nohup: ignoring input The following values were not passed to `accelerate launch` and had defaults used instead: `--num_processes` was set to a value of `1` `--num_machines` was set to a value of `1` `--dynamo_backend` was set to a value of `'no'` To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`. 10/07/2023 03:21:05 - INFO - __main__ - Distributed environment: NO Num processes: 1 Process index: 0 Local process index: 0 Device: cuda Mixed precision type: fp16 {'variance_type', 'sample_max_value', 'thresholding', 'prediction_type', 'clip_sample_range', 'dynamic_thresholding_ratio', 'timestep_spacing'} was not found in config. Values will be initialized to default values. {'force_upcast', 'scaling_factor'} was not found in config. Values will be initialized to default values. {'dual_cross_attention', 'resnet_time_scale_shift', 'time_cond_proj_dim', 'conv_out_kernel', 'conv_in_kernel', 'transformer_layers_per_block', 'cross_attention_norm', 'only_cross_attention', 'addition_embed_type_num_heads', 'upcast_attention', 'time_embedding_act_fn', 'time_embedding_type', 'time_embedding_dim', 'resnet_skip_time_act', 'resnet_out_scale_factor', 'dropout', 'encoder_hid_dim_type', 'mid_block_only_cross_attention', 'num_attention_heads', 'addition_time_embed_dim', 'encoder_hid_dim', 'class_embed_type', 'attention_type', 'timestep_post_act', 'mid_block_type', 'num_class_embeds', 'class_embeddings_concat', 'projection_class_embeddings_input_dim', 'use_linear_projection', 'addition_embed_type'} was not found in config. Values will be initialized to default values. /opt/conda/envs/pytorch/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 8 worker processes in total. Our suggested max number of worker in current system is 4, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary. warnings.warn(_create_warning_msg( 10/07/2023 03:21:10 - INFO - __main__ - ***** Running training ***** 10/07/2023 03:21:10 - INFO - __main__ - Num examples = 833 10/07/2023 03:21:10 - INFO - __main__ - Num Epochs = 72 10/07/2023 03:21:10 - INFO - __main__ - Instantaneous batch size per device = 1 10/07/2023 03:21:10 - INFO - __main__ - Total train batch size (w. parallel, distributed & accumulation) = 4 10/07/2023 03:21:10 - INFO - __main__ - Gradient Accumulation steps = 4 10/07/2023 03:21:10 - INFO - __main__ - Total optimization steps = 15000 Steps: 0%| | 0/15000 [00:00