You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I was trying to use autotrain on google colab and i got this error when i start training:
Device 0: Tesla T4 - 260.9MiB/15360MiB
INFO | 2024-04-13 15:23:39 | autotrain.app_utils:get_running_jobs:33 - Process 2603 is already completed. Skipping...
INFO | 2024-04-13 15:23:39 | autotrain.app_utils:get_running_jobs:32 - Error while killing process: [Errno 3] No such process
INFO | 2024-04-13 15:23:39 | autotrain.app_utils:get_running_jobs:28 - Killing PID: 2603
{'latents_mean', 'latents_std'} was not found in config. Values will be initialized to default values.
{'variance_type', 'thresholding', 'dynamic_thresholding_ratio', 'clip_sample_range'} was not found in config. Values will be initialized to default values.
You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
INFO | 2024-04-13 15:21:10 | autotrain.backend:create:305 - Training PID: 2603
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: token, id_column, model, valid_split, categorical_columns, username, repo_id, target_columns, seed, numerical_columns, num_trials, train_split, task, time_limit, project_name, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: lora_r, model, weight_decay, gradient_accumulation, repo_id, max_seq_length, target_column, warmup_ratio, lr, max_target_length, logging_steps, text_column, token, save_total_limit, valid_split, batch_size, epochs, username, seed, scheduler, lora_dropout, quantization, train_split, lora_alpha, max_grad_norm, auto_find_batch_size, evaluation_strategy, optimizer, project_name, peft, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: token, save_total_limit, model, batch_size, valid_split, save_strategy, weight_decay, epochs, gradient_accumulation, username, repo_id, target_column, seed, warmup_ratio, image_column, lr, scheduler, logging_steps, train_split, max_grad_norm, auto_find_batch_size, evaluation_strategy, optimizer, project_name, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: token, save_total_limit, model, batch_size, valid_split, save_strategy, weight_decay, epochs, gradient_accumulation, username, repo_id, max_seq_length, target_column, seed, warmup_ratio, lr, scheduler, logging_steps, train_split, text_column, max_grad_norm, auto_find_batch_size, evaluation_strategy, optimizer, project_name, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: dpo_beta, lora_r, model, weight_decay, gradient_accumulation, repo_id, model_max_length, prompt_text_column, rejected_text_column, warmup_ratio, merge_adapter, use_flash_attention_2, lr, logging_steps, text_column, model_ref, token, save_total_limit, valid_split, batch_size, username, seed, disable_gradient_checkpointing, trainer, scheduler, lora_dropout, train_split, lora_alpha, add_eos_token, max_grad_norm, evaluation_strategy, auto_find_batch_size, optimizer, project_name, data_path, push_to_hub
INFO | 2024-04-13 15:20:14 | autotrain.app::30 - Starting AutoTrain...
Your installed package nvidia-ml-py is corrupted. Skip patch functions nvmlDeviceGetMemoryInfo. You may get incorrect or incomplete results. Please consider reinstall package nvidia-ml-py via pip3 install --force-reinstall nvidia-ml-py nvitop.
Your installed package nvidia-ml-py is corrupted. Skip patch functions nvmlDeviceGet{Compute,Graphics,MPSCompute}RunningProcesses. You may get incorrect or incomplete results. Please consider reinstall package nvidia-ml-py via pip3 install --force-reinstall nvidia-ml-py nvitop.
The text was updated successfully, but these errors were encountered:
have you tried sdxl? was epicrealism working before?
no i didnt, i was thinking to use epicrealism because i want to create an ai influencer and i want to look as real as possible. i tried on rendernet epicrealism and i saw the results are pretty good and seems real.
do u have a better idea tho?
I was trying to use autotrain on google colab and i got this error when i start training:
INFO | 2024-04-13 15:23:39 | autotrain.app_utils:get_running_jobs:33 - Process 2603 is already completed. Skipping...
INFO | 2024-04-13 15:23:39 | autotrain.app_utils:get_running_jobs:32 - Error while killing process: [Errno 3] No such process
INFO | 2024-04-13 15:23:39 | autotrain.app_utils:get_running_jobs:28 - Killing PID: 2603
{'latents_mean', 'latents_std'} was not found in config. Values will be initialized to default values.
{'variance_type', 'thresholding', 'dynamic_thresholding_ratio', 'clip_sample_range'} was not found in config. Values will be initialized to default values.
You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
INFO | 2024-04-13 15:21:10 | autotrain.backend:create:305 - Training PID: 2603
INFO | 2024-04-13 15:21:10 | autotrain.commands:launch_command:339 - {'model': 'stablediffusionapi/epicrealism-xl', 'vae_model': '', 'revision': None, 'tokenizer': None, 'image_path': 'autotrain-tp7lr-fasg3/autotrain-data', 'class_image_path': None, 'prompt': '', 'class_prompt': None, 'num_class_images': 100, 'class_labels_conditioning': None, 'prior_preservation': False, 'prior_loss_weight': 1.0, 'project_name': 'autotrain-tp7lr-fasg3', 'seed': 42, 'resolution': 1024, 'center_crop': False, 'train_text_encoder': False, 'batch_size': 1, 'sample_batch_size': 4, 'epochs': 1, 'num_steps': 500, 'checkpointing_steps': 500, 'resume_from_checkpoint': None, 'gradient_accumulation': 4, 'disable_gradient_checkpointing': False, 'lr': 0.0001, 'scale_lr': False, 'scheduler': 'constant', 'warmup_steps': 0, 'num_cycles': 1, 'lr_power': 1.0, 'dataloader_num_workers': 0, 'use_8bit_adam': False, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_weight_decay': 0.01, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'allow_tf32': False, 'prior_generation_precision': None, 'local_rank': -1, 'xformers': False, 'pre_compute_text_embeddings': False, 'tokenizer_max_length': None, 'text_encoder_use_attention_mask': False, 'rank': 4, 'xl': False, 'mixed_precision': 'fp16', 'token': '*****', 'repo_id': 'bobitalent/autotrain-tp7lr-fasg3', 'push_to_hub': True, 'username': 'bobitalent', 'validation_prompt': None, 'num_validation_images': 4, 'validation_epochs': 50, 'checkpoints_total_limit': None, 'validation_images': None, 'logging': False}
INFO | 2024-04-13 15:21:10 | autotrain.commands:launch_command:338 - ['python', '-m', 'autotrain.trainers.dreambooth', '--training_config', 'autotrain-tp7lr-fasg3/training_params.json']
INFO | 2024-04-13 15:21:10 | autotrain.backend:create:300 - Starting local training...
WARNING | 2024-04-13 15:21:10 | autotrain.trainers.common:init:176 - Parameters supplied but not used: data_path
WARNING | 2024-04-13 15:21:10 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: local_rank, scale_lr, center_crop, xl, adam_epsilon, train_text_encoder, validation_prompt, num_validation_images, lr_power, prior_generation_precision, class_labels_conditioning, sample_batch_size, logging, text_encoder_use_attention_mask, adam_weight_decay, allow_tf32, adam_beta1, validation_images, revision, epochs, validation_epochs, dataloader_num_workers, class_image_path, prior_preservation, pre_compute_text_embeddings, warmup_steps, resume_from_checkpoint, seed, disable_gradient_checkpointing, tokenizer, num_class_images, prior_loss_weight, adam_beta2, rank, tokenizer_max_length, checkpoints_total_limit, max_grad_norm, class_prompt, num_cycles
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abd960>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abf550>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abfd00>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abe440>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab58eea03d0>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab58eea1120>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab58eea1060>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abe110>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abe140>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abe770>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abe410>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abe2f0>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abf370>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abee60>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abf160>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abeb60>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:63 - <starlette.datastructures.UploadFile object at 0x7ab595abdc00>
INFO | 2024-04-13 15:21:10 | autotrain.preprocessor.dreambooth:_save_concept_images:62 - Saving concept images
INFO | 2024-04-13 15:21:09 | autotrain.app:handle_form:435 - hardware: Local
INFO | 2024-04-13 15:20:39 | autotrain.app:fetch_params:206 - Task: dreambooth
INFO | 2024-04-13 15:20:29 | autotrain.app:fetch_params:206 - Task: llm:sft
INFO | 2024-04-13 15:20:23 | autotrain.app::152 - AutoTrain started successfully
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: token, save_total_limit, model, batch_size, valid_split, save_strategy, weight_decay, epochs, gradient_accumulation, username, repo_id, max_seq_length, seed, warmup_ratio, lr, tokens_column, scheduler, logging_steps, train_split, tags_column, max_grad_norm, auto_find_batch_size, evaluation_strategy, optimizer, project_name, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: local_rank, checkpointing_steps, scale_lr, center_crop, model, xl, adam_epsilon, repo_id, validation_prompt, num_validation_images, lr_power, prior_generation_precision, num_cycles, class_labels_conditioning, sample_batch_size, logging, text_encoder_use_attention_mask, adam_weight_decay, adam_beta1, allow_tf32, token, validation_images, revision, epochs, dataloader_num_workers, validation_epochs, username, prior_preservation, pre_compute_text_embeddings, warmup_steps, resume_from_checkpoint, seed, image_path, tokenizer, num_class_images, prior_loss_weight, scheduler, adam_beta2, tokenizer_max_length, rank, checkpoints_total_limit, max_grad_norm, class_prompt, class_image_path, project_name, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: token, id_column, model, valid_split, categorical_columns, username, repo_id, target_columns, seed, numerical_columns, num_trials, train_split, task, time_limit, project_name, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: lora_r, model, weight_decay, gradient_accumulation, repo_id, max_seq_length, target_column, warmup_ratio, lr, max_target_length, logging_steps, text_column, token, save_total_limit, valid_split, batch_size, epochs, username, seed, scheduler, lora_dropout, quantization, train_split, lora_alpha, max_grad_norm, auto_find_batch_size, evaluation_strategy, optimizer, project_name, peft, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: token, save_total_limit, model, batch_size, valid_split, save_strategy, weight_decay, epochs, gradient_accumulation, username, repo_id, target_column, seed, warmup_ratio, image_column, lr, scheduler, logging_steps, train_split, max_grad_norm, auto_find_batch_size, evaluation_strategy, optimizer, project_name, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: token, save_total_limit, model, batch_size, valid_split, save_strategy, weight_decay, epochs, gradient_accumulation, username, repo_id, max_seq_length, target_column, seed, warmup_ratio, lr, scheduler, logging_steps, train_split, text_column, max_grad_norm, auto_find_batch_size, evaluation_strategy, optimizer, project_name, data_path, push_to_hub
WARNING | 2024-04-13 15:20:14 | autotrain.trainers.common:init:170 - Parameters not supplied by user and set to default: dpo_beta, lora_r, model, weight_decay, gradient_accumulation, repo_id, model_max_length, prompt_text_column, rejected_text_column, warmup_ratio, merge_adapter, use_flash_attention_2, lr, logging_steps, text_column, model_ref, token, save_total_limit, valid_split, batch_size, username, seed, disable_gradient_checkpointing, trainer, scheduler, lora_dropout, train_split, lora_alpha, add_eos_token, max_grad_norm, evaluation_strategy, auto_find_batch_size, optimizer, project_name, data_path, push_to_hub
INFO | 2024-04-13 15:20:14 | autotrain.app::30 - Starting AutoTrain...
Your installed package
nvidia-ml-py
is corrupted. Skip patch functionsnvmlDeviceGetMemoryInfo
. You may get incorrect or incomplete results. Please consider reinstall packagenvidia-ml-py
viapip3 install --force-reinstall nvidia-ml-py nvitop
.Your installed package
nvidia-ml-py
is corrupted. Skip patch functionsnvmlDeviceGet{Compute,Graphics,MPSCompute}RunningProcesses
. You may get incorrect or incomplete results. Please consider reinstall packagenvidia-ml-py
viapip3 install --force-reinstall nvidia-ml-py nvitop
.The text was updated successfully, but these errors were encountered: