The above reply took more than a few days to be reflected, so it’s become a bit of a mystery to everyone…
opened 09:54AM - 01 May 24 UTC
17:45:46-693860 INFO Training has ended.
17:52:57-749330 INFO Start tra… ining LoRA Standard ...
17:52:57-751289 INFO Validating lr scheduler arguments...
17:52:57-751289 INFO Validating optimizer arguments...
17:52:57-752288 INFO Validating model file or folder path
G:/Comfyui/ComfyUI-aki-v1.3/models/checkpoints/sdXL_v10.safetensors existence...
17:52:57-754288 INFO ...valid
17:52:57-754288 INFO Validating output_dir path G:/Comfyui/kohyass/output existence...
17:52:57-755710 INFO ...valid
17:52:57-756715 INFO Validating train_data_dir path G:/Comfyui/kohyass/train data/30_2D existence...
17:52:57-757716 INFO ...valid
17:52:57-757716 INFO reg_data_dir not specified, skipping validation
17:52:57-759719 INFO logging_dir not specified, skipping validation
17:52:57-762722 INFO log_tracker_config not specified, skipping validation
17:52:57-763719 INFO resume not specified, skipping validation
17:52:57-764718 INFO vae not specified, skipping validation
17:52:57-765720 INFO network_weights not specified, skipping validation
17:52:57-766717 INFO dataset_config not specified, skipping validation
17:52:57-769718 INFO Regulatization factor: 1
17:52:57-771717 INFO Total steps: 0
17:52:57-772717 INFO Train batch size: 2
17:52:57-773738 INFO Gradient accumulation steps: 1
17:52:57-774817 INFO Epoch: 30
17:52:57-775824 INFO Max train steps: 1600
17:52:57-777824 INFO stop_text_encoder_training = 0
17:52:57-777824 INFO lr_warmup_steps = 0
17:52:57-780823 INFO Saving training config to G:/Comfyui/kohyass/output\glass_20240501-175257.json...
17:52:57-782823 INFO Executing command: "G:\Comfyui\kohyass\kohya_ss\venv\Scripts\accelerate.EXE" launch
--dynamo_backend no --dynamo_mode default --mixed_precision bf16 --num_processes 1
--num_machines 1 --num_cpu_threads_per_process 2
"G:/Comfyui/kohyass/kohya_ss/sd-scripts/sdxl_train_network.py" --config_file
"./outputs/config_lora-20240501-175257.toml" with shell=True
17:52:57-788823 INFO Command executed.
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
2024-05-01 17:53:04 INFO Loading settings from ./outputs/config_lora-20240501-175257.toml... train_util.py:3744
INFO ./outputs/config_lora-20240501-175257 train_util.py:3763
2024-05-01 17:53:04 INFO prepare tokenizers sdxl_train_util.py:134
2024-05-01 17:53:06 INFO update token length: 75 sdxl_train_util.py:159
INFO Using DreamBooth method. train_network.py:172
INFO prepare images. train_util.py:1572
INFO 0 train images with repeating. train_util.py:1613
INFO 0 reg images. train_util.py:1616
WARNING no regularization images / 正則化画像が見つかりませんでした train_util.py:1621
INFO [Dataset 0] config_util.py:565
batch_size: 2
resolution: (1024, 1024)
enable_bucket: False
network_multiplier: 1.0
INFO [Dataset 0] config_util.py:571
INFO loading image sizes. train_util.py:853
0it [00:00, ?it/s]
INFO make buckets train_util.py:859
WARNING min_bucket_reso and max_bucket_reso are ignored if bucket_no_upscale is train_util.py:876
set, because bucket reso is defined by image size automatically /
bucket_no_upscaleが指定された場合は、bucketの解像度は画像サイズから自動計
算されるため、min_bucket_resoとmax_bucket_resoは無視されます
INFO number of images (including repeats) / train_util.py:905
各bucketの画像枚数（繰り返し回数を含む）
G:\Comfyui\kohyass\kohya_ss\venv\lib\site-packages\numpy\core\fromnumeric.py:3504: RuntimeWarning: Mean of empty slice.
return _methods._mean(a, axis=axis, dtype=dtype,
G:\Comfyui\kohyass\kohya_ss\venv\lib\site-packages\numpy\core\_methods.py:129: RuntimeWarning: invalid value encountered in scalar divide
ret = ret.dtype.type(ret / rcount)
INFO mean ar error (without repeats): nan train_util.py:915
ERROR No data found. Please verify arguments (train_data_dir must be the train_network.py:212
parent of folders with images) /
画像がありません。引数指定を確認してください（train_data_dirには画像が
あるフォルダではなく、画像があるフォルダの親フォルダを指定する必要があ
ります）
17:53:08-090420 INFO Training has ended.
1 Like
