Runner: <LogsViewRunner nb_logs=56 exit_code=1>

[lestersssss]

2024-11-01 17:58:06] [INFO] To avoid this warning pass in values for each of the problematic parameters or run accelerate config. [2024-11-01 17:58:10] [INFO] 2024-11-01 17:58:10 INFO highvram is enabled / train_util.py:4106 [2024-11-01 17:58:10] [INFO] highvramが有効です [2024-11-01 17:58:10] [INFO] WARNING cache_latents_to_disk is train_util.py:4123 [2024-11-01 17:58:10] [INFO] enabled, so cache_latents is [2024-11-01 17:58:10] [INFO] also enabled / [2024-11-01 17:58:10] [INFO] cache_latents_to_diskが有効なた [2024-11-01 17:58:10] [INFO] め、cache_latentsを有効にします [2024-11-01 17:58:10] [INFO] 2024-11-01 17:58:10 INFO Checking the state dict: flux_utils.py:62 [2024-11-01 17:58:10] [INFO] Diffusers or BFL, dev or schnell [2024-11-01 17:58:10] [INFO] INFO t5xxl_max_token_length: flux_train_network.py:152 [2024-11-01 17:58:10] [INFO] 512 [2024-11-01 17:58:10] [INFO] Traceback (most recent call last): [2024-11-01 17:58:10] [INFO] File "E:\fluxgym\sd-scripts\flux_train_network.py", line 564, in [2024-11-01 17:58:10] [INFO] trainer.train(args) [2024-11-01 17:58:10] [INFO] File "E:\fluxgym\sd-scripts\train_network.py", line 292, in train [2024-11-01 17:58:10] [INFO] tokenize_strategy = self.get_tokenize_strategy(args) [2024-11-01 17:58:10] [INFO] File "E:\fluxgym\sd-scripts\flux_train_network.py", line 153, in get_tokenize_strategy [2024-11-01 17:58:10] [INFO] return strategy_flux.FluxTokenizeStrategy(t5xxl_max_token_length, args.tokenizer_cache_dir) [2024-11-01 17:58:10] [INFO] File "E:\fluxgym\sd-scripts\library\strategy_flux.py", line 26, in init [2024-11-01 17:58:10] [INFO] self.clip_l = self._load_tokenizer(CLIPTokenizer, CLIP_L_TOKENIZER_ID, tokenizer_cache_dir=tokenizer_cache_dir) [2024-11-01 17:58:10] [INFO] File "E:\fluxgym\sd-scripts\library\strategy_base.py", line 65, in _load_tokenizer [2024-11-01 17:58:10] [INFO] tokenizer = model_class.from_pretrained(model_id, subfolder=subfolder) [2024-11-01 17:58:10] [INFO] File "E:\fluxgym\env\lib\site-packages\transformers\tokenization_utils_base.py", line 2210, in from_pretrained [2024-11-01 17:58:10] [INFO] tokenizer_config = json.load(reader) [2024-11-01 17:58:10] [INFO] File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\json__init.py", line 293, in load [2024-11-01 17:58:10] [INFO] return loads(fp.read(), [2024-11-01 17:58:10] [INFO] File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\json__init__.py", line 346, in loads [2024-11-01 17:58:10] [INFO] return _default_decoder.decode(s) [2024-11-01 17:58:10] [INFO] File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 337, in decode [2024-11-01 17:58:10] [INFO] obj, end = self.raw_decode(s, idx=_w(s, 0).end()) [2024-11-01 17:58:10] [INFO] File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 355, in raw_decode [2024-11-01 17:58:10] [INFO] raise JSONDecodeError("Expecting value", s, err.value) from None [2024-11-01 17:58:10] [INFO] json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0) [2024-11-01 17:58:11] [INFO] Traceback (most recent call last): [2024-11-01 17:58:11] [INFO] File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main [2024-11-01 17:58:11] [INFO] return _run_code(code, main_globals, None, [2024-11-01 17:58:11] [INFO] File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code [2024-11-01 17:58:11] [INFO] exec(code, run_globals) [2024-11-01 17:58:11] [INFO] File "E:\fluxgym\env\Scripts\accelerate.exe\main__.py", line 7, in [2024-11-01 17:58:11] [INFO] sys.exit(main()) [2024-11-01 17:58:11] [INFO] File "E:\fluxgym\env\lib\site-packages\accelerate\commands\accelerate_cli.py", line 48, in main [2024-11-01 17:58:11] [INFO] args.func(args) [2024-11-01 17:58:11] [INFO] File "E:\fluxgym\env\lib\site-packages\accelerate\commands\launch.py", line 1106, in launch_command [2024-11-01 17:58:11] [INFO] simple_launcher(args) [2024-11-01 17:58:11] [INFO] File "E:\fluxgym\env\lib\site-packages\accelerate\commands\launch.py", line 704, in simple_launcher [2024-11-01 17:58:11] [INFO] raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) [2024-11-01 17:58:11] [INFO] subprocess.CalledProcessError: Command '['E:\fluxgym\env\Scripts\python.exe', 'sd-scripts/flux_train_network.py', '--pretrained_model_name_or_path', 'E:\fluxgym\models\unet\flux1-dev.sft', '--clip_l', 'E:\fluxgym\models\clip\clip_l.safetensors', '--t5xxl', 'E:\fluxgym\models\clip\t5xxl_fp16.safetensors', '--ae', 'E:\fluxgym\models\vae\ae.sft', '--cache_latents_to_disk', '--save_model_as', 'safetensors', '--sdpa', '--persistent_data_loader_workers', '--max_data_loader_n_workers', '2', '--seed', '42', '--gradient_checkpointing', '--mixed_precision', 'bf16', '--save_precision', 'bf16', '--network_module', 'networks.lora_flux', '--network_dim', '4', '--optimizer_type', 'adafactor', '--optimizer_args', 'relative_step=False', 'scale_parameter=False', 'warmup_init=False', '--lr_scheduler', 'constant_with_warmup', '--max_grad_norm', '0.0', '--learning_rate', '8e-4', '--cache_text_encoder_outputs', '--cache_text_encoder_outputs_to_disk', '--fp8_base', '--highvram', '--max_train_epochs', '16', '--save_every_n_epochs', '4', '--dataset_config', 'E:\fluxgym\outputs\xb-lora\dataset.toml', '--output_dir', 'E:\fluxgym\outputs\xb-lora', '--output_name', 'xb-lora', '--timestep_sampling', 'shift', '--discrete_flow_shift', '3.1582', '--model_prediction_type', 'raw', '--guidance_scale', '1', '--loss_type', 'l2']' returned non-zero exit status 1. [2024-11-01 17:58:11] [ERROR] Command exited with code 1 [2024-11-01 17:58:11] [INFO] Runner:

[Hiddengenie]

Check whether your ae.sft (in the vae folder) is complete and uncorrupted. If it is then try uploading an older version - I uploaded a version from September and that solved the isse.

[alexnikospb]

I have the same problem: Runner: LogsViewRunner nb_logs=38 exit_code=1

[lestersssss]

Check whether your ae.sft (in the vae folder) is complete and uncorrupted. If it is then try uploading an older version - I uploaded a version from September and that solved the isse.

thank you!

[Samchris01]

Check whether your ae.sft (in the vae folder) is complete and uncorrupted. If it is then try uploading an older version - I uploaded

How to download