(glv) pritam@drona:~/Gen-L-Video$ accelerate launch one-shot-tuning.py
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`.
goooooooooooooooooooooooooooooooooooooooo
ggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggg
{'clip_sample_range', 'thresholding', 'variance_type', 'sample_max_value', 'dynamic_thresholding_ratio', 'prediction_type'} was not found in config. Values will be initialized to default values.
{'scaling_factor'} was not found in config. Values will be initialized to default values.
{'class_embed_type', 'resnet_time_scale_shift', 'upcast_attention', 'num_class_embeds', 'only_cross_attention'} was not found in config. Values will be initialized to default values.
hhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh
inssert down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q
inssert down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q
inssert down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q
inssert down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q
inssert down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q
inssert down_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q
inssert up_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q
inssert up_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q
inssert up_blocks.1.attentions.2.transformer_blocks.0.attn1.to_q
inssert up_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q
inssert up_blocks.2.attentions.1.transformer_blocks.0.attn1.to_q
inssert up_blocks.2.attentions.2.transformer_blocks.0.attn1.to_q
inssert up_blocks.3.attentions.0.transformer_blocks.0.attn1.to_q
inssert up_blocks.3.attentions.1.transformer_blocks.0.attn1.to_q
inssert up_blocks.3.attentions.2.transformer_blocks.0.attn1.to_q
inssert mid_block.attentions.0.transformer_blocks.0.attn1.to_q
rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
{'clip_sample_range', 'thresholding', 'sample_max_value', 'dynamic_thresholding_ratio', 'prediction_type'} was not found in config. Values will be initialized to default values.
{'clip_sample_range', 'thresholding', 'sample_max_value', 'dynamic_thresholding_ratio', 'prediction_type'} was not found in config. Values will be initialized to default values.
02/24/2024 21:13:18 - INFO - root - ***** Running training *****
02/24/2024 21:13:18 - INFO - root -   Num examples = 5
02/24/2024 21:13:18 - INFO - root -   Num Epochs = 67
02/24/2024 21:13:18 - INFO - root -   Instantaneous batch size per device = 2
02/24/2024 21:13:18 - INFO - root -   Total train batch size (w. parallel, distributed & accumulation) = 2
02/24/2024 21:13:18 - INFO - root -   Gradient Accumulation steps = 1
02/24/2024 21:13:18 - INFO - root -   Total optimization steps = 200
Steps:   0%|                                                                                                                                                                       | 0/200 [00:00<?, ?it/s]hereeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee
/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/diffusers/configuration_utils.py:134: FutureWarning: Accessing config attribute `num_train_timesteps` directly via 'DDPMScheduler' object attribute is deprecated. Please access 'num_train_timesteps' over 'DDPMScheduler's config object instead, e.g. 'scheduler.config.num_train_timesteps'.
  deprecate("direct config name access", "1.0.0", deprecation_message, standard_warn=False)
/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/diffusers/configuration_utils.py:134: FutureWarning: Accessing config attribute `prediction_type` directly via 'DDPMScheduler' object attribute is deprecated. Please access 'prediction_type' over 'DDPMScheduler's config object instead, e.g. 'scheduler.config.prediction_type'.
  deprecate("direct config name access", "1.0.0", deprecation_message, standard_warn=False)
Traceback (most recent call last):
  File "one-shot-tuning.py", line 525, in <module>
    main(**conf)
  File "one-shot-tuning.py", line 371, in main
    model_pred = unet(noisy_latents, timesteps, clip_id, encoder_hidden_states,control=control).sample
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/accelerate/utils/operations.py", line 495, in __call__
    return convert_to_fp32(self.model_forward(*args, **kwargs))
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/torch/amp/autocast_mode.py", line 14, in decorate_autocast
    return func(*args, **kwargs)
  File "/home/pritam/Gen-L-Video/glv/models/unet.py", line 409, in forward
    sample = self.conv_in(sample)
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/pritam/Gen-L-Video/glv/models/resnet.py", line 15, in forward
    x = super().forward(x)
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 463, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 459, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [320, 9, 3, 3], expected input[32, 4, 64, 64] to have 9 channels, but got 4 channels instead
Steps:   0%|                                                                                                                                                                       | 0/200 [00:03<?, ?it/s]
Traceback (most recent call last):
  File "/home/pritam/anaconda3/envs/glv/bin/accelerate", line 8, in <module>
    sys.exit(main())
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/accelerate/commands/accelerate_cli.py", line 45, in main
    args.func(args)
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/accelerate/commands/launch.py", line 923, in launch_command
    simple_launcher(args)
  File "/home/pritam/anaconda3/envs/glv/lib/python3.8/site-packages/accelerate/commands/launch.py", line 579, in simple_launcher
    raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/home/pritam/anaconda3/envs/glv/bin/python', 'one-shot-tuning.py']' returned non-zero exit status 1.