predict 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` `--mixed_precision` was set to a value of `'no'` `--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`. A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton' running with config: pretrained_model_path: ./checkpoints/stable-diffusion-v1-4 output_dir: /outputs train_data: n_sample_frames: 8 sample_start_idx: 0 prompt: a man surfing video_path: /tmp/tmpk5ml9tquman%20surfing.mp4 width: 512 height: 512 sample_frame_rate: 1 validation_data: num_inference_steps: 50 guidance_scale: 7.5 prompts: - a panda surfing - a cartoon sloth surfing video_length: 5 width: 512 height: 512 learning_rate: 3.0e-05 train_batch_size: 1 max_train_steps: 300 checkpointing_steps: 1000 validation_steps: 100 trainable_modules: - attn1.to_q - attn2.to_q - attn_temp seed: 33 mixed_precision: fp16 use_8bit_adam: false gradient_checkpointing: true enable_xformers_memory_efficient_attention: true 01/29/2023 09:21:16 - INFO - __main__ - Distributed environment: NO Num processes: 1 Process index: 0 Local process index: 0 Device: cuda Mixed precision type: fp16 {'prediction_type', 'variance_type'} was not found in config. Values will be initialized to default values. {'norm_num_groups'} was not found in config. Values will be initialized to default values. {'class_embed_type', 'use_linear_projection', 'upcast_attention', 'only_cross_attention', 'dual_cross_attention', 'mid_block_type', 'num_class_embeds', 'resnet_time_scale_shift'} was not found in config. Values will be initialized to default values. {'prediction_type'} was not found in config. Values will be initialized to default values. 01/29/2023 09:21:32 - INFO - __main__ - ***** Running training ***** 01/29/2023 09:21:32 - INFO - __main__ - Num examples = 1 01/29/2023 09:21:32 - INFO - __main__ - Num Epochs = 300 01/29/2023 09:21:32 - INFO - __main__ - Instantaneous batch size per device = 1 01/29/2023 09:21:32 - INFO - __main__ - Total train batch size (w. parallel, distributed & accumulation) = 1 01/29/2023 09:21:32 - INFO - __main__ - Gradient Accumulation steps = 1 01/29/2023 09:21:32 - INFO - __main__ - Total optimization steps = 300 0%| | 0/300 [00:00