Upload folder using huggingface_hub
Browse files
stage2/lightningdit-xl-dinov2-vit-l-bf16/checkpoints/0025000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c69c2d3ac5c47ee43893477aa530a0ebbbeff3fcd17f3e563189d699a41643
|
| 3 |
+
size 19243018610
|
stage2/lightningdit-xl-dinov2-vit-l-bf16/checkpoints/0050000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8d966c2d54cabc48ec1342137d74368ec39f56f5da19127346b49bd27943c96
|
| 3 |
+
size 19243018610
|
stage2/lightningdit-xl-dinov2-vit-l-bf16/checkpoints/0075000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b682923a8191050f30d1becbb63f1f3f31df0c81c9dc95beabf55163ac2c9353
|
| 3 |
+
size 19243018674
|
stage2/lightningdit-xl-dinov2-vit-l-bf16/log.txt
ADDED
|
@@ -0,0 +1,1042 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[[34m2025-10-29 05:42:47[0m] Experiment directory created at results/stage2/hfdata/lightningdit-xl-dinov2-vit-l-bf16
|
| 2 |
+
[[34m2025-10-29 05:42:51[0m] using MLP layer as FFN
|
| 3 |
+
[[34m2025-10-29 05:43:10[0m] Model Parameters: 1202.82M
|
| 4 |
+
[[34m2025-10-29 05:43:15[0m] Dataset contains 1,281,167 images (/scratch/xingjian.leng/data/dinov2-vit-l_hfdataset_precentercrop_True_train_bfloat16)
|
| 5 |
+
[[34m2025-10-29 05:43:15[0m] Gradient accumulation: steps=1, micro batch=128, per-GPU batch=128, global batch=1024
|
| 6 |
+
[[34m2025-10-29 05:43:15[0m] Precision mode: bf16
|
| 7 |
+
[[34m2025-10-29 05:43:15[0m] Training configured for 80 epochs, 1251 steps per epoch.
|
| 8 |
+
[[34m2025-10-29 05:43:15[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 05:43:16[0m] Training for 80 epochs...
|
| 11 |
+
[[34m2025-10-29 05:43:16[0m] Beginning epoch 0...
|
| 12 |
+
[[34m2025-10-29 05:43:22[0m] Generating EMA samples...
|
| 13 |
+
[[34m2025-10-29 05:43:52[0m] Generating EMA samples done.
|
| 14 |
+
[[34m2025-10-29 05:45:18[0m] (step=0000100) Train Loss: 1.6582, Train Steps/Sec: 0.81
|
| 15 |
+
[[34m2025-10-29 05:46:47[0m] (step=0000200) Train Loss: 1.3236, Train Steps/Sec: 1.13
|
| 16 |
+
[[34m2025-10-29 05:48:15[0m] (step=0000300) Train Loss: 1.1640, Train Steps/Sec: 1.14
|
| 17 |
+
[[34m2025-10-29 05:49:43[0m] (step=0000400) Train Loss: 1.0483, Train Steps/Sec: 1.14
|
| 18 |
+
[[34m2025-10-29 05:51:11[0m] (step=0000500) Train Loss: 0.9756, Train Steps/Sec: 1.14
|
| 19 |
+
[[34m2025-10-29 05:52:39[0m] (step=0000600) Train Loss: 0.9281, Train Steps/Sec: 1.14
|
| 20 |
+
[[34m2025-10-29 05:54:07[0m] (step=0000700) Train Loss: 0.8916, Train Steps/Sec: 1.14
|
| 21 |
+
[[34m2025-10-29 05:55:35[0m] (step=0000800) Train Loss: 0.8646, Train Steps/Sec: 1.14
|
| 22 |
+
[[34m2025-10-29 05:57:03[0m] (step=0000900) Train Loss: 0.8404, Train Steps/Sec: 1.14
|
| 23 |
+
[[34m2025-10-29 05:58:31[0m] (step=0001000) Train Loss: 0.8239, Train Steps/Sec: 1.13
|
| 24 |
+
[[34m2025-10-29 05:59:59[0m] (step=0001100) Train Loss: 0.8083, Train Steps/Sec: 1.14
|
| 25 |
+
[[34m2025-10-29 06:01:27[0m] (step=0001200) Train Loss: 0.7963, Train Steps/Sec: 1.14
|
| 26 |
+
[[34m2025-10-29 06:02:13[0m] Beginning epoch 1...
|
| 27 |
+
[[34m2025-10-29 06:02:58[0m] (step=0001300) Train Loss: 0.7846, Train Steps/Sec: 1.10
|
| 28 |
+
[[34m2025-10-29 06:04:26[0m] (step=0001400) Train Loss: 0.7747, Train Steps/Sec: 1.14
|
| 29 |
+
[[34m2025-10-29 06:05:54[0m] (step=0001500) Train Loss: 0.7656, Train Steps/Sec: 1.14
|
| 30 |
+
[[34m2025-10-29 06:07:22[0m] (step=0001600) Train Loss: 0.7572, Train Steps/Sec: 1.14
|
| 31 |
+
[[34m2025-10-29 06:08:50[0m] (step=0001700) Train Loss: 0.7531, Train Steps/Sec: 1.13
|
| 32 |
+
[[34m2025-10-29 06:10:19[0m] (step=0001800) Train Loss: 0.7464, Train Steps/Sec: 1.13
|
| 33 |
+
[[34m2025-10-29 06:11:47[0m] (step=0001900) Train Loss: 0.7397, Train Steps/Sec: 1.13
|
| 34 |
+
[[34m2025-10-29 06:13:15[0m] (step=0002000) Train Loss: 0.7344, Train Steps/Sec: 1.13
|
| 35 |
+
[[34m2025-10-29 06:14:43[0m] (step=0002100) Train Loss: 0.7300, Train Steps/Sec: 1.14
|
| 36 |
+
[[34m2025-10-29 06:16:12[0m] (step=0002200) Train Loss: 0.7264, Train Steps/Sec: 1.14
|
| 37 |
+
[[34m2025-10-29 06:17:40[0m] (step=0002300) Train Loss: 0.7221, Train Steps/Sec: 1.14
|
| 38 |
+
[[34m2025-10-29 06:19:08[0m] (step=0002400) Train Loss: 0.7189, Train Steps/Sec: 1.14
|
| 39 |
+
[[34m2025-10-29 06:20:36[0m] (step=0002500) Train Loss: 0.7117, Train Steps/Sec: 1.13
|
| 40 |
+
[[34m2025-10-29 06:20:38[0m] Beginning epoch 2...
|
| 41 |
+
[[34m2025-10-29 06:22:06[0m] (step=0002600) Train Loss: 0.7093, Train Steps/Sec: 1.10
|
| 42 |
+
[[34m2025-10-29 06:23:35[0m] (step=0002700) Train Loss: 0.7069, Train Steps/Sec: 1.13
|
| 43 |
+
[[34m2025-10-29 06:25:03[0m] (step=0002800) Train Loss: 0.7034, Train Steps/Sec: 1.14
|
| 44 |
+
[[34m2025-10-29 06:26:31[0m] (step=0002900) Train Loss: 0.7012, Train Steps/Sec: 1.14
|
| 45 |
+
[[34m2025-10-29 06:27:59[0m] (step=0003000) Train Loss: 0.6985, Train Steps/Sec: 1.13
|
| 46 |
+
[[34m2025-10-29 06:29:27[0m] (step=0003100) Train Loss: 0.6970, Train Steps/Sec: 1.14
|
| 47 |
+
[[34m2025-10-29 06:30:55[0m] (step=0003200) Train Loss: 0.6928, Train Steps/Sec: 1.13
|
| 48 |
+
[[34m2025-10-29 06:32:23[0m] (step=0003300) Train Loss: 0.6917, Train Steps/Sec: 1.14
|
| 49 |
+
[[34m2025-10-29 06:33:52[0m] (step=0003400) Train Loss: 0.6886, Train Steps/Sec: 1.14
|
| 50 |
+
[[34m2025-10-29 06:35:20[0m] (step=0003500) Train Loss: 0.6870, Train Steps/Sec: 1.14
|
| 51 |
+
[[34m2025-10-29 06:36:48[0m] (step=0003600) Train Loss: 0.6858, Train Steps/Sec: 1.13
|
| 52 |
+
[[34m2025-10-29 06:38:16[0m] (step=0003700) Train Loss: 0.6826, Train Steps/Sec: 1.14
|
| 53 |
+
[[34m2025-10-29 06:39:03[0m] Beginning epoch 3...
|
| 54 |
+
[[34m2025-10-29 06:39:47[0m] (step=0003800) Train Loss: 0.6810, Train Steps/Sec: 1.11
|
| 55 |
+
[[34m2025-10-29 06:41:15[0m] (step=0003900) Train Loss: 0.6798, Train Steps/Sec: 1.14
|
| 56 |
+
[[34m2025-10-29 06:42:43[0m] (step=0004000) Train Loss: 0.6775, Train Steps/Sec: 1.13
|
| 57 |
+
[[34m2025-10-29 06:44:11[0m] (step=0004100) Train Loss: 0.6768, Train Steps/Sec: 1.14
|
| 58 |
+
[[34m2025-10-29 06:45:39[0m] (step=0004200) Train Loss: 0.6743, Train Steps/Sec: 1.13
|
| 59 |
+
[[34m2025-10-29 06:47:07[0m] (step=0004300) Train Loss: 0.6721, Train Steps/Sec: 1.14
|
| 60 |
+
[[34m2025-10-29 06:48:36[0m] (step=0004400) Train Loss: 0.6716, Train Steps/Sec: 1.13
|
| 61 |
+
[[34m2025-10-29 06:50:04[0m] (step=0004500) Train Loss: 0.6702, Train Steps/Sec: 1.14
|
| 62 |
+
[[34m2025-10-29 06:51:32[0m] (step=0004600) Train Loss: 0.6701, Train Steps/Sec: 1.14
|
| 63 |
+
[[34m2025-10-29 06:53:00[0m] (step=0004700) Train Loss: 0.6667, Train Steps/Sec: 1.13
|
| 64 |
+
[[34m2025-10-29 06:54:28[0m] (step=0004800) Train Loss: 0.6661, Train Steps/Sec: 1.13
|
| 65 |
+
[[34m2025-10-29 06:55:56[0m] (step=0004900) Train Loss: 0.6642, Train Steps/Sec: 1.14
|
| 66 |
+
[[34m2025-10-29 06:57:24[0m] (step=0005000) Train Loss: 0.6637, Train Steps/Sec: 1.14
|
| 67 |
+
[[34m2025-10-29 06:57:28[0m] Beginning epoch 4...
|
| 68 |
+
[[34m2025-10-29 06:58:55[0m] (step=0005100) Train Loss: 0.6613, Train Steps/Sec: 1.10
|
| 69 |
+
[[34m2025-10-29 07:00:23[0m] (step=0005200) Train Loss: 0.6614, Train Steps/Sec: 1.13
|
| 70 |
+
[[34m2025-10-29 07:01:52[0m] (step=0005300) Train Loss: 0.6602, Train Steps/Sec: 1.13
|
| 71 |
+
[[34m2025-10-29 07:03:20[0m] (step=0005400) Train Loss: 0.6597, Train Steps/Sec: 1.14
|
| 72 |
+
[[34m2025-10-29 07:04:48[0m] (step=0005500) Train Loss: 0.6577, Train Steps/Sec: 1.14
|
| 73 |
+
[[34m2025-10-29 07:06:16[0m] (step=0005600) Train Loss: 0.6574, Train Steps/Sec: 1.13
|
| 74 |
+
[[34m2025-10-29 07:07:44[0m] (step=0005700) Train Loss: 0.6562, Train Steps/Sec: 1.14
|
| 75 |
+
[[34m2025-10-29 07:09:12[0m] (step=0005800) Train Loss: 0.6556, Train Steps/Sec: 1.14
|
| 76 |
+
[[34m2025-10-29 07:10:40[0m] (step=0005900) Train Loss: 0.6547, Train Steps/Sec: 1.14
|
| 77 |
+
[[34m2025-10-29 07:12:09[0m] (step=0006000) Train Loss: 0.6535, Train Steps/Sec: 1.14
|
| 78 |
+
[[34m2025-10-29 07:13:37[0m] (step=0006100) Train Loss: 0.6530, Train Steps/Sec: 1.14
|
| 79 |
+
[[34m2025-10-29 07:15:05[0m] (step=0006200) Train Loss: 0.6520, Train Steps/Sec: 1.13
|
| 80 |
+
[[34m2025-10-29 07:15:54[0m] Beginning epoch 5...
|
| 81 |
+
[[34m2025-10-29 07:16:35[0m] (step=0006300) Train Loss: 0.6503, Train Steps/Sec: 1.11
|
| 82 |
+
[[34m2025-10-29 07:18:04[0m] (step=0006400) Train Loss: 0.6494, Train Steps/Sec: 1.13
|
| 83 |
+
[[34m2025-10-29 07:19:32[0m] (step=0006500) Train Loss: 0.6497, Train Steps/Sec: 1.14
|
| 84 |
+
[[34m2025-10-29 07:21:00[0m] (step=0006600) Train Loss: 0.6500, Train Steps/Sec: 1.14
|
| 85 |
+
[[34m2025-10-29 07:22:28[0m] (step=0006700) Train Loss: 0.6466, Train Steps/Sec: 1.13
|
| 86 |
+
[[34m2025-10-29 07:23:56[0m] (step=0006800) Train Loss: 0.6459, Train Steps/Sec: 1.14
|
| 87 |
+
[[34m2025-10-29 07:25:24[0m] (step=0006900) Train Loss: 0.6470, Train Steps/Sec: 1.14
|
| 88 |
+
[[34m2025-10-29 07:26:53[0m] (step=0007000) Train Loss: 0.6457, Train Steps/Sec: 1.13
|
| 89 |
+
[[34m2025-10-29 07:28:21[0m] (step=0007100) Train Loss: 0.6445, Train Steps/Sec: 1.14
|
| 90 |
+
[[34m2025-10-29 07:29:49[0m] (step=0007200) Train Loss: 0.6456, Train Steps/Sec: 1.14
|
| 91 |
+
[[34m2025-10-29 07:31:17[0m] (step=0007300) Train Loss: 0.6432, Train Steps/Sec: 1.14
|
| 92 |
+
[[34m2025-10-29 07:32:45[0m] (step=0007400) Train Loss: 0.6431, Train Steps/Sec: 1.14
|
| 93 |
+
[[34m2025-10-29 07:34:13[0m] (step=0007500) Train Loss: 0.6415, Train Steps/Sec: 1.14
|
| 94 |
+
[[34m2025-10-29 07:34:19[0m] Beginning epoch 6...
|
| 95 |
+
[[34m2025-10-29 07:35:44[0m] (step=0007600) Train Loss: 0.6415, Train Steps/Sec: 1.10
|
| 96 |
+
[[34m2025-10-29 07:37:12[0m] (step=0007700) Train Loss: 0.6405, Train Steps/Sec: 1.14
|
| 97 |
+
[[34m2025-10-29 07:38:40[0m] (step=0007800) Train Loss: 0.6397, Train Steps/Sec: 1.14
|
| 98 |
+
[[34m2025-10-29 07:40:09[0m] (step=0007900) Train Loss: 0.6397, Train Steps/Sec: 1.13
|
| 99 |
+
[[34m2025-10-29 07:41:37[0m] (step=0008000) Train Loss: 0.6388, Train Steps/Sec: 1.14
|
| 100 |
+
[[34m2025-10-29 07:43:05[0m] (step=0008100) Train Loss: 0.6389, Train Steps/Sec: 1.14
|
| 101 |
+
[[34m2025-10-29 07:44:33[0m] (step=0008200) Train Loss: 0.6381, Train Steps/Sec: 1.14
|
| 102 |
+
[[34m2025-10-29 07:46:01[0m] (step=0008300) Train Loss: 0.6380, Train Steps/Sec: 1.14
|
| 103 |
+
[[34m2025-10-29 07:47:29[0m] (step=0008400) Train Loss: 0.6369, Train Steps/Sec: 1.14
|
| 104 |
+
[[34m2025-10-29 07:48:57[0m] (step=0008500) Train Loss: 0.6365, Train Steps/Sec: 1.14
|
| 105 |
+
[[34m2025-10-29 07:50:25[0m] (step=0008600) Train Loss: 0.6362, Train Steps/Sec: 1.14
|
| 106 |
+
[[34m2025-10-29 07:51:54[0m] (step=0008700) Train Loss: 0.6341, Train Steps/Sec: 1.13
|
| 107 |
+
[[34m2025-10-29 07:52:44[0m] Beginning epoch 7...
|
| 108 |
+
[[34m2025-10-29 07:53:24[0m] (step=0008800) Train Loss: 0.6342, Train Steps/Sec: 1.10
|
| 109 |
+
[[34m2025-10-29 07:54:52[0m] (step=0008900) Train Loss: 0.6339, Train Steps/Sec: 1.14
|
| 110 |
+
[[34m2025-10-29 07:56:20[0m] (step=0009000) Train Loss: 0.6339, Train Steps/Sec: 1.14
|
| 111 |
+
[[34m2025-10-29 07:57:48[0m] (step=0009100) Train Loss: 0.6342, Train Steps/Sec: 1.14
|
| 112 |
+
[[34m2025-10-29 07:59:16[0m] (step=0009200) Train Loss: 0.6330, Train Steps/Sec: 1.14
|
| 113 |
+
[[34m2025-10-29 08:00:44[0m] (step=0009300) Train Loss: 0.6327, Train Steps/Sec: 1.14
|
| 114 |
+
[[34m2025-10-29 08:02:12[0m] (step=0009400) Train Loss: 0.6308, Train Steps/Sec: 1.14
|
| 115 |
+
[[34m2025-10-29 08:03:41[0m] (step=0009500) Train Loss: 0.6304, Train Steps/Sec: 1.13
|
| 116 |
+
[[34m2025-10-29 08:05:09[0m] (step=0009600) Train Loss: 0.6299, Train Steps/Sec: 1.13
|
| 117 |
+
[[34m2025-10-29 08:06:37[0m] (step=0009700) Train Loss: 0.6294, Train Steps/Sec: 1.14
|
| 118 |
+
[[34m2025-10-29 08:08:05[0m] (step=0009800) Train Loss: 0.6308, Train Steps/Sec: 1.14
|
| 119 |
+
[[34m2025-10-29 08:09:33[0m] (step=0009900) Train Loss: 0.6289, Train Steps/Sec: 1.14
|
| 120 |
+
[[34m2025-10-29 08:11:01[0m] (step=0010000) Train Loss: 0.6291, Train Steps/Sec: 1.14
|
| 121 |
+
[[34m2025-10-29 08:11:09[0m] Beginning epoch 8...
|
| 122 |
+
[[34m2025-10-29 08:12:32[0m] (step=0010100) Train Loss: 0.6289, Train Steps/Sec: 1.10
|
| 123 |
+
[[34m2025-10-29 08:14:00[0m] (step=0010200) Train Loss: 0.6277, Train Steps/Sec: 1.14
|
| 124 |
+
[[34m2025-10-29 08:15:28[0m] (step=0010300) Train Loss: 0.6269, Train Steps/Sec: 1.13
|
| 125 |
+
[[34m2025-10-29 08:16:56[0m] (step=0010400) Train Loss: 0.6285, Train Steps/Sec: 1.14
|
| 126 |
+
[[34m2025-10-29 08:18:25[0m] (step=0010500) Train Loss: 0.6268, Train Steps/Sec: 1.13
|
| 127 |
+
[[34m2025-10-29 08:19:53[0m] (step=0010600) Train Loss: 0.6268, Train Steps/Sec: 1.14
|
| 128 |
+
[[34m2025-10-29 08:21:21[0m] (step=0010700) Train Loss: 0.6257, Train Steps/Sec: 1.14
|
| 129 |
+
[[34m2025-10-29 08:22:49[0m] (step=0010800) Train Loss: 0.6250, Train Steps/Sec: 1.14
|
| 130 |
+
[[34m2025-10-29 08:24:17[0m] (step=0010900) Train Loss: 0.6243, Train Steps/Sec: 1.14
|
| 131 |
+
[[34m2025-10-29 08:25:45[0m] (step=0011000) Train Loss: 0.6249, Train Steps/Sec: 1.14
|
| 132 |
+
[[34m2025-10-29 08:27:13[0m] (step=0011100) Train Loss: 0.6247, Train Steps/Sec: 1.14
|
| 133 |
+
[[34m2025-10-29 08:28:41[0m] (step=0011200) Train Loss: 0.6242, Train Steps/Sec: 1.14
|
| 134 |
+
[[34m2025-10-29 08:29:34[0m] Beginning epoch 9...
|
| 135 |
+
[[34m2025-10-29 08:30:12[0m] (step=0011300) Train Loss: 0.6227, Train Steps/Sec: 1.10
|
| 136 |
+
[[34m2025-10-29 08:31:40[0m] (step=0011400) Train Loss: 0.6228, Train Steps/Sec: 1.14
|
| 137 |
+
[[34m2025-10-29 08:33:08[0m] (step=0011500) Train Loss: 0.6229, Train Steps/Sec: 1.14
|
| 138 |
+
[[34m2025-10-29 08:34:36[0m] (step=0011600) Train Loss: 0.6227, Train Steps/Sec: 1.14
|
| 139 |
+
[[34m2025-10-29 08:36:04[0m] (step=0011700) Train Loss: 0.6223, Train Steps/Sec: 1.14
|
| 140 |
+
[[34m2025-10-29 08:37:32[0m] (step=0011800) Train Loss: 0.6211, Train Steps/Sec: 1.14
|
| 141 |
+
[[34m2025-10-29 08:39:01[0m] (step=0011900) Train Loss: 0.6211, Train Steps/Sec: 1.14
|
| 142 |
+
[[34m2025-10-29 08:40:29[0m] (step=0012000) Train Loss: 0.6218, Train Steps/Sec: 1.14
|
| 143 |
+
[[34m2025-10-29 08:41:57[0m] (step=0012100) Train Loss: 0.6193, Train Steps/Sec: 1.13
|
| 144 |
+
[[34m2025-10-29 08:43:25[0m] (step=0012200) Train Loss: 0.6202, Train Steps/Sec: 1.13
|
| 145 |
+
[[34m2025-10-29 08:44:53[0m] (step=0012300) Train Loss: 0.6193, Train Steps/Sec: 1.14
|
| 146 |
+
[[34m2025-10-29 08:46:21[0m] (step=0012400) Train Loss: 0.6200, Train Steps/Sec: 1.14
|
| 147 |
+
[[34m2025-10-29 08:47:49[0m] (step=0012500) Train Loss: 0.6195, Train Steps/Sec: 1.14
|
| 148 |
+
[[34m2025-10-29 08:47:58[0m] Beginning epoch 10...
|
| 149 |
+
[[34m2025-10-29 08:49:20[0m] (step=0012600) Train Loss: 0.6196, Train Steps/Sec: 1.10
|
| 150 |
+
[[34m2025-10-29 08:50:48[0m] (step=0012700) Train Loss: 0.6189, Train Steps/Sec: 1.14
|
| 151 |
+
[[34m2025-10-29 08:52:16[0m] (step=0012800) Train Loss: 0.6186, Train Steps/Sec: 1.14
|
| 152 |
+
[[34m2025-10-29 08:53:44[0m] (step=0012900) Train Loss: 0.6182, Train Steps/Sec: 1.14
|
| 153 |
+
[[34m2025-10-29 08:55:12[0m] (step=0013000) Train Loss: 0.6169, Train Steps/Sec: 1.13
|
| 154 |
+
[[34m2025-10-29 08:56:40[0m] (step=0013100) Train Loss: 0.6154, Train Steps/Sec: 1.13
|
| 155 |
+
[[34m2025-10-29 08:58:08[0m] (step=0013200) Train Loss: 0.6155, Train Steps/Sec: 1.14
|
| 156 |
+
[[34m2025-10-29 08:59:36[0m] (step=0013300) Train Loss: 0.6174, Train Steps/Sec: 1.14
|
| 157 |
+
[[34m2025-10-29 09:01:05[0m] (step=0013400) Train Loss: 0.6151, Train Steps/Sec: 1.14
|
| 158 |
+
[[34m2025-10-29 09:02:33[0m] (step=0013500) Train Loss: 0.6151, Train Steps/Sec: 1.14
|
| 159 |
+
[[34m2025-10-29 09:04:01[0m] (step=0013600) Train Loss: 0.6164, Train Steps/Sec: 1.14
|
| 160 |
+
[[34m2025-10-29 09:05:29[0m] (step=0013700) Train Loss: 0.6138, Train Steps/Sec: 1.14
|
| 161 |
+
[[34m2025-10-29 09:06:23[0m] Beginning epoch 11...
|
| 162 |
+
[[34m2025-10-29 09:06:59[0m] (step=0013800) Train Loss: 0.6157, Train Steps/Sec: 1.10
|
| 163 |
+
[[34m2025-10-29 09:08:28[0m] (step=0013900) Train Loss: 0.6158, Train Steps/Sec: 1.13
|
| 164 |
+
[[34m2025-10-29 09:09:56[0m] (step=0014000) Train Loss: 0.6138, Train Steps/Sec: 1.14
|
| 165 |
+
[[34m2025-10-29 09:11:24[0m] (step=0014100) Train Loss: 0.6135, Train Steps/Sec: 1.14
|
| 166 |
+
[[34m2025-10-29 09:12:52[0m] (step=0014200) Train Loss: 0.6147, Train Steps/Sec: 1.13
|
| 167 |
+
[[34m2025-10-29 09:14:20[0m] (step=0014300) Train Loss: 0.6144, Train Steps/Sec: 1.14
|
| 168 |
+
[[34m2025-10-29 09:15:48[0m] (step=0014400) Train Loss: 0.6136, Train Steps/Sec: 1.14
|
| 169 |
+
[[34m2025-10-29 09:17:16[0m] (step=0014500) Train Loss: 0.6129, Train Steps/Sec: 1.14
|
| 170 |
+
[[34m2025-10-29 09:18:44[0m] (step=0014600) Train Loss: 0.6138, Train Steps/Sec: 1.14
|
| 171 |
+
[[34m2025-10-29 09:20:12[0m] (step=0014700) Train Loss: 0.6127, Train Steps/Sec: 1.13
|
| 172 |
+
[[34m2025-10-29 09:21:41[0m] (step=0014800) Train Loss: 0.6114, Train Steps/Sec: 1.13
|
| 173 |
+
[[34m2025-10-29 09:23:09[0m] (step=0014900) Train Loss: 0.6131, Train Steps/Sec: 1.14
|
| 174 |
+
[[34m2025-10-29 09:24:37[0m] (step=0015000) Train Loss: 0.6110, Train Steps/Sec: 1.13
|
| 175 |
+
[[34m2025-10-29 09:24:48[0m] Beginning epoch 12...
|
| 176 |
+
[[34m2025-10-29 09:26:08[0m] (step=0015100) Train Loss: 0.6124, Train Steps/Sec: 1.10
|
| 177 |
+
[[34m2025-10-29 09:27:36[0m] (step=0015200) Train Loss: 0.6106, Train Steps/Sec: 1.14
|
| 178 |
+
[[34m2025-10-29 09:29:04[0m] (step=0015300) Train Loss: 0.6112, Train Steps/Sec: 1.14
|
| 179 |
+
[[34m2025-10-29 09:30:32[0m] (step=0015400) Train Loss: 0.6107, Train Steps/Sec: 1.14
|
| 180 |
+
[[34m2025-10-29 09:32:00[0m] (step=0015500) Train Loss: 0.6102, Train Steps/Sec: 1.14
|
| 181 |
+
[[34m2025-10-29 09:33:28[0m] (step=0015600) Train Loss: 0.6108, Train Steps/Sec: 1.13
|
| 182 |
+
[[34m2025-10-29 09:34:57[0m] (step=0015700) Train Loss: 0.6106, Train Steps/Sec: 1.13
|
| 183 |
+
[[34m2025-10-29 09:36:25[0m] (step=0015800) Train Loss: 0.6096, Train Steps/Sec: 1.14
|
| 184 |
+
[[34m2025-10-29 09:37:53[0m] (step=0015900) Train Loss: 0.6092, Train Steps/Sec: 1.14
|
| 185 |
+
[[34m2025-10-29 09:39:21[0m] (step=0016000) Train Loss: 0.6095, Train Steps/Sec: 1.14
|
| 186 |
+
[[34m2025-10-29 09:40:49[0m] (step=0016100) Train Loss: 0.6083, Train Steps/Sec: 1.14
|
| 187 |
+
[[34m2025-10-29 09:42:17[0m] (step=0016200) Train Loss: 0.6087, Train Steps/Sec: 1.14
|
| 188 |
+
[[34m2025-10-29 09:43:13[0m] Beginning epoch 13...
|
| 189 |
+
[[34m2025-10-29 09:43:48[0m] (step=0016300) Train Loss: 0.6089, Train Steps/Sec: 1.10
|
| 190 |
+
[[34m2025-10-29 09:45:16[0m] (step=0016400) Train Loss: 0.6080, Train Steps/Sec: 1.13
|
| 191 |
+
[[34m2025-10-29 09:46:45[0m] (step=0016500) Train Loss: 0.6070, Train Steps/Sec: 1.13
|
| 192 |
+
[[34m2025-10-29 09:48:13[0m] (step=0016600) Train Loss: 0.6076, Train Steps/Sec: 1.14
|
| 193 |
+
[[34m2025-10-29 09:49:41[0m] (step=0016700) Train Loss: 0.6098, Train Steps/Sec: 1.14
|
| 194 |
+
[[34m2025-10-29 09:51:09[0m] (step=0016800) Train Loss: 0.6067, Train Steps/Sec: 1.14
|
| 195 |
+
[[34m2025-10-29 09:52:37[0m] (step=0016900) Train Loss: 0.6068, Train Steps/Sec: 1.14
|
| 196 |
+
[[34m2025-10-29 09:54:05[0m] (step=0017000) Train Loss: 0.6070, Train Steps/Sec: 1.14
|
| 197 |
+
[[34m2025-10-29 09:55:33[0m] (step=0017100) Train Loss: 0.6078, Train Steps/Sec: 1.14
|
| 198 |
+
[[34m2025-10-29 09:57:01[0m] (step=0017200) Train Loss: 0.6061, Train Steps/Sec: 1.14
|
| 199 |
+
[[34m2025-10-29 09:58:30[0m] (step=0017300) Train Loss: 0.6059, Train Steps/Sec: 1.13
|
| 200 |
+
[[34m2025-10-29 09:59:58[0m] (step=0017400) Train Loss: 0.6049, Train Steps/Sec: 1.13
|
| 201 |
+
[[34m2025-10-29 10:01:26[0m] (step=0017500) Train Loss: 0.6061, Train Steps/Sec: 1.14
|
| 202 |
+
[[34m2025-10-29 10:01:39[0m] Beginning epoch 14...
|
| 203 |
+
[[34m2025-10-29 10:02:57[0m] (step=0017600) Train Loss: 0.6054, Train Steps/Sec: 1.10
|
| 204 |
+
[[34m2025-10-29 10:04:25[0m] (step=0017700) Train Loss: 0.6041, Train Steps/Sec: 1.14
|
| 205 |
+
[[34m2025-10-29 10:05:53[0m] (step=0017800) Train Loss: 0.6053, Train Steps/Sec: 1.14
|
| 206 |
+
[[34m2025-10-29 10:07:21[0m] (step=0017900) Train Loss: 0.6051, Train Steps/Sec: 1.14
|
| 207 |
+
[[34m2025-10-29 10:08:49[0m] (step=0018000) Train Loss: 0.6048, Train Steps/Sec: 1.14
|
| 208 |
+
[[34m2025-10-29 10:10:17[0m] (step=0018100) Train Loss: 0.6045, Train Steps/Sec: 1.13
|
| 209 |
+
[[34m2025-10-29 10:11:46[0m] (step=0018200) Train Loss: 0.6046, Train Steps/Sec: 1.13
|
| 210 |
+
[[34m2025-10-29 10:13:14[0m] (step=0018300) Train Loss: 0.6047, Train Steps/Sec: 1.13
|
| 211 |
+
[[34m2025-10-29 10:14:42[0m] (step=0018400) Train Loss: 0.6040, Train Steps/Sec: 1.14
|
| 212 |
+
[[34m2025-10-29 10:16:10[0m] (step=0018500) Train Loss: 0.6039, Train Steps/Sec: 1.14
|
| 213 |
+
[[34m2025-10-29 10:17:38[0m] (step=0018600) Train Loss: 0.6043, Train Steps/Sec: 1.14
|
| 214 |
+
[[34m2025-10-29 10:19:06[0m] (step=0018700) Train Loss: 0.6033, Train Steps/Sec: 1.14
|
| 215 |
+
[[34m2025-10-29 10:20:04[0m] Beginning epoch 15...
|
| 216 |
+
[[34m2025-10-29 10:20:37[0m] (step=0018800) Train Loss: 0.6042, Train Steps/Sec: 1.10
|
| 217 |
+
[[34m2025-10-29 10:22:05[0m] (step=0018900) Train Loss: 0.6033, Train Steps/Sec: 1.13
|
| 218 |
+
[[34m2025-10-29 10:23:33[0m] (step=0019000) Train Loss: 0.6033, Train Steps/Sec: 1.14
|
| 219 |
+
[[34m2025-10-29 10:25:01[0m] (step=0019100) Train Loss: 0.6024, Train Steps/Sec: 1.13
|
| 220 |
+
[[34m2025-10-29 10:26:29[0m] (step=0019200) Train Loss: 0.6026, Train Steps/Sec: 1.14
|
| 221 |
+
[[34m2025-10-29 10:27:57[0m] (step=0019300) Train Loss: 0.6015, Train Steps/Sec: 1.14
|
| 222 |
+
[[34m2025-10-29 10:29:26[0m] (step=0019400) Train Loss: 0.6034, Train Steps/Sec: 1.14
|
| 223 |
+
[[34m2025-10-29 10:30:54[0m] (step=0019500) Train Loss: 0.6017, Train Steps/Sec: 1.14
|
| 224 |
+
[[34m2025-10-29 10:32:22[0m] (step=0019600) Train Loss: 0.6026, Train Steps/Sec: 1.14
|
| 225 |
+
[[34m2025-10-29 10:33:50[0m] (step=0019700) Train Loss: 0.6018, Train Steps/Sec: 1.13
|
| 226 |
+
[[34m2025-10-29 10:35:18[0m] (step=0019800) Train Loss: 0.5997, Train Steps/Sec: 1.14
|
| 227 |
+
[[34m2025-10-29 10:36:46[0m] (step=0019900) Train Loss: 0.6015, Train Steps/Sec: 1.14
|
| 228 |
+
[[34m2025-10-29 10:38:14[0m] (step=0020000) Train Loss: 0.6014, Train Steps/Sec: 1.13
|
| 229 |
+
[[34m2025-10-29 10:38:29[0m] Beginning epoch 16...
|
| 230 |
+
[[34m2025-10-29 10:39:45[0m] (step=0020100) Train Loss: 0.5992, Train Steps/Sec: 1.10
|
| 231 |
+
[[34m2025-10-29 10:41:13[0m] (step=0020200) Train Loss: 0.6000, Train Steps/Sec: 1.14
|
| 232 |
+
[[34m2025-10-29 10:42:41[0m] (step=0020300) Train Loss: 0.6001, Train Steps/Sec: 1.14
|
| 233 |
+
[[34m2025-10-29 10:44:09[0m] (step=0020400) Train Loss: 0.5998, Train Steps/Sec: 1.13
|
| 234 |
+
[[34m2025-10-29 10:45:37[0m] (step=0020500) Train Loss: 0.5994, Train Steps/Sec: 1.14
|
| 235 |
+
[[34m2025-10-29 10:47:05[0m] (step=0020600) Train Loss: 0.5988, Train Steps/Sec: 1.14
|
| 236 |
+
[[34m2025-10-29 10:48:33[0m] (step=0020700) Train Loss: 0.5994, Train Steps/Sec: 1.14
|
| 237 |
+
[[34m2025-10-29 10:50:02[0m] (step=0020800) Train Loss: 0.5994, Train Steps/Sec: 1.13
|
| 238 |
+
[[34m2025-10-29 10:51:30[0m] (step=0020900) Train Loss: 0.5990, Train Steps/Sec: 1.14
|
| 239 |
+
[[34m2025-10-29 10:52:58[0m] (step=0021000) Train Loss: 0.5993, Train Steps/Sec: 1.14
|
| 240 |
+
[[34m2025-10-29 10:54:26[0m] (step=0021100) Train Loss: 0.5978, Train Steps/Sec: 1.14
|
| 241 |
+
[[34m2025-10-29 10:55:54[0m] (step=0021200) Train Loss: 0.5994, Train Steps/Sec: 1.13
|
| 242 |
+
[[34m2025-10-29 10:56:54[0m] Beginning epoch 17...
|
| 243 |
+
[[34m2025-10-29 10:57:25[0m] (step=0021300) Train Loss: 0.5980, Train Steps/Sec: 1.11
|
| 244 |
+
[[34m2025-10-29 10:58:53[0m] (step=0021400) Train Loss: 0.5986, Train Steps/Sec: 1.14
|
| 245 |
+
[[34m2025-10-29 11:00:21[0m] (step=0021500) Train Loss: 0.5979, Train Steps/Sec: 1.14
|
| 246 |
+
[[34m2025-10-29 11:01:49[0m] (step=0021600) Train Loss: 0.5975, Train Steps/Sec: 1.13
|
| 247 |
+
[[34m2025-10-29 11:03:18[0m] (step=0021700) Train Loss: 0.5981, Train Steps/Sec: 1.13
|
| 248 |
+
[[34m2025-10-29 11:04:46[0m] (step=0021800) Train Loss: 0.5974, Train Steps/Sec: 1.14
|
| 249 |
+
[[34m2025-10-29 11:06:14[0m] (step=0021900) Train Loss: 0.5979, Train Steps/Sec: 1.14
|
| 250 |
+
[[34m2025-10-29 11:07:42[0m] (step=0022000) Train Loss: 0.5961, Train Steps/Sec: 1.13
|
| 251 |
+
[[34m2025-10-29 11:09:10[0m] (step=0022100) Train Loss: 0.5986, Train Steps/Sec: 1.14
|
| 252 |
+
[[34m2025-10-29 11:10:38[0m] (step=0022200) Train Loss: 0.5968, Train Steps/Sec: 1.14
|
| 253 |
+
[[34m2025-10-29 11:12:06[0m] (step=0022300) Train Loss: 0.5970, Train Steps/Sec: 1.14
|
| 254 |
+
[[34m2025-10-29 11:13:34[0m] (step=0022400) Train Loss: 0.5959, Train Steps/Sec: 1.13
|
| 255 |
+
[[34m2025-10-29 11:15:02[0m] (step=0022500) Train Loss: 0.5967, Train Steps/Sec: 1.13
|
| 256 |
+
[[34m2025-10-29 11:15:19[0m] Beginning epoch 18...
|
| 257 |
+
[[34m2025-10-29 11:16:33[0m] (step=0022600) Train Loss: 0.5963, Train Steps/Sec: 1.10
|
| 258 |
+
[[34m2025-10-29 11:18:01[0m] (step=0022700) Train Loss: 0.5963, Train Steps/Sec: 1.14
|
| 259 |
+
[[34m2025-10-29 11:19:30[0m] (step=0022800) Train Loss: 0.5955, Train Steps/Sec: 1.13
|
| 260 |
+
[[34m2025-10-29 11:20:58[0m] (step=0022900) Train Loss: 0.5964, Train Steps/Sec: 1.14
|
| 261 |
+
[[34m2025-10-29 11:22:26[0m] (step=0023000) Train Loss: 0.5955, Train Steps/Sec: 1.14
|
| 262 |
+
[[34m2025-10-29 11:23:54[0m] (step=0023100) Train Loss: 0.5954, Train Steps/Sec: 1.14
|
| 263 |
+
[[34m2025-10-29 11:25:22[0m] (step=0023200) Train Loss: 0.5954, Train Steps/Sec: 1.14
|
| 264 |
+
[[34m2025-10-29 11:26:50[0m] (step=0023300) Train Loss: 0.5954, Train Steps/Sec: 1.13
|
| 265 |
+
[[34m2025-10-29 11:28:19[0m] (step=0023400) Train Loss: 0.5937, Train Steps/Sec: 1.13
|
| 266 |
+
[[34m2025-10-29 11:29:47[0m] (step=0023500) Train Loss: 0.5948, Train Steps/Sec: 1.14
|
| 267 |
+
[[34m2025-10-29 11:31:15[0m] (step=0023600) Train Loss: 0.5947, Train Steps/Sec: 1.14
|
| 268 |
+
[[34m2025-10-29 11:32:43[0m] (step=0023700) Train Loss: 0.5942, Train Steps/Sec: 1.14
|
| 269 |
+
[[34m2025-10-29 11:33:44[0m] Beginning epoch 19...
|
| 270 |
+
[[34m2025-10-29 11:34:13[0m] (step=0023800) Train Loss: 0.5926, Train Steps/Sec: 1.10
|
| 271 |
+
[[34m2025-10-29 11:35:41[0m] (step=0023900) Train Loss: 0.5941, Train Steps/Sec: 1.14
|
| 272 |
+
[[34m2025-10-29 11:37:10[0m] (step=0024000) Train Loss: 0.5927, Train Steps/Sec: 1.14
|
| 273 |
+
[[34m2025-10-29 11:38:38[0m] (step=0024100) Train Loss: 0.5934, Train Steps/Sec: 1.13
|
| 274 |
+
[[34m2025-10-29 11:40:06[0m] (step=0024200) Train Loss: 0.5927, Train Steps/Sec: 1.14
|
| 275 |
+
[[34m2025-10-29 11:41:35[0m] (step=0024300) Train Loss: 0.5947, Train Steps/Sec: 1.13
|
| 276 |
+
[[34m2025-10-29 11:43:03[0m] (step=0024400) Train Loss: 0.5936, Train Steps/Sec: 1.14
|
| 277 |
+
[[34m2025-10-29 11:44:31[0m] (step=0024500) Train Loss: 0.5934, Train Steps/Sec: 1.14
|
| 278 |
+
[[34m2025-10-29 11:45:59[0m] (step=0024600) Train Loss: 0.5933, Train Steps/Sec: 1.14
|
| 279 |
+
[[34m2025-10-29 11:47:27[0m] (step=0024700) Train Loss: 0.5929, Train Steps/Sec: 1.14
|
| 280 |
+
[[34m2025-10-29 11:48:55[0m] (step=0024800) Train Loss: 0.5930, Train Steps/Sec: 1.14
|
| 281 |
+
[[34m2025-10-29 11:50:23[0m] (step=0024900) Train Loss: 0.5919, Train Steps/Sec: 1.14
|
| 282 |
+
[[34m2025-10-29 11:51:51[0m] (step=0025000) Train Loss: 0.5933, Train Steps/Sec: 1.14
|
| 283 |
+
[[34m2025-10-29 11:52:47[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-l-bf16/checkpoints/0025000.pt
|
| 284 |
+
[[34m2025-10-29 11:52:47[0m] Generating EMA samples...
|
| 285 |
+
[[34m2025-10-29 11:53:15[0m] Generating EMA samples done.
|
| 286 |
+
[[34m2025-10-29 11:53:33[0m] Beginning epoch 20...
|
| 287 |
+
[[34m2025-10-29 11:54:46[0m] (step=0025100) Train Loss: 0.5911, Train Steps/Sec: 0.57
|
| 288 |
+
[[34m2025-10-29 11:56:14[0m] (step=0025200) Train Loss: 0.5929, Train Steps/Sec: 1.13
|
| 289 |
+
[[34m2025-10-29 11:57:42[0m] (step=0025300) Train Loss: 0.5913, Train Steps/Sec: 1.14
|
| 290 |
+
[[34m2025-10-29 11:59:10[0m] (step=0025400) Train Loss: 0.5905, Train Steps/Sec: 1.14
|
| 291 |
+
[[34m2025-10-29 12:00:38[0m] (step=0025500) Train Loss: 0.5907, Train Steps/Sec: 1.14
|
| 292 |
+
[[34m2025-10-29 12:02:06[0m] (step=0025600) Train Loss: 0.5922, Train Steps/Sec: 1.14
|
| 293 |
+
[[34m2025-10-29 12:03:34[0m] (step=0025700) Train Loss: 0.5913, Train Steps/Sec: 1.14
|
| 294 |
+
[[34m2025-10-29 12:05:02[0m] (step=0025800) Train Loss: 0.5917, Train Steps/Sec: 1.14
|
| 295 |
+
[[34m2025-10-29 12:06:30[0m] (step=0025900) Train Loss: 0.5906, Train Steps/Sec: 1.13
|
| 296 |
+
[[34m2025-10-29 12:07:59[0m] (step=0026000) Train Loss: 0.5911, Train Steps/Sec: 1.13
|
| 297 |
+
[[34m2025-10-29 12:09:27[0m] (step=0026100) Train Loss: 0.5905, Train Steps/Sec: 1.14
|
| 298 |
+
[[34m2025-10-29 12:10:55[0m] (step=0026200) Train Loss: 0.5896, Train Steps/Sec: 1.14
|
| 299 |
+
[[34m2025-10-29 12:11:58[0m] Beginning epoch 21...
|
| 300 |
+
[[34m2025-10-29 12:12:26[0m] (step=0026300) Train Loss: 0.5899, Train Steps/Sec: 1.10
|
| 301 |
+
[[34m2025-10-29 12:13:54[0m] (step=0026400) Train Loss: 0.5889, Train Steps/Sec: 1.14
|
| 302 |
+
[[34m2025-10-29 12:15:22[0m] (step=0026500) Train Loss: 0.5901, Train Steps/Sec: 1.14
|
| 303 |
+
[[34m2025-10-29 12:16:50[0m] (step=0026600) Train Loss: 0.5904, Train Steps/Sec: 1.13
|
| 304 |
+
[[34m2025-10-29 12:18:18[0m] (step=0026700) Train Loss: 0.5887, Train Steps/Sec: 1.13
|
| 305 |
+
[[34m2025-10-29 12:19:47[0m] (step=0026800) Train Loss: 0.5900, Train Steps/Sec: 1.13
|
| 306 |
+
[[34m2025-10-29 12:21:15[0m] (step=0026900) Train Loss: 0.5891, Train Steps/Sec: 1.13
|
| 307 |
+
[[34m2025-10-29 12:22:43[0m] (step=0027000) Train Loss: 0.5885, Train Steps/Sec: 1.14
|
| 308 |
+
[[34m2025-10-29 12:24:11[0m] (step=0027100) Train Loss: 0.5887, Train Steps/Sec: 1.14
|
| 309 |
+
[[34m2025-10-29 12:25:39[0m] (step=0027200) Train Loss: 0.5891, Train Steps/Sec: 1.14
|
| 310 |
+
[[34m2025-10-29 12:27:07[0m] (step=0027300) Train Loss: 0.5887, Train Steps/Sec: 1.14
|
| 311 |
+
[[34m2025-10-29 12:28:36[0m] (step=0027400) Train Loss: 0.5884, Train Steps/Sec: 1.13
|
| 312 |
+
[[34m2025-10-29 12:30:04[0m] (step=0027500) Train Loss: 0.5889, Train Steps/Sec: 1.13
|
| 313 |
+
[[34m2025-10-29 12:30:24[0m] Beginning epoch 22...
|
| 314 |
+
[[34m2025-10-29 12:31:35[0m] (step=0027600) Train Loss: 0.5868, Train Steps/Sec: 1.10
|
| 315 |
+
[[34m2025-10-29 12:33:03[0m] (step=0027700) Train Loss: 0.5880, Train Steps/Sec: 1.13
|
| 316 |
+
[[34m2025-10-29 12:34:31[0m] (step=0027800) Train Loss: 0.5874, Train Steps/Sec: 1.13
|
| 317 |
+
[[34m2025-10-29 12:35:59[0m] (step=0027900) Train Loss: 0.5885, Train Steps/Sec: 1.14
|
| 318 |
+
[[34m2025-10-29 12:37:27[0m] (step=0028000) Train Loss: 0.5852, Train Steps/Sec: 1.14
|
| 319 |
+
[[34m2025-10-29 12:38:56[0m] (step=0028100) Train Loss: 0.5880, Train Steps/Sec: 1.14
|
| 320 |
+
[[34m2025-10-29 12:40:24[0m] (step=0028200) Train Loss: 0.5883, Train Steps/Sec: 1.13
|
| 321 |
+
[[34m2025-10-29 12:41:52[0m] (step=0028300) Train Loss: 0.5877, Train Steps/Sec: 1.14
|
| 322 |
+
[[34m2025-10-29 12:43:20[0m] (step=0028400) Train Loss: 0.5879, Train Steps/Sec: 1.14
|
| 323 |
+
[[34m2025-10-29 12:44:48[0m] (step=0028500) Train Loss: 0.5873, Train Steps/Sec: 1.14
|
| 324 |
+
[[34m2025-10-29 12:46:16[0m] (step=0028600) Train Loss: 0.5875, Train Steps/Sec: 1.13
|
| 325 |
+
[[34m2025-10-29 12:47:44[0m] (step=0028700) Train Loss: 0.5870, Train Steps/Sec: 1.14
|
| 326 |
+
[[34m2025-10-29 12:48:49[0m] Beginning epoch 23...
|
| 327 |
+
[[34m2025-10-29 12:49:15[0m] (step=0028800) Train Loss: 0.5862, Train Steps/Sec: 1.10
|
| 328 |
+
[[34m2025-10-29 12:50:43[0m] (step=0028900) Train Loss: 0.5865, Train Steps/Sec: 1.14
|
| 329 |
+
[[34m2025-10-29 12:52:11[0m] (step=0029000) Train Loss: 0.5848, Train Steps/Sec: 1.13
|
| 330 |
+
[[34m2025-10-29 12:53:39[0m] (step=0029100) Train Loss: 0.5864, Train Steps/Sec: 1.14
|
| 331 |
+
[[34m2025-10-29 12:55:07[0m] (step=0029200) Train Loss: 0.5855, Train Steps/Sec: 1.14
|
| 332 |
+
[[34m2025-10-29 12:56:35[0m] (step=0029300) Train Loss: 0.5852, Train Steps/Sec: 1.13
|
| 333 |
+
[[34m2025-10-29 12:58:04[0m] (step=0029400) Train Loss: 0.5840, Train Steps/Sec: 1.13
|
| 334 |
+
[[34m2025-10-29 12:59:32[0m] (step=0029500) Train Loss: 0.5858, Train Steps/Sec: 1.13
|
| 335 |
+
[[34m2025-10-29 13:01:00[0m] (step=0029600) Train Loss: 0.5863, Train Steps/Sec: 1.14
|
| 336 |
+
[[34m2025-10-29 13:02:28[0m] (step=0029700) Train Loss: 0.5866, Train Steps/Sec: 1.14
|
| 337 |
+
[[34m2025-10-29 13:03:56[0m] (step=0029800) Train Loss: 0.5857, Train Steps/Sec: 1.14
|
| 338 |
+
[[34m2025-10-29 13:05:24[0m] (step=0029900) Train Loss: 0.5858, Train Steps/Sec: 1.14
|
| 339 |
+
[[34m2025-10-29 13:06:52[0m] (step=0030000) Train Loss: 0.5858, Train Steps/Sec: 1.14
|
| 340 |
+
[[34m2025-10-29 13:07:14[0m] Beginning epoch 24...
|
| 341 |
+
[[34m2025-10-29 13:08:23[0m] (step=0030100) Train Loss: 0.5848, Train Steps/Sec: 1.10
|
| 342 |
+
[[34m2025-10-29 13:09:51[0m] (step=0030200) Train Loss: 0.5840, Train Steps/Sec: 1.14
|
| 343 |
+
[[34m2025-10-29 13:11:20[0m] (step=0030300) Train Loss: 0.5850, Train Steps/Sec: 1.13
|
| 344 |
+
[[34m2025-10-29 13:12:48[0m] (step=0030400) Train Loss: 0.5834, Train Steps/Sec: 1.14
|
| 345 |
+
[[34m2025-10-29 13:14:16[0m] (step=0030500) Train Loss: 0.5838, Train Steps/Sec: 1.14
|
| 346 |
+
[[34m2025-10-29 13:15:44[0m] (step=0030600) Train Loss: 0.5842, Train Steps/Sec: 1.13
|
| 347 |
+
[[34m2025-10-29 13:17:12[0m] (step=0030700) Train Loss: 0.5848, Train Steps/Sec: 1.14
|
| 348 |
+
[[34m2025-10-29 13:18:40[0m] (step=0030800) Train Loss: 0.5838, Train Steps/Sec: 1.14
|
| 349 |
+
[[34m2025-10-29 13:20:08[0m] (step=0030900) Train Loss: 0.5827, Train Steps/Sec: 1.14
|
| 350 |
+
[[34m2025-10-29 13:21:37[0m] (step=0031000) Train Loss: 0.5840, Train Steps/Sec: 1.13
|
| 351 |
+
[[34m2025-10-29 13:23:05[0m] (step=0031100) Train Loss: 0.5841, Train Steps/Sec: 1.14
|
| 352 |
+
[[34m2025-10-29 13:24:33[0m] (step=0031200) Train Loss: 0.5848, Train Steps/Sec: 1.13
|
| 353 |
+
[[34m2025-10-29 13:25:40[0m] Beginning epoch 25...
|
| 354 |
+
[[34m2025-10-29 13:26:04[0m] (step=0031300) Train Loss: 0.5839, Train Steps/Sec: 1.10
|
| 355 |
+
[[34m2025-10-29 13:27:32[0m] (step=0031400) Train Loss: 0.5832, Train Steps/Sec: 1.13
|
| 356 |
+
[[34m2025-10-29 13:29:00[0m] (step=0031500) Train Loss: 0.5833, Train Steps/Sec: 1.14
|
| 357 |
+
[[34m2025-10-29 13:30:28[0m] (step=0031600) Train Loss: 0.5821, Train Steps/Sec: 1.14
|
| 358 |
+
[[34m2025-10-29 13:31:56[0m] (step=0031700) Train Loss: 0.5814, Train Steps/Sec: 1.14
|
| 359 |
+
[[34m2025-10-29 13:33:24[0m] (step=0031800) Train Loss: 0.5831, Train Steps/Sec: 1.14
|
| 360 |
+
[[34m2025-10-29 13:34:52[0m] (step=0031900) Train Loss: 0.5834, Train Steps/Sec: 1.13
|
| 361 |
+
[[34m2025-10-29 13:36:21[0m] (step=0032000) Train Loss: 0.5818, Train Steps/Sec: 1.13
|
| 362 |
+
[[34m2025-10-29 13:37:49[0m] (step=0032100) Train Loss: 0.5815, Train Steps/Sec: 1.13
|
| 363 |
+
[[34m2025-10-29 13:39:17[0m] (step=0032200) Train Loss: 0.5824, Train Steps/Sec: 1.14
|
| 364 |
+
[[34m2025-10-29 13:40:45[0m] (step=0032300) Train Loss: 0.5823, Train Steps/Sec: 1.14
|
| 365 |
+
[[34m2025-10-29 13:42:13[0m] (step=0032400) Train Loss: 0.5814, Train Steps/Sec: 1.14
|
| 366 |
+
[[34m2025-10-29 13:43:41[0m] (step=0032500) Train Loss: 0.5823, Train Steps/Sec: 1.14
|
| 367 |
+
[[34m2025-10-29 13:44:05[0m] Beginning epoch 26...
|
| 368 |
+
[[34m2025-10-29 13:45:12[0m] (step=0032600) Train Loss: 0.5824, Train Steps/Sec: 1.10
|
| 369 |
+
[[34m2025-10-29 13:46:40[0m] (step=0032700) Train Loss: 0.5810, Train Steps/Sec: 1.13
|
| 370 |
+
[[34m2025-10-29 13:48:08[0m] (step=0032800) Train Loss: 0.5812, Train Steps/Sec: 1.14
|
| 371 |
+
[[34m2025-10-29 13:49:37[0m] (step=0032900) Train Loss: 0.5800, Train Steps/Sec: 1.13
|
| 372 |
+
[[34m2025-10-29 13:51:05[0m] (step=0033000) Train Loss: 0.5808, Train Steps/Sec: 1.14
|
| 373 |
+
[[34m2025-10-29 13:52:33[0m] (step=0033100) Train Loss: 0.5803, Train Steps/Sec: 1.14
|
| 374 |
+
[[34m2025-10-29 13:54:01[0m] (step=0033200) Train Loss: 0.5792, Train Steps/Sec: 1.14
|
| 375 |
+
[[34m2025-10-29 13:55:29[0m] (step=0033300) Train Loss: 0.5798, Train Steps/Sec: 1.14
|
| 376 |
+
[[34m2025-10-29 13:56:57[0m] (step=0033400) Train Loss: 0.5800, Train Steps/Sec: 1.14
|
| 377 |
+
[[34m2025-10-29 13:58:25[0m] (step=0033500) Train Loss: 0.5793, Train Steps/Sec: 1.14
|
| 378 |
+
[[34m2025-10-29 13:59:53[0m] (step=0033600) Train Loss: 0.5797, Train Steps/Sec: 1.13
|
| 379 |
+
[[34m2025-10-29 14:01:22[0m] (step=0033700) Train Loss: 0.5807, Train Steps/Sec: 1.13
|
| 380 |
+
[[34m2025-10-29 14:02:30[0m] Beginning epoch 27...
|
| 381 |
+
[[34m2025-10-29 14:02:52[0m] (step=0033800) Train Loss: 0.5802, Train Steps/Sec: 1.10
|
| 382 |
+
[[34m2025-10-29 14:04:20[0m] (step=0033900) Train Loss: 0.5807, Train Steps/Sec: 1.14
|
| 383 |
+
[[34m2025-10-29 14:05:49[0m] (step=0034000) Train Loss: 0.5806, Train Steps/Sec: 1.14
|
| 384 |
+
[[34m2025-10-29 14:07:17[0m] (step=0034100) Train Loss: 0.5789, Train Steps/Sec: 1.14
|
| 385 |
+
[[34m2025-10-29 14:08:45[0m] (step=0034200) Train Loss: 0.5796, Train Steps/Sec: 1.14
|
| 386 |
+
[[34m2025-10-29 14:10:13[0m] (step=0034300) Train Loss: 0.5786, Train Steps/Sec: 1.14
|
| 387 |
+
[[34m2025-10-29 14:11:41[0m] (step=0034400) Train Loss: 0.5801, Train Steps/Sec: 1.13
|
| 388 |
+
[[34m2025-10-29 14:13:09[0m] (step=0034500) Train Loss: 0.5781, Train Steps/Sec: 1.13
|
| 389 |
+
[[34m2025-10-29 14:14:37[0m] (step=0034600) Train Loss: 0.5798, Train Steps/Sec: 1.13
|
| 390 |
+
[[34m2025-10-29 14:16:05[0m] (step=0034700) Train Loss: 0.5805, Train Steps/Sec: 1.13
|
| 391 |
+
[[34m2025-10-29 14:17:33[0m] (step=0034800) Train Loss: 0.5794, Train Steps/Sec: 1.14
|
| 392 |
+
[[34m2025-10-29 14:19:01[0m] (step=0034900) Train Loss: 0.5805, Train Steps/Sec: 1.14
|
| 393 |
+
[[34m2025-10-29 14:20:29[0m] (step=0035000) Train Loss: 0.5787, Train Steps/Sec: 1.14
|
| 394 |
+
[[34m2025-10-29 14:20:55[0m] Beginning epoch 28...
|
| 395 |
+
[[34m2025-10-29 14:22:00[0m] (step=0035100) Train Loss: 0.5778, Train Steps/Sec: 1.10
|
| 396 |
+
[[34m2025-10-29 14:23:28[0m] (step=0035200) Train Loss: 0.5769, Train Steps/Sec: 1.14
|
| 397 |
+
[[34m2025-10-29 14:24:56[0m] (step=0035300) Train Loss: 0.5777, Train Steps/Sec: 1.13
|
| 398 |
+
[[34m2025-10-29 14:26:25[0m] (step=0035400) Train Loss: 0.5783, Train Steps/Sec: 1.14
|
| 399 |
+
[[34m2025-10-29 14:27:53[0m] (step=0035500) Train Loss: 0.5770, Train Steps/Sec: 1.13
|
| 400 |
+
[[34m2025-10-29 14:29:21[0m] (step=0035600) Train Loss: 0.5771, Train Steps/Sec: 1.14
|
| 401 |
+
[[34m2025-10-29 14:30:49[0m] (step=0035700) Train Loss: 0.5778, Train Steps/Sec: 1.14
|
| 402 |
+
[[34m2025-10-29 14:32:17[0m] (step=0035800) Train Loss: 0.5777, Train Steps/Sec: 1.14
|
| 403 |
+
[[34m2025-10-29 14:33:45[0m] (step=0035900) Train Loss: 0.5768, Train Steps/Sec: 1.14
|
| 404 |
+
[[34m2025-10-29 14:35:13[0m] (step=0036000) Train Loss: 0.5777, Train Steps/Sec: 1.14
|
| 405 |
+
[[34m2025-10-29 14:36:41[0m] (step=0036100) Train Loss: 0.5779, Train Steps/Sec: 1.14
|
| 406 |
+
[[34m2025-10-29 14:38:09[0m] (step=0036200) Train Loss: 0.5776, Train Steps/Sec: 1.13
|
| 407 |
+
[[34m2025-10-29 14:39:19[0m] Beginning epoch 29...
|
| 408 |
+
[[34m2025-10-29 14:39:41[0m] (step=0036300) Train Loss: 0.5782, Train Steps/Sec: 1.09
|
| 409 |
+
[[34m2025-10-29 14:41:09[0m] (step=0036400) Train Loss: 0.5777, Train Steps/Sec: 1.13
|
| 410 |
+
[[34m2025-10-29 14:42:37[0m] (step=0036500) Train Loss: 0.5760, Train Steps/Sec: 1.14
|
| 411 |
+
[[34m2025-10-29 14:44:05[0m] (step=0036600) Train Loss: 0.5767, Train Steps/Sec: 1.14
|
| 412 |
+
[[34m2025-10-29 14:45:33[0m] (step=0036700) Train Loss: 0.5761, Train Steps/Sec: 1.14
|
| 413 |
+
[[34m2025-10-29 14:47:01[0m] (step=0036800) Train Loss: 0.5764, Train Steps/Sec: 1.14
|
| 414 |
+
[[34m2025-10-29 14:48:30[0m] (step=0036900) Train Loss: 0.5766, Train Steps/Sec: 1.13
|
| 415 |
+
[[34m2025-10-29 14:49:58[0m] (step=0037000) Train Loss: 0.5769, Train Steps/Sec: 1.13
|
| 416 |
+
[[34m2025-10-29 14:51:26[0m] (step=0037100) Train Loss: 0.5768, Train Steps/Sec: 1.14
|
| 417 |
+
[[34m2025-10-29 14:52:54[0m] (step=0037200) Train Loss: 0.5772, Train Steps/Sec: 1.13
|
| 418 |
+
[[34m2025-10-29 14:54:22[0m] (step=0037300) Train Loss: 0.5752, Train Steps/Sec: 1.14
|
| 419 |
+
[[34m2025-10-29 14:55:50[0m] (step=0037400) Train Loss: 0.5771, Train Steps/Sec: 1.14
|
| 420 |
+
[[34m2025-10-29 14:57:18[0m] (step=0037500) Train Loss: 0.5752, Train Steps/Sec: 1.14
|
| 421 |
+
[[34m2025-10-29 14:57:45[0m] Beginning epoch 30...
|
| 422 |
+
[[34m2025-10-29 14:58:49[0m] (step=0037600) Train Loss: 0.5752, Train Steps/Sec: 1.10
|
| 423 |
+
[[34m2025-10-29 15:00:17[0m] (step=0037700) Train Loss: 0.5760, Train Steps/Sec: 1.14
|
| 424 |
+
[[34m2025-10-29 15:01:45[0m] (step=0037800) Train Loss: 0.5748, Train Steps/Sec: 1.14
|
| 425 |
+
[[34m2025-10-29 15:03:13[0m] (step=0037900) Train Loss: 0.5757, Train Steps/Sec: 1.13
|
| 426 |
+
[[34m2025-10-29 15:04:41[0m] (step=0038000) Train Loss: 0.5744, Train Steps/Sec: 1.14
|
| 427 |
+
[[34m2025-10-29 15:06:09[0m] (step=0038100) Train Loss: 0.5754, Train Steps/Sec: 1.13
|
| 428 |
+
[[34m2025-10-29 15:07:37[0m] (step=0038200) Train Loss: 0.5753, Train Steps/Sec: 1.14
|
| 429 |
+
[[34m2025-10-29 15:09:05[0m] (step=0038300) Train Loss: 0.5756, Train Steps/Sec: 1.14
|
| 430 |
+
[[34m2025-10-29 15:10:33[0m] (step=0038400) Train Loss: 0.5742, Train Steps/Sec: 1.14
|
| 431 |
+
[[34m2025-10-29 15:12:01[0m] (step=0038500) Train Loss: 0.5756, Train Steps/Sec: 1.14
|
| 432 |
+
[[34m2025-10-29 15:13:29[0m] (step=0038600) Train Loss: 0.5749, Train Steps/Sec: 1.14
|
| 433 |
+
[[34m2025-10-29 15:14:58[0m] (step=0038700) Train Loss: 0.5758, Train Steps/Sec: 1.13
|
| 434 |
+
[[34m2025-10-29 15:16:09[0m] Beginning epoch 31...
|
| 435 |
+
[[34m2025-10-29 15:16:28[0m] (step=0038800) Train Loss: 0.5750, Train Steps/Sec: 1.10
|
| 436 |
+
[[34m2025-10-29 15:17:57[0m] (step=0038900) Train Loss: 0.5745, Train Steps/Sec: 1.13
|
| 437 |
+
[[34m2025-10-29 15:19:25[0m] (step=0039000) Train Loss: 0.5744, Train Steps/Sec: 1.13
|
| 438 |
+
[[34m2025-10-29 15:20:53[0m] (step=0039100) Train Loss: 0.5741, Train Steps/Sec: 1.14
|
| 439 |
+
[[34m2025-10-29 15:22:21[0m] (step=0039200) Train Loss: 0.5734, Train Steps/Sec: 1.13
|
| 440 |
+
[[34m2025-10-29 15:23:49[0m] (step=0039300) Train Loss: 0.5734, Train Steps/Sec: 1.14
|
| 441 |
+
[[34m2025-10-29 15:25:17[0m] (step=0039400) Train Loss: 0.5733, Train Steps/Sec: 1.14
|
| 442 |
+
[[34m2025-10-29 15:26:45[0m] (step=0039500) Train Loss: 0.5739, Train Steps/Sec: 1.14
|
| 443 |
+
[[34m2025-10-29 15:28:13[0m] (step=0039600) Train Loss: 0.5745, Train Steps/Sec: 1.14
|
| 444 |
+
[[34m2025-10-29 15:29:41[0m] (step=0039700) Train Loss: 0.5740, Train Steps/Sec: 1.14
|
| 445 |
+
[[34m2025-10-29 15:31:09[0m] (step=0039800) Train Loss: 0.5735, Train Steps/Sec: 1.13
|
| 446 |
+
[[34m2025-10-29 15:32:37[0m] (step=0039900) Train Loss: 0.5739, Train Steps/Sec: 1.14
|
| 447 |
+
[[34m2025-10-29 15:34:05[0m] (step=0040000) Train Loss: 0.5728, Train Steps/Sec: 1.14
|
| 448 |
+
[[34m2025-10-29 15:34:34[0m] Beginning epoch 32...
|
| 449 |
+
[[34m2025-10-29 15:35:36[0m] (step=0040100) Train Loss: 0.5740, Train Steps/Sec: 1.11
|
| 450 |
+
[[34m2025-10-29 15:37:04[0m] (step=0040200) Train Loss: 0.5736, Train Steps/Sec: 1.14
|
| 451 |
+
[[34m2025-10-29 15:38:32[0m] (step=0040300) Train Loss: 0.5728, Train Steps/Sec: 1.14
|
| 452 |
+
[[34m2025-10-29 15:40:00[0m] (step=0040400) Train Loss: 0.5730, Train Steps/Sec: 1.13
|
| 453 |
+
[[34m2025-10-29 15:41:28[0m] (step=0040500) Train Loss: 0.5724, Train Steps/Sec: 1.14
|
| 454 |
+
[[34m2025-10-29 15:42:56[0m] (step=0040600) Train Loss: 0.5733, Train Steps/Sec: 1.13
|
| 455 |
+
[[34m2025-10-29 15:44:25[0m] (step=0040700) Train Loss: 0.5723, Train Steps/Sec: 1.13
|
| 456 |
+
[[34m2025-10-29 15:45:53[0m] (step=0040800) Train Loss: 0.5731, Train Steps/Sec: 1.14
|
| 457 |
+
[[34m2025-10-29 15:47:21[0m] (step=0040900) Train Loss: 0.5737, Train Steps/Sec: 1.14
|
| 458 |
+
[[34m2025-10-29 15:48:49[0m] (step=0041000) Train Loss: 0.5722, Train Steps/Sec: 1.14
|
| 459 |
+
[[34m2025-10-29 15:50:17[0m] (step=0041100) Train Loss: 0.5715, Train Steps/Sec: 1.14
|
| 460 |
+
[[34m2025-10-29 15:51:45[0m] (step=0041200) Train Loss: 0.5725, Train Steps/Sec: 1.14
|
| 461 |
+
[[34m2025-10-29 15:52:58[0m] Beginning epoch 33...
|
| 462 |
+
[[34m2025-10-29 15:53:15[0m] (step=0041300) Train Loss: 0.5723, Train Steps/Sec: 1.11
|
| 463 |
+
[[34m2025-10-29 15:54:43[0m] (step=0041400) Train Loss: 0.5730, Train Steps/Sec: 1.14
|
| 464 |
+
[[34m2025-10-29 15:56:12[0m] (step=0041500) Train Loss: 0.5700, Train Steps/Sec: 1.13
|
| 465 |
+
[[34m2025-10-29 15:57:40[0m] (step=0041600) Train Loss: 0.5729, Train Steps/Sec: 1.13
|
| 466 |
+
[[34m2025-10-29 15:59:08[0m] (step=0041700) Train Loss: 0.5726, Train Steps/Sec: 1.14
|
| 467 |
+
[[34m2025-10-29 16:00:36[0m] (step=0041800) Train Loss: 0.5717, Train Steps/Sec: 1.14
|
| 468 |
+
[[34m2025-10-29 16:02:04[0m] (step=0041900) Train Loss: 0.5716, Train Steps/Sec: 1.14
|
| 469 |
+
[[34m2025-10-29 16:03:32[0m] (step=0042000) Train Loss: 0.5712, Train Steps/Sec: 1.14
|
| 470 |
+
[[34m2025-10-29 16:05:00[0m] (step=0042100) Train Loss: 0.5718, Train Steps/Sec: 1.13
|
| 471 |
+
[[34m2025-10-29 16:06:28[0m] (step=0042200) Train Loss: 0.5729, Train Steps/Sec: 1.14
|
| 472 |
+
[[34m2025-10-29 16:07:56[0m] (step=0042300) Train Loss: 0.5720, Train Steps/Sec: 1.14
|
| 473 |
+
[[34m2025-10-29 16:09:25[0m] (step=0042400) Train Loss: 0.5730, Train Steps/Sec: 1.13
|
| 474 |
+
[[34m2025-10-29 16:10:53[0m] (step=0042500) Train Loss: 0.5708, Train Steps/Sec: 1.14
|
| 475 |
+
[[34m2025-10-29 16:11:23[0m] Beginning epoch 34...
|
| 476 |
+
[[34m2025-10-29 16:12:23[0m] (step=0042600) Train Loss: 0.5705, Train Steps/Sec: 1.10
|
| 477 |
+
[[34m2025-10-29 16:13:51[0m] (step=0042700) Train Loss: 0.5708, Train Steps/Sec: 1.14
|
| 478 |
+
[[34m2025-10-29 16:15:19[0m] (step=0042800) Train Loss: 0.5712, Train Steps/Sec: 1.14
|
| 479 |
+
[[34m2025-10-29 16:16:47[0m] (step=0042900) Train Loss: 0.5715, Train Steps/Sec: 1.14
|
| 480 |
+
[[34m2025-10-29 16:18:15[0m] (step=0043000) Train Loss: 0.5697, Train Steps/Sec: 1.14
|
| 481 |
+
[[34m2025-10-29 16:19:43[0m] (step=0043100) Train Loss: 0.5713, Train Steps/Sec: 1.14
|
| 482 |
+
[[34m2025-10-29 16:21:12[0m] (step=0043200) Train Loss: 0.5705, Train Steps/Sec: 1.13
|
| 483 |
+
[[34m2025-10-29 16:22:40[0m] (step=0043300) Train Loss: 0.5700, Train Steps/Sec: 1.13
|
| 484 |
+
[[34m2025-10-29 16:24:08[0m] (step=0043400) Train Loss: 0.5712, Train Steps/Sec: 1.14
|
| 485 |
+
[[34m2025-10-29 16:25:36[0m] (step=0043500) Train Loss: 0.5703, Train Steps/Sec: 1.14
|
| 486 |
+
[[34m2025-10-29 16:27:04[0m] (step=0043600) Train Loss: 0.5712, Train Steps/Sec: 1.14
|
| 487 |
+
[[34m2025-10-29 16:28:32[0m] (step=0043700) Train Loss: 0.5704, Train Steps/Sec: 1.14
|
| 488 |
+
[[34m2025-10-29 16:29:48[0m] Beginning epoch 35...
|
| 489 |
+
[[34m2025-10-29 16:30:03[0m] (step=0043800) Train Loss: 0.5697, Train Steps/Sec: 1.10
|
| 490 |
+
[[34m2025-10-29 16:31:31[0m] (step=0043900) Train Loss: 0.5685, Train Steps/Sec: 1.13
|
| 491 |
+
[[34m2025-10-29 16:32:59[0m] (step=0044000) Train Loss: 0.5707, Train Steps/Sec: 1.14
|
| 492 |
+
[[34m2025-10-29 16:34:28[0m] (step=0044100) Train Loss: 0.5702, Train Steps/Sec: 1.13
|
| 493 |
+
[[34m2025-10-29 16:35:56[0m] (step=0044200) Train Loss: 0.5688, Train Steps/Sec: 1.13
|
| 494 |
+
[[34m2025-10-29 16:37:24[0m] (step=0044300) Train Loss: 0.5700, Train Steps/Sec: 1.14
|
| 495 |
+
[[34m2025-10-29 16:38:52[0m] (step=0044400) Train Loss: 0.5696, Train Steps/Sec: 1.14
|
| 496 |
+
[[34m2025-10-29 16:40:20[0m] (step=0044500) Train Loss: 0.5694, Train Steps/Sec: 1.14
|
| 497 |
+
[[34m2025-10-29 16:41:48[0m] (step=0044600) Train Loss: 0.5694, Train Steps/Sec: 1.14
|
| 498 |
+
[[34m2025-10-29 16:43:16[0m] (step=0044700) Train Loss: 0.5696, Train Steps/Sec: 1.14
|
| 499 |
+
[[34m2025-10-29 16:44:44[0m] (step=0044800) Train Loss: 0.5689, Train Steps/Sec: 1.14
|
| 500 |
+
[[34m2025-10-29 16:46:12[0m] (step=0044900) Train Loss: 0.5678, Train Steps/Sec: 1.14
|
| 501 |
+
[[34m2025-10-29 16:47:40[0m] (step=0045000) Train Loss: 0.5686, Train Steps/Sec: 1.13
|
| 502 |
+
[[34m2025-10-29 16:48:13[0m] Beginning epoch 36...
|
| 503 |
+
[[34m2025-10-29 16:49:11[0m] (step=0045100) Train Loss: 0.5686, Train Steps/Sec: 1.10
|
| 504 |
+
[[34m2025-10-29 16:50:39[0m] (step=0045200) Train Loss: 0.5688, Train Steps/Sec: 1.14
|
| 505 |
+
[[34m2025-10-29 16:52:07[0m] (step=0045300) Train Loss: 0.5680, Train Steps/Sec: 1.14
|
| 506 |
+
[[34m2025-10-29 16:53:35[0m] (step=0045400) Train Loss: 0.5684, Train Steps/Sec: 1.14
|
| 507 |
+
[[34m2025-10-29 16:55:03[0m] (step=0045500) Train Loss: 0.5699, Train Steps/Sec: 1.14
|
| 508 |
+
[[34m2025-10-29 16:56:31[0m] (step=0045600) Train Loss: 0.5667, Train Steps/Sec: 1.13
|
| 509 |
+
[[34m2025-10-29 16:57:59[0m] (step=0045700) Train Loss: 0.5676, Train Steps/Sec: 1.14
|
| 510 |
+
[[34m2025-10-29 16:59:28[0m] (step=0045800) Train Loss: 0.5693, Train Steps/Sec: 1.13
|
| 511 |
+
[[34m2025-10-29 17:00:56[0m] (step=0045900) Train Loss: 0.5670, Train Steps/Sec: 1.13
|
| 512 |
+
[[34m2025-10-29 17:02:24[0m] (step=0046000) Train Loss: 0.5673, Train Steps/Sec: 1.14
|
| 513 |
+
[[34m2025-10-29 17:03:52[0m] (step=0046100) Train Loss: 0.5680, Train Steps/Sec: 1.14
|
| 514 |
+
[[34m2025-10-29 17:05:20[0m] (step=0046200) Train Loss: 0.5691, Train Steps/Sec: 1.14
|
| 515 |
+
[[34m2025-10-29 17:06:37[0m] Beginning epoch 37...
|
| 516 |
+
[[34m2025-10-29 17:06:51[0m] (step=0046300) Train Loss: 0.5694, Train Steps/Sec: 1.11
|
| 517 |
+
[[34m2025-10-29 17:08:19[0m] (step=0046400) Train Loss: 0.5686, Train Steps/Sec: 1.13
|
| 518 |
+
[[34m2025-10-29 17:09:47[0m] (step=0046500) Train Loss: 0.5677, Train Steps/Sec: 1.14
|
| 519 |
+
[[34m2025-10-29 17:11:15[0m] (step=0046600) Train Loss: 0.5686, Train Steps/Sec: 1.14
|
| 520 |
+
[[34m2025-10-29 17:12:44[0m] (step=0046700) Train Loss: 0.5667, Train Steps/Sec: 1.13
|
| 521 |
+
[[34m2025-10-29 17:14:12[0m] (step=0046800) Train Loss: 0.5676, Train Steps/Sec: 1.13
|
| 522 |
+
[[34m2025-10-29 17:15:40[0m] (step=0046900) Train Loss: 0.5682, Train Steps/Sec: 1.14
|
| 523 |
+
[[34m2025-10-29 17:17:08[0m] (step=0047000) Train Loss: 0.5675, Train Steps/Sec: 1.14
|
| 524 |
+
[[34m2025-10-29 17:18:36[0m] (step=0047100) Train Loss: 0.5664, Train Steps/Sec: 1.14
|
| 525 |
+
[[34m2025-10-29 17:20:04[0m] (step=0047200) Train Loss: 0.5668, Train Steps/Sec: 1.14
|
| 526 |
+
[[34m2025-10-29 17:21:32[0m] (step=0047300) Train Loss: 0.5676, Train Steps/Sec: 1.13
|
| 527 |
+
[[34m2025-10-29 17:23:00[0m] (step=0047400) Train Loss: 0.5665, Train Steps/Sec: 1.14
|
| 528 |
+
[[34m2025-10-29 17:24:28[0m] (step=0047500) Train Loss: 0.5672, Train Steps/Sec: 1.14
|
| 529 |
+
[[34m2025-10-29 17:25:02[0m] Beginning epoch 38...
|
| 530 |
+
[[34m2025-10-29 17:25:59[0m] (step=0047600) Train Loss: 0.5672, Train Steps/Sec: 1.10
|
| 531 |
+
[[34m2025-10-29 17:27:27[0m] (step=0047700) Train Loss: 0.5669, Train Steps/Sec: 1.14
|
| 532 |
+
[[34m2025-10-29 17:28:55[0m] (step=0047800) Train Loss: 0.5681, Train Steps/Sec: 1.14
|
| 533 |
+
[[34m2025-10-29 17:30:23[0m] (step=0047900) Train Loss: 0.5669, Train Steps/Sec: 1.13
|
| 534 |
+
[[34m2025-10-29 17:31:51[0m] (step=0048000) Train Loss: 0.5655, Train Steps/Sec: 1.14
|
| 535 |
+
[[34m2025-10-29 17:33:19[0m] (step=0048100) Train Loss: 0.5671, Train Steps/Sec: 1.14
|
| 536 |
+
[[34m2025-10-29 17:34:47[0m] (step=0048200) Train Loss: 0.5668, Train Steps/Sec: 1.14
|
| 537 |
+
[[34m2025-10-29 17:36:15[0m] (step=0048300) Train Loss: 0.5668, Train Steps/Sec: 1.14
|
| 538 |
+
[[34m2025-10-29 17:37:43[0m] (step=0048400) Train Loss: 0.5682, Train Steps/Sec: 1.13
|
| 539 |
+
[[34m2025-10-29 17:39:12[0m] (step=0048500) Train Loss: 0.5674, Train Steps/Sec: 1.13
|
| 540 |
+
[[34m2025-10-29 17:40:40[0m] (step=0048600) Train Loss: 0.5664, Train Steps/Sec: 1.14
|
| 541 |
+
[[34m2025-10-29 17:42:08[0m] (step=0048700) Train Loss: 0.5673, Train Steps/Sec: 1.14
|
| 542 |
+
[[34m2025-10-29 17:43:27[0m] Beginning epoch 39...
|
| 543 |
+
[[34m2025-10-29 17:43:38[0m] (step=0048800) Train Loss: 0.5672, Train Steps/Sec: 1.10
|
| 544 |
+
[[34m2025-10-29 17:45:06[0m] (step=0048900) Train Loss: 0.5657, Train Steps/Sec: 1.14
|
| 545 |
+
[[34m2025-10-29 17:46:34[0m] (step=0049000) Train Loss: 0.5656, Train Steps/Sec: 1.14
|
| 546 |
+
[[34m2025-10-29 17:48:02[0m] (step=0049100) Train Loss: 0.5654, Train Steps/Sec: 1.14
|
| 547 |
+
[[34m2025-10-29 17:49:30[0m] (step=0049200) Train Loss: 0.5671, Train Steps/Sec: 1.14
|
| 548 |
+
[[34m2025-10-29 17:50:59[0m] (step=0049300) Train Loss: 0.5663, Train Steps/Sec: 1.13
|
| 549 |
+
[[34m2025-10-29 17:52:27[0m] (step=0049400) Train Loss: 0.5657, Train Steps/Sec: 1.13
|
| 550 |
+
[[34m2025-10-29 17:53:55[0m] (step=0049500) Train Loss: 0.5656, Train Steps/Sec: 1.13
|
| 551 |
+
[[34m2025-10-29 17:55:23[0m] (step=0049600) Train Loss: 0.5650, Train Steps/Sec: 1.14
|
| 552 |
+
[[34m2025-10-29 17:56:51[0m] (step=0049700) Train Loss: 0.5656, Train Steps/Sec: 1.14
|
| 553 |
+
[[34m2025-10-29 17:58:19[0m] (step=0049800) Train Loss: 0.5656, Train Steps/Sec: 1.14
|
| 554 |
+
[[34m2025-10-29 17:59:47[0m] (step=0049900) Train Loss: 0.5637, Train Steps/Sec: 1.14
|
| 555 |
+
[[34m2025-10-29 18:01:15[0m] (step=0050000) Train Loss: 0.5656, Train Steps/Sec: 1.14
|
| 556 |
+
[[34m2025-10-29 18:02:12[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-l-bf16/checkpoints/0050000.pt
|
| 557 |
+
[[34m2025-10-29 18:02:12[0m] Generating EMA samples...
|
| 558 |
+
[[34m2025-10-29 18:02:41[0m] Generating EMA samples done.
|
| 559 |
+
[[34m2025-10-29 18:03:16[0m] Beginning epoch 40...
|
| 560 |
+
[[34m2025-10-29 18:04:11[0m] (step=0050100) Train Loss: 0.5650, Train Steps/Sec: 0.57
|
| 561 |
+
[[34m2025-10-29 18:05:39[0m] (step=0050200) Train Loss: 0.5658, Train Steps/Sec: 1.13
|
| 562 |
+
[[34m2025-10-29 18:07:07[0m] (step=0050300) Train Loss: 0.5653, Train Steps/Sec: 1.14
|
| 563 |
+
[[34m2025-10-29 18:08:35[0m] (step=0050400) Train Loss: 0.5660, Train Steps/Sec: 1.14
|
| 564 |
+
[[34m2025-10-29 18:10:04[0m] (step=0050500) Train Loss: 0.5645, Train Steps/Sec: 1.14
|
| 565 |
+
[[34m2025-10-29 18:11:32[0m] (step=0050600) Train Loss: 0.5652, Train Steps/Sec: 1.14
|
| 566 |
+
[[34m2025-10-29 18:13:00[0m] (step=0050700) Train Loss: 0.5652, Train Steps/Sec: 1.13
|
| 567 |
+
[[34m2025-10-29 18:14:28[0m] (step=0050800) Train Loss: 0.5646, Train Steps/Sec: 1.14
|
| 568 |
+
[[34m2025-10-29 18:15:56[0m] (step=0050900) Train Loss: 0.5643, Train Steps/Sec: 1.14
|
| 569 |
+
[[34m2025-10-29 18:17:24[0m] (step=0051000) Train Loss: 0.5652, Train Steps/Sec: 1.13
|
| 570 |
+
[[34m2025-10-29 18:18:52[0m] (step=0051100) Train Loss: 0.5648, Train Steps/Sec: 1.13
|
| 571 |
+
[[34m2025-10-29 18:20:20[0m] (step=0051200) Train Loss: 0.5649, Train Steps/Sec: 1.14
|
| 572 |
+
[[34m2025-10-29 18:21:41[0m] Beginning epoch 41...
|
| 573 |
+
[[34m2025-10-29 18:21:51[0m] (step=0051300) Train Loss: 0.5664, Train Steps/Sec: 1.11
|
| 574 |
+
[[34m2025-10-29 18:23:19[0m] (step=0051400) Train Loss: 0.5643, Train Steps/Sec: 1.14
|
| 575 |
+
[[34m2025-10-29 18:24:47[0m] (step=0051500) Train Loss: 0.5650, Train Steps/Sec: 1.14
|
| 576 |
+
[[34m2025-10-29 18:26:15[0m] (step=0051600) Train Loss: 0.5642, Train Steps/Sec: 1.13
|
| 577 |
+
[[34m2025-10-29 18:27:43[0m] (step=0051700) Train Loss: 0.5643, Train Steps/Sec: 1.14
|
| 578 |
+
[[34m2025-10-29 18:29:11[0m] (step=0051800) Train Loss: 0.5631, Train Steps/Sec: 1.14
|
| 579 |
+
[[34m2025-10-29 18:30:40[0m] (step=0051900) Train Loss: 0.5649, Train Steps/Sec: 1.13
|
| 580 |
+
[[34m2025-10-29 18:32:08[0m] (step=0052000) Train Loss: 0.5633, Train Steps/Sec: 1.13
|
| 581 |
+
[[34m2025-10-29 18:33:36[0m] (step=0052100) Train Loss: 0.5642, Train Steps/Sec: 1.14
|
| 582 |
+
[[34m2025-10-29 18:35:04[0m] (step=0052200) Train Loss: 0.5649, Train Steps/Sec: 1.14
|
| 583 |
+
[[34m2025-10-29 18:36:32[0m] (step=0052300) Train Loss: 0.5638, Train Steps/Sec: 1.14
|
| 584 |
+
[[34m2025-10-29 18:38:00[0m] (step=0052400) Train Loss: 0.5647, Train Steps/Sec: 1.14
|
| 585 |
+
[[34m2025-10-29 18:39:28[0m] (step=0052500) Train Loss: 0.5641, Train Steps/Sec: 1.14
|
| 586 |
+
[[34m2025-10-29 18:40:06[0m] Beginning epoch 42...
|
| 587 |
+
[[34m2025-10-29 18:40:59[0m] (step=0052600) Train Loss: 0.5635, Train Steps/Sec: 1.11
|
| 588 |
+
[[34m2025-10-29 18:42:27[0m] (step=0052700) Train Loss: 0.5650, Train Steps/Sec: 1.13
|
| 589 |
+
[[34m2025-10-29 18:43:56[0m] (step=0052800) Train Loss: 0.5642, Train Steps/Sec: 1.13
|
| 590 |
+
[[34m2025-10-29 18:45:24[0m] (step=0052900) Train Loss: 0.5636, Train Steps/Sec: 1.14
|
| 591 |
+
[[34m2025-10-29 18:46:52[0m] (step=0053000) Train Loss: 0.5644, Train Steps/Sec: 1.13
|
| 592 |
+
[[34m2025-10-29 18:48:20[0m] (step=0053100) Train Loss: 0.5622, Train Steps/Sec: 1.14
|
| 593 |
+
[[34m2025-10-29 18:49:48[0m] (step=0053200) Train Loss: 0.5635, Train Steps/Sec: 1.14
|
| 594 |
+
[[34m2025-10-29 18:51:16[0m] (step=0053300) Train Loss: 0.5641, Train Steps/Sec: 1.14
|
| 595 |
+
[[34m2025-10-29 18:52:44[0m] (step=0053400) Train Loss: 0.5636, Train Steps/Sec: 1.13
|
| 596 |
+
[[34m2025-10-29 18:54:12[0m] (step=0053500) Train Loss: 0.5625, Train Steps/Sec: 1.14
|
| 597 |
+
[[34m2025-10-29 18:55:40[0m] (step=0053600) Train Loss: 0.5646, Train Steps/Sec: 1.13
|
| 598 |
+
[[34m2025-10-29 18:57:09[0m] (step=0053700) Train Loss: 0.5647, Train Steps/Sec: 1.14
|
| 599 |
+
[[34m2025-10-29 18:58:31[0m] Beginning epoch 43...
|
| 600 |
+
[[34m2025-10-29 18:58:39[0m] (step=0053800) Train Loss: 0.5643, Train Steps/Sec: 1.11
|
| 601 |
+
[[34m2025-10-29 19:00:07[0m] (step=0053900) Train Loss: 0.5646, Train Steps/Sec: 1.14
|
| 602 |
+
[[34m2025-10-29 19:01:35[0m] (step=0054000) Train Loss: 0.5643, Train Steps/Sec: 1.14
|
| 603 |
+
[[34m2025-10-29 19:03:03[0m] (step=0054100) Train Loss: 0.5635, Train Steps/Sec: 1.14
|
| 604 |
+
[[34m2025-10-29 19:04:31[0m] (step=0054200) Train Loss: 0.5614, Train Steps/Sec: 1.13
|
| 605 |
+
[[34m2025-10-29 19:05:59[0m] (step=0054300) Train Loss: 0.5627, Train Steps/Sec: 1.14
|
| 606 |
+
[[34m2025-10-29 19:07:28[0m] (step=0054400) Train Loss: 0.5639, Train Steps/Sec: 1.14
|
| 607 |
+
[[34m2025-10-29 19:08:56[0m] (step=0054500) Train Loss: 0.5633, Train Steps/Sec: 1.13
|
| 608 |
+
[[34m2025-10-29 19:10:24[0m] (step=0054600) Train Loss: 0.5643, Train Steps/Sec: 1.14
|
| 609 |
+
[[34m2025-10-29 19:11:52[0m] (step=0054700) Train Loss: 0.5625, Train Steps/Sec: 1.14
|
| 610 |
+
[[34m2025-10-29 19:13:20[0m] (step=0054800) Train Loss: 0.5629, Train Steps/Sec: 1.14
|
| 611 |
+
[[34m2025-10-29 19:14:48[0m] (step=0054900) Train Loss: 0.5623, Train Steps/Sec: 1.14
|
| 612 |
+
[[34m2025-10-29 19:16:17[0m] (step=0055000) Train Loss: 0.5635, Train Steps/Sec: 1.13
|
| 613 |
+
[[34m2025-10-29 19:16:56[0m] Beginning epoch 44...
|
| 614 |
+
[[34m2025-10-29 19:17:47[0m] (step=0055100) Train Loss: 0.5614, Train Steps/Sec: 1.10
|
| 615 |
+
[[34m2025-10-29 19:19:15[0m] (step=0055200) Train Loss: 0.5622, Train Steps/Sec: 1.14
|
| 616 |
+
[[34m2025-10-29 19:20:44[0m] (step=0055300) Train Loss: 0.5615, Train Steps/Sec: 1.13
|
| 617 |
+
[[34m2025-10-29 19:22:12[0m] (step=0055400) Train Loss: 0.5628, Train Steps/Sec: 1.13
|
| 618 |
+
[[34m2025-10-29 19:23:40[0m] (step=0055500) Train Loss: 0.5636, Train Steps/Sec: 1.14
|
| 619 |
+
[[34m2025-10-29 19:25:08[0m] (step=0055600) Train Loss: 0.5616, Train Steps/Sec: 1.14
|
| 620 |
+
[[34m2025-10-29 19:26:36[0m] (step=0055700) Train Loss: 0.5619, Train Steps/Sec: 1.13
|
| 621 |
+
[[34m2025-10-29 19:28:04[0m] (step=0055800) Train Loss: 0.5620, Train Steps/Sec: 1.14
|
| 622 |
+
[[34m2025-10-29 19:29:33[0m] (step=0055900) Train Loss: 0.5607, Train Steps/Sec: 1.13
|
| 623 |
+
[[34m2025-10-29 19:31:01[0m] (step=0056000) Train Loss: 0.5625, Train Steps/Sec: 1.14
|
| 624 |
+
[[34m2025-10-29 19:32:29[0m] (step=0056100) Train Loss: 0.5627, Train Steps/Sec: 1.14
|
| 625 |
+
[[34m2025-10-29 19:33:57[0m] (step=0056200) Train Loss: 0.5628, Train Steps/Sec: 1.13
|
| 626 |
+
[[34m2025-10-29 19:35:21[0m] Beginning epoch 45...
|
| 627 |
+
[[34m2025-10-29 19:35:28[0m] (step=0056300) Train Loss: 0.5616, Train Steps/Sec: 1.10
|
| 628 |
+
[[34m2025-10-29 19:36:56[0m] (step=0056400) Train Loss: 0.5610, Train Steps/Sec: 1.14
|
| 629 |
+
[[34m2025-10-29 19:38:24[0m] (step=0056500) Train Loss: 0.5606, Train Steps/Sec: 1.13
|
| 630 |
+
[[34m2025-10-29 19:39:52[0m] (step=0056600) Train Loss: 0.5625, Train Steps/Sec: 1.14
|
| 631 |
+
[[34m2025-10-29 19:41:20[0m] (step=0056700) Train Loss: 0.5613, Train Steps/Sec: 1.14
|
| 632 |
+
[[34m2025-10-29 19:42:48[0m] (step=0056800) Train Loss: 0.5612, Train Steps/Sec: 1.13
|
| 633 |
+
[[34m2025-10-29 19:44:16[0m] (step=0056900) Train Loss: 0.5617, Train Steps/Sec: 1.14
|
| 634 |
+
[[34m2025-10-29 19:45:45[0m] (step=0057000) Train Loss: 0.5625, Train Steps/Sec: 1.13
|
| 635 |
+
[[34m2025-10-29 19:47:13[0m] (step=0057100) Train Loss: 0.5608, Train Steps/Sec: 1.13
|
| 636 |
+
[[34m2025-10-29 19:48:41[0m] (step=0057200) Train Loss: 0.5615, Train Steps/Sec: 1.14
|
| 637 |
+
[[34m2025-10-29 19:50:09[0m] (step=0057300) Train Loss: 0.5626, Train Steps/Sec: 1.13
|
| 638 |
+
[[34m2025-10-29 19:51:37[0m] (step=0057400) Train Loss: 0.5614, Train Steps/Sec: 1.14
|
| 639 |
+
[[34m2025-10-29 19:53:05[0m] (step=0057500) Train Loss: 0.5602, Train Steps/Sec: 1.14
|
| 640 |
+
[[34m2025-10-29 19:53:46[0m] Beginning epoch 46...
|
| 641 |
+
[[34m2025-10-29 19:54:36[0m] (step=0057600) Train Loss: 0.5626, Train Steps/Sec: 1.10
|
| 642 |
+
[[34m2025-10-29 19:56:04[0m] (step=0057700) Train Loss: 0.5611, Train Steps/Sec: 1.14
|
| 643 |
+
[[34m2025-10-29 19:57:32[0m] (step=0057800) Train Loss: 0.5611, Train Steps/Sec: 1.14
|
| 644 |
+
[[34m2025-10-29 19:59:00[0m] (step=0057900) Train Loss: 0.5607, Train Steps/Sec: 1.13
|
| 645 |
+
[[34m2025-10-29 20:00:29[0m] (step=0058000) Train Loss: 0.5599, Train Steps/Sec: 1.13
|
| 646 |
+
[[34m2025-10-29 20:01:57[0m] (step=0058100) Train Loss: 0.5603, Train Steps/Sec: 1.14
|
| 647 |
+
[[34m2025-10-29 20:03:25[0m] (step=0058200) Train Loss: 0.5610, Train Steps/Sec: 1.14
|
| 648 |
+
[[34m2025-10-29 20:04:53[0m] (step=0058300) Train Loss: 0.5610, Train Steps/Sec: 1.14
|
| 649 |
+
[[34m2025-10-29 20:06:21[0m] (step=0058400) Train Loss: 0.5613, Train Steps/Sec: 1.14
|
| 650 |
+
[[34m2025-10-29 20:07:49[0m] (step=0058500) Train Loss: 0.5600, Train Steps/Sec: 1.14
|
| 651 |
+
[[34m2025-10-29 20:09:17[0m] (step=0058600) Train Loss: 0.5604, Train Steps/Sec: 1.14
|
| 652 |
+
[[34m2025-10-29 20:10:45[0m] (step=0058700) Train Loss: 0.5599, Train Steps/Sec: 1.14
|
| 653 |
+
[[34m2025-10-29 20:12:11[0m] Beginning epoch 47...
|
| 654 |
+
[[34m2025-10-29 20:12:16[0m] (step=0058800) Train Loss: 0.5612, Train Steps/Sec: 1.10
|
| 655 |
+
[[34m2025-10-29 20:13:44[0m] (step=0058900) Train Loss: 0.5593, Train Steps/Sec: 1.13
|
| 656 |
+
[[34m2025-10-29 20:15:12[0m] (step=0059000) Train Loss: 0.5585, Train Steps/Sec: 1.14
|
| 657 |
+
[[34m2025-10-29 20:16:40[0m] (step=0059100) Train Loss: 0.5605, Train Steps/Sec: 1.14
|
| 658 |
+
[[34m2025-10-29 20:18:08[0m] (step=0059200) Train Loss: 0.5604, Train Steps/Sec: 1.14
|
| 659 |
+
[[34m2025-10-29 20:19:37[0m] (step=0059300) Train Loss: 0.5614, Train Steps/Sec: 1.13
|
| 660 |
+
[[34m2025-10-29 20:21:05[0m] (step=0059400) Train Loss: 0.5606, Train Steps/Sec: 1.14
|
| 661 |
+
[[34m2025-10-29 20:22:33[0m] (step=0059500) Train Loss: 0.5599, Train Steps/Sec: 1.14
|
| 662 |
+
[[34m2025-10-29 20:24:01[0m] (step=0059600) Train Loss: 0.5606, Train Steps/Sec: 1.13
|
| 663 |
+
[[34m2025-10-29 20:25:29[0m] (step=0059700) Train Loss: 0.5610, Train Steps/Sec: 1.13
|
| 664 |
+
[[34m2025-10-29 20:26:58[0m] (step=0059800) Train Loss: 0.5612, Train Steps/Sec: 1.14
|
| 665 |
+
[[34m2025-10-29 20:28:26[0m] (step=0059900) Train Loss: 0.5594, Train Steps/Sec: 1.14
|
| 666 |
+
[[34m2025-10-29 20:29:54[0m] (step=0060000) Train Loss: 0.5607, Train Steps/Sec: 1.14
|
| 667 |
+
[[34m2025-10-29 20:30:36[0m] Beginning epoch 48...
|
| 668 |
+
[[34m2025-10-29 20:31:24[0m] (step=0060100) Train Loss: 0.5591, Train Steps/Sec: 1.10
|
| 669 |
+
[[34m2025-10-29 20:32:52[0m] (step=0060200) Train Loss: 0.5605, Train Steps/Sec: 1.14
|
| 670 |
+
[[34m2025-10-29 20:34:20[0m] (step=0060300) Train Loss: 0.5590, Train Steps/Sec: 1.14
|
| 671 |
+
[[34m2025-10-29 20:35:48[0m] (step=0060400) Train Loss: 0.5614, Train Steps/Sec: 1.14
|
| 672 |
+
[[34m2025-10-29 20:37:17[0m] (step=0060500) Train Loss: 0.5609, Train Steps/Sec: 1.13
|
| 673 |
+
[[34m2025-10-29 20:38:45[0m] (step=0060600) Train Loss: 0.5598, Train Steps/Sec: 1.13
|
| 674 |
+
[[34m2025-10-29 20:40:13[0m] (step=0060700) Train Loss: 0.5596, Train Steps/Sec: 1.14
|
| 675 |
+
[[34m2025-10-29 20:41:41[0m] (step=0060800) Train Loss: 0.5592, Train Steps/Sec: 1.14
|
| 676 |
+
[[34m2025-10-29 20:43:09[0m] (step=0060900) Train Loss: 0.5611, Train Steps/Sec: 1.14
|
| 677 |
+
[[34m2025-10-29 20:44:37[0m] (step=0061000) Train Loss: 0.5602, Train Steps/Sec: 1.14
|
| 678 |
+
[[34m2025-10-29 20:46:05[0m] (step=0061100) Train Loss: 0.5600, Train Steps/Sec: 1.14
|
| 679 |
+
[[34m2025-10-29 20:47:33[0m] (step=0061200) Train Loss: 0.5594, Train Steps/Sec: 1.14
|
| 680 |
+
[[34m2025-10-29 20:49:01[0m] Beginning epoch 49...
|
| 681 |
+
[[34m2025-10-29 20:49:04[0m] (step=0061300) Train Loss: 0.5588, Train Steps/Sec: 1.10
|
| 682 |
+
[[34m2025-10-29 20:50:33[0m] (step=0061400) Train Loss: 0.5589, Train Steps/Sec: 1.13
|
| 683 |
+
[[34m2025-10-29 20:52:01[0m] (step=0061500) Train Loss: 0.5589, Train Steps/Sec: 1.14
|
| 684 |
+
[[34m2025-10-29 20:53:29[0m] (step=0061600) Train Loss: 0.5592, Train Steps/Sec: 1.14
|
| 685 |
+
[[34m2025-10-29 20:54:57[0m] (step=0061700) Train Loss: 0.5601, Train Steps/Sec: 1.14
|
| 686 |
+
[[34m2025-10-29 20:56:25[0m] (step=0061800) Train Loss: 0.5584, Train Steps/Sec: 1.14
|
| 687 |
+
[[34m2025-10-29 20:57:53[0m] (step=0061900) Train Loss: 0.5578, Train Steps/Sec: 1.14
|
| 688 |
+
[[34m2025-10-29 20:59:21[0m] (step=0062000) Train Loss: 0.5602, Train Steps/Sec: 1.14
|
| 689 |
+
[[34m2025-10-29 21:00:49[0m] (step=0062100) Train Loss: 0.5583, Train Steps/Sec: 1.14
|
| 690 |
+
[[34m2025-10-29 21:02:17[0m] (step=0062200) Train Loss: 0.5587, Train Steps/Sec: 1.13
|
| 691 |
+
[[34m2025-10-29 21:03:45[0m] (step=0062300) Train Loss: 0.5594, Train Steps/Sec: 1.13
|
| 692 |
+
[[34m2025-10-29 21:05:14[0m] (step=0062400) Train Loss: 0.5596, Train Steps/Sec: 1.14
|
| 693 |
+
[[34m2025-10-29 21:06:42[0m] (step=0062500) Train Loss: 0.5584, Train Steps/Sec: 1.14
|
| 694 |
+
[[34m2025-10-29 21:07:26[0m] Beginning epoch 50...
|
| 695 |
+
[[34m2025-10-29 21:08:12[0m] (step=0062600) Train Loss: 0.5573, Train Steps/Sec: 1.11
|
| 696 |
+
[[34m2025-10-29 21:09:40[0m] (step=0062700) Train Loss: 0.5590, Train Steps/Sec: 1.14
|
| 697 |
+
[[34m2025-10-29 21:11:08[0m] (step=0062800) Train Loss: 0.5577, Train Steps/Sec: 1.13
|
| 698 |
+
[[34m2025-10-29 21:12:36[0m] (step=0062900) Train Loss: 0.5577, Train Steps/Sec: 1.14
|
| 699 |
+
[[34m2025-10-29 21:14:05[0m] (step=0063000) Train Loss: 0.5588, Train Steps/Sec: 1.14
|
| 700 |
+
[[34m2025-10-29 21:15:33[0m] (step=0063100) Train Loss: 0.5585, Train Steps/Sec: 1.13
|
| 701 |
+
[[34m2025-10-29 21:17:01[0m] (step=0063200) Train Loss: 0.5577, Train Steps/Sec: 1.13
|
| 702 |
+
[[34m2025-10-29 21:18:29[0m] (step=0063300) Train Loss: 0.5586, Train Steps/Sec: 1.14
|
| 703 |
+
[[34m2025-10-29 21:19:57[0m] (step=0063400) Train Loss: 0.5599, Train Steps/Sec: 1.14
|
| 704 |
+
[[34m2025-10-29 21:21:25[0m] (step=0063500) Train Loss: 0.5580, Train Steps/Sec: 1.14
|
| 705 |
+
[[34m2025-10-29 21:22:53[0m] (step=0063600) Train Loss: 0.5586, Train Steps/Sec: 1.13
|
| 706 |
+
[[34m2025-10-29 21:24:21[0m] (step=0063700) Train Loss: 0.5580, Train Steps/Sec: 1.14
|
| 707 |
+
[[34m2025-10-29 21:25:49[0m] (step=0063800) Train Loss: 0.5583, Train Steps/Sec: 1.14
|
| 708 |
+
[[34m2025-10-29 21:25:51[0m] Beginning epoch 51...
|
| 709 |
+
[[34m2025-10-29 21:27:20[0m] (step=0063900) Train Loss: 0.5580, Train Steps/Sec: 1.10
|
| 710 |
+
[[34m2025-10-29 21:28:49[0m] (step=0064000) Train Loss: 0.5573, Train Steps/Sec: 1.13
|
| 711 |
+
[[34m2025-10-29 21:30:17[0m] (step=0064100) Train Loss: 0.5591, Train Steps/Sec: 1.14
|
| 712 |
+
[[34m2025-10-29 21:31:45[0m] (step=0064200) Train Loss: 0.5594, Train Steps/Sec: 1.14
|
| 713 |
+
[[34m2025-10-29 21:33:13[0m] (step=0064300) Train Loss: 0.5591, Train Steps/Sec: 1.14
|
| 714 |
+
[[34m2025-10-29 21:34:41[0m] (step=0064400) Train Loss: 0.5578, Train Steps/Sec: 1.13
|
| 715 |
+
[[34m2025-10-29 21:36:09[0m] (step=0064500) Train Loss: 0.5585, Train Steps/Sec: 1.14
|
| 716 |
+
[[34m2025-10-29 21:37:37[0m] (step=0064600) Train Loss: 0.5571, Train Steps/Sec: 1.14
|
| 717 |
+
[[34m2025-10-29 21:39:05[0m] (step=0064700) Train Loss: 0.5585, Train Steps/Sec: 1.14
|
| 718 |
+
[[34m2025-10-29 21:40:33[0m] (step=0064800) Train Loss: 0.5578, Train Steps/Sec: 1.13
|
| 719 |
+
[[34m2025-10-29 21:42:01[0m] (step=0064900) Train Loss: 0.5567, Train Steps/Sec: 1.13
|
| 720 |
+
[[34m2025-10-29 21:43:29[0m] (step=0065000) Train Loss: 0.5583, Train Steps/Sec: 1.14
|
| 721 |
+
[[34m2025-10-29 21:44:16[0m] Beginning epoch 52...
|
| 722 |
+
[[34m2025-10-29 21:45:00[0m] (step=0065100) Train Loss: 0.5585, Train Steps/Sec: 1.11
|
| 723 |
+
[[34m2025-10-29 21:46:28[0m] (step=0065200) Train Loss: 0.5572, Train Steps/Sec: 1.14
|
| 724 |
+
[[34m2025-10-29 21:47:56[0m] (step=0065300) Train Loss: 0.5591, Train Steps/Sec: 1.14
|
| 725 |
+
[[34m2025-10-29 21:49:24[0m] (step=0065400) Train Loss: 0.5586, Train Steps/Sec: 1.14
|
| 726 |
+
[[34m2025-10-29 21:50:52[0m] (step=0065500) Train Loss: 0.5581, Train Steps/Sec: 1.14
|
| 727 |
+
[[34m2025-10-29 21:52:20[0m] (step=0065600) Train Loss: 0.5594, Train Steps/Sec: 1.14
|
| 728 |
+
[[34m2025-10-29 21:53:49[0m] (step=0065700) Train Loss: 0.5581, Train Steps/Sec: 1.13
|
| 729 |
+
[[34m2025-10-29 21:55:17[0m] (step=0065800) Train Loss: 0.5574, Train Steps/Sec: 1.13
|
| 730 |
+
[[34m2025-10-29 21:56:45[0m] (step=0065900) Train Loss: 0.5566, Train Steps/Sec: 1.14
|
| 731 |
+
[[34m2025-10-29 21:58:13[0m] (step=0066000) Train Loss: 0.5579, Train Steps/Sec: 1.14
|
| 732 |
+
[[34m2025-10-29 21:59:41[0m] (step=0066100) Train Loss: 0.5596, Train Steps/Sec: 1.14
|
| 733 |
+
[[34m2025-10-29 22:01:09[0m] (step=0066200) Train Loss: 0.5582, Train Steps/Sec: 1.14
|
| 734 |
+
[[34m2025-10-29 22:02:37[0m] (step=0066300) Train Loss: 0.5579, Train Steps/Sec: 1.14
|
| 735 |
+
[[34m2025-10-29 22:02:40[0m] Beginning epoch 53...
|
| 736 |
+
[[34m2025-10-29 22:04:08[0m] (step=0066400) Train Loss: 0.5581, Train Steps/Sec: 1.10
|
| 737 |
+
[[34m2025-10-29 22:05:36[0m] (step=0066500) Train Loss: 0.5567, Train Steps/Sec: 1.13
|
| 738 |
+
[[34m2025-10-29 22:07:04[0m] (step=0066600) Train Loss: 0.5569, Train Steps/Sec: 1.13
|
| 739 |
+
[[34m2025-10-29 22:08:32[0m] (step=0066700) Train Loss: 0.5586, Train Steps/Sec: 1.14
|
| 740 |
+
[[34m2025-10-29 22:10:00[0m] (step=0066800) Train Loss: 0.5581, Train Steps/Sec: 1.14
|
| 741 |
+
[[34m2025-10-29 22:11:28[0m] (step=0066900) Train Loss: 0.5592, Train Steps/Sec: 1.14
|
| 742 |
+
[[34m2025-10-29 22:12:57[0m] (step=0067000) Train Loss: 0.5573, Train Steps/Sec: 1.13
|
| 743 |
+
[[34m2025-10-29 22:14:25[0m] (step=0067100) Train Loss: 0.5580, Train Steps/Sec: 1.14
|
| 744 |
+
[[34m2025-10-29 22:15:53[0m] (step=0067200) Train Loss: 0.5565, Train Steps/Sec: 1.14
|
| 745 |
+
[[34m2025-10-29 22:17:21[0m] (step=0067300) Train Loss: 0.5583, Train Steps/Sec: 1.14
|
| 746 |
+
[[34m2025-10-29 22:18:49[0m] (step=0067400) Train Loss: 0.5574, Train Steps/Sec: 1.13
|
| 747 |
+
[[34m2025-10-29 22:20:17[0m] (step=0067500) Train Loss: 0.5577, Train Steps/Sec: 1.13
|
| 748 |
+
[[34m2025-10-29 22:21:05[0m] Beginning epoch 54...
|
| 749 |
+
[[34m2025-10-29 22:21:48[0m] (step=0067600) Train Loss: 0.5580, Train Steps/Sec: 1.10
|
| 750 |
+
[[34m2025-10-29 22:23:16[0m] (step=0067700) Train Loss: 0.5558, Train Steps/Sec: 1.14
|
| 751 |
+
[[34m2025-10-29 22:24:44[0m] (step=0067800) Train Loss: 0.5576, Train Steps/Sec: 1.14
|
| 752 |
+
[[34m2025-10-29 22:26:12[0m] (step=0067900) Train Loss: 0.5569, Train Steps/Sec: 1.14
|
| 753 |
+
[[34m2025-10-29 22:27:40[0m] (step=0068000) Train Loss: 0.5566, Train Steps/Sec: 1.14
|
| 754 |
+
[[34m2025-10-29 22:29:08[0m] (step=0068100) Train Loss: 0.5563, Train Steps/Sec: 1.14
|
| 755 |
+
[[34m2025-10-29 22:30:36[0m] (step=0068200) Train Loss: 0.5567, Train Steps/Sec: 1.14
|
| 756 |
+
[[34m2025-10-29 22:32:05[0m] (step=0068300) Train Loss: 0.5568, Train Steps/Sec: 1.13
|
| 757 |
+
[[34m2025-10-29 22:33:33[0m] (step=0068400) Train Loss: 0.5570, Train Steps/Sec: 1.14
|
| 758 |
+
[[34m2025-10-29 22:35:01[0m] (step=0068500) Train Loss: 0.5559, Train Steps/Sec: 1.14
|
| 759 |
+
[[34m2025-10-29 22:36:29[0m] (step=0068600) Train Loss: 0.5555, Train Steps/Sec: 1.14
|
| 760 |
+
[[34m2025-10-29 22:37:57[0m] (step=0068700) Train Loss: 0.5581, Train Steps/Sec: 1.14
|
| 761 |
+
[[34m2025-10-29 22:39:25[0m] (step=0068800) Train Loss: 0.5566, Train Steps/Sec: 1.14
|
| 762 |
+
[[34m2025-10-29 22:39:30[0m] Beginning epoch 55...
|
| 763 |
+
[[34m2025-10-29 22:40:56[0m] (step=0068900) Train Loss: 0.5564, Train Steps/Sec: 1.11
|
| 764 |
+
[[34m2025-10-29 22:42:24[0m] (step=0069000) Train Loss: 0.5565, Train Steps/Sec: 1.14
|
| 765 |
+
[[34m2025-10-29 22:43:52[0m] (step=0069100) Train Loss: 0.5567, Train Steps/Sec: 1.13
|
| 766 |
+
[[34m2025-10-29 22:45:21[0m] (step=0069200) Train Loss: 0.5560, Train Steps/Sec: 1.13
|
| 767 |
+
[[34m2025-10-29 22:46:49[0m] (step=0069300) Train Loss: 0.5567, Train Steps/Sec: 1.14
|
| 768 |
+
[[34m2025-10-29 22:48:17[0m] (step=0069400) Train Loss: 0.5568, Train Steps/Sec: 1.14
|
| 769 |
+
[[34m2025-10-29 22:49:45[0m] (step=0069500) Train Loss: 0.5550, Train Steps/Sec: 1.14
|
| 770 |
+
[[34m2025-10-29 22:51:13[0m] (step=0069600) Train Loss: 0.5558, Train Steps/Sec: 1.14
|
| 771 |
+
[[34m2025-10-29 22:52:41[0m] (step=0069700) Train Loss: 0.5553, Train Steps/Sec: 1.14
|
| 772 |
+
[[34m2025-10-29 22:54:09[0m] (step=0069800) Train Loss: 0.5567, Train Steps/Sec: 1.14
|
| 773 |
+
[[34m2025-10-29 22:55:37[0m] (step=0069900) Train Loss: 0.5556, Train Steps/Sec: 1.14
|
| 774 |
+
[[34m2025-10-29 22:57:05[0m] (step=0070000) Train Loss: 0.5565, Train Steps/Sec: 1.13
|
| 775 |
+
[[34m2025-10-29 22:57:55[0m] Beginning epoch 56...
|
| 776 |
+
[[34m2025-10-29 22:58:36[0m] (step=0070100) Train Loss: 0.5546, Train Steps/Sec: 1.10
|
| 777 |
+
[[34m2025-10-29 23:00:04[0m] (step=0070200) Train Loss: 0.5566, Train Steps/Sec: 1.14
|
| 778 |
+
[[34m2025-10-29 23:01:32[0m] (step=0070300) Train Loss: 0.5542, Train Steps/Sec: 1.14
|
| 779 |
+
[[34m2025-10-29 23:03:00[0m] (step=0070400) Train Loss: 0.5562, Train Steps/Sec: 1.14
|
| 780 |
+
[[34m2025-10-29 23:04:28[0m] (step=0070500) Train Loss: 0.5558, Train Steps/Sec: 1.13
|
| 781 |
+
[[34m2025-10-29 23:05:56[0m] (step=0070600) Train Loss: 0.5561, Train Steps/Sec: 1.14
|
| 782 |
+
[[34m2025-10-29 23:07:24[0m] (step=0070700) Train Loss: 0.5564, Train Steps/Sec: 1.13
|
| 783 |
+
[[34m2025-10-29 23:08:52[0m] (step=0070800) Train Loss: 0.5559, Train Steps/Sec: 1.14
|
| 784 |
+
[[34m2025-10-29 23:10:20[0m] (step=0070900) Train Loss: 0.5561, Train Steps/Sec: 1.13
|
| 785 |
+
[[34m2025-10-29 23:11:49[0m] (step=0071000) Train Loss: 0.5555, Train Steps/Sec: 1.14
|
| 786 |
+
[[34m2025-10-29 23:13:17[0m] (step=0071100) Train Loss: 0.5556, Train Steps/Sec: 1.14
|
| 787 |
+
[[34m2025-10-29 23:14:45[0m] (step=0071200) Train Loss: 0.5571, Train Steps/Sec: 1.14
|
| 788 |
+
[[34m2025-10-29 23:16:13[0m] (step=0071300) Train Loss: 0.5551, Train Steps/Sec: 1.14
|
| 789 |
+
[[34m2025-10-29 23:16:19[0m] Beginning epoch 57...
|
| 790 |
+
[[34m2025-10-29 23:17:43[0m] (step=0071400) Train Loss: 0.5551, Train Steps/Sec: 1.11
|
| 791 |
+
[[34m2025-10-29 23:19:11[0m] (step=0071500) Train Loss: 0.5543, Train Steps/Sec: 1.13
|
| 792 |
+
[[34m2025-10-29 23:20:39[0m] (step=0071600) Train Loss: 0.5563, Train Steps/Sec: 1.14
|
| 793 |
+
[[34m2025-10-29 23:22:08[0m] (step=0071700) Train Loss: 0.5562, Train Steps/Sec: 1.13
|
| 794 |
+
[[34m2025-10-29 23:23:36[0m] (step=0071800) Train Loss: 0.5551, Train Steps/Sec: 1.13
|
| 795 |
+
[[34m2025-10-29 23:25:04[0m] (step=0071900) Train Loss: 0.5560, Train Steps/Sec: 1.14
|
| 796 |
+
[[34m2025-10-29 23:26:32[0m] (step=0072000) Train Loss: 0.5563, Train Steps/Sec: 1.14
|
| 797 |
+
[[34m2025-10-29 23:28:00[0m] (step=0072100) Train Loss: 0.5559, Train Steps/Sec: 1.14
|
| 798 |
+
[[34m2025-10-29 23:29:28[0m] (step=0072200) Train Loss: 0.5547, Train Steps/Sec: 1.13
|
| 799 |
+
[[34m2025-10-29 23:30:56[0m] (step=0072300) Train Loss: 0.5544, Train Steps/Sec: 1.14
|
| 800 |
+
[[34m2025-10-29 23:32:24[0m] (step=0072400) Train Loss: 0.5543, Train Steps/Sec: 1.14
|
| 801 |
+
[[34m2025-10-29 23:33:52[0m] (step=0072500) Train Loss: 0.5549, Train Steps/Sec: 1.14
|
| 802 |
+
[[34m2025-10-29 23:34:44[0m] Beginning epoch 58...
|
| 803 |
+
[[34m2025-10-29 23:35:23[0m] (step=0072600) Train Loss: 0.5548, Train Steps/Sec: 1.10
|
| 804 |
+
[[34m2025-10-29 23:36:51[0m] (step=0072700) Train Loss: 0.5564, Train Steps/Sec: 1.14
|
| 805 |
+
[[34m2025-10-29 23:38:19[0m] (step=0072800) Train Loss: 0.5540, Train Steps/Sec: 1.14
|
| 806 |
+
[[34m2025-10-29 23:39:47[0m] (step=0072900) Train Loss: 0.5546, Train Steps/Sec: 1.14
|
| 807 |
+
[[34m2025-10-29 23:41:16[0m] (step=0073000) Train Loss: 0.5551, Train Steps/Sec: 1.13
|
| 808 |
+
[[34m2025-10-29 23:42:44[0m] (step=0073100) Train Loss: 0.5560, Train Steps/Sec: 1.14
|
| 809 |
+
[[34m2025-10-29 23:44:12[0m] (step=0073200) Train Loss: 0.5547, Train Steps/Sec: 1.14
|
| 810 |
+
[[34m2025-10-29 23:45:40[0m] (step=0073300) Train Loss: 0.5544, Train Steps/Sec: 1.14
|
| 811 |
+
[[34m2025-10-29 23:47:08[0m] (step=0073400) Train Loss: 0.5549, Train Steps/Sec: 1.13
|
| 812 |
+
[[34m2025-10-29 23:48:36[0m] (step=0073500) Train Loss: 0.5565, Train Steps/Sec: 1.13
|
| 813 |
+
[[34m2025-10-29 23:50:04[0m] (step=0073600) Train Loss: 0.5552, Train Steps/Sec: 1.14
|
| 814 |
+
[[34m2025-10-29 23:51:32[0m] (step=0073700) Train Loss: 0.5539, Train Steps/Sec: 1.14
|
| 815 |
+
[[34m2025-10-29 23:53:00[0m] (step=0073800) Train Loss: 0.5542, Train Steps/Sec: 1.14
|
| 816 |
+
[[34m2025-10-29 23:53:09[0m] Beginning epoch 59...
|
| 817 |
+
[[34m2025-10-29 23:54:32[0m] (step=0073900) Train Loss: 0.5560, Train Steps/Sec: 1.10
|
| 818 |
+
[[34m2025-10-29 23:56:00[0m] (step=0074000) Train Loss: 0.5544, Train Steps/Sec: 1.14
|
| 819 |
+
[[34m2025-10-29 23:57:28[0m] (step=0074100) Train Loss: 0.5552, Train Steps/Sec: 1.14
|
| 820 |
+
[[34m2025-10-29 23:58:56[0m] (step=0074200) Train Loss: 0.5530, Train Steps/Sec: 1.14
|
| 821 |
+
[[34m2025-10-30 00:00:24[0m] (step=0074300) Train Loss: 0.5537, Train Steps/Sec: 1.13
|
| 822 |
+
[[34m2025-10-30 00:01:52[0m] (step=0074400) Train Loss: 0.5555, Train Steps/Sec: 1.13
|
| 823 |
+
[[34m2025-10-30 00:03:20[0m] (step=0074500) Train Loss: 0.5560, Train Steps/Sec: 1.14
|
| 824 |
+
[[34m2025-10-30 00:04:48[0m] (step=0074600) Train Loss: 0.5555, Train Steps/Sec: 1.13
|
| 825 |
+
[[34m2025-10-30 00:06:16[0m] (step=0074700) Train Loss: 0.5545, Train Steps/Sec: 1.14
|
| 826 |
+
[[34m2025-10-30 00:07:45[0m] (step=0074800) Train Loss: 0.5546, Train Steps/Sec: 1.14
|
| 827 |
+
[[34m2025-10-30 00:09:13[0m] (step=0074900) Train Loss: 0.5541, Train Steps/Sec: 1.14
|
| 828 |
+
[[34m2025-10-30 00:10:41[0m] (step=0075000) Train Loss: 0.5549, Train Steps/Sec: 1.14
|
| 829 |
+
[[34m2025-10-30 00:11:35[0m] Saved checkpoint to results/stage2/hfdata/lightningdit-xl-dinov2-vit-l-bf16/checkpoints/0075000.pt
|
| 830 |
+
[[34m2025-10-30 00:11:35[0m] Generating EMA samples...
|
| 831 |
+
[[34m2025-10-30 00:12:04[0m] Generating EMA samples done.
|
| 832 |
+
[[34m2025-10-30 00:12:56[0m] Beginning epoch 60...
|
| 833 |
+
[[34m2025-10-30 00:13:34[0m] (step=0075100) Train Loss: 0.5537, Train Steps/Sec: 0.58
|
| 834 |
+
[[34m2025-10-30 00:15:02[0m] (step=0075200) Train Loss: 0.5543, Train Steps/Sec: 1.13
|
| 835 |
+
[[34m2025-10-30 00:16:30[0m] (step=0075300) Train Loss: 0.5541, Train Steps/Sec: 1.14
|
| 836 |
+
[[34m2025-10-30 00:17:59[0m] (step=0075400) Train Loss: 0.5539, Train Steps/Sec: 1.13
|
| 837 |
+
[[34m2025-10-30 00:19:27[0m] (step=0075500) Train Loss: 0.5539, Train Steps/Sec: 1.14
|
| 838 |
+
[[34m2025-10-30 00:20:55[0m] (step=0075600) Train Loss: 0.5555, Train Steps/Sec: 1.13
|
| 839 |
+
[[34m2025-10-30 00:22:23[0m] (step=0075700) Train Loss: 0.5546, Train Steps/Sec: 1.14
|
| 840 |
+
[[34m2025-10-30 00:23:51[0m] (step=0075800) Train Loss: 0.5546, Train Steps/Sec: 1.14
|
| 841 |
+
[[34m2025-10-30 00:25:19[0m] (step=0075900) Train Loss: 0.5545, Train Steps/Sec: 1.14
|
| 842 |
+
[[34m2025-10-30 00:26:47[0m] (step=0076000) Train Loss: 0.5549, Train Steps/Sec: 1.13
|
| 843 |
+
[[34m2025-10-30 00:28:16[0m] (step=0076100) Train Loss: 0.5537, Train Steps/Sec: 1.13
|
| 844 |
+
[[34m2025-10-30 00:29:44[0m] (step=0076200) Train Loss: 0.5534, Train Steps/Sec: 1.14
|
| 845 |
+
[[34m2025-10-30 00:31:12[0m] (step=0076300) Train Loss: 0.5533, Train Steps/Sec: 1.14
|
| 846 |
+
[[34m2025-10-30 00:31:22[0m] Beginning epoch 61...
|
| 847 |
+
[[34m2025-10-30 00:32:42[0m] (step=0076400) Train Loss: 0.5523, Train Steps/Sec: 1.11
|
| 848 |
+
[[34m2025-10-30 00:34:11[0m] (step=0076500) Train Loss: 0.5531, Train Steps/Sec: 1.13
|
| 849 |
+
[[34m2025-10-30 00:35:39[0m] (step=0076600) Train Loss: 0.5533, Train Steps/Sec: 1.14
|
| 850 |
+
[[34m2025-10-30 00:37:07[0m] (step=0076700) Train Loss: 0.5547, Train Steps/Sec: 1.13
|
| 851 |
+
[[34m2025-10-30 00:38:35[0m] (step=0076800) Train Loss: 0.5535, Train Steps/Sec: 1.14
|
| 852 |
+
[[34m2025-10-30 00:40:03[0m] (step=0076900) Train Loss: 0.5534, Train Steps/Sec: 1.13
|
| 853 |
+
[[34m2025-10-30 00:41:32[0m] (step=0077000) Train Loss: 0.5530, Train Steps/Sec: 1.13
|
| 854 |
+
[[34m2025-10-30 00:43:00[0m] (step=0077100) Train Loss: 0.5531, Train Steps/Sec: 1.14
|
| 855 |
+
[[34m2025-10-30 00:44:28[0m] (step=0077200) Train Loss: 0.5529, Train Steps/Sec: 1.14
|
| 856 |
+
[[34m2025-10-30 00:45:56[0m] (step=0077300) Train Loss: 0.5549, Train Steps/Sec: 1.14
|
| 857 |
+
[[34m2025-10-30 00:47:24[0m] (step=0077400) Train Loss: 0.5531, Train Steps/Sec: 1.14
|
| 858 |
+
[[34m2025-10-30 00:48:52[0m] (step=0077500) Train Loss: 0.5526, Train Steps/Sec: 1.14
|
| 859 |
+
[[34m2025-10-30 00:49:47[0m] Beginning epoch 62...
|
| 860 |
+
[[34m2025-10-30 00:50:22[0m] (step=0077600) Train Loss: 0.5544, Train Steps/Sec: 1.11
|
| 861 |
+
[[34m2025-10-30 00:51:51[0m] (step=0077700) Train Loss: 0.5535, Train Steps/Sec: 1.13
|
| 862 |
+
[[34m2025-10-30 00:53:19[0m] (step=0077800) Train Loss: 0.5534, Train Steps/Sec: 1.13
|
| 863 |
+
[[34m2025-10-30 00:54:47[0m] (step=0077900) Train Loss: 0.5530, Train Steps/Sec: 1.14
|
| 864 |
+
[[34m2025-10-30 00:56:15[0m] (step=0078000) Train Loss: 0.5529, Train Steps/Sec: 1.14
|
| 865 |
+
[[34m2025-10-30 00:57:43[0m] (step=0078100) Train Loss: 0.5525, Train Steps/Sec: 1.14
|
| 866 |
+
[[34m2025-10-30 00:59:11[0m] (step=0078200) Train Loss: 0.5535, Train Steps/Sec: 1.13
|
| 867 |
+
[[34m2025-10-30 01:00:40[0m] (step=0078300) Train Loss: 0.5538, Train Steps/Sec: 1.14
|
| 868 |
+
[[34m2025-10-30 01:02:08[0m] (step=0078400) Train Loss: 0.5537, Train Steps/Sec: 1.14
|
| 869 |
+
[[34m2025-10-30 01:03:36[0m] (step=0078500) Train Loss: 0.5531, Train Steps/Sec: 1.14
|
| 870 |
+
[[34m2025-10-30 01:05:04[0m] (step=0078600) Train Loss: 0.5530, Train Steps/Sec: 1.13
|
| 871 |
+
[[34m2025-10-30 01:06:32[0m] (step=0078700) Train Loss: 0.5548, Train Steps/Sec: 1.14
|
| 872 |
+
[[34m2025-10-30 01:08:00[0m] (step=0078800) Train Loss: 0.5543, Train Steps/Sec: 1.14
|
| 873 |
+
[[34m2025-10-30 01:08:12[0m] Beginning epoch 63...
|
| 874 |
+
[[34m2025-10-30 01:09:31[0m] (step=0078900) Train Loss: 0.5521, Train Steps/Sec: 1.10
|
| 875 |
+
[[34m2025-10-30 01:10:59[0m] (step=0079000) Train Loss: 0.5527, Train Steps/Sec: 1.14
|
| 876 |
+
[[34m2025-10-30 01:12:27[0m] (step=0079100) Train Loss: 0.5518, Train Steps/Sec: 1.14
|
| 877 |
+
[[34m2025-10-30 01:13:55[0m] (step=0079200) Train Loss: 0.5538, Train Steps/Sec: 1.14
|
| 878 |
+
[[34m2025-10-30 01:15:23[0m] (step=0079300) Train Loss: 0.5534, Train Steps/Sec: 1.13
|
| 879 |
+
[[34m2025-10-30 01:16:51[0m] (step=0079400) Train Loss: 0.5525, Train Steps/Sec: 1.14
|
| 880 |
+
[[34m2025-10-30 01:18:20[0m] (step=0079500) Train Loss: 0.5521, Train Steps/Sec: 1.13
|
| 881 |
+
[[34m2025-10-30 01:19:48[0m] (step=0079600) Train Loss: 0.5539, Train Steps/Sec: 1.13
|
| 882 |
+
[[34m2025-10-30 01:21:16[0m] (step=0079700) Train Loss: 0.5511, Train Steps/Sec: 1.14
|
| 883 |
+
[[34m2025-10-30 01:22:44[0m] (step=0079800) Train Loss: 0.5526, Train Steps/Sec: 1.14
|
| 884 |
+
[[34m2025-10-30 01:24:12[0m] (step=0079900) Train Loss: 0.5527, Train Steps/Sec: 1.13
|
| 885 |
+
[[34m2025-10-30 01:25:40[0m] (step=0080000) Train Loss: 0.5529, Train Steps/Sec: 1.14
|
| 886 |
+
[[34m2025-10-30 01:26:37[0m] Beginning epoch 64...
|
| 887 |
+
[[34m2025-10-30 01:27:11[0m] (step=0080100) Train Loss: 0.5525, Train Steps/Sec: 1.10
|
| 888 |
+
[[34m2025-10-30 01:28:39[0m] (step=0080200) Train Loss: 0.5527, Train Steps/Sec: 1.14
|
| 889 |
+
[[34m2025-10-30 01:30:08[0m] (step=0080300) Train Loss: 0.5528, Train Steps/Sec: 1.13
|
| 890 |
+
[[34m2025-10-30 01:31:36[0m] (step=0080400) Train Loss: 0.5541, Train Steps/Sec: 1.13
|
| 891 |
+
[[34m2025-10-30 01:33:04[0m] (step=0080500) Train Loss: 0.5532, Train Steps/Sec: 1.14
|
| 892 |
+
[[34m2025-10-30 01:34:32[0m] (step=0080600) Train Loss: 0.5527, Train Steps/Sec: 1.14
|
| 893 |
+
[[34m2025-10-30 01:36:00[0m] (step=0080700) Train Loss: 0.5530, Train Steps/Sec: 1.14
|
| 894 |
+
[[34m2025-10-30 01:37:28[0m] (step=0080800) Train Loss: 0.5516, Train Steps/Sec: 1.13
|
| 895 |
+
[[34m2025-10-30 01:38:56[0m] (step=0080900) Train Loss: 0.5524, Train Steps/Sec: 1.13
|
| 896 |
+
[[34m2025-10-30 01:40:24[0m] (step=0081000) Train Loss: 0.5529, Train Steps/Sec: 1.14
|
| 897 |
+
[[34m2025-10-30 01:41:53[0m] (step=0081100) Train Loss: 0.5528, Train Steps/Sec: 1.14
|
| 898 |
+
[[34m2025-10-30 01:43:21[0m] (step=0081200) Train Loss: 0.5526, Train Steps/Sec: 1.13
|
| 899 |
+
[[34m2025-10-30 01:44:49[0m] (step=0081300) Train Loss: 0.5530, Train Steps/Sec: 1.13
|
| 900 |
+
[[34m2025-10-30 01:45:03[0m] Beginning epoch 65...
|
| 901 |
+
[[34m2025-10-30 01:46:19[0m] (step=0081400) Train Loss: 0.5526, Train Steps/Sec: 1.11
|
| 902 |
+
[[34m2025-10-30 01:47:47[0m] (step=0081500) Train Loss: 0.5526, Train Steps/Sec: 1.14
|
| 903 |
+
[[34m2025-10-30 01:49:16[0m] (step=0081600) Train Loss: 0.5526, Train Steps/Sec: 1.13
|
| 904 |
+
[[34m2025-10-30 01:50:44[0m] (step=0081700) Train Loss: 0.5525, Train Steps/Sec: 1.13
|
| 905 |
+
[[34m2025-10-30 01:52:12[0m] (step=0081800) Train Loss: 0.5528, Train Steps/Sec: 1.14
|
| 906 |
+
[[34m2025-10-30 01:53:40[0m] (step=0081900) Train Loss: 0.5515, Train Steps/Sec: 1.14
|
| 907 |
+
[[34m2025-10-30 01:55:08[0m] (step=0082000) Train Loss: 0.5521, Train Steps/Sec: 1.14
|
| 908 |
+
[[34m2025-10-30 01:56:37[0m] (step=0082100) Train Loss: 0.5520, Train Steps/Sec: 1.13
|
| 909 |
+
[[34m2025-10-30 01:58:05[0m] (step=0082200) Train Loss: 0.5512, Train Steps/Sec: 1.13
|
| 910 |
+
[[34m2025-10-30 01:59:33[0m] (step=0082300) Train Loss: 0.5535, Train Steps/Sec: 1.14
|
| 911 |
+
[[34m2025-10-30 02:01:01[0m] (step=0082400) Train Loss: 0.5512, Train Steps/Sec: 1.14
|
| 912 |
+
[[34m2025-10-30 02:02:29[0m] (step=0082500) Train Loss: 0.5512, Train Steps/Sec: 1.14
|
| 913 |
+
[[34m2025-10-30 02:03:28[0m] Beginning epoch 66...
|
| 914 |
+
[[34m2025-10-30 02:04:00[0m] (step=0082600) Train Loss: 0.5521, Train Steps/Sec: 1.11
|
| 915 |
+
[[34m2025-10-30 02:05:28[0m] (step=0082700) Train Loss: 0.5509, Train Steps/Sec: 1.14
|
| 916 |
+
[[34m2025-10-30 02:06:56[0m] (step=0082800) Train Loss: 0.5530, Train Steps/Sec: 1.14
|
| 917 |
+
[[34m2025-10-30 02:08:24[0m] (step=0082900) Train Loss: 0.5519, Train Steps/Sec: 1.13
|
| 918 |
+
[[34m2025-10-30 02:09:53[0m] (step=0083000) Train Loss: 0.5514, Train Steps/Sec: 1.13
|
| 919 |
+
[[34m2025-10-30 02:11:21[0m] (step=0083100) Train Loss: 0.5505, Train Steps/Sec: 1.14
|
| 920 |
+
[[34m2025-10-30 02:12:49[0m] (step=0083200) Train Loss: 0.5524, Train Steps/Sec: 1.13
|
| 921 |
+
[[34m2025-10-30 02:14:17[0m] (step=0083300) Train Loss: 0.5518, Train Steps/Sec: 1.13
|
| 922 |
+
[[34m2025-10-30 02:15:45[0m] (step=0083400) Train Loss: 0.5518, Train Steps/Sec: 1.14
|
| 923 |
+
[[34m2025-10-30 02:17:13[0m] (step=0083500) Train Loss: 0.5510, Train Steps/Sec: 1.14
|
| 924 |
+
[[34m2025-10-30 02:18:41[0m] (step=0083600) Train Loss: 0.5511, Train Steps/Sec: 1.14
|
| 925 |
+
[[34m2025-10-30 02:20:09[0m] (step=0083700) Train Loss: 0.5511, Train Steps/Sec: 1.14
|
| 926 |
+
[[34m2025-10-30 02:21:38[0m] (step=0083800) Train Loss: 0.5526, Train Steps/Sec: 1.13
|
| 927 |
+
[[34m2025-10-30 02:21:53[0m] Beginning epoch 67...
|
| 928 |
+
[[34m2025-10-30 02:23:08[0m] (step=0083900) Train Loss: 0.5525, Train Steps/Sec: 1.11
|
| 929 |
+
[[34m2025-10-30 02:24:36[0m] (step=0084000) Train Loss: 0.5523, Train Steps/Sec: 1.13
|
| 930 |
+
[[34m2025-10-30 02:26:04[0m] (step=0084100) Train Loss: 0.5517, Train Steps/Sec: 1.14
|
| 931 |
+
[[34m2025-10-30 02:27:33[0m] (step=0084200) Train Loss: 0.5513, Train Steps/Sec: 1.13
|
| 932 |
+
[[34m2025-10-30 02:29:01[0m] (step=0084300) Train Loss: 0.5523, Train Steps/Sec: 1.14
|
| 933 |
+
[[34m2025-10-30 02:30:29[0m] (step=0084400) Train Loss: 0.5515, Train Steps/Sec: 1.14
|
| 934 |
+
[[34m2025-10-30 02:31:57[0m] (step=0084500) Train Loss: 0.5519, Train Steps/Sec: 1.14
|
| 935 |
+
[[34m2025-10-30 02:33:25[0m] (step=0084600) Train Loss: 0.5512, Train Steps/Sec: 1.14
|
| 936 |
+
[[34m2025-10-30 02:34:53[0m] (step=0084700) Train Loss: 0.5506, Train Steps/Sec: 1.13
|
| 937 |
+
[[34m2025-10-30 02:36:21[0m] (step=0084800) Train Loss: 0.5513, Train Steps/Sec: 1.13
|
| 938 |
+
[[34m2025-10-30 02:37:50[0m] (step=0084900) Train Loss: 0.5519, Train Steps/Sec: 1.14
|
| 939 |
+
[[34m2025-10-30 02:39:18[0m] (step=0085000) Train Loss: 0.5516, Train Steps/Sec: 1.14
|
| 940 |
+
[[34m2025-10-30 02:40:18[0m] Beginning epoch 68...
|
| 941 |
+
[[34m2025-10-30 02:40:48[0m] (step=0085100) Train Loss: 0.5510, Train Steps/Sec: 1.10
|
| 942 |
+
[[34m2025-10-30 02:42:16[0m] (step=0085200) Train Loss: 0.5502, Train Steps/Sec: 1.14
|
| 943 |
+
[[34m2025-10-30 02:43:44[0m] (step=0085300) Train Loss: 0.5522, Train Steps/Sec: 1.14
|
| 944 |
+
[[34m2025-10-30 02:45:12[0m] (step=0085400) Train Loss: 0.5510, Train Steps/Sec: 1.14
|
| 945 |
+
[[34m2025-10-30 02:46:41[0m] (step=0085500) Train Loss: 0.5507, Train Steps/Sec: 1.13
|
| 946 |
+
[[34m2025-10-30 02:48:09[0m] (step=0085600) Train Loss: 0.5513, Train Steps/Sec: 1.13
|
| 947 |
+
[[34m2025-10-30 02:49:37[0m] (step=0085700) Train Loss: 0.5513, Train Steps/Sec: 1.14
|
| 948 |
+
[[34m2025-10-30 02:51:05[0m] (step=0085800) Train Loss: 0.5522, Train Steps/Sec: 1.14
|
| 949 |
+
[[34m2025-10-30 02:52:33[0m] (step=0085900) Train Loss: 0.5498, Train Steps/Sec: 1.14
|
| 950 |
+
[[34m2025-10-30 02:54:01[0m] (step=0086000) Train Loss: 0.5527, Train Steps/Sec: 1.14
|
| 951 |
+
[[34m2025-10-30 02:55:29[0m] (step=0086100) Train Loss: 0.5506, Train Steps/Sec: 1.14
|
| 952 |
+
[[34m2025-10-30 02:56:57[0m] (step=0086200) Train Loss: 0.5512, Train Steps/Sec: 1.14
|
| 953 |
+
[[34m2025-10-30 02:58:25[0m] (step=0086300) Train Loss: 0.5503, Train Steps/Sec: 1.14
|
| 954 |
+
[[34m2025-10-30 02:58:43[0m] Beginning epoch 69...
|
| 955 |
+
[[34m2025-10-30 02:59:56[0m] (step=0086400) Train Loss: 0.5494, Train Steps/Sec: 1.10
|
| 956 |
+
[[34m2025-10-30 03:01:25[0m] (step=0086500) Train Loss: 0.5504, Train Steps/Sec: 1.13
|
| 957 |
+
[[34m2025-10-30 03:02:53[0m] (step=0086600) Train Loss: 0.5513, Train Steps/Sec: 1.14
|
| 958 |
+
[[34m2025-10-30 03:04:21[0m] (step=0086700) Train Loss: 0.5501, Train Steps/Sec: 1.14
|
| 959 |
+
[[34m2025-10-30 03:05:49[0m] (step=0086800) Train Loss: 0.5505, Train Steps/Sec: 1.14
|
| 960 |
+
[[34m2025-10-30 03:07:17[0m] (step=0086900) Train Loss: 0.5511, Train Steps/Sec: 1.14
|
| 961 |
+
[[34m2025-10-30 03:08:45[0m] (step=0087000) Train Loss: 0.5500, Train Steps/Sec: 1.14
|
| 962 |
+
[[34m2025-10-30 03:10:13[0m] (step=0087100) Train Loss: 0.5514, Train Steps/Sec: 1.14
|
| 963 |
+
[[34m2025-10-30 03:11:41[0m] (step=0087200) Train Loss: 0.5508, Train Steps/Sec: 1.13
|
| 964 |
+
[[34m2025-10-30 03:13:09[0m] (step=0087300) Train Loss: 0.5512, Train Steps/Sec: 1.13
|
| 965 |
+
[[34m2025-10-30 03:14:37[0m] (step=0087400) Train Loss: 0.5506, Train Steps/Sec: 1.14
|
| 966 |
+
[[34m2025-10-30 03:16:06[0m] (step=0087500) Train Loss: 0.5504, Train Steps/Sec: 1.14
|
| 967 |
+
[[34m2025-10-30 03:17:08[0m] Beginning epoch 70...
|
| 968 |
+
[[34m2025-10-30 03:17:36[0m] (step=0087600) Train Loss: 0.5513, Train Steps/Sec: 1.11
|
| 969 |
+
[[34m2025-10-30 03:19:04[0m] (step=0087700) Train Loss: 0.5504, Train Steps/Sec: 1.14
|
| 970 |
+
[[34m2025-10-30 03:20:32[0m] (step=0087800) Train Loss: 0.5506, Train Steps/Sec: 1.14
|
| 971 |
+
[[34m2025-10-30 03:22:00[0m] (step=0087900) Train Loss: 0.5501, Train Steps/Sec: 1.14
|
| 972 |
+
[[34m2025-10-30 03:23:28[0m] (step=0088000) Train Loss: 0.5508, Train Steps/Sec: 1.13
|
| 973 |
+
[[34m2025-10-30 03:24:57[0m] (step=0088100) Train Loss: 0.5516, Train Steps/Sec: 1.13
|
| 974 |
+
[[34m2025-10-30 03:26:25[0m] (step=0088200) Train Loss: 0.5512, Train Steps/Sec: 1.13
|
| 975 |
+
[[34m2025-10-30 03:27:53[0m] (step=0088300) Train Loss: 0.5495, Train Steps/Sec: 1.14
|
| 976 |
+
[[34m2025-10-30 03:29:21[0m] (step=0088400) Train Loss: 0.5508, Train Steps/Sec: 1.14
|
| 977 |
+
[[34m2025-10-30 03:30:49[0m] (step=0088500) Train Loss: 0.5502, Train Steps/Sec: 1.14
|
| 978 |
+
[[34m2025-10-30 03:32:17[0m] (step=0088600) Train Loss: 0.5491, Train Steps/Sec: 1.14
|
| 979 |
+
[[34m2025-10-30 03:33:45[0m] (step=0088700) Train Loss: 0.5503, Train Steps/Sec: 1.14
|
| 980 |
+
[[34m2025-10-30 03:35:13[0m] (step=0088800) Train Loss: 0.5508, Train Steps/Sec: 1.14
|
| 981 |
+
[[34m2025-10-30 03:35:32[0m] Beginning epoch 71...
|
| 982 |
+
[[34m2025-10-30 03:36:44[0m] (step=0088900) Train Loss: 0.5505, Train Steps/Sec: 1.10
|
| 983 |
+
[[34m2025-10-30 03:38:12[0m] (step=0089000) Train Loss: 0.5501, Train Steps/Sec: 1.13
|
| 984 |
+
[[34m2025-10-30 03:39:41[0m] (step=0089100) Train Loss: 0.5512, Train Steps/Sec: 1.13
|
| 985 |
+
[[34m2025-10-30 03:41:09[0m] (step=0089200) Train Loss: 0.5505, Train Steps/Sec: 1.14
|
| 986 |
+
[[34m2025-10-30 03:42:37[0m] (step=0089300) Train Loss: 0.5501, Train Steps/Sec: 1.14
|
| 987 |
+
[[34m2025-10-30 03:44:05[0m] (step=0089400) Train Loss: 0.5498, Train Steps/Sec: 1.14
|
| 988 |
+
[[34m2025-10-30 03:45:33[0m] (step=0089500) Train Loss: 0.5499, Train Steps/Sec: 1.13
|
| 989 |
+
[[34m2025-10-30 03:47:01[0m] (step=0089600) Train Loss: 0.5504, Train Steps/Sec: 1.14
|
| 990 |
+
[[34m2025-10-30 03:48:29[0m] (step=0089700) Train Loss: 0.5516, Train Steps/Sec: 1.14
|
| 991 |
+
[[34m2025-10-30 03:49:57[0m] (step=0089800) Train Loss: 0.5508, Train Steps/Sec: 1.13
|
| 992 |
+
[[34m2025-10-30 03:51:25[0m] (step=0089900) Train Loss: 0.5500, Train Steps/Sec: 1.13
|
| 993 |
+
[[34m2025-10-30 03:52:53[0m] (step=0090000) Train Loss: 0.5499, Train Steps/Sec: 1.14
|
| 994 |
+
[[34m2025-10-30 03:53:57[0m] Beginning epoch 72...
|
| 995 |
+
[[34m2025-10-30 03:54:24[0m] (step=0090100) Train Loss: 0.5511, Train Steps/Sec: 1.10
|
| 996 |
+
[[34m2025-10-30 03:55:52[0m] (step=0090200) Train Loss: 0.5507, Train Steps/Sec: 1.14
|
| 997 |
+
[[34m2025-10-30 03:57:20[0m] (step=0090300) Train Loss: 0.5502, Train Steps/Sec: 1.13
|
| 998 |
+
[[34m2025-10-30 03:58:48[0m] (step=0090400) Train Loss: 0.5496, Train Steps/Sec: 1.14
|
| 999 |
+
[[34m2025-10-30 04:00:16[0m] (step=0090500) Train Loss: 0.5495, Train Steps/Sec: 1.14
|
| 1000 |
+
[[34m2025-10-30 04:01:44[0m] (step=0090600) Train Loss: 0.5510, Train Steps/Sec: 1.14
|
| 1001 |
+
[[34m2025-10-30 04:03:13[0m] (step=0090700) Train Loss: 0.5502, Train Steps/Sec: 1.13
|
| 1002 |
+
[[34m2025-10-30 04:04:41[0m] (step=0090800) Train Loss: 0.5486, Train Steps/Sec: 1.13
|
| 1003 |
+
[[34m2025-10-30 04:06:09[0m] (step=0090900) Train Loss: 0.5508, Train Steps/Sec: 1.14
|
| 1004 |
+
[[34m2025-10-30 04:07:37[0m] (step=0091000) Train Loss: 0.5493, Train Steps/Sec: 1.14
|
| 1005 |
+
[[34m2025-10-30 04:09:05[0m] (step=0091100) Train Loss: 0.5493, Train Steps/Sec: 1.14
|
| 1006 |
+
[[34m2025-10-30 04:10:33[0m] (step=0091200) Train Loss: 0.5500, Train Steps/Sec: 1.14
|
| 1007 |
+
[[34m2025-10-30 04:12:01[0m] (step=0091300) Train Loss: 0.5513, Train Steps/Sec: 1.14
|
| 1008 |
+
[[34m2025-10-30 04:12:22[0m] Beginning epoch 73...
|
| 1009 |
+
[[34m2025-10-30 04:13:32[0m] (step=0091400) Train Loss: 0.5491, Train Steps/Sec: 1.11
|
| 1010 |
+
[[34m2025-10-30 04:15:00[0m] (step=0091500) Train Loss: 0.5496, Train Steps/Sec: 1.13
|
| 1011 |
+
[[34m2025-10-30 04:16:28[0m] (step=0091600) Train Loss: 0.5495, Train Steps/Sec: 1.13
|
| 1012 |
+
[[34m2025-10-30 04:17:57[0m] (step=0091700) Train Loss: 0.5484, Train Steps/Sec: 1.13
|
| 1013 |
+
[[34m2025-10-30 04:19:25[0m] (step=0091800) Train Loss: 0.5490, Train Steps/Sec: 1.14
|
| 1014 |
+
[[34m2025-10-30 04:20:53[0m] (step=0091900) Train Loss: 0.5508, Train Steps/Sec: 1.13
|
| 1015 |
+
[[34m2025-10-30 04:22:21[0m] (step=0092000) Train Loss: 0.5497, Train Steps/Sec: 1.14
|
| 1016 |
+
[[34m2025-10-30 04:23:49[0m] (step=0092100) Train Loss: 0.5506, Train Steps/Sec: 1.14
|
| 1017 |
+
[[34m2025-10-30 04:25:17[0m] (step=0092200) Train Loss: 0.5487, Train Steps/Sec: 1.14
|
| 1018 |
+
[[34m2025-10-30 04:26:45[0m] (step=0092300) Train Loss: 0.5503, Train Steps/Sec: 1.14
|
| 1019 |
+
[[34m2025-10-30 04:28:13[0m] (step=0092400) Train Loss: 0.5504, Train Steps/Sec: 1.13
|
| 1020 |
+
[[34m2025-10-30 04:29:41[0m] (step=0092500) Train Loss: 0.5494, Train Steps/Sec: 1.13
|
| 1021 |
+
[[34m2025-10-30 04:30:47[0m] Beginning epoch 74...
|
| 1022 |
+
[[34m2025-10-30 04:31:12[0m] (step=0092600) Train Loss: 0.5489, Train Steps/Sec: 1.10
|
| 1023 |
+
[[34m2025-10-30 04:32:40[0m] (step=0092700) Train Loss: 0.5508, Train Steps/Sec: 1.13
|
| 1024 |
+
[[34m2025-10-30 04:34:08[0m] (step=0092800) Train Loss: 0.5500, Train Steps/Sec: 1.13
|
| 1025 |
+
[[34m2025-10-30 04:35:36[0m] (step=0092900) Train Loss: 0.5501, Train Steps/Sec: 1.14
|
| 1026 |
+
[[34m2025-10-30 04:37:04[0m] (step=0093000) Train Loss: 0.5481, Train Steps/Sec: 1.14
|
| 1027 |
+
[[34m2025-10-30 04:38:32[0m] (step=0093100) Train Loss: 0.5503, Train Steps/Sec: 1.14
|
| 1028 |
+
[[34m2025-10-30 04:40:00[0m] (step=0093200) Train Loss: 0.5498, Train Steps/Sec: 1.14
|
| 1029 |
+
[[34m2025-10-30 04:41:29[0m] (step=0093300) Train Loss: 0.5481, Train Steps/Sec: 1.13
|
| 1030 |
+
[[34m2025-10-30 04:42:57[0m] (step=0093400) Train Loss: 0.5485, Train Steps/Sec: 1.13
|
| 1031 |
+
[[34m2025-10-30 04:44:25[0m] (step=0093500) Train Loss: 0.5494, Train Steps/Sec: 1.13
|
| 1032 |
+
[[34m2025-10-30 04:45:53[0m] (step=0093600) Train Loss: 0.5506, Train Steps/Sec: 1.14
|
| 1033 |
+
[[34m2025-10-30 04:47:21[0m] (step=0093700) Train Loss: 0.5487, Train Steps/Sec: 1.13
|
| 1034 |
+
[[34m2025-10-30 04:48:49[0m] (step=0093800) Train Loss: 0.5491, Train Steps/Sec: 1.14
|
| 1035 |
+
[[34m2025-10-30 04:49:12[0m] Beginning epoch 75...
|
| 1036 |
+
[[34m2025-10-30 04:50:20[0m] (step=0093900) Train Loss: 0.5503, Train Steps/Sec: 1.10
|
| 1037 |
+
[[34m2025-10-30 04:51:48[0m] (step=0094000) Train Loss: 0.5493, Train Steps/Sec: 1.14
|
| 1038 |
+
[[34m2025-10-30 04:53:16[0m] (step=0094100) Train Loss: 0.5483, Train Steps/Sec: 1.14
|
| 1039 |
+
[[34m2025-10-30 04:54:44[0m] (step=0094200) Train Loss: 0.5485, Train Steps/Sec: 1.13
|
| 1040 |
+
[[34m2025-10-30 04:56:13[0m] (step=0094300) Train Loss: 0.5489, Train Steps/Sec: 1.14
|
| 1041 |
+
[[34m2025-10-30 04:57:41[0m] (step=0094400) Train Loss: 0.5482, Train Steps/Sec: 1.14
|
| 1042 |
+
[[34m2025-10-30 04:59:09[0m] (step=0094500) Train Loss: 0.5486, Train Steps/Sec: 1.14
|