Sec: 1.24
|
| 249 |
+
[[34m2025-10-29 10:32:58[0m] (step=0021900) Train Loss: 0.5098, Train Steps/Sec: 1.24
|
| 250 |
+
[[34m2025-10-29 10:34:19[0m] (step=0022000) Train Loss: 0.5099, Train Steps/Sec: 1.24
|
| 251 |
+
[[34m2025-10-29 10:35:40[0m] (step=0022100) Train Loss: 0.5094, Train Steps/Sec: 1.24
|
| 252 |
+
[[34m2025-10-29 10:37:00[0m] (step=0022200) Train Loss: 0.5096, Train Steps/Sec: 1.24
|
| 253 |
+
[[34m2025-10-29 10:38:21[0m] (step=0022300) Train Loss: 0.5109, Train Steps/Sec: 1.24
|
| 254 |
+
[[34m2025-10-29 10:39:42[0m] (step=0022400) Train Loss: 0.5094, Train Steps/Sec: 1.24
|
| 255 |
+
[[34m2025-10-29 10:41:02[0m] (step=0022500) Train Loss: 0.5084, Train Steps/Sec: 1.24
|
| 256 |
+
[[34m2025-10-29 10:41:17[0m] Beginning epoch 18...
|
| 257 |
+
[[34m2025-10-29 10:42:25[0m] (step=0022600) Train Loss: 0.5085, Train Steps/Sec: 1.20
|
| 258 |
+
[[34m2025-10-29 10:43:47[0m] (step=0022700) Train Loss: 0.5072, Train Steps/Sec: 1.23
|
| 259 |
+
[[34m2025-10-29 10:45:08[0m] (step=0022800) Train Loss: 0.5090, Train Steps/Sec: 1.24
|
| 260 |
+
[[34m2025-10-29 10:46:28[0m] (step=0022900) Train Loss: 0.5082, Train Steps/Sec: 1.24
|
| 261 |
+
[[34m2025-10-29 10:47:49[0m] (step=0023000) Train Loss: 0.5073, Train Steps/Sec: 1.24
|
| 262 |
+
[[34m2025-10-29 10:49:10[0m] (step=0023100) Train Loss: 0.5082, Train Steps/Sec: 1.24
|
| 263 |
+
[[34m2025-10-29 10:50:30[0m] (step=0023200) Train Loss: 0.5068, Train Steps/Sec: 1.24
|
| 264 |
+
[[34m2025-10-29 10:51:51[0m] (step=0023300) Train Loss: 0.5078, Train Steps/Sec: 1.24
|
| 265 |
+
[[34m2025-10-29 10:53:12[0m] (step=0023400) Train Loss: 0.5078, Train Steps/Sec: 1.24
|
| 266 |
+
[[34m2025-10-29 10:54:32[0m] (step=0023500) Train Loss: 0.5066, Train Steps/Sec: 1.24
|
| 267 |
+
[[34m2025-10-29 10:55:53[0m] (step=0023600) Train Loss: 0.5056, Train Steps/Sec: 1.24
|
| 268 |
+
[[34m2025-10-29 10:57:14[0m] (step=0023700) Train Loss: 0.5072, Train Steps/Sec: 1.24
|
| 269 |
+
[[34m2025-10-29 10:58:10[0m] Beginning epoch 19...
|
| 270 |
+
[[34m2025-10-29 10:58:37[0m] (step=0023800) Train Loss: 0.5067, Train Steps/Sec: 1.20
|
| 271 |
+
[[34m2025-10-29 10:59:58[0m] (step=0023900) Train Loss: 0.5070, Train Steps/Sec: 1.24
|
| 272 |
+
[[34m2025-10-29 11:01:18[0m] (step=0024000) Train Loss: 0.5066, Train Steps/Sec: 1.24
|
| 273 |
+
[[34m2025-10-29 11:02:39[0m] (step=0024100) Train Loss: 0.5069, Train Steps/Sec: 1.24
|
| 274 |
+
[[34m2025-10-29 11:04:00[0m] (step=0024200) Train Loss: 0.5052, Train Steps/Sec: 1.24
|
| 275 |
+
[[34m2025-10-29 11:05:20[0m] (step=0024300) Train Loss: 0.5059, Train Steps/Sec: 1.24
|
| 276 |
+
[[34m2025-10-29 11:06:42[0m] (step=0024400) Train Loss: 0.5049, Train Steps/Sec: 1.23
|
| 277 |
+
[[34m2025-10-29 11:08:02[0m] (step=0024500) Train Loss: 0.5056, Train Steps/Sec: 1.24
|
| 278 |
+
[[34m2025-10-29 11:09:23[0m] (step=0024600) Train Loss: 0.5055, Train Steps/Sec: 1.24
|
| 279 |
+
[[34m2025-10-29 11:10:44[0m] (step=0024700) Train Loss: 0.5053, Train Steps/Sec: 1.24
|
| 280 |
+
[[34m2025-10-29 11:12:05[0m] (step=0024800) Train Loss: 0.5060, Train Steps/Sec: 1.24
|
| 281 |
+
[[34m2025-10-29 11:13:25[0m] (step=0024900) Train Loss: 0.5050, Train Steps/Sec: 1.24
|
| 282 |
+
[[34m2025-10-29 11:14:46[0m] (step=0025000) Train Loss: 0.5049, Train Steps/Sec: 1.24
|
| 283 |
+
[[34m2025-10-29 11:15:42[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0025000.pt
|
| 284 |
+
[[34m2025-10-29 11:15:42[0m] Generating EMA samples...
|
| 285 |
+
[[34m2025-10-29 11:16:10[0m] Generating EMA samples done.
|
| 286 |
+
[[34m2025-10-29 11:16:27[0m] Beginning epoch 20...
|
| 287 |
+
[[34m2025-10-29 11:17:33[0m] (step=0025100) Train Loss: 0.5038, Train Steps/Sec: 0.60
|
| 288 |
+
[[34m2025-10-29 11:18:54[0m] (step=0025200) Train Loss: 0.5045, Train Steps/Sec: 1.24
|
| 289 |
+
[[34m2025-10-29 11:20:14[0m] (step=0025300) Train Loss: 0.5058, Train Steps/Sec: 1.24
|
| 290 |
+
[[34m2025-10-29 11:21:35[0m] (step=0025400) Train Loss: 0.5048, Train Steps/Sec: 1.24
|
| 291 |
+
[[34m2025-10-29 11:22:56[0m] (step=0025500) Train Loss: 0.5043, Train Steps/Sec: 1.24
|
| 292 |
+
[[34m2025-10-29 11:24:17[0m] (step=0025600) Train Loss: 0.5035, Train Steps/Sec: 1.24
|
| 293 |
+
[[34m2025-10-29 11:25:37[0m] (step=0025700) Train Loss: 0.5034, Train Steps/Sec: 1.24
|
| 294 |
+
[[34m2025-10-29 11:26:58[0m] (step=0025800) Train Loss: 0.5054, Train Steps/Sec: 1.24
|
| 295 |
+
[[34m2025-10-29 11:28:19[0m] (step=0025900) Train Loss: 0.5040, Train Steps/Sec: 1.24
|
| 296 |
+
[[34m2025-10-29 11:29:39[0m] (step=0026000) Train Loss: 0.5048, Train Steps/Sec: 1.24
|
| 297 |
+
[[34m2025-10-29 11:31:01[0m] (step=0026100) Train Loss: 0.5038, Train Steps/Sec: 1.23
|
| 298 |
+
[[34m2025-10-29 11:32:21[0m] (step=0026200) Train Loss: 0.5021, Train Steps/Sec: 1.24
|
| 299 |
+
[[34m2025-10-29 11:33:19[0m] Beginning epoch 21...
|
| 300 |
+
[[34m2025-10-29 11:33:44[0m] (step=0026300) Train Loss: 0.5028, Train Steps/Sec: 1.21
|
| 301 |
+
[[34m2025-10-29 11:35:05[0m] (step=0026400) Train Loss: 0.5022, Train Steps/Sec: 1.24
|
| 302 |
+
[[34m2025-10-29 11:36:26[0m] (step=0026500) Train Loss: 0.5019, Train Steps/Sec: 1.24
|
| 303 |
+
[[34m2025-10-29 11:37:46[0m] (step=0026600) Train Loss: 0.5037, Train Steps/Sec: 1.24
|
| 304 |
+
[[34m2025-10-29 11:39:07[0m] (step=0026700) Train Loss: 0.5021, Train Steps/Sec: 1.24
|
| 305 |
+
[[34m2025-10-29 11:40:28[0m] (step=0026800) Train Loss: 0.5019, Train Steps/Sec: 1.24
|
| 306 |
+
[[34m2025-10-29 11:41:48[0m] (step=0026900) Train Loss: 0.5034, Train Steps/Sec: 1.24
|
| 307 |
+
[[34m2025-10-29 11:43:09[0m] (step=0027000) Train Loss: 0.5037, Train Steps/Sec: 1.24
|
| 308 |
+
[[34m2025-10-29 11:44:30[0m] (step=0027100) Train Loss: 0.5021, Train Steps/Sec: 1.24
|
| 309 |
+
[[34m2025-10-29 11:45:50[0m] (step=0027200) Train Loss: 0.5024, Train Steps/Sec: 1.24
|
| 310 |
+
[[34m2025-10-29 11:47:11[0m] (step=0027300) Train Loss: 0.5021, Train Steps/Sec: 1.24
|
| 311 |
+
[[34m2025-10-29 11:48:32[0m] (step=0027400) Train Loss: 0.5023, Train Steps/Sec: 1.24
|
| 312 |
+
[[34m2025-10-29 11:49:52[0m] (step=0027500) Train Loss: 0.5006, Train Steps/Sec: 1.24
|
| 313 |
+
[[34m2025-10-29 11:50:11[0m] Beginning epoch 22...
|
| 314 |
+
[[34m2025-10-29 11:51:15[0m] (step=0027600) Train Loss: 0.5009, Train Steps/Sec: 1.20
|
| 315 |
+
[[34m2025-10-29 11:52:37[0m] (step=0027700) Train Loss: 0.4999, Train Steps/Sec: 1.23
|
| 316 |
+
[[34m2025-10-29 11:53:58[0m] (step=0027800) Train Loss: 0.5012, Train Steps/Sec: 1.24
|
| 317 |
+
[[34m2025-10-29 11:55:18[0m] (step=0027900) Train Loss: 0.5013, Train Steps/Sec: 1.24
|
| 318 |
+
[[34m2025-10-29 11:56:39[0m] (step=0028000) Train Loss: 0.5012, Train Steps/Sec: 1.24
|
| 319 |
+
[[34m2025-10-29 11:58:00[0m] (step=0028100) Train Loss: 0.4996, Train Steps/Sec: 1.24
|
| 320 |
+
[[34m2025-10-29 11:59:20[0m] (step=0028200) Train Loss: 0.5017, Train Steps/Sec: 1.24
|
| 321 |
+
[[34m2025-10-29 12:00:41[0m] (step=0028300) Train Loss: 0.5006, Train Steps/Sec: 1.24
|
| 322 |
+
[[34m2025-10-29 12:02:02[0m] (step=0028400) Train Loss: 0.5006, Train Steps/Sec: 1.24
|
| 323 |
+
[[34m2025-10-29 12:03:22[0m] (step=0028500) Train Loss: 0.5003, Train Steps/Sec: 1.24
|
| 324 |
+
[[34m2025-10-29 12:04:43[0m] (step=0028600) Train Loss: 0.5009, Train Steps/Sec: 1.24
|
| 325 |
+
[[34m2025-10-29 12:06:04[0m] (step=0028700) Train Loss: 0.5006, Train Steps/Sec: 1.24
|
| 326 |
+
[[34m2025-10-29 12:07:03[0m] Beginning epoch 23...
|
| 327 |
+
[[34m2025-10-29 12:07:27[0m] (step=0028800) Train Loss: 0.4997, Train Steps/Sec: 1.20
|
| 328 |
+
[[34m2025-10-29 12:08:48[0m] (step=0028900) Train Loss: 0.4998, Train Steps/Sec: 1.24
|
| 329 |
+
[[34m2025-10-29 12:10:08[0m] (step=0029000) Train Loss: 0.4995, Train Steps/Sec: 1.24
|
| 330 |
+
[[34m2025-10-29 12:11:29[0m] (step=0029100) Train Loss: 0.5003, Train Steps/Sec: 1.24
|
| 331 |
+
[[34m2025-10-29 12:12:50[0m] (step=0029200) Train Loss: 0.5004, Train Steps/Sec: 1.24
|
| 332 |
+
[[34m2025-10-29 12:14:10[0m] (step=0029300) Train Loss: 0.4988, Train Steps/Sec: 1.24
|
| 333 |
+
[[34m2025-10-29 12:15:32[0m] (step=0029400) Train Loss: 0.4975, Train Steps/Sec: 1.23
|
| 334 |
+
[[34m2025-10-29 12:16:52[0m] (step=0029500) Train Loss: 0.4975, Train Steps/Sec: 1.24
|
| 335 |
+
[[34m2025-10-29 12:18:13[0m] (step=0029600) Train Loss: 0.4993, Train Steps/Sec: 1.24
|
| 336 |
+
[[34m2025-10-29 12:19:34[0m] (step=0029700) Train Loss: 0.4994, Train Steps/Sec: 1.24
|
| 337 |
+
[[34m2025-10-29 12:20:54[0m] (step=0029800) Train Loss: 0.4992, Train Steps/Sec: 1.24
|
| 338 |
+
[[34m2025-10-29 12:22:15[0m] (step=0029900) Train Loss: 0.4994, Train Steps/Sec: 1.24
|
| 339 |
+
[[34m2025-10-29 12:23:36[0m] (step=0030000) Train Loss: 0.4990, Train Steps/Sec: 1.24
|
| 340 |
+
[[34m2025-10-29 12:23:56[0m] Beginning epoch 24...
|
| 341 |
+
[[34m2025-10-29 12:24:59[0m] (step=0030100) Train Loss: 0.4989, Train Steps/Sec: 1.20
|
| 342 |
+
[[34m2025-10-29 12:26:20[0m] (step=0030200) Train Loss: 0.4986, Train Steps/Sec: 1.24
|
| 343 |
+
[[34m2025-10-29 12:27:40[0m] (step=0030300) Train Loss: 0.4992, Train Steps/Sec: 1.24
|
| 344 |
+
[[34m2025-10-29 12:29:01[0m] (step=0030400) Train Loss: 0.4976, Train Steps/Sec: 1.24
|
| 345 |
+
[[34m2025-10-29 12:30:22[0m] (step=0030500) Train Loss: 0.4966, Train Steps/Sec: 1.24
|
| 346 |
+
[[34m2025-10-29 12:31:43[0m] (step=0030600) Train Loss: 0.4990, Train Steps/Sec: 1.24
|
| 347 |
+
[[34m2025-10-29 12:33:03[0m] (step=0030700) Train Loss: 0.4982, Train Steps/Sec: 1.24
|
| 348 |
+
[[34m2025-10-29 12:34:24[0m] (step=0030800) Train Loss: 0.4980, Train Steps/Sec: 1.24
|
| 349 |
+
[[34m2025-10-29 12:35:45[0m] (step=0030900) Train Loss: 0.4980, Train Steps/Sec: 1.24
|
| 350 |
+
[[34m2025-10-29 12:37:05[0m] (step=0031000) Train Loss: 0.4967, Train Steps/Sec: 1.24
|
| 351 |
+
[[34m2025-10-29 12:38:27[0m] (step=0031100) Train Loss: 0.4978, Train Steps/Sec: 1.23
|
| 352 |
+
[[34m2025-10-29 12:39:47[0m] (step=0031200) Train Loss: 0.4968, Train Steps/Sec: 1.24
|
| 353 |
+
[[34m2025-10-29 12:40:48[0m] Beginning epoch 25...
|
| 354 |
+
[[34m2025-10-29 12:41:10[0m] (step=0031300) Train Loss: 0.4969, Train Steps/Sec: 1.21
|
| 355 |
+
[[34m2025-10-29 12:42:31[0m] (step=0031400) Train Loss: 0.4975, Train Steps/Sec: 1.24
|
| 356 |
+
[[34m2025-10-29 12:43:52[0m] (step=0031500) Train Loss: 0.4969, Train Steps/Sec: 1.24
|
| 357 |
+
[[34m2025-10-29 12:45:12[0m] (step=0031600) Train Loss: 0.4968, Train Steps/Sec: 1.24
|
| 358 |
+
[[34m2025-10-29 12:46:33[0m] (step=0031700) Train Loss: 0.4970, Train Steps/Sec: 1.24
|
| 359 |
+
[[34m2025-10-29 12:47:54[0m] (step=0031800) Train Loss: 0.4962, Train Steps/Sec: 1.24
|
| 360 |
+
[[34m2025-10-29 12:49:14[0m] (step=0031900) Train Loss: 0.4951, Train Steps/Sec: 1.24
|
| 361 |
+
[[34m2025-10-29 12:50:35[0m] (step=0032000) Train Loss: 0.4959, Train Steps/Sec: 1.24
|
| 362 |
+
[[34m2025-10-29 12:51:56[0m] (step=0032100) Train Loss: 0.4964, Train Steps/Sec: 1.24
|
| 363 |
+
[[34m2025-10-29 12:53:16[0m] (step=0032200) Train Loss: 0.4973, Train Steps/Sec: 1.24
|
| 364 |
+
[[34m2025-10-29 12:54:37[0m] (step=0032300) Train Loss: 0.4972, Train Steps/Sec: 1.24
|
| 365 |
+
[[34m2025-10-29 12:55:58[0m] (step=0032400) Train Loss: 0.4959, Train Steps/Sec: 1.24
|
| 366 |
+
[[34m2025-10-29 12:57:18[0m] (step=0032500) Train Loss: 0.4966, Train Steps/Sec: 1.24
|
| 367 |
+
[[34m2025-10-29 12:57:40[0m] Beginning epoch 26...
|
| 368 |
+
[[34m2025-10-29 12:58:42[0m] (step=0032600) Train Loss: 0.4960, Train Steps/Sec: 1.20
|
| 369 |
+
[[34m2025-10-29 13:00:03[0m] (step=0032700) Train Loss: 0.4943, Train Steps/Sec: 1.24
|
| 370 |
+
[[34m2025-10-29 13:01:24[0m] (step=0032800) Train Loss: 0.4948, Train Steps/Sec: 1.23
|
| 371 |
+
[[34m2025-10-29 13:02:45[0m] (step=0032900) Train Loss: 0.4941, Train Steps/Sec: 1.24
|
| 372 |
+
[[34m2025-10-29 13:04:05[0m] (step=0033000) Train Loss: 0.4962, Train Steps/Sec: 1.24
|
| 373 |
+
[[34m2025-10-29 13:05:26[0m] (step=0033100) Train Loss: 0.4958, Train Steps/Sec: 1.24
|
| 374 |
+
[[34m2025-10-29 13:06:47[0m] (step=0033200) Train Loss: 0.4948, Train Steps/Sec: 1.24
|
| 375 |
+
[[34m2025-10-29 13:08:08[0m] (step=0033300) Train Loss: 0.4953, Train Steps/Sec: 1.24
|
| 376 |
+
[[34m2025-10-29 13:09:28[0m] (step=0033400) Train Loss: 0.4974, Train Steps/Sec: 1.24
|
| 377 |
+
[[34m2025-10-29 13:10:49[0m] (step=0033500) Train Loss: 0.4958, Train Steps/Sec: 1.24
|
| 378 |
+
[[34m2025-10-29 13:12:10[0m] (step=0033600) Train Loss: 0.4952, Train Steps/Sec: 1.24
|
| 379 |
+
[[34m2025-10-29 13:13:30[0m] (step=0033700) Train Loss: 0.4935, Train Steps/Sec: 1.24
|
| 380 |
+
[[34m2025-10-29 13:14:33[0m] Beginning epoch 27...
|
| 381 |
+
[[34m2025-10-29 13:14:53[0m] (step=0033800) Train Loss: 0.4944, Train Steps/Sec: 1.20
|
| 382 |
+
[[34m2025-10-29 13:16:14[0m] (step=0033900) Train Loss: 0.4947, Train Steps/Sec: 1.24
|
| 383 |
+
[[34m2025-10-29 13:17:35[0m] (step=0034000) Train Loss: 0.4940, Train Steps/Sec: 1.24
|
| 384 |
+
[[34m2025-10-29 13:18:55[0m] (step=0034100) Train Loss: 0.4942, Train Steps/Sec: 1.24
|
| 385 |
+
[[34m2025-10-29 13:20:16[0m] (step=0034200) Train Loss: 0.4949, Train Steps/Sec: 1.24
|
| 386 |
+
[[34m2025-10-29 13:21:37[0m] (step=0034300) Train Loss: 0.4935, Train Steps/Sec: 1.24
|
| 387 |
+
[[34m2025-10-29 13:22:58[0m] (step=0034400) Train Loss: 0.4933, Train Steps/Sec: 1.23
|
| 388 |
+
[[34m2025-10-29 13:24:19[0m] (step=0034500) Train Loss: 0.4930, Train Steps/Sec: 1.24
|
| 389 |
+
[[34m2025-10-29 13:25:40[0m] (step=0034600) Train Loss: 0.4945, Train Steps/Sec: 1.24
|
| 390 |
+
[[34m2025-10-29 13:27:00[0m] (step=0034700) Train Loss: 0.4944, Train Steps/Sec: 1.24
|
| 391 |
+
[[34m2025-10-29 13:28:21[0m] (step=0034800) Train Loss: 0.4941, Train Steps/Sec: 1.24
|
| 392 |
+
[[34m2025-10-29 13:29:42[0m] (step=0034900) Train Loss: 0.4935, Train Steps/Sec: 1.24
|
| 393 |
+
[[34m2025-10-29 13:31:02[0m] (step=0035000) Train Loss: 0.4937, Train Steps/Sec: 1.24
|
| 394 |
+
[[34m2025-10-29 13:31:25[0m] Beginning epoch 28...
|
| 395 |
+
[[34m2025-10-29 13:32:25[0m] (step=0035100) Train Loss: 0.4932, Train Steps/Sec: 1.20
|
| 396 |
+
[[34m2025-10-29 13:33:46[0m] (step=0035200) Train Loss: 0.4938, Train Steps/Sec: 1.24
|
| 397 |
+
[[34m2025-10-29 13:35:07[0m] (step=0035300) Train Loss: 0.4936, Train Steps/Sec: 1.24
|
| 398 |
+
[[34m2025-10-29 13:36:27[0m] (step=0035400) Train Loss: 0.4942, Train Steps/Sec: 1.24
|
| 399 |
+
[[34m2025-10-29 13:37:48[0m] (step=0035500) Train Loss: 0.4920, Train Steps/Sec: 1.24
|
| 400 |
+
[[34m2025-10-29 13:39:09[0m] (step=0035600) Train Loss: 0.4930, Train Steps/Sec: 1.24
|
| 401 |
+
[[34m2025-10-29 13:40:29[0m] (step=0035700) Train Loss: 0.4917, Train Steps/Sec: 1.24
|
| 402 |
+
[[34m2025-10-29 13:41:50[0m] (step=0035800) Train Loss: 0.4920, Train Steps/Sec: 1.24
|
| 403 |
+
[[34m2025-10-29 13:43:11[0m] (step=0035900) Train Loss: 0.4937, Train Steps/Sec: 1.24
|
| 404 |
+
[[34m2025-10-29 13:44:32[0m] (step=0036000) Train Loss: 0.4934, Train Steps/Sec: 1.24
|
| 405 |
+
[[34m2025-10-29 13:45:53[0m] (step=0036100) Train Loss: 0.4927, Train Steps/Sec: 1.23
|
| 406 |
+
[[34m2025-10-29 13:47:14[0m] (step=0036200) Train Loss: 0.4930, Train Steps/Sec: 1.24
|
| 407 |
+
[[34m2025-10-29 13:48:18[0m] Beginning epoch 29...
|
| 408 |
+
[[34m2025-10-29 13:48:37[0m] (step=0036300) Train Loss: 0.4931, Train Steps/Sec: 1.20
|
| 409 |
+
[[34m2025-10-29 13:49:58[0m] (step=0036400) Train Loss: 0.4925, Train Steps/Sec: 1.24
|
| 410 |
+
[[34m2025-10-29 13:51:18[0m] (step=0036500) Train Loss: 0.4912, Train Steps/Sec: 1.24
|
| 411 |
+
[[34m2025-10-29 13:52:39[0m] (step=0036600) Train Loss: 0.4916, Train Steps/Sec: 1.24
|
| 412 |
+
[[34m2025-10-29 13:54:00[0m] (step=0036700) Train Loss: 0.4923, Train Steps/Sec: 1.24
|
| 413 |
+
[[34m2025-10-29 13:55:20[0m] (step=0036800) Train Loss: 0.4931, Train Steps/Sec: 1.24
|
| 414 |
+
[[34m2025-10-29 13:56:41[0m] (step=0036900) Train Loss: 0.4926, Train Steps/Sec: 1.24
|
| 415 |
+
[[34m2025-10-29 13:58:02[0m] (step=0037000) Train Loss: 0.4924, Train Steps/Sec: 1.24
|
| 416 |
+
[[34m2025-10-29 13:59:22[0m] (step=0037100) Train Loss: 0.4919, Train Steps/Sec: 1.24
|
| 417 |
+
[[34m2025-10-29 14:00:43[0m] (step=0037200) Train Loss: 0.4913, Train Steps/Sec: 1.24
|
| 418 |
+
[[34m2025-10-29 14:02:04[0m] (step=0037300) Train Loss: 0.4921, Train Steps/Sec: 1.24
|
| 419 |
+
[[34m2025-10-29 14:03:24[0m] (step=0037400) Train Loss: 0.4905, Train Steps/Sec: 1.24
|
| 420 |
+
[[34m2025-10-29 14:04:45[0m] (step=0037500) Train Loss: 0.4914, Train Steps/Sec: 1.24
|
| 421 |
+
[[34m2025-10-29 14:05:10[0m] Beginning epoch 30...
|
| 422 |
+
[[34m2025-10-29 14:06:08[0m] (step=0037600) Train Loss: 0.4913, Train Steps/Sec: 1.20
|
| 423 |
+
[[34m2025-10-29 14:07:29[0m] (step=0037700) Train Loss: 0.4921, Train Steps/Sec: 1.24
|
| 424 |
+
[[34m2025-10-29 14:08:50[0m] (step=0037800) Train Loss: 0.4923, Train Steps/Sec: 1.23
|
| 425 |
+
[[34m2025-10-29 14:10:11[0m] (step=0037900) Train Loss: 0.4914, Train Steps/Sec: 1.24
|
| 426 |
+
[[34m2025-10-29 14:11:32[0m] (step=0038000) Train Loss: 0.4913, Train Steps/Sec: 1.24
|
| 427 |
+
[[34m2025-10-29 14:12:52[0m] (step=0038100) Train Loss: 0.4914, Train Steps/Sec: 1.24
|
| 428 |
+
[[34m2025-10-29 14:14:13[0m] (step=0038200) Train Loss: 0.4917, Train Steps/Sec: 1.24
|
| 429 |
+
[[34m2025-10-29 14:15:34[0m] (step=0038300) Train Loss: 0.4915, Train Steps/Sec: 1.24
|
| 430 |
+
[[34m2025-10-29 14:16:54[0m] (step=0038400) Train Loss: 0.4909, Train Steps/Sec: 1.24
|
| 431 |
+
[[34m2025-10-29 14:18:15[0m] (step=0038500) Train Loss: 0.4909, Train Steps/Sec: 1.24
|
| 432 |
+
[[34m2025-10-29 14:19:36[0m] (step=0038600) Train Loss: 0.4893, Train Steps/Sec: 1.24
|
| 433 |
+
[[34m2025-10-29 14:20:57[0m] (step=0038700) Train Loss: 0.4919, Train Steps/Sec: 1.24
|
| 434 |
+
[[34m2025-10-29 14:22:02[0m] Beginning epoch 31...
|
| 435 |
+
[[34m2025-10-29 14:22:20[0m] (step=0038800) Train Loss: 0.4919, Train Steps/Sec: 1.20
|
| 436 |
+
[[34m2025-10-29 14:23:41[0m] (step=0038900) Train Loss: 0.4913, Train Steps/Sec: 1.24
|
| 437 |
+
[[34m2025-10-29 14:25:01[0m] (step=0039000) Train Loss: 0.4893, Train Steps/Sec: 1.24
|
| 438 |
+
[[34m2025-10-29 14:26:22[0m] (step=0039100) Train Loss: 0.4906, Train Steps/Sec: 1.24
|
| 439 |
+
[[34m2025-10-29 14:27:43[0m] (step=0039200) Train Loss: 0.4898, Train Steps/Sec: 1.24
|
| 440 |
+
[[34m2025-10-29 14:29:03[0m] (step=0039300) Train Loss: 0.4909, Train Steps/Sec: 1.24
|
| 441 |
+
[[34m2025-10-29 14:30:24[0m] (step=0039400) Train Loss: 0.4896, Train Steps/Sec: 1.24
|
| 442 |
+
[[34m2025-10-29 14:31:46[0m] (step=0039500) Train Loss: 0.4894, Train Steps/Sec: 1.23
|
| 443 |
+
[[34m2025-10-29 14:33:06[0m] (step=0039600) Train Loss: 0.4893, Train Steps/Sec: 1.24
|
| 444 |
+
[[34m2025-10-29 14:34:27[0m] (step=0039700) Train Loss: 0.4906, Train Steps/Sec: 1.24
|
| 445 |
+
[[34m2025-10-29 14:35:48[0m] (step=0039800) Train Loss: 0.4898, Train Steps/Sec: 1.24
|
| 446 |
+
[[34m2025-10-29 14:37:08[0m] (step=0039900) Train Loss: 0.4913, Train Steps/Sec: 1.24
|
| 447 |
+
[[34m2025-10-29 14:38:29[0m] (step=0040000) Train Loss: 0.4897, Train Steps/Sec: 1.24
|
| 448 |
+
[[34m2025-10-29 14:38:55[0m] Beginning epoch 32...
|
| 449 |
+
[[34m2025-10-29 14:39:52[0m] (step=0040100) Train Loss: 0.4889, Train Steps/Sec: 1.20
|
| 450 |
+
[[34m2025-10-29 14:41:13[0m] (step=0040200) Train Loss: 0.4904, Train Steps/Sec: 1.24
|
| 451 |
+
[[34m2025-10-29 14:42:34[0m] (step=0040300) Train Loss: 0.4899, Train Steps/Sec: 1.24
|
| 452 |
+
[[34m2025-10-29 14:43:54[0m] (step=0040400) Train Loss: 0.4899, Train Steps/Sec: 1.24
|
| 453 |
+
[[34m2025-10-29 14:45:15[0m] (step=0040500) Train Loss: 0.4877, Train Steps/Sec: 1.24
|
| 454 |
+
[[34m2025-10-29 14:46:36[0m] (step=0040600) Train Loss: 0.4895, Train Steps/Sec: 1.24
|
| 455 |
+
[[34m2025-10-29 14:47:57[0m] (step=0040700) Train Loss: 0.4908, Train Steps/Sec: 1.24
|
| 456 |
+
[[34m2025-10-29 14:49:17[0m] (step=0040800) Train Loss: 0.4885, Train Steps/Sec: 1.24
|
| 457 |
+
[[34m2025-10-29 14:50:38[0m] (step=0040900) Train Loss: 0.4878, Train Steps/Sec: 1.24
|
| 458 |
+
[[34m2025-10-29 14:51:59[0m] (step=0041000) Train Loss: 0.4889, Train Steps/Sec: 1.24
|
| 459 |
+
[[34m2025-10-29 14:53:20[0m] (step=0041100) Train Loss: 0.4880, Train Steps/Sec: 1.23
|
| 460 |
+
[[34m2025-10-29 14:54:41[0m] (step=0041200) Train Loss: 0.4877, Train Steps/Sec: 1.24
|
| 461 |
+
[[34m2025-10-29 14:55:49[0m] Beginning epoch 33...
|
| 462 |
+
[[34m2025-10-29 14:56:04[0m] (step=0041300) Train Loss: 0.4887, Train Steps/Sec: 1.20
|
| 463 |
+
[[34m2025-10-29 14:57:25[0m] (step=0041400) Train Loss: 0.4882, Train Steps/Sec: 1.24
|
| 464 |
+
[[34m2025-10-29 14:58:45[0m] (step=0041500) Train Loss: 0.4877, Train Steps/Sec: 1.24
|
| 465 |
+
[[34m2025-10-29 15:00:06[0m] (step=0041600) Train Loss: 0.4887, Train Steps/Sec: 1.24
|
| 466 |
+
[[34m2025-10-29 15:01:27[0m] (step=0041700) Train Loss: 0.4874, Train Steps/Sec: 1.24
|
| 467 |
+
[[34m2025-10-29 15:02:48[0m] (step=0041800) Train Loss: 0.4876, Train Steps/Sec: 1.24
|
| 468 |
+
[[34m2025-10-29 15:04:08[0m] (step=0041900) Train Loss: 0.4896, Train Steps/Sec: 1.24
|
| 469 |
+
[[34m2025-10-29 15:05:29[0m] (step=0042000) Train Loss: 0.4876, Train Steps/Sec: 1.24
|
| 470 |
+
[[34m2025-10-29 15:06:50[0m] (step=0042100) Train Loss: 0.4886, Train Steps/Sec: 1.24
|
| 471 |
+
[[34m2025-10-29 15:08:10[0m] (step=0042200) Train Loss: 0.4876, Train Steps/Sec: 1.24
|
| 472 |
+
[[34m2025-10-29 15:09:31[0m] (step=0042300) Train Loss: 0.4879, Train Steps/Sec: 1.24
|
| 473 |
+
[[34m2025-10-29 15:10:52[0m] (step=0042400) Train Loss: 0.4870, Train Steps/Sec: 1.24
|
| 474 |
+
[[34m2025-10-29 15:12:12[0m] (step=0042500) Train Loss: 0.4865, Train Steps/Sec: 1.24
|
| 475 |
+
[[34m2025-10-29 15:12:40[0m] Beginning epoch 34...
|
| 476 |
+
[[34m2025-10-29 15:13:36[0m] (step=0042600) Train Loss: 0.4880, Train Steps/Sec: 1.20
|
| 477 |
+
[[34m2025-10-29 15:14:56[0m] (step=0042700) Train Loss: 0.4879, Train Steps/Sec: 1.24
|
| 478 |
+
[[34m2025-10-29 15:16:18[0m] (step=0042800) Train Loss: 0.4884, Train Steps/Sec: 1.23
|
| 479 |
+
[[34m2025-10-29 15:17:39[0m] (step=0042900) Train Loss: 0.4879, Train Steps/Sec: 1.24
|
| 480 |
+
[[34m2025-10-29 15:18:59[0m] (step=0043000) Train Loss: 0.4883, Train Steps/Sec: 1.24
|
| 481 |
+
[[34m2025-10-29 15:20:20[0m] (step=0043100) Train Loss: 0.4860, Train Steps/Sec: 1.24
|
| 482 |
+
[[34m2025-10-29 15:21:41[0m] (step=0043200) Train Loss: 0.4882, Train Steps/Sec: 1.24
|
| 483 |
+
[[34m2025-10-29 15:23:01[0m] (step=0043300) Train Loss: 0.4874, Train Steps/Sec: 1.24
|
| 484 |
+
[[34m2025-10-29 15:24:22[0m] (step=0043400) Train Loss: 0.4880, Train Steps/Sec: 1.24
|
| 485 |
+
[[34m2025-10-29 15:25:43[0m] (step=0043500) Train Loss: 0.4873, Train Steps/Sec: 1.24
|
| 486 |
+
[[34m2025-10-29 15:27:03[0m] (step=0043600) Train Loss: 0.4873, Train Steps/Sec: 1.24
|
| 487 |
+
[[34m2025-10-29 15:28:24[0m] (step=0043700) Train Loss: 0.4871, Train Steps/Sec: 1.24
|
| 488 |
+
[[34m2025-10-29 15:29:33[0m] Beginning epoch 35...
|
| 489 |
+
[[34m2025-10-29 15:29:47[0m] (step=0043800) Train Loss: 0.4875, Train Steps/Sec: 1.21
|
| 490 |
+
[[34m2025-10-29 15:31:08[0m] (step=0043900) Train Loss: 0.4863, Train Steps/Sec: 1.24
|
| 491 |
+
[[34m2025-10-29 15:32:28[0m] (step=0044000) Train Loss: 0.4863, Train Steps/Sec: 1.24
|
| 492 |
+
[[34m2025-10-29 15:33:49[0m] (step=0044100) Train Loss: 0.4869, Train Steps/Sec: 1.24
|
| 493 |
+
[[34m2025-10-29 15:35:10[0m] (step=0044200) Train Loss: 0.4871, Train Steps/Sec: 1.24
|
| 494 |
+
[[34m2025-10-29 15:36:30[0m] (step=0044300) Train Loss: 0.4873, Train Steps/Sec: 1.24
|
| 495 |
+
[[34m2025-10-29 15:37:51[0m] (step=0044400) Train Loss: 0.4858, Train Steps/Sec: 1.24
|
| 496 |
+
[[34m2025-10-29 15:39:13[0m] (step=0044500) Train Loss: 0.4868, Train Steps/Sec: 1.23
|
| 497 |
+
[[34m2025-10-29 15:40:33[0m] (step=0044600) Train Loss: 0.4862, Train Steps/Sec: 1.24
|
| 498 |
+
[[34m2025-10-29 15:41:54[0m] (step=0044700) Train Loss: 0.4884, Train Steps/Sec: 1.24
|
| 499 |
+
[[34m2025-10-29 15:43:15[0m] (step=0044800) Train Loss: 0.4869, Train Steps/Sec: 1.24
|
| 500 |
+
[[34m2025-10-29 15:44:35[0m] (step=0044900) Train Loss: 0.4859, Train Steps/Sec: 1.24
|
| 501 |
+
[[34m2025-10-29 15:45:56[0m] (step=0045000) Train Loss: 0.4868, Train Steps/Sec: 1.24
|
| 502 |
+
[[34m2025-10-29 15:46:25[0m] Beginning epoch 36...
|
| 503 |
+
[[34m2025-10-29 15:47:19[0m] (step=0045100) Train Loss: 0.4871, Train Steps/Sec: 1.20
|
| 504 |
+
[[34m2025-10-29 15:48:40[0m] (step=0045200) Train Loss: 0.4859, Train Steps/Sec: 1.24
|
| 505 |
+
[[34m2025-10-29 15:50:00[0m] (step=0045300) Train Loss: 0.4849, Train Steps/Sec: 1.24
|
| 506 |
+
[[34m2025-10-29 15:51:21[0m] (step=0045400) Train Loss: 0.4870, Train Steps/Sec: 1.24
|
| 507 |
+
[[34m2025-10-29 15:52:42[0m] (step=0045500) Train Loss: 0.4867, Train Steps/Sec: 1.24
|
| 508 |
+
[[34m2025-10-29 15:54:02[0m] (step=0045600) Train Loss: 0.4856, Train Steps/Sec: 1.24
|
| 509 |
+
[[34m2025-10-29 15:55:23[0m] (step=0045700) Train Loss: 0.4862, Train Steps/Sec: 1.24
|
| 510 |
+
[[34m2025-10-29 15:56:44[0m] (step=0045800) Train Loss: 0.4862, Train Steps/Sec: 1.24
|
| 511 |
+
[[34m2025-10-29 15:58:04[0m] (step=0045900) Train Loss: 0.4847, Train Steps/Sec: 1.24
|
| 512 |
+
[[34m2025-10-29 15:59:25[0m] (step=0046000) Train Loss: 0.4847, Train Steps/Sec: 1.24
|
| 513 |
+
[[34m2025-10-29 16:00:46[0m] (step=0046100) Train Loss: 0.4846, Train Steps/Sec: 1.24
|
| 514 |
+
[[34m2025-10-29 16:02:07[0m] (step=0046200) Train Loss: 0.4867, Train Steps/Sec: 1.23
|
| 515 |
+
[[34m2025-10-29 16:03:18[0m] Beginning epoch 37...
|
| 516 |
+
[[34m2025-10-29 16:03:30[0m] (step=0046300) Train Loss: 0.4863, Train Steps/Sec: 1.20
|
| 517 |
+
[[34m2025-10-29 16:04:51[0m] (step=0046400) Train Loss: 0.4865, Train Steps/Sec: 1.24
|
| 518 |
+
[[34m2025-10-29 16:06:12[0m] (step=0046500) Train Loss: 0.4842, Train Steps/Sec: 1.24
|
| 519 |
+
[[34m2025-10-29 16:07:32[0m] (step=0046600) Train Loss: 0.4837, Train Steps/Sec: 1.24
|
| 520 |
+
[[34m2025-10-29 16:08:53[0m] (step=0046700) Train Loss: 0.4851, Train Steps/Sec: 1.24
|
| 521 |
+
[[34m2025-10-29 16:10:14[0m] (step=0046800) Train Loss: 0.4851, Train Steps/Sec: 1.24
|
| 522 |
+
[[34m2025-10-29 16:11:34[0m] (step=0046900) Train Loss: 0.4855, Train Steps/Sec: 1.24
|
| 523 |
+
[[34m2025-10-29 16:12:55[0m] (step=0047000) Train Loss: 0.4844, Train Steps/Sec: 1.24
|
| 524 |
+
[[34m2025-10-29 16:14:16[0m] (step=0047100) Train Loss: 0.4851, Train Steps/Sec: 1.24
|
| 525 |
+
[[34m2025-10-29 16:15:36[0m] (step=0047200) Train Loss: 0.4860, Train Steps/Sec: 1.24
|
| 526 |
+
[[34m2025-10-29 16:16:57[0m] (step=0047300) Train Loss: 0.4853, Train Steps/Sec: 1.24
|
| 527 |
+
[[34m2025-10-29 16:18:18[0m] (step=0047400) Train Loss: 0.4852, Train Steps/Sec: 1.24
|
| 528 |
+
[[34m2025-10-29 16:19:38[0m] (step=0047500) Train Loss: 0.4855, Train Steps/Sec: 1.24
|
| 529 |
+
[[34m2025-10-29 16:20:10[0m] Beginning epoch 38...
|
| 530 |
+
[[34m2025-10-29 16:21:01[0m] (step=0047600) Train Loss: 0.4837, Train Steps/Sec: 1.21
|
| 531 |
+
[[34m2025-10-29 16:22:22[0m] (step=0047700) Train Loss: 0.4849, Train Steps/Sec: 1.24
|
| 532 |
+
[[34m2025-10-29 16:23:44[0m] (step=0047800) Train Loss: 0.4835, Train Steps/Sec: 1.23
|
| 533 |
+
[[34m2025-10-29 16:25:04[0m] (step=0047900) Train Loss: 0.4849, Train Steps/Sec: 1.24
|
| 534 |
+
[[34m2025-10-29 16:26:25[0m] (step=0048000) Train Loss: 0.4848, Train Steps/Sec: 1.24
|
| 535 |
+
[[34m2025-10-29 16:27:46[0m] (step=0048100) Train Loss: 0.4859, Train Steps/Sec: 1.24
|
| 536 |
+
[[34m2025-10-29 16:29:06[0m] (step=0048200) Train Loss: 0.4864, Train Steps/Sec: 1.24
|
| 537 |
+
[[34m2025-10-29 16:30:27[0m] (step=0048300) Train Loss: 0.4838, Train Steps/Sec: 1.24
|
| 538 |
+
[[34m2025-10-29 16:31:48[0m] (step=0048400) Train Loss: 0.4855, Train Steps/Sec: 1.24
|
| 539 |
+
[[34m2025-10-29 16:33:08[0m] (step=0048500) Train Loss: 0.4840, Train Steps/Sec: 1.24
|
| 540 |
+
[[34m2025-10-29 16:34:29[0m] (step=0048600) Train Loss: 0.4845, Train Steps/Sec: 1.24
|
| 541 |
+
[[34m2025-10-29 16:35:49[0m] (step=0048700) Train Loss: 0.4851, Train Steps/Sec: 1.24
|
| 542 |
+
[[34m2025-10-29 16:37:02[0m] Beginning epoch 39...
|
| 543 |
+
[[34m2025-10-29 16:37:13[0m] (step=0048800) Train Loss: 0.4837, Train Steps/Sec: 1.20
|
| 544 |
+
[[34m2025-10-29 16:38:34[0m] (step=0048900) Train Loss: 0.4814, Train Steps/Sec: 1.24
|
| 545 |
+
[[34m2025-10-29 16:39:54[0m] (step=0049000) Train Loss: 0.4831, Train Steps/Sec: 1.24
|
| 546 |
+
[[34m2025-10-29 16:41:15[0m] (step=0049100) Train Loss: 0.4833, Train Steps/Sec: 1.24
|
| 547 |
+
[[34m2025-10-29 16:42:35[0m] (step=0049200) Train Loss: 0.4848, Train Steps/Sec: 1.24
|
| 548 |
+
[[34m2025-10-29 16:43:56[0m] (step=0049300) Train Loss: 0.4831, Train Steps/Sec: 1.24
|
| 549 |
+
[[34m2025-10-29 16:45:17[0m] (step=0049400) Train Loss: 0.4837, Train Steps/Sec: 1.24
|
| 550 |
+
[[34m2025-10-29 16:46:38[0m] (step=0049500) Train Loss: 0.4832, Train Steps/Sec: 1.23
|
| 551 |
+
[[34m2025-10-29 16:47:59[0m] (step=0049600) Train Loss: 0.4830, Train Steps/Sec: 1.24
|
| 552 |
+
[[34m2025-10-29 16:49:20[0m] (step=0049700) Train Loss: 0.4837, Train Steps/Sec: 1.24
|
| 553 |
+
[[34m2025-10-29 16:50:40[0m] (step=0049800) Train Loss: 0.4827, Train Steps/Sec: 1.24
|
| 554 |
+
[[34m2025-10-29 16:52:01[0m] (step=0049900) Train Loss: 0.4833, Train Steps/Sec: 1.24
|
| 555 |
+
[[34m2025-10-29 16:53:22[0m] (step=0050000) Train Loss: 0.4846, Train Steps/Sec: 1.24
|
| 556 |
+
[[34m2025-10-29 16:54:19[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0050000.pt
|
| 557 |
+
[[34m2025-10-29 16:54:19[0m] Generating EMA samples...
|
| 558 |
+
[[34m2025-10-29 16:54:47[0m] Generating EMA samples done.
|
| 559 |
+
[[34m2025-10-29 16:55:20[0m] Beginning epoch 40...
|
| 560 |
+
[[34m2025-10-29 16:56:10[0m] (step=0050100) Train Loss: 0.4833, Train Steps/Sec: 0.60
|
| 561 |
+
[[34m2025-10-29 16:57:30[0m] (step=0050200) Train Loss: 0.4833, Train Steps/Sec: 1.24
|
| 562 |
+
[[34m2025-10-29 16:58:51[0m] (step=0050300) Train Loss: 0.4835, Train Steps/Sec: 1.24
|
| 563 |
+
[[34m2025-10-29 17:00:12[0m] (step=0050400) Train Loss: 0.4849, Train Steps/Sec: 1.24
|
| 564 |
+
[[34m2025-10-29 17:01:33[0m] (step=0050500) Train Loss: 0.4835, Train Steps/Sec: 1.24
|
| 565 |
+
[[34m2025-10-29 17:02:53[0m] (step=0050600) Train Loss: 0.4820, Train Steps/Sec: 1.24
|
| 566 |
+
[[34m2025-10-29 17:04:14[0m] (step=0050700) Train Loss: 0.4831, Train Steps/Sec: 1.24
|
| 567 |
+
[[34m2025-10-29 17:05:34[0m] (step=0050800) Train Loss: 0.4844, Train Steps/Sec: 1.24
|
| 568 |
+
[[34m2025-10-29 17:06:55[0m] (step=0050900) Train Loss: 0.4846, Train Steps/Sec: 1.24
|
| 569 |
+
[[34m2025-10-29 17:08:16[0m] (step=0051000) Train Loss: 0.4835, Train Steps/Sec: 1.24
|
| 570 |
+
[[34m2025-10-29 17:09:36[0m] (step=0051100) Train Loss: 0.4841, Train Steps/Sec: 1.24
|
| 571 |
+
[[34m2025-10-29 17:10:58[0m] (step=0051200) Train Loss: 0.4833, Train Steps/Sec: 1.22
|
| 572 |
+
[[34m2025-10-29 17:12:12[0m] Beginning epoch 41...
|
| 573 |
+
[[34m2025-10-29 17:12:21[0m] (step=0051300) Train Loss: 0.4823, Train Steps/Sec: 1.21
|
| 574 |
+
[[34m2025-10-29 17:13:42[0m] (step=0051400) Train Loss: 0.4824, Train Steps/Sec: 1.24
|
| 575 |
+
[[34m2025-10-29 17:15:02[0m] (step=0051500) Train Loss: 0.4825, Train Steps/Sec: 1.24
|
| 576 |
+
[[34m2025-10-29 17:16:23[0m] (step=0051600) Train Loss: 0.4830, Train Steps/Sec: 1.24
|
| 577 |
+
[[34m2025-10-29 17:17:44[0m] (step=0051700) Train Loss: 0.4824, Train Steps/Sec: 1.24
|
| 578 |
+
[[34m2025-10-29 17:19:04[0m] (step=0051800) Train Loss: 0.4834, Train Steps/Sec: 1.24
|
| 579 |
+
[[34m2025-10-29 17:20:25[0m] (step=0051900) Train Loss: 0.4823, Train Steps/Sec: 1.24
|
| 580 |
+
[[34m2025-10-29 17:21:46[0m] (step=0052000) Train Loss: 0.4824, Train Steps/Sec: 1.24
|
| 581 |
+
[[34m2025-10-29 17:23:07[0m] (step=0052100) Train Loss: 0.4827, Train Steps/Sec: 1.24
|
| 582 |
+
[[34m2025-10-29 17:24:27[0m] (step=0052200) Train Loss: 0.4831, Train Steps/Sec: 1.24
|
| 583 |
+
[[34m2025-10-29 17:25:48[0m] (step=0052300) Train Loss: 0.4828, Train Steps/Sec: 1.24
|
| 584 |
+
[[34m2025-10-29 17:27:09[0m] (step=0052400) Train Loss: 0.4825, Train Steps/Sec: 1.24
|
| 585 |
+
[[34m2025-10-29 17:28:29[0m] (step=0052500) Train Loss: 0.4824, Train Steps/Sec: 1.24
|
| 586 |
+
[[34m2025-10-29 17:29:04[0m] Beginning epoch 42...
|
| 587 |
+
[[34m2025-10-29 17:29:53[0m] (step=0052600) Train Loss: 0.4819, Train Steps/Sec: 1.20
|
| 588 |
+
[[34m2025-10-29 17:31:13[0m] (step=0052700) Train Loss: 0.4820, Train Steps/Sec: 1.24
|
| 589 |
+
[[34m2025-10-29 17:32:35[0m] (step=0052800) Train Loss: 0.4813, Train Steps/Sec: 1.23
|
| 590 |
+
[[34m2025-10-29 17:33:55[0m] (step=0052900) Train Loss: 0.4832, Train Steps/Sec: 1.24
|
| 591 |
+
[[34m2025-10-29 17:35:16[0m] (step=0053000) Train Loss: 0.4815, Train Steps/Sec: 1.24
|
| 592 |
+
[[34m2025-10-29 17:36:37[0m] (step=0053100) Train Loss: 0.4809, Train Steps/Sec: 1.24
|
| 593 |
+
[[34m2025-10-29 17:37:58[0m] (step=0053200) Train Loss: 0.4810, Train Steps/Sec: 1.24
|
| 594 |
+
[[34m2025-10-29 17:39:18[0m] (step=0053300) Train Loss: 0.4811, Train Steps/Sec: 1.24
|
| 595 |
+
[[34m2025-10-29 17:40:39[0m] (step=0053400) Train Loss: 0.4811, Train Steps/Sec: 1.24
|
| 596 |
+
[[34m2025-10-29 17:42:00[0m] (step=0053500) Train Loss: 0.4818, Train Steps/Sec: 1.24
|
| 597 |
+
[[34m2025-10-29 17:43:21[0m] (step=0053600) Train Loss: 0.4810, Train Steps/Sec: 1.24
|
| 598 |
+
[[34m2025-10-29 17:44:41[0m] (step=0053700) Train Loss: 0.4814, Train Steps/Sec: 1.24
|
| 599 |
+
[[34m2025-10-29 17:45:57[0m] Beginning epoch 43...
|
| 600 |
+
[[34m2025-10-29 17:46:04[0m] (step=0053800) Train Loss: 0.4813, Train Steps/Sec: 1.20
|
| 601 |
+
[[34m2025-10-29 17:47:25[0m] (step=0053900) Train Loss: 0.4805, Train Steps/Sec: 1.24
|
| 602 |
+
[[34m2025-10-29 17:48:46[0m] (step=0054000) Train Loss: 0.4819, Train Steps/Sec: 1.24
|
| 603 |
+
[[34m2025-10-29 17:50:06[0m] (step=0054100) Train Loss: 0.4825, Train Steps/Sec: 1.24
|
| 604 |
+
[[34m2025-10-29 17:51:27[0m] (step=0054200) Train Loss: 0.4810, Train Steps/Sec: 1.24
|
| 605 |
+
[[34m2025-10-29 17:52:48[0m] (step=0054300) Train Loss: 0.4813, Train Steps/Sec: 1.24
|
| 606 |
+
[[34m2025-10-29 17:54:09[0m] (step=0054400) Train Loss: 0.4820, Train Steps/Sec: 1.24
|
| 607 |
+
[[34m2025-10-29 17:55:30[0m] (step=0054500) Train Loss: 0.4812, Train Steps/Sec: 1.22
|
| 608 |
+
[[34m2025-10-29 17:56:51[0m] (step=0054600) Train Loss: 0.4811, Train Steps/Sec: 1.24
|
| 609 |
+
[[34m2025-10-29 17:58:12[0m] (step=0054700) Train Loss: 0.4808, Train Steps/Sec: 1.24
|
| 610 |
+
[[34m2025-10-29 17:59:32[0m] (step=0054800) Train Loss: 0.4826, Train Steps/Sec: 1.24
|
| 611 |
+
[[34m2025-10-29 18:00:53[0m] (step=0054900) Train Loss: 0.4819, Train Steps/Sec: 1.24
|
| 612 |
+
[[34m2025-10-29 18:02:14[0m] (step=0055000) Train Loss: 0.4816, Train Steps/Sec: 1.24
|
| 613 |
+
[[34m2025-10-29 18:02:50[0m] Beginning epoch 44...
|
| 614 |
+
[[34m2025-10-29 18:03:37[0m] (step=0055100) Train Loss: 0.4811, Train Steps/Sec: 1.20
|
| 615 |
+
[[34m2025-10-29 18:04:57[0m] (step=0055200) Train Loss: 0.4793, Train Steps/Sec: 1.24
|
| 616 |
+
[[34m2025-10-29 18:06:18[0m] (step=0055300) Train Loss: 0.4812, Train Steps/Sec: 1.24
|
| 617 |
+
[[34m2025-10-29 18:07:39[0m] (step=0055400) Train Loss: 0.4804, Train Steps/Sec: 1.24
|
| 618 |
+
[[34m2025-10-29 18:08:59[0m] (step=0055500) Train Loss: 0.4808, Train Steps/Sec: 1.24
|
| 619 |
+
[[34m2025-10-29 18:10:20[0m] (step=0055600) Train Loss: 0.4814, Train Steps/Sec: 1.24
|
| 620 |
+
[[34m2025-10-29 18:11:41[0m] (step=0055700) Train Loss: 0.4806, Train Steps/Sec: 1.24
|
| 621 |
+
[[34m2025-10-29 18:13:02[0m] (step=0055800) Train Loss: 0.4801, Train Steps/Sec: 1.24
|
| 622 |
+
[[34m2025-10-29 18:14:22[0m] (step=0055900) Train Loss: 0.4821, Train Steps/Sec: 1.24
|
| 623 |
+
[[34m2025-10-29 18:15:43[0m] (step=0056000) Train Loss: 0.4787, Train Steps/Sec: 1.24
|
| 624 |
+
[[34m2025-10-29 18:17:03[0m] (step=0056100) Train Loss: 0.4804, Train Steps/Sec: 1.24
|
| 625 |
+
[[34m2025-10-29 18:18:25[0m] (step=0056200) Train Loss: 0.4808, Train Steps/Sec: 1.23
|
| 626 |
+
[[34m2025-10-29 18:19:43[0m] Beginning epoch 45...
|
| 627 |
+
[[34m2025-10-29 18:19:48[0m] (step=0056300) Train Loss: 0.4811, Train Steps/Sec: 1.21
|
| 628 |
+
[[34m2025-10-29 18:21:09[0m] (step=0056400) Train Loss: 0.4819, Train Steps/Sec: 1.24
|
| 629 |
+
[[34m2025-10-29 18:22:30[0m] (step=0056500) Train Loss: 0.4783, Train Steps/Sec: 1.24
|
| 630 |
+
[[34m2025-10-29 18:23:50[0m] (step=0056600) Train Loss: 0.4798, Train Steps/Sec: 1.24
|
| 631 |
+
[[34m2025-10-29 18:25:11[0m] (step=0056700) Train Loss: 0.4803, Train Steps/Sec: 1.24
|
| 632 |
+
[[34m2025-10-29 18:26:32[0m] (step=0056800) Train Loss: 0.4800, Train Steps/Sec: 1.24
|
| 633 |
+
[[34m2025-10-29 18:27:52[0m] (step=0056900) Train Loss: 0.4806, Train Steps/Sec: 1.24
|
| 634 |
+
[[34m2025-10-29 18:29:13[0m] (step=0057000) Train Loss: 0.4804, Train Steps/Sec: 1.24
|
| 635 |
+
[[34m2025-10-29 18:30:34[0m] (step=0057100) Train Loss: 0.4795, Train Steps/Sec: 1.24
|
| 636 |
+
[[34m2025-10-29 18:31:54[0m] (step=0057200) Train Loss: 0.4811, Train Steps/Sec: 1.24
|
| 637 |
+
[[34m2025-10-29 18:33:15[0m] (step=0057300) Train Loss: 0.4798, Train Steps/Sec: 1.24
|
| 638 |
+
[[34m2025-10-29 18:34:36[0m] (step=0057400) Train Loss: 0.4804, Train Steps/Sec: 1.24
|
| 639 |
+
[[34m2025-10-29 18:35:56[0m] (step=0057500) Train Loss: 0.4796, Train Steps/Sec: 1.24
|
| 640 |
+
[[34m2025-10-29 18:36:34[0m] Beginning epoch 46...
|
| 641 |
+
[[34m2025-10-29 18:37:20[0m] (step=0057600) Train Loss: 0.4795, Train Steps/Sec: 1.20
|
| 642 |
+
[[34m2025-10-29 18:38:40[0m] (step=0057700) Train Loss: 0.4801, Train Steps/Sec: 1.24
|
| 643 |
+
[[34m2025-10-29 18:40:01[0m] (step=0057800) Train Loss: 0.4784, Train Steps/Sec: 1.24
|
| 644 |
+
[[34m2025-10-29 18:41:23[0m] (step=0057900) Train Loss: 0.4787, Train Steps/Sec: 1.23
|
| 645 |
+
[[34m2025-10-29 18:42:43[0m] (step=0058000) Train Loss: 0.4805, Train Steps/Sec: 1.24
|
| 646 |
+
[[34m2025-10-29 18:44:04[0m] (step=0058100) Train Loss: 0.4797, Train Steps/Sec: 1.24
|
| 647 |
+
[[34m2025-10-29 18:45:25[0m] (step=0058200) Train Loss: 0.4795, Train Steps/Sec: 1.24
|
| 648 |
+
[[34m2025-10-29 18:46:45[0m] (step=0058300) Train Loss: 0.4807, Train Steps/Sec: 1.24
|
| 649 |
+
[[34m2025-10-29 18:48:06[0m] (step=0058400) Train Loss: 0.4799, Train Steps/Sec: 1.24
|
| 650 |
+
[[34m2025-10-29 18:49:27[0m] (step=0058500) Train Loss: 0.4794, Train Steps/Sec: 1.24
|
| 651 |
+
[[34m2025-10-29 18:50:47[0m] (step=0058600) Train Loss: 0.4796, Train Steps/Sec: 1.24
|
| 652 |
+
[[34m2025-10-29 18:52:08[0m] (step=0058700) Train Loss: 0.4798, Train Steps/Sec: 1.24
|
| 653 |
+
[[34m2025-10-29 18:53:27[0m] Beginning epoch 47...
|
| 654 |
+
[[34m2025-10-29 18:53:31[0m] (step=0058800) Train Loss: 0.4808, Train Steps/Sec: 1.20
|
| 655 |
+
[[34m2025-10-29 18:54:52[0m] (step=0058900) Train Loss: 0.4791, Train Steps/Sec: 1.24
|
| 656 |
+
[[34m2025-10-29 18:56:13[0m] (step=0059000) Train Loss: 0.4779, Train Steps/Sec: 1.24
|
| 657 |
+
[[34m2025-10-29 18:57:33[0m] (step=0059100) Train Loss: 0.4799, Train Steps/Sec: 1.24
|
| 658 |
+
[[34m2025-10-29 18:58:54[0m] (step=0059200) Train Loss: 0.4783, Train Steps/Sec: 1.24
|
| 659 |
+
[[34m2025-10-29 19:00:15[0m] (step=0059300) Train Loss: 0.4797, Train Steps/Sec: 1.24
|
| 660 |
+
[[34m2025-10-29 19:01:35[0m] (step=0059400) Train Loss: 0.4790, Train Steps/Sec: 1.24
|
| 661 |
+
[[34m2025-10-29 19:02:57[0m] (step=0059500) Train Loss: 0.4784, Train Steps/Sec: 1.23
|
| 662 |
+
[[34m2025-10-29 19:04:18[0m] (step=0059600) Train Loss: 0.4787, Train Steps/Sec: 1.24
|
| 663 |
+
[[34m2025-10-29 19:05:38[0m] (step=0059700) Train Loss: 0.4789, Train Steps/Sec: 1.24
|
| 664 |
+
[[34m2025-10-29 19:06:59[0m] (step=0059800) Train Loss: 0.4789, Train Steps/Sec: 1.24
|
| 665 |
+
[[34m2025-10-29 19:08:20[0m] (step=0059900) Train Loss: 0.4773, Train Steps/Sec: 1.24
|
| 666 |
+
[[34m2025-10-29 19:09:40[0m] (step=0060000) Train Loss: 0.4781, Train Steps/Sec: 1.24
|
| 667 |
+
[[34m2025-10-29 19:10:20[0m] Beginning epoch 48...
|
| 668 |
+
[[34m2025-10-29 19:11:03[0m] (step=0060100) Train Loss: 0.4780, Train Steps/Sec: 1.20
|
| 669 |
+
[[34m2025-10-29 19:12:24[0m] (step=0060200) Train Loss: 0.4780, Train Steps/Sec: 1.24
|
| 670 |
+
[[34m2025-10-29 19:13:45[0m] (step=0060300) Train Loss: 0.4789, Train Steps/Sec: 1.24
|
| 671 |
+
[[34m2025-10-29 19:15:06[0m] (step=0060400) Train Loss: 0.4780, Train Steps/Sec: 1.24
|
| 672 |
+
[[34m2025-10-29 19:16:26[0m] (step=0060500) Train Loss: 0.4786, Train Steps/Sec: 1.24
|
| 673 |
+
[[34m2025-10-29 19:17:47[0m] (step=0060600) Train Loss: 0.4781, Train Steps/Sec: 1.24
|
| 674 |
+
[[34m2025-10-29 19:19:08[0m] (step=0060700) Train Loss: 0.4788, Train Steps/Sec: 1.24
|
| 675 |
+
[[34m2025-10-29 19:20:28[0m] (step=0060800) Train Loss: 0.4788, Train Steps/Sec: 1.24
|
| 676 |
+
[[34m2025-10-29 19:21:49[0m] (step=0060900) Train Loss: 0.4785, Train Steps/Sec: 1.24
|
| 677 |
+
[[34m2025-10-29 19:23:10[0m] (step=0061000) Train Loss: 0.4784, Train Steps/Sec: 1.24
|
| 678 |
+
[[34m2025-10-29 19:24:30[0m] (step=0061100) Train Loss: 0.4778, Train Steps/Sec: 1.24
|
| 679 |
+
[[34m2025-10-29 19:25:52[0m] (step=0061200) Train Loss: 0.4794, Train Steps/Sec: 1.23
|
| 680 |
+
[[34m2025-10-29 19:27:12[0m] Beginning epoch 49...
|
| 681 |
+
[[34m2025-10-29 19:27:15[0m] (step=0061300) Train Loss: 0.4778, Train Steps/Sec: 1.20
|
| 682 |
+
[[34m2025-10-29 19:28:36[0m] (step=0061400) Train Loss: 0.4794, Train Steps/Sec: 1.24
|
| 683 |
+
[[34m2025-10-29 19:29:56[0m] (step=0061500) Train Loss: 0.4778, Train Steps/Sec: 1.24
|
| 684 |
+
[[34m2025-10-29 19:31:17[0m] (step=0061600) Train Loss: 0.4777, Train Steps/Sec: 1.24
|
| 685 |
+
[[34m2025-10-29 19:32:38[0m] (step=0061700) Train Loss: 0.4777, Train Steps/Sec: 1.24
|
| 686 |
+
[[34m2025-10-29 19:33:58[0m] (step=0061800) Train Loss: 0.4777, Train Steps/Sec: 1.24
|
| 687 |
+
[[34m2025-10-29 19:35:19[0m] (step=0061900) Train Loss: 0.4775, Train Steps/Sec: 1.24
|
| 688 |
+
[[34m2025-10-29 19:36:40[0m] (step=0062000) Train Loss: 0.4785, Train Steps/Sec: 1.24
|
| 689 |
+
[[34m2025-10-29 19:38:01[0m] (step=0062100) Train Loss: 0.4777, Train Steps/Sec: 1.24
|
| 690 |
+
[[34m2025-10-29 19:39:21[0m] (step=0062200) Train Loss: 0.4781, Train Steps/Sec: 1.24
|
| 691 |
+
[[34m2025-10-29 19:40:42[0m] (step=0062300) Train Loss: 0.4790, Train Steps/Sec: 1.24
|
| 692 |
+
[[34m2025-10-29 19:42:03[0m] (step=0062400) Train Loss: 0.4782, Train Steps/Sec: 1.24
|
| 693 |
+
[[34m2025-10-29 19:43:24[0m] (step=0062500) Train Loss: 0.4789, Train Steps/Sec: 1.24
|
| 694 |
+
[[34m2025-10-29 19:44:04[0m] Beginning epoch 50...
|
| 695 |
+
[[34m2025-10-29 19:44:47[0m] (step=0062600) Train Loss: 0.4771, Train Steps/Sec: 1.21
|
| 696 |
+
[[34m2025-10-29 19:46:07[0m] (step=0062700) Train Loss: 0.4774, Train Steps/Sec: 1.24
|
| 697 |
+
[[34m2025-10-29 19:47:28[0m] (step=0062800) Train Loss: 0.4769, Train Steps/Sec: 1.24
|
| 698 |
+
[[34m2025-10-29 19:48:49[0m] (step=0062900) Train Loss: 0.4780, Train Steps/Sec: 1.23
|
| 699 |
+
[[34m2025-10-29 19:50:10[0m] (step=0063000) Train Loss: 0.4776, Train Steps/Sec: 1.24
|
| 700 |
+
[[34m2025-10-29 19:51:31[0m] (step=0063100) Train Loss: 0.4774, Train Steps/Sec: 1.24
|
| 701 |
+
[[34m2025-10-29 19:52:52[0m] (step=0063200) Train Loss: 0.4782, Train Steps/Sec: 1.24
|
| 702 |
+
[[34m2025-10-29 19:54:12[0m] (step=0063300) Train Loss: 0.4784, Train Steps/Sec: 1.24
|
| 703 |
+
[[34m2025-10-29 19:55:33[0m] (step=0063400) Train Loss: 0.4773, Train Steps/Sec: 1.24
|
| 704 |
+
[[34m2025-10-29 19:56:54[0m] (step=0063500) Train Loss: 0.4761, Train Steps/Sec: 1.24
|
| 705 |
+
[[34m2025-10-29 19:58:14[0m] (step=0063600) Train Loss: 0.4764, Train Steps/Sec: 1.24
|
| 706 |
+
[[34m2025-10-29 19:59:35[0m] (step=0063700) Train Loss: 0.4764, Train Steps/Sec: 1.24
|
| 707 |
+
[[34m2025-10-29 20:00:56[0m] (step=0063800) Train Loss: 0.4772, Train Steps/Sec: 1.24
|
| 708 |
+
[[34m2025-10-29 20:00:57[0m] Beginning epoch 51...
|
| 709 |
+
[[34m2025-10-29 20:02:19[0m] (step=0063900) Train Loss: 0.4775, Train Steps/Sec: 1.21
|
| 710 |
+
[[34m2025-10-29 20:03:39[0m] (step=0064000) Train Loss: 0.4769, Train Steps/Sec: 1.24
|
| 711 |
+
[[34m2025-10-29 20:05:00[0m] (step=0064100) Train Loss: 0.4763, Train Steps/Sec: 1.24
|
| 712 |
+
[[34m2025-10-29 20:06:21[0m] (step=0064200) Train Loss: 0.4768, Train Steps/Sec: 1.24
|
| 713 |
+
[[34m2025-10-29 20:07:41[0m] (step=0064300) Train Loss: 0.4769, Train Steps/Sec: 1.24
|
| 714 |
+
[[34m2025-10-29 20:09:02[0m] (step=0064400) Train Loss: 0.4764, Train Steps/Sec: 1.24
|
| 715 |
+
[[34m2025-10-29 20:10:23[0m] (step=0064500) Train Loss: 0.4778, Train Steps/Sec: 1.24
|
| 716 |
+
[[34m2025-10-29 20:11:44[0m] (step=0064600) Train Loss: 0.4774, Train Steps/Sec: 1.23
|
| 717 |
+
[[34m2025-10-29 20:13:05[0m] (step=0064700) Train Loss: 0.4759, Train Steps/Sec: 1.24
|
| 718 |
+
[[34m2025-10-29 20:14:26[0m] (step=0064800) Train Loss: 0.4777, Train Steps/Sec: 1.24
|
| 719 |
+
[[34m2025-10-29 20:15:46[0m] (step=0064900) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 720 |
+
[[34m2025-10-29 20:17:07[0m] (step=0065000) Train Loss: 0.4774, Train Steps/Sec: 1.24
|
| 721 |
+
[[34m2025-10-29 20:17:50[0m] Beginning epoch 52...
|
| 722 |
+
[[34m2025-10-29 20:18:30[0m] (step=0065100) Train Loss: 0.4766, Train Steps/Sec: 1.20
|
| 723 |
+
[[34m2025-10-29 20:19:51[0m] (step=0065200) Train Loss: 0.4773, Train Steps/Sec: 1.24
|
| 724 |
+
[[34m2025-10-29 20:21:12[0m] (step=0065300) Train Loss: 0.4766, Train Steps/Sec: 1.24
|
| 725 |
+
[[34m2025-10-29 20:22:32[0m] (step=0065400) Train Loss: 0.4775, Train Steps/Sec: 1.24
|
| 726 |
+
[[34m2025-10-29 20:23:53[0m] (step=0065500) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 727 |
+
[[34m2025-10-29 20:25:14[0m] (step=0065600) Train Loss: 0.4757, Train Steps/Sec: 1.24
|
| 728 |
+
[[34m2025-10-29 20:26:34[0m] (step=0065700) Train Loss: 0.4746, Train Steps/Sec: 1.24
|
| 729 |
+
[[34m2025-10-29 20:27:55[0m] (step=0065800) Train Loss: 0.4766, Train Steps/Sec: 1.24
|
| 730 |
+
[[34m2025-10-29 20:29:16[0m] (step=0065900) Train Loss: 0.4762, Train Steps/Sec: 1.24
|
| 731 |
+
[[34m2025-10-29 20:30:37[0m] (step=0066000) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 732 |
+
[[34m2025-10-29 20:31:57[0m] (step=0066100) Train Loss: 0.4753, Train Steps/Sec: 1.24
|
| 733 |
+
[[34m2025-10-29 20:33:19[0m] (step=0066200) Train Loss: 0.4774, Train Steps/Sec: 1.23
|
| 734 |
+
[[34m2025-10-29 20:34:39[0m] (step=0066300) Train Loss: 0.4773, Train Steps/Sec: 1.24
|
| 735 |
+
[[34m2025-10-29 20:34:42[0m] Beginning epoch 53...
|
| 736 |
+
[[34m2025-10-29 20:36:03[0m] (step=0066400) Train Loss: 0.4749, Train Steps/Sec: 1.20
|
| 737 |
+
[[34m2025-10-29 20:37:23[0m] (step=0066500) Train Loss: 0.4748, Train Steps/Sec: 1.24
|
| 738 |
+
[[34m2025-10-29 20:38:44[0m] (step=0066600) Train Loss: 0.4744, Train Steps/Sec: 1.24
|
| 739 |
+
[[34m2025-10-29 20:40:05[0m] (step=0066700) Train Loss: 0.4766, Train Steps/Sec: 1.24
|
| 740 |
+
[[34m2025-10-29 20:41:26[0m] (step=0066800) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 741 |
+
[[34m2025-10-29 20:42:46[0m] (step=0066900) Train Loss: 0.4761, Train Steps/Sec: 1.24
|
| 742 |
+
[[34m2025-10-29 20:44:07[0m] (step=0067000) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 743 |
+
[[34m2025-10-29 20:45:27[0m] (step=0067100) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 744 |
+
[[34m2025-10-29 20:46:48[0m] (step=0067200) Train Loss: 0.4748, Train Steps/Sec: 1.24
|
| 745 |
+
[[34m2025-10-29 20:48:09[0m] (step=0067300) Train Loss: 0.4763, Train Steps/Sec: 1.24
|
| 746 |
+
[[34m2025-10-29 20:49:30[0m] (step=0067400) Train Loss: 0.4766, Train Steps/Sec: 1.24
|
| 747 |
+
[[34m2025-10-29 20:50:50[0m] (step=0067500) Train Loss: 0.4751, Train Steps/Sec: 1.24
|
| 748 |
+
[[34m2025-10-29 20:51:34[0m] Beginning epoch 54...
|
| 749 |
+
[[34m2025-10-29 20:52:13[0m] (step=0067600) Train Loss: 0.4746, Train Steps/Sec: 1.20
|
| 750 |
+
[[34m2025-10-29 20:53:34[0m] (step=0067700) Train Loss: 0.4761, Train Steps/Sec: 1.24
|
| 751 |
+
[[34m2025-10-29 20:54:55[0m] (step=0067800) Train Loss: 0.4753, Train Steps/Sec: 1.24
|
| 752 |
+
[[34m2025-10-29 20:56:16[0m] (step=0067900) Train Loss: 0.4749, Train Steps/Sec: 1.23
|
| 753 |
+
[[34m2025-10-29 20:57:37[0m] (step=0068000) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 754 |
+
[[34m2025-10-29 20:58:57[0m] (step=0068100) Train Loss: 0.4762, Train Steps/Sec: 1.24
|
| 755 |
+
[[34m2025-10-29 21:00:18[0m] (step=0068200) Train Loss: 0.4753, Train Steps/Sec: 1.24
|
| 756 |
+
[[34m2025-10-29 21:01:39[0m] (step=0068300) Train Loss: 0.4746, Train Steps/Sec: 1.24
|
| 757 |
+
[[34m2025-10-29 21:02:59[0m] (step=0068400) Train Loss: 0.4760, Train Steps/Sec: 1.24
|
| 758 |
+
[[34m2025-10-29 21:04:20[0m] (step=0068500) Train Loss: 0.4748, Train Steps/Sec: 1.24
|
| 759 |
+
[[34m2025-10-29 21:05:41[0m] (step=0068600) Train Loss: 0.4764, Train Steps/Sec: 1.24
|
| 760 |
+
[[34m2025-10-29 21:07:02[0m] (step=0068700) Train Loss: 0.4745, Train Steps/Sec: 1.24
|
| 761 |
+
[[34m2025-10-29 21:08:22[0m] (step=0068800) Train Loss: 0.4757, Train Steps/Sec: 1.24
|
| 762 |
+
[[34m2025-10-29 21:08:27[0m] Beginning epoch 55...
|
| 763 |
+
[[34m2025-10-29 21:09:45[0m] (step=0068900) Train Loss: 0.4739, Train Steps/Sec: 1.21
|
| 764 |
+
[[34m2025-10-29 21:11:06[0m] (step=0069000) Train Loss: 0.4759, Train Steps/Sec: 1.24
|
| 765 |
+
[[34m2025-10-29 21:12:27[0m] (step=0069100) Train Loss: 0.4750, Train Steps/Sec: 1.24
|
| 766 |
+
[[34m2025-10-29 21:13:47[0m] (step=0069200) Train Loss: 0.4751, Train Steps/Sec: 1.24
|
| 767 |
+
[[34m2025-10-29 21:15:08[0m] (step=0069300) Train Loss: 0.4753, Train Steps/Sec: 1.24
|
| 768 |
+
[[34m2025-10-29 21:16:29[0m] (step=0069400) Train Loss: 0.4741, Train Steps/Sec: 1.24
|
| 769 |
+
[[34m2025-10-29 21:17:49[0m] (step=0069500) Train Loss: 0.4748, Train Steps/Sec: 1.24
|
| 770 |
+
[[34m2025-10-29 21:19:11[0m] (step=0069600) Train Loss: 0.4750, Train Steps/Sec: 1.23
|
| 771 |
+
[[34m2025-10-29 21:20:31[0m] (step=0069700) Train Loss: 0.4765, Train Steps/Sec: 1.24
|
| 772 |
+
[[34m2025-10-29 21:21:52[0m] (step=0069800) Train Loss: 0.4750, Train Steps/Sec: 1.24
|
| 773 |
+
[[34m2025-10-29 21:23:13[0m] (step=0069900) Train Loss: 0.4739, Train Steps/Sec: 1.24
|
| 774 |
+
[[34m2025-10-29 21:24:34[0m] (step=0070000) Train Loss: 0.4748, Train Steps/Sec: 1.24
|
| 775 |
+
[[34m2025-10-29 21:25:19[0m] Beginning epoch 56...
|
| 776 |
+
[[34m2025-10-29 21:25:56[0m] (step=0070100) Train Loss: 0.4750, Train Steps/Sec: 1.21
|
| 777 |
+
[[34m2025-10-29 21:27:17[0m] (step=0070200) Train Loss: 0.4749, Train Steps/Sec: 1.24
|
| 778 |
+
[[34m2025-10-29 21:28:38[0m] (step=0070300) Train Loss: 0.4755, Train Steps/Sec: 1.24
|
| 779 |
+
[[34m2025-10-29 21:29:59[0m] (step=0070400) Train Loss: 0.4747, Train Steps/Sec: 1.24
|
| 780 |
+
[[34m2025-10-29 21:31:19[0m] (step=0070500) Train Loss: 0.4755, Train Steps/Sec: 1.24
|
| 781 |
+
[[34m2025-10-29 21:32:40[0m] (step=0070600) Train Loss: 0.4753, Train Steps/Sec: 1.24
|
| 782 |
+
[[34m2025-10-29 21:34:01[0m] (step=0070700) Train Loss: 0.4749, Train Steps/Sec: 1.24
|
| 783 |
+
[[34m2025-10-29 21:35:22[0m] (step=0070800) Train Loss: 0.4758, Train Steps/Sec: 1.24
|
| 784 |
+
[[34m2025-10-29 21:36:42[0m] (step=0070900) Train Loss: 0.4742, Train Steps/Sec: 1.24
|
| 785 |
+
[[34m2025-10-29 21:38:03[0m] (step=0071000) Train Loss: 0.4741, Train Steps/Sec: 1.24
|
| 786 |
+
[[34m2025-10-29 21:39:24[0m] (step=0071100) Train Loss: 0.4753, Train Steps/Sec: 1.24
|
| 787 |
+
[[34m2025-10-29 21:40:45[0m] (step=0071200) Train Loss: 0.4746, Train Steps/Sec: 1.24
|
| 788 |
+
[[34m2025-10-29 21:42:06[0m] (step=0071300) Train Loss: 0.4751, Train Steps/Sec: 1.23
|
| 789 |
+
[[34m2025-10-29 21:42:12[0m] Beginning epoch 57...
|
| 790 |
+
[[34m2025-10-29 21:43:29[0m] (step=0071400) Train Loss: 0.4739, Train Steps/Sec: 1.20
|
| 791 |
+
[[34m2025-10-29 21:44:50[0m] (step=0071500) Train Loss: 0.4739, Train Steps/Sec: 1.24
|
| 792 |
+
[[34m2025-10-29 21:46:10[0m] (step=0071600) Train Loss: 0.4754, Train Steps/Sec: 1.24
|
| 793 |
+
[[34m2025-10-29 21:47:31[0m] (step=0071700) Train Loss: 0.4747, Train Steps/Sec: 1.24
|
| 794 |
+
[[34m2025-10-29 21:48:52[0m] (step=0071800) Train Loss: 0.4741, Train Steps/Sec: 1.24
|
| 795 |
+
[[34m2025-10-29 21:50:12[0m] (step=0071900) Train Loss: 0.4733, Train Steps/Sec: 1.24
|
| 796 |
+
[[34m2025-10-29 21:51:33[0m] (step=0072000) Train Loss: 0.4740, Train Steps/Sec: 1.24
|
| 797 |
+
[[34m2025-10-29 21:52:54[0m] (step=0072100) Train Loss: 0.4731, Train Steps/Sec: 1.24
|
| 798 |
+
[[34m2025-10-29 21:54:15[0m] (step=0072200) Train Loss: 0.4757, Train Steps/Sec: 1.24
|
| 799 |
+
[[34m2025-10-29 21:55:35[0m] (step=0072300) Train Loss: 0.4748, Train Steps/Sec: 1.24
|
| 800 |
+
[[34m2025-10-29 21:56:56[0m] (step=0072400) Train Loss: 0.4747, Train Steps/Sec: 1.24
|
| 801 |
+
[[34m2025-10-29 21:58:17[0m] (step=0072500) Train Loss: 0.4737, Train Steps/Sec: 1.24
|
| 802 |
+
[[34m2025-10-29 21:59:04[0m] Beginning epoch 58...
|
| 803 |
+
[[34m2025-10-29 21:59:39[0m] (step=0072600) Train Loss: 0.4737, Train Steps/Sec: 1.21
|
| 804 |
+
[[34m2025-10-29 22:01:00[0m] (step=0072700) Train Loss: 0.4750, Train Steps/Sec: 1.24
|
| 805 |
+
[[34m2025-10-29 22:02:21[0m] (step=0072800) Train Loss: 0.4747, Train Steps/Sec: 1.24
|
| 806 |
+
[[34m2025-10-29 22:03:42[0m] (step=0072900) Train Loss: 0.4737, Train Steps/Sec: 1.23
|
| 807 |
+
[[34m2025-10-29 22:05:03[0m] (step=0073000) Train Loss: 0.4738, Train Steps/Sec: 1.24
|
| 808 |
+
[[34m2025-10-29 22:06:24[0m] (step=0073100) Train Loss: 0.4740, Train Steps/Sec: 1.24
|
| 809 |
+
[[34m2025-10-29 22:07:45[0m] (step=0073200) Train Loss: 0.4732, Train Steps/Sec: 1.24
|
| 810 |
+
[[34m2025-10-29 22:09:05[0m] (step=0073300) Train Loss: 0.4733, Train Steps/Sec: 1.24
|
| 811 |
+
[[34m2025-10-29 22:10:26[0m] (step=0073400) Train Loss: 0.4730, Train Steps/Sec: 1.24
|
| 812 |
+
[[34m2025-10-29 22:11:47[0m] (step=0073500) Train Loss: 0.4742, Train Steps/Sec: 1.24
|
| 813 |
+
[[34m2025-10-29 22:13:07[0m] (step=0073600) Train Loss: 0.4727, Train Steps/Sec: 1.24
|
| 814 |
+
[[34m2025-10-29 22:14:28[0m] (step=0073700) Train Loss: 0.4736, Train Steps/Sec: 1.24
|
| 815 |
+
[[34m2025-10-29 22:15:49[0m] (step=0073800) Train Loss: 0.4739, Train Steps/Sec: 1.24
|
| 816 |
+
[[34m2025-10-29 22:15:56[0m] Beginning epoch 59...
|
| 817 |
+
[[34m2025-10-29 22:17:12[0m] (step=0073900) Train Loss: 0.4736, Train Steps/Sec: 1.20
|
| 818 |
+
[[34m2025-10-29 22:18:32[0m] (step=0074000) Train Loss: 0.4720, Train Steps/Sec: 1.24
|
| 819 |
+
[[34m2025-10-29 22:19:53[0m] (step=0074100) Train Loss: 0.4748, Train Steps/Sec: 1.24
|
| 820 |
+
[[34m2025-10-29 22:21:14[0m] (step=0074200) Train Loss: 0.4742, Train Steps/Sec: 1.24
|
| 821 |
+
[[34m2025-10-29 22:22:35[0m] (step=0074300) Train Loss: 0.4743, Train Steps/Sec: 1.24
|
| 822 |
+
[[34m2025-10-29 22:23:55[0m] (step=0074400) Train Loss: 0.4740, Train Steps/Sec: 1.24
|
| 823 |
+
[[34m2025-10-29 22:25:16[0m] (step=0074500) Train Loss: 0.4735, Train Steps/Sec: 1.24
|
| 824 |
+
[[34m2025-10-29 22:26:37[0m] (step=0074600) Train Loss: 0.4731, Train Steps/Sec: 1.23
|
| 825 |
+
[[34m2025-10-29 22:27:58[0m] (step=0074700) Train Loss: 0.4737, Train Steps/Sec: 1.24
|
| 826 |
+
[[34m2025-10-29 22:29:19[0m] (step=0074800) Train Loss: 0.4729, Train Steps/Sec: 1.24
|
| 827 |
+
[[34m2025-10-29 22:30:40[0m] (step=0074900) Train Loss: 0.4703, Train Steps/Sec: 1.24
|
| 828 |
+
[[34m2025-10-29 22:32:00[0m] (step=0075000) Train Loss: 0.4731, Train Steps/Sec: 1.24
|
| 829 |
+
[[34m2025-10-29 22:32:57[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0075000.pt
|
| 830 |
+
[[34m2025-10-29 22:32:57[0m] Generating EMA samples...
|
| 831 |
+
[[34m2025-10-29 22:33:25[0m] Generating EMA samples done.
|
| 832 |
+
[[34m2025-10-29 22:34:14[0m] Beginning epoch 60...
|
| 833 |
+
[[34m2025-10-29 22:34:48[0m] (step=0075100) Train Loss: 0.4725, Train Steps/Sec: 0.60
|
| 834 |
+
[[34m2025-10-29 22:36:09[0m] (step=0075200) Train Loss: 0.4733, Train Steps/Sec: 1.24
|
| 835 |
+
[[34m2025-10-29 22:37:29[0m] (step=0075300) Train Loss: 0.4737, Train Steps/Sec: 1.24
|
| 836 |
+
[[34m2025-10-29 22:38:50[0m] (step=0075400) Train Loss: 0.4726, Train Steps/Sec: 1.24
|
| 837 |
+
[[34m2025-10-29 22:40:11[0m] (step=0075500) Train Loss: 0.4739, Train Steps/Sec: 1.24
|
| 838 |
+
[[34m2025-10-29 22:41:31[0m] (step=0075600) Train Loss: 0.4723, Train Steps/Sec: 1.24
|
| 839 |
+
[[34m2025-10-29 22:42:52[0m] (step=0075700) Train Loss: 0.4719, Train Steps/Sec: 1.24
|
| 840 |
+
[[34m2025-10-29 22:44:13[0m] (step=0075800) Train Loss: 0.4742, Train Steps/Sec: 1.24
|
| 841 |
+
[[34m2025-10-29 22:45:33[0m] (step=0075900) Train Loss: 0.4727, Train Steps/Sec: 1.24
|
| 842 |
+
[[34m2025-10-29 22:46:54[0m] (step=0076000) Train Loss: 0.4731, Train Steps/Sec: 1.24
|
| 843 |
+
[[34m2025-10-29 22:48:15[0m] (step=0076100) Train Loss: 0.4704, Train Steps/Sec: 1.24
|
| 844 |
+
[[34m2025-10-29 22:49:35[0m] (step=0076200) Train Loss: 0.4728, Train Steps/Sec: 1.24
|
| 845 |
+
[[34m2025-10-29 22:50:57[0m] (step=0076300) Train Loss: 0.4732, Train Steps/Sec: 1.23
|
| 846 |
+
[[34m2025-10-29 22:51:06[0m] Beginning epoch 61...
|
| 847 |
+
[[34m2025-10-29 22:52:20[0m] (step=0076400) Train Loss: 0.4728, Train Steps/Sec: 1.20
|
| 848 |
+
[[34m2025-10-29 22:53:41[0m] (step=0076500) Train Loss: 0.4740, Train Steps/Sec: 1.24
|
| 849 |
+
[[34m2025-10-29 22:55:01[0m] (step=0076600) Train Loss: 0.4735, Train Steps/Sec: 1.24
|
| 850 |
+
[[34m2025-10-29 22:56:22[0m] (step=0076700) Train Loss: 0.4745, Train Steps/Sec: 1.24
|
| 851 |
+
[[34m2025-10-29 22:57:43[0m] (step=0076800) Train Loss: 0.4716, Train Steps/Sec: 1.24
|
| 852 |
+
[[34m2025-10-29 22:59:03[0m] (step=0076900) Train Loss: 0.4724, Train Steps/Sec: 1.24
|
| 853 |
+
[[34m2025-10-29 23:00:24[0m] (step=0077000) Train Loss: 0.4735, Train Steps/Sec: 1.24
|
| 854 |
+
[[34m2025-10-29 23:01:45[0m] (step=0077100) Train Loss: 0.4731, Train Steps/Sec: 1.24
|
| 855 |
+
[[34m2025-10-29 23:03:06[0m] (step=0077200) Train Loss: 0.4728, Train Steps/Sec: 1.24
|
| 856 |
+
[[34m2025-10-29 23:04:26[0m] (step=0077300) Train Loss: 0.4728, Train Steps/Sec: 1.24
|
| 857 |
+
[[34m2025-10-29 23:05:47[0m] (step=0077400) Train Loss: 0.4712, Train Steps/Sec: 1.24
|
| 858 |
+
[[34m2025-10-29 23:07:08[0m] (step=0077500) Train Loss: 0.4721, Train Steps/Sec: 1.24
|
| 859 |
+
[[34m2025-10-29 23:07:58[0m] Beginning epoch 62...
|
| 860 |
+
[[34m2025-10-29 23:08:31[0m] (step=0077600) Train Loss: 0.4723, Train Steps/Sec: 1.20
|
| 861 |
+
[[34m2025-10-29 23:09:51[0m] (step=0077700) Train Loss: 0.4726, Train Steps/Sec: 1.24
|
| 862 |
+
[[34m2025-10-29 23:11:12[0m] (step=0077800) Train Loss: 0.4721, Train Steps/Sec: 1.24
|
| 863 |
+
[[34m2025-10-29 23:12:33[0m] (step=0077900) Train Loss: 0.4737, Train Steps/Sec: 1.23
|
| 864 |
+
[[34m2025-10-29 23:13:54[0m] (step=0078000) Train Loss: 0.4721, Train Steps/Sec: 1.24
|
| 865 |
+
[[34m2025-10-29 23:15:15[0m] (step=0078100) Train Loss: 0.4708, Train Steps/Sec: 1.24
|
| 866 |
+
[[34m2025-10-29 23:16:36[0m] (step=0078200) Train Loss: 0.4721, Train Steps/Sec: 1.24
|
| 867 |
+
[[34m2025-10-29 23:17:56[0m] (step=0078300) Train Loss: 0.4717, Train Steps/Sec: 1.24
|
| 868 |
+
[[34m2025-10-29 23:19:17[0m] (step=0078400) Train Loss: 0.4729, Train Steps/Sec: 1.24
|
| 869 |
+
[[34m2025-10-29 23:20:38[0m] (step=0078500) Train Loss: 0.4718, Train Steps/Sec: 1.24
|
| 870 |
+
[[34m2025-10-29 23:21:58[0m] (step=0078600) Train Loss: 0.4716, Train Steps/Sec: 1.24
|
| 871 |
+
[[34m2025-10-29 23:23:19[0m] (step=0078700) Train Loss: 0.4713, Train Steps/Sec: 1.24
|
| 872 |
+
[[34m2025-10-29 23:24:40[0m] (step=0078800) Train Loss: 0.4720, Train Steps/Sec: 1.24
|
| 873 |
+
[[34m2025-10-29 23:24:51[0m] Beginning epoch 63...
|
| 874 |
+
[[34m2025-10-29 23:26:03[0m] (step=0078900) Train Loss: 0.4720, Train Steps/Sec: 1.21
|
| 875 |
+
[[34m2025-10-29 23:27:23[0m] (step=0079000) Train Loss: 0.4717, Train Steps/Sec: 1.24
|
| 876 |
+
[[34m2025-10-29 23:28:44[0m] (step=0079100) Train Loss: 0.4722, Train Steps/Sec: 1.24
|
| 877 |
+
[[34m2025-10-29 23:30:04[0m] (step=0079200) Train Loss: 0.4721, Train Steps/Sec: 1.24
|
| 878 |
+
[[34m2025-10-29 23:31:25[0m] (step=0079300) Train Loss: 0.4717, Train Steps/Sec: 1.24
|
| 879 |
+
[[34m2025-10-29 23:32:46[0m] (step=0079400) Train Loss: 0.4722, Train Steps/Sec: 1.24
|
| 880 |
+
[[34m2025-10-29 23:34:07[0m] (step=0079500) Train Loss: 0.4722, Train Steps/Sec: 1.24
|
| 881 |
+
[[34m2025-10-29 23:35:28[0m] (step=0079600) Train Loss: 0.4718, Train Steps/Sec: 1.23
|
| 882 |
+
[[34m2025-10-29 23:36:49[0m] (step=0079700) Train Loss: 0.4711, Train Steps/Sec: 1.24
|
| 883 |
+
[[34m2025-10-29 23:38:09[0m] (step=0079800) Train Loss: 0.4722, Train Steps/Sec: 1.24
|
| 884 |
+
[[34m2025-10-29 23:39:30[0m] (step=0079900) Train Loss: 0.4718, Train Steps/Sec: 1.24
|
| 885 |
+
[[34m2025-10-29 23:40:51[0m] (step=0080000) Train Loss: 0.4712, Train Steps/Sec: 1.24
|
| 886 |
+
[[34m2025-10-29 23:41:43[0m] Beginning epoch 64...
|
| 887 |
+
[[34m2025-10-29 23:42:14[0m] (step=0080100) Train Loss: 0.4714, Train Steps/Sec: 1.20
|
| 888 |
+
[[34m2025-10-29 23:43:35[0m] (step=0080200) Train Loss: 0.4718, Train Steps/Sec: 1.24
|
| 889 |
+
[[34m2025-10-29 23:44:55[0m] (step=0080300) Train Loss: 0.4711, Train Steps/Sec: 1.24
|
| 890 |
+
[[34m2025-10-29 23:46:16[0m] (step=0080400) Train Loss: 0.4710, Train Steps/Sec: 1.24
|
| 891 |
+
[[34m2025-10-29 23:47:37[0m] (step=0080500) Train Loss: 0.4720, Train Steps/Sec: 1.24
|
| 892 |
+
[[34m2025-10-29 23:48:57[0m] (step=0080600) Train Loss: 0.4714, Train Steps/Sec: 1.24
|
| 893 |
+
[[34m2025-10-29 23:50:18[0m] (step=0080700) Train Loss: 0.4714, Train Steps/Sec: 1.24
|
| 894 |
+
[[34m2025-10-29 23:51:39[0m] (step=0080800) Train Loss: 0.4726, Train Steps/Sec: 1.24
|
| 895 |
+
[[34m2025-10-29 23:52:59[0m] (step=0080900) Train Loss: 0.4707, Train Steps/Sec: 1.24
|
| 896 |
+
[[34m2025-10-29 23:54:20[0m] (step=0081000) Train Loss: 0.4714, Train Steps/Sec: 1.24
|
| 897 |
+
[[34m2025-10-29 23:55:41[0m] (step=0081100) Train Loss: 0.4706, Train Steps/Sec: 1.24
|
| 898 |
+
[[34m2025-10-29 23:57:01[0m] (step=0081200) Train Loss: 0.4715, Train Steps/Sec: 1.24
|
| 899 |
+
[[34m2025-10-29 23:58:23[0m] (step=0081300) Train Loss: 0.4709, Train Steps/Sec: 1.22
|
| 900 |
+
[[34m2025-10-29 23:58:36[0m] Beginning epoch 65...
|
| 901 |
+
[[34m2025-10-29 23:59:46[0m] (step=0081400) Train Loss: 0.4720, Train Steps/Sec: 1.20
|
| 902 |
+
[[34m2025-10-30 00:01:07[0m] (step=0081500) Train Loss: 0.4717, Train Steps/Sec: 1.24
|
| 903 |
+
[[34m2025-10-30 00:02:28[0m] (step=0081600) Train Loss: 0.4718, Train Steps/Sec: 1.24
|
| 904 |
+
[[34m2025-10-30 00:03:48[0m] (step=0081700) Train Loss: 0.4705, Train Steps/Sec: 1.24
|
| 905 |
+
[[34m2025-10-30 00:05:09[0m] (step=0081800) Train Loss: 0.4722, Train Steps/Sec: 1.24
|
| 906 |
+
[[34m2025-10-30 00:06:30[0m] (step=0081900) Train Loss: 0.4713, Train Steps/Sec: 1.24
|
| 907 |
+
[[34m2025-10-30 00:07:50[0m] (step=0082000) Train Loss: 0.4720, Train Steps/Sec: 1.24
|
| 908 |
+
[[34m2025-10-30 00:09:11[0m] (step=0082100) Train Loss: 0.4717, Train Steps/Sec: 1.24
|
| 909 |
+
[[34m2025-10-30 00:10:32[0m] (step=0082200) Train Loss: 0.4721, Train Steps/Sec: 1.24
|
| 910 |
+
[[34m2025-10-30 00:11:52[0m] (step=0082300) Train Loss: 0.4720, Train Steps/Sec: 1.24
|
| 911 |
+
[[34m2025-10-30 00:13:13[0m] (step=0082400) Train Loss: 0.4710, Train Steps/Sec: 1.24
|
| 912 |
+
[[34m2025-10-30 00:14:34[0m] (step=0082500) Train Loss: 0.4712, Train Steps/Sec: 1.24
|
| 913 |
+
[[34m2025-10-30 00:15:28[0m] Beginning epoch 66...
|
| 914 |
+
[[34m2025-10-30 00:15:57[0m] (step=0082600) Train Loss: 0.4708, Train Steps/Sec: 1.20
|
| 915 |
+
[[34m2025-10-30 00:17:18[0m] (step=0082700) Train Loss: 0.4708, Train Steps/Sec: 1.24
|
| 916 |
+
[[34m2025-10-30 00:18:39[0m] (step=0082800) Train Loss: 0.4709, Train Steps/Sec: 1.24
|
| 917 |
+
[[34m2025-10-30 00:20:00[0m] (step=0082900) Train Loss: 0.4703, Train Steps/Sec: 1.23
|
| 918 |
+
[[34m2025-10-30 00:21:21[0m] (step=0083000) Train Loss: 0.4709, Train Steps/Sec: 1.23
|
| 919 |
+
[[34m2025-10-30 00:22:42[0m] (step=0083100) Train Loss: 0.4693, Train Steps/Sec: 1.24
|
| 920 |
+
[[34m2025-10-30 00:24:02[0m] (step=0083200) Train Loss: 0.4712, Train Steps/Sec: 1.24
|
| 921 |
+
[[34m2025-10-30 00:25:23[0m] (step=0083300) Train Loss: 0.4720, Train Steps/Sec: 1.24
|
| 922 |
+
[[34m2025-10-30 00:26:44[0m] (step=0083400) Train Loss: 0.4719, Train Steps/Sec: 1.24
|
| 923 |
+
[[34m2025-10-30 00:28:04[0m] (step=0083500) Train Loss: 0.4706, Train Steps/Sec: 1.24
|
| 924 |
+
[[34m2025-10-30 00:29:25[0m] (step=0083600) Train Loss: 0.4699, Train Steps/Sec: 1.24
|
| 925 |
+
[[34m2025-10-30 00:30:46[0m] (step=0083700) Train Loss: 0.4711, Train Steps/Sec: 1.24
|
| 926 |
+
[[34m2025-10-30 00:32:06[0m] (step=0083800) Train Loss: 0.4709, Train Steps/Sec: 1.24
|
| 927 |
+
[[34m2025-10-30 00:32:21[0m] Beginning epoch 67...
|
| 928 |
+
[[34m2025-10-30 00:33:30[0m] (step=0083900) Train Loss: 0.4711, Train Steps/Sec: 1.20
|
| 929 |
+
[[34m2025-10-30 00:34:51[0m] (step=0084000) Train Loss: 0.4714, Train Steps/Sec: 1.24
|
| 930 |
+
[[34m2025-10-30 00:36:11[0m] (step=0084100) Train Loss: 0.4702, Train Steps/Sec: 1.24
|
| 931 |
+
[[34m2025-10-30 00:37:32[0m] (step=0084200) Train Loss: 0.4711, Train Steps/Sec: 1.24
|
| 932 |
+
[[34m2025-10-30 00:38:53[0m] (step=0084300) Train Loss: 0.4710, Train Steps/Sec: 1.24
|
| 933 |
+
[[34m2025-10-30 00:40:13[0m] (step=0084400) Train Loss: 0.4705, Train Steps/Sec: 1.24
|
| 934 |
+
[[34m2025-10-30 00:41:34[0m] (step=0084500) Train Loss: 0.4704, Train Steps/Sec: 1.24
|
| 935 |
+
[[34m2025-10-30 00:42:56[0m] (step=0084600) Train Loss: 0.4698, Train Steps/Sec: 1.23
|
| 936 |
+
[[34m2025-10-30 00:44:16[0m] (step=0084700) Train Loss: 0.4703, Train Steps/Sec: 1.24
|
| 937 |
+
[[34m2025-10-30 00:45:37[0m] (step=0084800) Train Loss: 0.4710, Train Steps/Sec: 1.24
|
| 938 |
+
[[34m2025-10-30 00:46:58[0m] (step=0084900) Train Loss: 0.4702, Train Steps/Sec: 1.24
|
| 939 |
+
[[34m2025-10-30 00:48:19[0m] (step=0085000) Train Loss: 0.4703, Train Steps/Sec: 1.24
|
| 940 |
+
[[34m2025-10-30 00:49:14[0m] Beginning epoch 68...
|
| 941 |
+
[[34m2025-10-30 00:49:42[0m] (step=0085100) Train Loss: 0.4717, Train Steps/Sec: 1.20
|
| 942 |
+
[[34m2025-10-30 00:51:02[0m] (step=0085200) Train Loss: 0.4696, Train Steps/Sec: 1.24
|
| 943 |
+
[[34m2025-10-30 00:52:23[0m] (step=0085300) Train Loss: 0.4697, Train Steps/Sec: 1.24
|
| 944 |
+
[[34m2025-10-30 00:53:44[0m] (step=0085400) Train Loss: 0.4705, Train Steps/Sec: 1.24
|
| 945 |
+
[[34m2025-10-30 00:55:05[0m] (step=0085500) Train Loss: 0.4710, Train Steps/Sec: 1.24
|
| 946 |
+
[[34m2025-10-30 00:56:25[0m] (step=0085600) Train Loss: 0.4715, Train Steps/Sec: 1.24
|
| 947 |
+
[[34m2025-10-30 00:57:46[0m] (step=0085700) Train Loss: 0.4717, Train Steps/Sec: 1.24
|
| 948 |
+
[[34m2025-10-30 00:59:07[0m] (step=0085800) Train Loss: 0.4711, Train Steps/Sec: 1.24
|
| 949 |
+
[[34m2025-10-30 01:00:27[0m] (step=0085900) Train Loss: 0.4703, Train Steps/Sec: 1.24
|
| 950 |
+
[[34m2025-10-30 01:01:48[0m] (step=0086000) Train Loss: 0.4704, Train Steps/Sec: 1.24
|
| 951 |
+
[[34m2025-10-30 01:03:09[0m] (step=0086100) Train Loss: 0.4716, Train Steps/Sec: 1.24
|
| 952 |
+
[[34m2025-10-30 01:04:30[0m] (step=0086200) Train Loss: 0.4716, Train Steps/Sec: 1.24
|
| 953 |
+
[[34m2025-10-30 01:05:51[0m] (step=0086300) Train Loss: 0.4692, Train Steps/Sec: 1.23
|
| 954 |
+
[[34m2025-10-30 01:06:07[0m] Beginning epoch 69...
|
| 955 |
+
[[34m2025-10-30 01:07:14[0m] (step=0086400) Train Loss: 0.4697, Train Steps/Sec: 1.20
|
| 956 |
+
[[34m2025-10-30 01:08:35[0m] (step=0086500) Train Loss: 0.4682, Train Steps/Sec: 1.24
|
| 957 |
+
[[34m2025-10-30 01:09:55[0m] (step=0086600) Train Loss: 0.4702, Train Steps/Sec: 1.24
|
| 958 |
+
[[34m2025-10-30 01:11:16[0m] (step=0086700) Train Loss: 0.4680, Train Steps/Sec: 1.24
|
| 959 |
+
[[34m2025-10-30 01:12:37[0m] (step=0086800) Train Loss: 0.4696, Train Steps/Sec: 1.24
|
| 960 |
+
[[34m2025-10-30 01:13:58[0m] (step=0086900) Train Loss: 0.4687, Train Steps/Sec: 1.24
|
| 961 |
+
[[34m2025-10-30 01:15:18[0m] (step=0087000) Train Loss: 0.4708, Train Steps/Sec: 1.24
|
| 962 |
+
[[34m2025-10-30 01:16:39[0m] (step=0087100) Train Loss: 0.4705, Train Steps/Sec: 1.24
|
| 963 |
+
[[34m2025-10-30 01:18:00[0m] (step=0087200) Train Loss: 0.4701, Train Steps/Sec: 1.24
|
| 964 |
+
[[34m2025-10-30 01:19:21[0m] (step=0087300) Train Loss: 0.4718, Train Steps/Sec: 1.24
|
| 965 |
+
[[34m2025-10-30 01:20:41[0m] (step=0087400) Train Loss: 0.4696, Train Steps/Sec: 1.24
|
| 966 |
+
[[34m2025-10-30 01:22:02[0m] (step=0087500) Train Loss: 0.4703, Train Steps/Sec: 1.24
|
| 967 |
+
[[34m2025-10-30 01:22:59[0m] Beginning epoch 70...
|
| 968 |
+
[[34m2025-10-30 01:23:25[0m] (step=0087600) Train Loss: 0.4706, Train Steps/Sec: 1.20
|
| 969 |
+
[[34m2025-10-30 01:24:46[0m] (step=0087700) Train Loss: 0.4691, Train Steps/Sec: 1.24
|
| 970 |
+
[[34m2025-10-30 01:26:06[0m] (step=0087800) Train Loss: 0.4699, Train Steps/Sec: 1.24
|
| 971 |
+
[[34m2025-10-30 01:27:27[0m] (step=0087900) Train Loss: 0.4695, Train Steps/Sec: 1.24
|
| 972 |
+
[[34m2025-10-30 01:28:49[0m] (step=0088000) Train Loss: 0.4696, Train Steps/Sec: 1.23
|
| 973 |
+
[[34m2025-10-30 01:30:09[0m] (step=0088100) Train Loss: 0.4684, Train Steps/Sec: 1.24
|
| 974 |
+
[[34m2025-10-30 01:31:30[0m] (step=0088200) Train Loss: 0.4715, Train Steps/Sec: 1.24
|
| 975 |
+
[[34m2025-10-30 01:32:51[0m] (step=0088300) Train Loss: 0.4707, Train Steps/Sec: 1.24
|
| 976 |
+
[[34m2025-10-30 01:34:11[0m] (step=0088400) Train Loss: 0.4693, Train Steps/Sec: 1.24
|
| 977 |
+
[[34m2025-10-30 01:35:32[0m] (step=0088500) Train Loss: 0.4693, Train Steps/Sec: 1.24
|
| 978 |
+
[[34m2025-10-30 01:36:53[0m] (step=0088600) Train Loss: 0.4697, Train Steps/Sec: 1.24
|
| 979 |
+
[[34m2025-10-30 01:38:13[0m] (step=0088700) Train Loss: 0.4705, Train Steps/Sec: 1.24
|
| 980 |
+
[[34m2025-10-30 01:39:34[0m] (step=0088800) Train Loss: 0.4704, Train Steps/Sec: 1.24
|
| 981 |
+
[[34m2025-10-30 01:39:52[0m] Beginning epoch 71...
|
| 982 |
+
[[34m2025-10-30 01:40:57[0m] (step=0088900) Train Loss: 0.4679, Train Steps/Sec: 1.21
|
| 983 |
+
[[34m2025-10-30 01:42:18[0m] (step=0089000) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 984 |
+
[[34m2025-10-30 01:43:38[0m] (step=0089100) Train Loss: 0.4699, Train Steps/Sec: 1.24
|
| 985 |
+
[[34m2025-10-30 01:44:59[0m] (step=0089200) Train Loss: 0.4697, Train Steps/Sec: 1.24
|
| 986 |
+
[[34m2025-10-30 01:46:20[0m] (step=0089300) Train Loss: 0.4695, Train Steps/Sec: 1.24
|
| 987 |
+
[[34m2025-10-30 01:47:40[0m] (step=0089400) Train Loss: 0.4688, Train Steps/Sec: 1.24
|
| 988 |
+
[[34m2025-10-30 01:49:01[0m] (step=0089500) Train Loss: 0.4692, Train Steps/Sec: 1.24
|
| 989 |
+
[[34m2025-10-30 01:50:22[0m] (step=0089600) Train Loss: 0.4713, Train Steps/Sec: 1.23
|
| 990 |
+
[[34m2025-10-30 01:51:43[0m] (step=0089700) Train Loss: 0.4687, Train Steps/Sec: 1.23
|
| 991 |
+
[[34m2025-10-30 01:53:04[0m] (step=0089800) Train Loss: 0.4702, Train Steps/Sec: 1.24
|
| 992 |
+
[[34m2025-10-30 01:54:25[0m] (step=0089900) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 993 |
+
[[34m2025-10-30 01:55:45[0m] (step=0090000) Train Loss: 0.4696, Train Steps/Sec: 1.24
|
| 994 |
+
[[34m2025-10-30 01:56:44[0m] Beginning epoch 72...
|
| 995 |
+
[[34m2025-10-30 01:57:08[0m] (step=0090100) Train Loss: 0.4688, Train Steps/Sec: 1.21
|
| 996 |
+
[[34m2025-10-30 01:58:29[0m] (step=0090200) Train Loss: 0.4676, Train Steps/Sec: 1.24
|
| 997 |
+
[[34m2025-10-30 01:59:50[0m] (step=0090300) Train Loss: 0.4703, Train Steps/Sec: 1.24
|
| 998 |
+
[[34m2025-10-30 02:01:10[0m] (step=0090400) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 999 |
+
[[34m2025-10-30 02:02:31[0m] (step=0090500) Train Loss: 0.4679, Train Steps/Sec: 1.24
|
| 1000 |
+
[[34m2025-10-30 02:03:52[0m] (step=0090600) Train Loss: 0.4705, Train Steps/Sec: 1.24
|
| 1001 |
+
[[34m2025-10-30 02:05:12[0m] (step=0090700) Train Loss: 0.4695, Train Steps/Sec: 1.24
|
| 1002 |
+
[[34m2025-10-30 02:06:33[0m] (step=0090800) Train Loss: 0.4697, Train Steps/Sec: 1.24
|
| 1003 |
+
[[34m2025-10-30 02:07:54[0m] (step=0090900) Train Loss: 0.4677, Train Steps/Sec: 1.24
|
| 1004 |
+
[[34m2025-10-30 02:09:14[0m] (step=0091000) Train Loss: 0.4694, Train Steps/Sec: 1.24
|
| 1005 |
+
[[34m2025-10-30 02:10:35[0m] (step=0091100) Train Loss: 0.4688, Train Steps/Sec: 1.24
|
| 1006 |
+
[[34m2025-10-30 02:11:56[0m] (step=0091200) Train Loss: 0.4690, Train Steps/Sec: 1.24
|
| 1007 |
+
[[34m2025-10-30 02:13:17[0m] (step=0091300) Train Loss: 0.4683, Train Steps/Sec: 1.23
|
| 1008 |
+
[[34m2025-10-30 02:13:36[0m] Beginning epoch 73...
|
| 1009 |
+
[[34m2025-10-30 02:14:40[0m] (step=0091400) Train Loss: 0.4693, Train Steps/Sec: 1.20
|
| 1010 |
+
[[34m2025-10-30 02:16:01[0m] (step=0091500) Train Loss: 0.4688, Train Steps/Sec: 1.24
|
| 1011 |
+
[[34m2025-10-30 02:17:22[0m] (step=0091600) Train Loss: 0.4699, Train Steps/Sec: 1.24
|
| 1012 |
+
[[34m2025-10-30 02:18:42[0m] (step=0091700) Train Loss: 0.4682, Train Steps/Sec: 1.24
|
| 1013 |
+
[[34m2025-10-30 02:20:03[0m] (step=0091800) Train Loss: 0.4693, Train Steps/Sec: 1.24
|
| 1014 |
+
[[34m2025-10-30 02:21:24[0m] (step=0091900) Train Loss: 0.4691, Train Steps/Sec: 1.24
|
| 1015 |
+
[[34m2025-10-30 02:22:44[0m] (step=0092000) Train Loss: 0.4703, Train Steps/Sec: 1.24
|
| 1016 |
+
[[34m2025-10-30 02:24:05[0m] (step=0092100) Train Loss: 0.4698, Train Steps/Sec: 1.24
|
| 1017 |
+
[[34m2025-10-30 02:25:26[0m] (step=0092200) Train Loss: 0.4678, Train Steps/Sec: 1.24
|
| 1018 |
+
[[34m2025-10-30 02:26:47[0m] (step=0092300) Train Loss: 0.4690, Train Steps/Sec: 1.24
|
| 1019 |
+
[[34m2025-10-30 02:28:07[0m] (step=0092400) Train Loss: 0.4687, Train Steps/Sec: 1.24
|
| 1020 |
+
[[34m2025-10-30 02:29:28[0m] (step=0092500) Train Loss: 0.4696, Train Steps/Sec: 1.24
|
| 1021 |
+
[[34m2025-10-30 02:30:28[0m] Beginning epoch 74...
|
| 1022 |
+
[[34m2025-10-30 02:30:51[0m] (step=0092600) Train Loss: 0.4681, Train Steps/Sec: 1.20
|
| 1023 |
+
[[34m2025-10-30 02:32:12[0m] (step=0092700) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 1024 |
+
[[34m2025-10-30 02:33:33[0m] (step=0092800) Train Loss: 0.4673, Train Steps/Sec: 1.24
|
| 1025 |
+
[[34m2025-10-30 02:34:54[0m] (step=0092900) Train Loss: 0.4692, Train Steps/Sec: 1.24
|
| 1026 |
+
[[34m2025-10-30 02:36:15[0m] (step=0093000) Train Loss: 0.4679, Train Steps/Sec: 1.23
|
| 1027 |
+
[[34m2025-10-30 02:37:36[0m] (step=0093100) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 1028 |
+
[[34m2025-10-30 02:38:57[0m] (step=0093200) Train Loss: 0.4692, Train Steps/Sec: 1.24
|
| 1029 |
+
[[34m2025-10-30 02:40:17[0m] (step=0093300) Train Loss: 0.4685, Train Steps/Sec: 1.24
|
| 1030 |
+
[[34m2025-10-30 02:41:38[0m] (step=0093400) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 1031 |
+
[[34m2025-10-30 02:42:59[0m] (step=0093500) Train Loss: 0.4683, Train Steps/Sec: 1.24
|
| 1032 |
+
[[34m2025-10-30 02:44:19[0m] (step=0093600) Train Loss: 0.4700, Train Steps/Sec: 1.24
|
| 1033 |
+
[[34m2025-10-30 02:45:40[0m] (step=0093700) Train Loss: 0.4685, Train Steps/Sec: 1.24
|
| 1034 |
+
[[34m2025-10-30 02:47:01[0m] (step=0093800) Train Loss: 0.4677, Train Steps/Sec: 1.24
|
| 1035 |
+
[[34m2025-10-30 02:47:22[0m] Beginning epoch 75...
|
| 1036 |
+
[[34m2025-10-30 02:48:24[0m] (step=0093900) Train Loss: 0.4683, Train Steps/Sec: 1.20
|
| 1037 |
+
[[34m2025-10-30 02:49:45[0m] (step=0094000) Train Loss: 0.4677, Train Steps/Sec: 1.24
|
| 1038 |
+
[[34m2025-10-30 02:51:05[0m] (step=0094100) Train Loss: 0.4677, Train Steps/Sec: 1.24
|
| 1039 |
+
[[34m2025-10-30 02:52:26[0m] (step=0094200) Train Loss: 0.4697, Train Steps/Sec: 1.24
|
| 1040 |
+
[[34m2025-10-30 02:53:47[0m] (step=0094300) Train Loss: 0.4680, Train Steps/Sec: 1.24
|
| 1041 |
+
[[34m2025-10-30 02:55:08[0m] (step=0094400) Train Loss: 0.4683, Train Steps/Sec: 1.24
|
| 1042 |
+
[[34m2025-10-30 02:56:28[0m] (step=0094500) Train Loss: 0.4672, Train Steps/Sec: 1.24
|
| 1043 |
+
[[34m2025-10-30 02:57:49[0m] (step=0094600) Train Loss: 0.4683, Train Steps/Sec: 1.24
|
| 1044 |
+
[[34m2025-10-30 02:59:10[0m] (step=0094700) Train Loss: 0.4679, Train Steps/Sec: 1.23
|
| 1045 |
+
[[34m2025-10-30 03:00:31[0m] (step=0094800) Train Loss: 0.4683, Train Steps/Sec: 1.24
|
| 1046 |
+
[[34m2025-10-30 03:01:52[0m] (step=0094900) Train Loss: 0.4691, Train Steps/Sec: 1.24
|
| 1047 |
+
[[34m2025-10-30 03:03:12[0m] (step=0095000) Train Loss: 0.4690, Train Steps/Sec: 1.24
|
| 1048 |
+
[[34m2025-10-30 03:04:14[0m] Beginning epoch 76...
|
| 1049 |
+
[[34m2025-10-30 03:04:36[0m] (step=0095100) Train Loss: 0.4680, Train Steps/Sec: 1.20
|
| 1050 |
+
[[34m2025-10-30 03:05:56[0m] (step=0095200) Train Loss: 0.4681, Train Steps/Sec: 1.24
|
| 1051 |
+
[[34m2025-10-30 03:07:17[0m] (step=0095300) Train Loss: 0.4687, Train Steps/Sec: 1.24
|
| 1052 |
+
[[34m2025-10-30 03:08:38[0m] (step=0095400) Train Loss: 0.4675, Train Steps/Sec: 1.24
|
| 1053 |
+
[[34m2025-10-30 03:09:59[0m] (step=0095500) Train Loss: 0.4665, Train Steps/Sec: 1.24
|
| 1054 |
+
[[34m2025-10-30 03:11:19[0m] (step=0095600) Train Loss: 0.4686, Train Steps/Sec: 1.24
|
| 1055 |
+
[[34m2025-10-30 03:12:40[0m] (step=0095700) Train Loss: 0.4660, Train Steps/Sec: 1.24
|
| 1056 |
+
[[34m2025-10-30 03:14:01[0m] (step=0095800) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 1057 |
+
[[34m2025-10-30 03:15:21[0m] (step=0095900) Train Loss: 0.4687, Train Steps/Sec: 1.24
|
| 1058 |
+
[[34m2025-10-30 03:16:42[0m] (step=0096000) Train Loss: 0.4674, Train Steps/Sec: 1.24
|
| 1059 |
+
[[34m2025-10-30 03:18:03[0m] (step=0096100) Train Loss: 0.4673, Train Steps/Sec: 1.24
|
| 1060 |
+
[[34m2025-10-30 03:19:24[0m] (step=0096200) Train Loss: 0.4675, Train Steps/Sec: 1.24
|
| 1061 |
+
[[34m2025-10-30 03:20:45[0m] (step=0096300) Train Loss: 0.4680, Train Steps/Sec: 1.23
|
| 1062 |
+
[[34m2025-10-30 03:21:07[0m] Beginning epoch 77...
|
| 1063 |
+
[[34m2025-10-30 03:22:09[0m] (step=0096400) Train Loss: 0.4679, Train Steps/Sec: 1.19
|
| 1064 |
+
[[34m2025-10-30 03:23:29[0m] (step=0096500) Train Loss: 0.4695, Train Steps/Sec: 1.24
|
| 1065 |
+
[[34m2025-10-30 03:24:50[0m] (step=0096600) Train Loss: 0.4672, Train Steps/Sec: 1.24
|
| 1066 |
+
[[34m2025-10-30 03:26:11[0m] (step=0096700) Train Loss: 0.4681, Train Steps/Sec: 1.24
|
| 1067 |
+
[[34m2025-10-30 03:27:31[0m] (step=0096800) Train Loss: 0.4678, Train Steps/Sec: 1.24
|
| 1068 |
+
[[34m2025-10-30 03:28:52[0m] (step=0096900) Train Loss: 0.4677, Train Steps/Sec: 1.24
|
| 1069 |
+
[[34m2025-10-30 03:30:13[0m] (step=0097000) Train Loss: 0.4670, Train Steps/Sec: 1.24
|
| 1070 |
+
[[34m2025-10-30 03:31:34[0m] (step=0097100) Train Loss: 0.4685, Train Steps/Sec: 1.24
|
| 1071 |
+
[[34m2025-10-30 03:32:54[0m] (step=0097200) Train Loss: 0.4682, Train Steps/Sec: 1.24
|
| 1072 |
+
[[34m2025-10-30 03:34:15[0m] (step=0097300) Train Loss: 0.4686, Train Steps/Sec: 1.24
|
| 1073 |
+
[[34m2025-10-30 03:35:36[0m] (step=0097400) Train Loss: 0.4678, Train Steps/Sec: 1.24
|
| 1074 |
+
[[34m2025-10-30 03:36:56[0m] (step=0097500) Train Loss: 0.4674, Train Steps/Sec: 1.24
|
| 1075 |
+
[[34m2025-10-30 03:38:00[0m] Beginning epoch 78...
|
| 1076 |
+
[[34m2025-10-30 03:38:19[0m] (step=0097600) Train Loss: 0.4676, Train Steps/Sec: 1.20
|
| 1077 |
+
[[34m2025-10-30 03:39:40[0m] (step=0097700) Train Loss: 0.4660, Train Steps/Sec: 1.24
|
| 1078 |
+
[[34m2025-10-30 03:41:01[0m] (step=0097800) Train Loss: 0.4675, Train Steps/Sec: 1.24
|
| 1079 |
+
[[34m2025-10-30 03:42:21[0m] (step=0097900) Train Loss: 0.4668, Train Steps/Sec: 1.24
|
| 1080 |
+
[[34m2025-10-30 03:43:43[0m] (step=0098000) Train Loss: 0.4692, Train Steps/Sec: 1.23
|
| 1081 |
+
[[34m2025-10-30 03:45:04[0m] (step=0098100) Train Loss: 0.4672, Train Steps/Sec: 1.24
|
| 1082 |
+
[[34m2025-10-30 03:46:24[0m] (step=0098200) Train Loss: 0.4666, Train Steps/Sec: 1.24
|
| 1083 |
+
[[34m2025-10-30 03:47:45[0m] (step=0098300) Train Loss: 0.4670, Train Steps/Sec: 1.24
|
| 1084 |
+
[[34m2025-10-30 03:49:06[0m] (step=0098400) Train Loss: 0.4668, Train Steps/Sec: 1.24
|
| 1085 |
+
[[34m2025-10-30 03:50:26[0m] (step=0098500) Train Loss: 0.4660, Train Steps/Sec: 1.24
|
| 1086 |
+
[[34m2025-10-30 03:51:47[0m] (step=0098600) Train Loss: 0.4667, Train Steps/Sec: 1.24
|
| 1087 |
+
[[34m2025-10-30 03:53:08[0m] (step=0098700) Train Loss: 0.4676, Train Steps/Sec: 1.24
|
| 1088 |
+
[[34m2025-10-30 03:54:28[0m] (step=0098800) Train Loss: 0.4674, Train Steps/Sec: 1.24
|
| 1089 |
+
[[34m2025-10-30 03:54:52[0m] Beginning epoch 79...
|
| 1090 |
+
[[34m2025-10-30 03:55:51[0m] (step=0098900) Train Loss: 0.4665, Train Steps/Sec: 1.20
|
| 1091 |
+
[[34m2025-10-30 03:57:12[0m] (step=0099000) Train Loss: 0.4671, Train Steps/Sec: 1.24
|
| 1092 |
+
[[34m2025-10-30 03:58:33[0m] (step=0099100) Train Loss: 0.4689, Train Steps/Sec: 1.24
|
| 1093 |
+
[[34m2025-10-30 03:59:53[0m] (step=0099200) Train Loss: 0.4663, Train Steps/Sec: 1.24
|
| 1094 |
+
[[34m2025-10-30 04:01:14[0m] (step=0099300) Train Loss: 0.4681, Train Steps/Sec: 1.24
|
| 1095 |
+
[[34m2025-10-30 04:02:35[0m] (step=0099400) Train Loss: 0.4676, Train Steps/Sec: 1.24
|
| 1096 |
+
[[34m2025-10-30 04:03:55[0m] (step=0099500) Train Loss: 0.4661, Train Steps/Sec: 1.24
|
| 1097 |
+
[[34m2025-10-30 04:05:16[0m] (step=0099600) Train Loss: 0.4669, Train Steps/Sec: 1.24
|
| 1098 |
+
[[34m2025-10-30 04:06:38[0m] (step=0099700) Train Loss: 0.4673, Train Steps/Sec: 1.22
|
| 1099 |
+
[[34m2025-10-30 04:07:58[0m] (step=0099800) Train Loss: 0.4679, Train Steps/Sec: 1.24
|
| 1100 |
+
[[34m2025-10-30 04:09:19[0m] (step=0099900) Train Loss: 0.4686, Train Steps/Sec: 1.24
|
| 1101 |
+
[[34m2025-10-30 04:10:40[0m] (step=0100000) Train Loss: 0.4668, Train Steps/Sec: 1.24
|
| 1102 |
+
[[34m2025-10-30 04:11:36[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-b-bf16/checkpoints/0100000.pt
|
| 1103 |
+
[[34m2025-10-30 04:11:36[0m] Generating EMA samples...
|
| 1104 |
+
[[34m2025-10-30 04:12:04[0m] Generating EMA samples done.
|
| 1105 |
+
[[34m2025-10-30 04:13:09[0m] Done!
|