在执行Lora模型训练这一步的时候:执行如下命令,设置num_train_epochs为200,进行lora模型的训练:
! export MODEL_NAME="chilloutmix-ni" && \
export DATASET_NAME="cloth_train_example" && \
accelerate launch --mixed_precision="fp16" train_text_to_image_lora.py \
--pretrained_model_name_or_path=$MODEL_NAME \
--dataset_name=$DATASET_NAME --caption_column="text" \
--width=640 --height=768 --random_flip \
--train_batch_size=1 \
--num_train_epochs=200 --checkpointing_steps=5000 \
--learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
--seed=42 \
--output_dir="cloth-model-lora" \
--validation_prompt="cloth1" --validation_epochs=100
出现问题:
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py:337 │
│ in load_config │
│ │
│ 334 │ │ else: │
│ 335 │ │ │ try: │
│ 336 │ │ │ │ # Load from URL or cache if already cached │
│ ❱ 337 │ │ │ │ config_file = hf_hub_download( │
│ 338 │ │ │ │ │ pretrained_model_name_or_path, │
│ 339 │ │ │ │ │ filename=cls.config_name, │
│ 340 │ │ │ │ │ cache_dir=cache_dir, │
│ │
│ /usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py │
│ :120 in _inner_fn │
│ │
│ 117 │ │ if check_use_auth_token: │
│ 118 │ │ │ kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__na │
│ 119 │ │ │
│ ❱ 120 │ │ return fn(args, *kwargs) │
│ 121 │ │
│ 122 │ return _inner_fn # type: ignore │
│ 123 │
│ │
│ /usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:125 │
│ 3 in hf_hub_download │
│ │
│ 1250 │ │ │ │ " and downloads online, set 'local_files_only' to Fal │
│ 1251 │ │ │ ) │
│ 1252 │ │ else: │
│ ❱ 1253 │ │ │ raise LocalEntryNotFoundError( │
│ 1254 │ │ │ │ "Connection error, and we cannot find the requested f │
│ 1255 │ │ │ │ " the disk cache. Please try again or make sure your │
│ 1256 │ │ │ │ " connection is on." │
╰──────────────────────────────────────────────────────────────────────────────╯
LocalEntryNotFoundError: Connection error, and we cannot find the requested
files in the disk cache. Please try again or make sure your Internet connection
is on.
During handling of the above exception, another exception occurred:
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /mnt/workspace/train_text_to_image_lora.py:896 in │
│ │
│ 893 │
│ 894 │
│ 895 if name == "main": │
│ ❱ 896 │ main() │
│ 897 │
│ │
│ /mnt/workspace/train_text_to_image_lora.py:440 in main │
│ │
│ 437 │ │ │ os.makedirs(args.output_dir, exist_ok=True) │
│ 438 │ │
│ 439 │ # Load scheduler, tokenizer and models. │
│ ❱ 440 │ noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_mo │
│ 441 │ tokenizer = CLIPTokenizer.from_pretrained( │
│ 442 │ │ args.pretrained_model_name_or_path, subfolder="tokenizer", rev │
│ 443 │ ) │
│ │
│ /usr/local/lib/python3.10/dist-packages/diffusers/schedulers/scheduling_util │
│ s.py:139 in from_pretrained │
│ │
│ 136 │ │ │
│ 137 │ │ │
│ 138 │ │ """ │
│ ❱ 139 │ │ config, kwargs, commit_hash = cls.load_config( │
│ 140 │ │ │ pretrained_model_name_or_path=pretrained_model_name_or_pat │
│ 141 │ │ │ subfolder=subfolder, │
│ 142 │ │ │ return_unused_kwargs=True, │
│ │
│ /usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py:364 │
│ in load_config │
│ │
│ 361 │ │ │ │ │ f" 'https://huggingface.co/{pretrained_model_name_ │
│ 362 │ │ │ │ ) │
│ 363 │ │ │ except EntryNotFoundError: │
│ ❱ 364 │ │ │ │ raise EnvironmentError( │
│ 365 │ │ │ │ │ f"{pretrained_model_name_or_path} does not appear │
│ 366 │ │ │ │ ) │
│ 367 │ │ │ except HTTPError as err: │
╰──────────────────────────────────────────────────────────────────────────────╯
OSError: chilloutmix-ni does not appear to have a file named
scheduler_config.json.
[02:18:28] ERROR failed (exitcode: 1) local_rank: 0 (pid: 502) of ]8;id=222292;file:///usr/local/lib/python3.10/dist-packages/torch/distributed/elastic/multiprocessing/api.py\api.py]8;;:]8;id=930720;file:///usr/local/lib/python3.10/dist-packages/torch/distributed/elastic/multiprocessing/api.py#673\673]8;;
binary: /usr/bin/python3
版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。
人工智能平台 PAI(Platform for AI,原机器学习平台PAI)是面向开发者和企业的机器学习/深度学习工程平台,提供包含数据标注、模型构建、模型训练、模型部署、推理优化在内的AI开发全链路服务,内置140+种优化算法,具备丰富的行业场景插件,为用户提供低门槛、高性能的云原生AI工程化能力。