Modular Diffusers is currently an experimental feature under active development. The API is subject to breaking changes in future releases.
/home/hans/ai/onetrainer/venv/lib/python3.13/site-packages/tensorboard/default.py:30: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
  import pkg_resources
TensorFlow installation not found - running with reduced feature set.

NOTE: Using experimental fast data loading logic. To disable, pass
    "--load_fast=false" and report issues on GitHub. More details:
    https://github.com/tensorflow/tensorboard/issues/4784

Serving TensorBoard on localhost; to expose to the network, use a proxy or pass --bind_all
TensorBoard 2.20.0 at http://localhost:6006/ (Press CTRL+C to quit)
CUDA -> XPU hijacking active
nvCOMP: no backend available (low-level: ModuleNotFoundError: No module named 'nvidia'; high-level: ModuleNotFoundError: No module named 'nvidia')
Clearing cache directory /home/hans/ai/training/workspace-cache/amyadams-axad! You can disable this if you want to continue using the same cache.
Warning: Mixed precision training is untested on device type 'xpu'.
Attention backends are an experimental feature and the API may be subject to change.
Selected layers: 210
Deselected layers: 66
Note: Enable Debug mode to see the full list of layer names
enumerating sample paths: 100%|██████████| 1/1 [00:00<00:00, 1951.75it/s]
caching: 100%|██████████| 56/56 [00:11<00:00,  5.05it/s] ?it/s]
caching: 100%|██████████| 56/56 [00:04<00:00, 12.11it/s]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.05it/s]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.14it/s]
step: 100%|██████████| 112/112 [08:27<00:00,  4.53s/it, loss=0.424, smooth loss=0.261]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.311, smooth loss=0.257] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.11it/s]oss=0.311, smooth loss=0.257]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.16it/s]ss=0.282, smooth loss=0.257]
step: 100%|██████████| 112/112 [08:33<00:00,  4.58s/it, loss=0.332, smooth loss=0.262]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.415, smooth loss=0.267]
epoch:   8%|▊         | 4/50 [33:25<5:38:43, 441.82s/it]loss=0.415, smooth loss=0.267
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_17-45-57-save-499-4-51.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.13it/s]ss=0.186, smooth loss=0.268]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.19it/s]
step: 100%|██████████| 112/112 [08:36<00:00,  4.61s/it, loss=0.231, smooth loss=0.259]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.184, smooth loss=0.261]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.14it/s]oss=0.184, smooth loss=0.261]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.22it/s]ss=0.44, smooth loss=0.26]  
step: 100%|██████████| 112/112 [08:31<00:00,  4.57s/it, loss=0.239, smooth loss=0.25]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.201, smooth loss=0.253]
epoch:  16%|█▌        | 8/50 [1:06:19<5:06:32, 437.93s/it]ss=0.201, smooth loss=0.253]
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_18-18-51-save-999-8-103.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.16it/s]oss=0.265, smooth loss=0.247]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.07it/s]
step: 100%|██████████| 112/112 [08:37<00:00,  4.62s/it, loss=0.227, smooth loss=0.245]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.299, smooth loss=0.252]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.381, smooth loss=0.263]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.03it/s]t]s=0.381, smooth loss=0.263]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.05it/s]ss=0.282, smooth loss=0.265]
step: 100%|██████████| 112/112 [08:31<00:00,  4.56s/it, loss=0.175, smooth loss=0.253]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.372, smooth loss=0.25]] 
epoch:  26%|██▌       | 13/50 [1:39:14<4:24:36, 429.09s/it]s=0.372, smooth loss=0.25
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_18-51-46-save-1499-13-43.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.16it/s]ss=0.167, smooth loss=0.25]  
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.01it/s]
step: 100%|██████████| 112/112 [08:36<00:00,  4.61s/it, loss=0.124, smooth loss=0.254]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.173, smooth loss=0.253]
sampling: 100%|██████████| 28/28 [00:04<00:00,  5.99it/s]t]s=0.173, smooth loss=0.253]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.34it/s]ss=0.351, smooth loss=0.255]
step: 100%|██████████| 112/112 [08:30<00:00,  4.56s/it, loss=0.448, smooth loss=0.255]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.132, smooth loss=0.254]
epoch:  34%|███▍      | 17/50 [2:12:07<3:59:14, 435.00s/it]s=0.132, smooth loss=0.25
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_19-24-39-save-1999-17-95.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.12it/s]ss=0.22, smooth loss=0.246]  
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.19it/s]
step: 100%|██████████| 112/112 [08:37<00:00,  4.62s/it, loss=0.354, smooth loss=0.246]
step: 100%|██████████| 112/112 [06:22<00:00,  3.42s/it, loss=0.265, smooth loss=0.242]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.285, smooth loss=0.244]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.17it/s]t]s=0.285, smooth loss=0.244]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.27it/s]ss=0.223, smooth loss=0.242]
step: 100%|██████████| 112/112 [08:29<00:00,  4.55s/it, loss=0.175, smooth loss=0.244]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.237, smooth loss=0.245]
epoch:  44%|████▍     | 22/50 [2:44:58<3:19:51, 428.28s/it]s=0.237, smooth loss=0.245
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_19-57-30-save-2499-22-35.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.19it/s]ss=0.368, smooth loss=0.244]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.21it/s]
step: 100%|██████████| 112/112 [08:34<00:00,  4.59s/it, loss=0.166, smooth loss=0.245]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.132, smooth loss=0.24]]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.22it/s]t]s=0.132, smooth loss=0.24] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.32it/s]ss=0.143, smooth loss=0.245]
step: 100%|██████████| 112/112 [08:29<00:00,  4.55s/it, loss=0.4, smooth loss=0.239]
step: 100%|██████████| 112/112 [06:22<00:00,  3.42s/it, loss=0.304, smooth loss=0.246]
epoch:  52%|█████▏    | 26/50 [3:17:48<2:53:42, 434.28s/it]s=0.304, smooth loss=0.246
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_20-30-20-save-2999-26-87.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.13it/s]ss=0.297, smooth loss=0.236] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.28it/s]
step: 100%|██████████| 112/112 [08:35<00:00,  4.60s/it, loss=0.16, smooth loss=0.242]
step: 100%|██████████| 112/112 [06:22<00:00,  3.42s/it, loss=0.181, smooth loss=0.236]
step: 100%|██████████| 112/112 [06:22<00:00,  3.42s/it, loss=0.186, smooth loss=0.244]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.28it/s]t]s=0.186, smooth loss=0.244]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.33it/s]s=0.195, smooth loss=0.243]
step: 100%|██████████| 112/112 [08:29<00:00,  4.55s/it, loss=0.381, smooth loss=0.249]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.23, smooth loss=0.23]9]
epoch:  62%|██████▏   | 31/50 [3:50:38<2:15:30, 427.95s/it]s=0.23, smooth loss=0.23]
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_21-03-10-save-3499-31-27.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.20it/s]ss=0.319, smooth loss=0.234]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.28it/s]
step: 100%|██████████| 112/112 [08:34<00:00,  4.60s/it, loss=0.163, smooth loss=0.236]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.194, smooth loss=0.241] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.18it/s]t]s=0.194, smooth loss=0.241]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.25it/s]ss=0.245, smooth loss=0.248] 
step: 100%|██████████| 112/112 [08:29<00:00,  4.55s/it, loss=0.239, smooth loss=0.241]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.16, smooth loss=0.234]]
epoch:  70%|███████   | 35/50 [4:23:28<1:48:33, 434.25s/it]s=0.16, smooth loss=0.234]
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_21-36-00-save-3999-35-79.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.17it/s]ss=0.386, smooth loss=0.235]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.25it/s]
step: 100%|██████████| 112/112 [08:34<00:00,  4.59s/it, loss=0.338, smooth loss=0.242]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.131, smooth loss=0.24]]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.16it/s]t]s=0.131, smooth loss=0.24] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.22it/s]oss=0.308, smooth loss=0.24] 
step: 100%|██████████| 112/112 [08:29<00:00,  4.55s/it, loss=0.423, smooth loss=0.239]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.262, smooth loss=0.234] 
step: 100%|██████████| 112/112 [06:22<00:00,  3.42s/it, loss=0.196, smooth loss=0.24]] 
epoch:  80%|████████  | 40/50 [4:56:17<1:09:58, 419.88s/it]s=0.196, smooth loss=0.24]
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_22-08-49-save-4499-40-19.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.15it/s]ss=0.178, smooth loss=0.237]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.27it/s]
step: 100%|██████████| 112/112 [08:34<00:00,  4.59s/it, loss=0.291, smooth loss=0.242]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.274, smooth loss=0.236] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.12it/s]  s=0.274, smooth loss=0.236] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.25it/s]ss=0.227, smooth loss=0.239]
step: 100%|██████████| 112/112 [08:30<00:00,  4.56s/it, loss=0.267, smooth loss=0.231]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.238, smooth loss=0.227]
epoch:  88%|████████▊ | 44/50 [5:29:07<43:14, 432.44s/it]oss=0.238, smooth loss=0.227
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_22-41-39-save-4999-44-71.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.18it/s]ss=0.129, smooth loss=0.228]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.18it/s]
step: 100%|██████████| 112/112 [08:34<00:00,  4.59s/it, loss=0.162, smooth loss=0.217]
step: 100%|██████████| 112/112 [06:23<00:00,  3.42s/it, loss=0.203, smooth loss=0.224] 
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.19it/s]oss=0.203, smooth loss=0.224]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.26it/s]ss=0.0976, smooth loss=0.23] 
step: 100%|██████████| 112/112 [08:30<00:00,  4.55s/it, loss=0.45, smooth loss=0.231]
step: 100%|██████████| 112/112 [06:22<00:00,  3.42s/it, loss=0.151, smooth loss=0.224]
step: 100%|██████████| 112/112 [06:22<00:00,  3.42s/it, loss=0.102, smooth loss=0.232]
epoch:  98%|█████████▊| 49/50 [6:01:57<06:59, 419.59s/it]oss=0.102, smooth loss=0.232
Saving /home/hans/ai/training/workspace/amyadams-axad/save/2026-08-24_23-14-28-save-5499-49-11.safetensors
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.14it/s]ss=0.163, smooth loss=0.233]
sampling: 100%|██████████| 28/28 [00:04<00:00,  6.20it/s]
step: 100%|██████████| 112/112 [08:34<00:00,  4.59s/it, loss=0.245, smooth loss=0.223]
epoch: 100%|██████████| 50/50 [6:09:51<00:00, 443.83s/it]oss=0.245, smooth loss=0.223]