Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/A_5fps_300s_{000000..000002}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/a_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', save_prefix='a_gimel', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) model: base_learning_rate: 1.0e-05 params: ddconfig: attn_resolutions: - 32 ch: 128 ch_mult: - 1 - 1 - 2 - 4 double_z: false dropout: 0.0 in_channels: 3 num_res_blocks: 2 out_ch: 3 resolution: 256 z_channels: 256 embed_dim: 256 lossconfig: params: codebook_weight: 1.0 disc_conditional: false disc_in_channels: 3 disc_start: 100001 disc_weight: 0.2 target: vqloss.VQLPIPSWithDiscriminator n_embed: 8192 target: vqmodel.VQModel Working with z of shape (1, 256, 32, 32) = 262144 dimensions. /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth VQLPIPSWithDiscriminator running with hinge loss. /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/utils/data/dataloader.py:563: 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( Number of parameters: 730671360 Running on 16 GPUs total => no checkpoint loaded, will train from scratch /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) /scratch/eo41/miniconda3/envs/llm/lib/python3.9/site-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='none' instead. warnings.warn(warning.format(ret)) Iteration: 0 | Training loss: 9.283171653747559 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_0.pt Iteration: 10000 | Training loss: 5.8971640702486035 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_10000.pt Iteration: 20000 | Training loss: 5.4968702283144 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_20000.pt Iteration: 30000 | Training loss: 5.361090888786316 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_30000.pt Iteration: 40000 | Training loss: 5.2772094738245015 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_40000.pt Iteration: 50000 | Training loss: 5.21737945227623 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_50000.pt Iteration: 60000 | Training loss: 5.180605615353584 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_60000.pt Iteration: 70000 | Training loss: 5.144675075793266 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/a_gimel_70000.pt slurmstepd: error: *** STEP 29613492.0 ON ga013 CANCELLED AT 2023-01-31T16:58:41 *** slurmstepd: error: *** JOB 29613492 ON ga013 CANCELLED AT 2023-01-31T16:58:41 *** srun: Job step aborted: Waiting up to 32 seconds for job step to finish.