ValueError: no metadata / メタデータファイルがありません: /content/LoRA/meta_lat.json

[AbbyaaS]

When using kohya-LoRA-trainer-XL.ipynb(https://colab.research.google.com/github/panguin6010/kohya_ss_google_colab/blob/master/kohya_ss_colab.ipynb),
the following error occurred:
If anyone knows the solution to this, please let me know.
what is "metadata"?
both the training images and their caption text files are directly uploaded to train_data_dir.

╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /content/kohya-trainer/sdxl_train_network.py:174 in │
│ │
│ 171 │ args = train_util.read_config_from_file(args, parser) │
│ 172 │ │
│ 173 │ trainer = SdxlNetworkTrainer() │
│ ❱ 174 │ trainer.train(args) │
│ 175 │
│ │
│ /content/kohya-trainer/train_network.py:177 in train │
│ │
│ 174 │ │ │ │ │ } │
│ 175 │ │ │ │
│ 176 │ │ │ blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokeni │
│ ❱ 177 │ │ │ train_dataset_group = config_util.generate_dataset_group_by_blueprint(bluepr │
│ 178 │ │ else: │
│ 179 │ │ │ # use arbitrary dataset class │
│ 180 │ │ │ train_dataset_group = train_util.load_arbitrary_dataset(args, tokenizer) │
│ │
│ /content/kohya-trainer/library/config_util.py:426 in generate_dataset_group_by_blueprint │
│ │
│ 423 │ dataset_klass = FineTuningDataset │
│ 424 │ │
│ 425 │ subsets = [subset_klass(**asdict(subset_blueprint.params)) for subset_blueprint in d │
│ ❱ 426 │ dataset = dataset_klass(subsets=subsets, **asdict(dataset_blueprint.params)) │
│ 427 │ datasets.append(dataset) │
│ 428 │
│ 429 # print info │
│ │
│ /content/kohya-trainer/library/train_util.py:1477 in init │
│ │
│ 1474 │ │ │ │ with open(subset.metadata_file, "rt", encoding="utf-8") as f: │
│ 1475 │ │ │ │ │ metadata = json.load(f) │
│ 1476 │ │ │ else: │
│ ❱ 1477 │ │ │ │ raise ValueError(f"no metadata / メタデータファイルがありません: {subset │
│ 1478 │ │ │ │
│ 1479 │ │ │ if len(metadata) < 1: │
│ 1480 │ │ │ │ print(f"ignore subset with '{subset.metadata_file}': no image entries fo │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ValueError: no metadata / メタデータファイルがありません: /content/LoRA/meta_lat.json
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /usr/local/bin/accelerate:8 in │
│ │
│ 5 from accelerate.commands.accelerate_cli import main │
│ 6 if name == 'main': │
│ 7 │ sys.argv[0] = re.sub(r'(-script.pyw|.exe)?$', '', sys.argv[0]) │
│ ❱ 8 │ sys.exit(main()) │
│ 9 │
│ │
│ /usr/local/lib/python3.10/dist-packages/accelerate/commands/accelerate_cli.py:45 in main │
│ │
│ 42 │ │ exit(1) │
│ 43 │ │
│ 44 │ # Run │
│ ❱ 45 │ args.func(args) │
│ 46 │
│ 47 │
│ 48 if name == "main": │
│ │
│ /usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py:918 in launch_command │
│ │
│ 915 │ elif defaults is not None and defaults.compute_environment == ComputeEnvironment.AMA │
│ 916 │ │ sagemaker_launcher(defaults, args) │
│ 917 │ else: │
│ ❱ 918 │ │ simple_launcher(args) │
│ 919 │
│ 920 │
│ 921 def main(): │
│ │
│ /usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py:580 in simple_launcher │
│ │
│ 577 │ process.wait() │
│ 578 │ if process.returncode != 0: │
│ 579 │ │ if not args.quiet: │
│ ❱ 580 │ │ │ raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) │
│ 581 │ │ else: │
│ 582 │ │ │ sys.exit(1) │
│ 583 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
CalledProcessError: Command '['/usr/bin/python3', 'sdxl_train_network.py',
'--sample_prompts=/content/LoRA/config/sample_prompt.toml',
'--config_file=/content/LoRA/config/config_file.toml',
'--wandb_api_key=???????????']' returned non-zero exit status 1.

and following is training-config
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[sdxl_arguments]
cache_text_encoder_outputs = true
no_half_vae = true
min_timestep = 0
max_timestep = 1000
shuffle_caption = false
lowram = true

[model_arguments]
pretrained_model_name_or_path = "Linaqruf/animagine-xl"
vae = "/content/vae/sdxl_vae.safetensors"

[dataset_arguments]
debug_dataset = false
in_json = "/content/LoRA/meta_lat.json"
train_data_dir = "/content/drive/MyDrive/kohya_ss/train_images/scheiren/10_scheiren"
dataset_repeats = 10
keep_tokens = 1
resolution = "1024,1024"
color_aug = false
token_warmup_min = 1
token_warmup_step = 0

[training_arguments]
output_dir = "/content/drive/MyDrive/kohya-trainer/output/sdxl_lora_scheiren1"
output_name = "sdxl_lora_scheiren1"
save_precision = "fp16"
save_every_n_epochs = 2
train_batch_size = 4
max_token_length = 225
mem_eff_attn = false
sdpa = false
xformers = true
max_train_epochs = 10
max_data_loader_n_workers = 8
persistent_data_loader_workers = true
gradient_checkpointing = true
gradient_accumulation_steps = 1
mixed_precision = "fp16"

[logging_arguments]
log_with = "wandb"
log_tracker_name = "sdxl_lora1"
logging_dir = "/content/LoRA/logs"

[sample_prompt_arguments]
sample_every_n_epochs = 2
sample_sampler = "euler_a"

[saving_arguments]
save_model_as = "safetensors"

[optimizer_arguments]
optimizer_type = "AdamW"
learning_rate = 0.0001
max_grad_norm = 0
optimizer_args = [ "scale_parameter=False", "relative_step=False", "warmup_init=False",]
lr_scheduler = "constant_with_warmup"
lr_warmup_steps = 100

[additional_network_arguments]
no_metadata = false
network_module = "lycoris.kohya"
network_dim = 8
network_alpha = 4
network_args = [ "algo=loha", "conv_dim=4", "conv_alpha=1",]
network_train_unet_only = true

[advanced_training_config]
save_state = false
save_last_n_epochs_state = false
caption_dropout_rate = 0
caption_tag_dropout_rate = 0.5
caption_dropout_every_n_epochs = 0
min_snr_gamma = 5
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

[Karbadel]

Try changing "mixed_precision = "fp16" to "No".
Not really sure, but that helped me.

[bryanlovely]

I also just ran into this issue.