Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1) Namespace(data_path='/scratch/eo41/data/saycam/SAY_5fps_300s_{000000..000009}.tar', vqconfig_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.yaml', vqmodel_path='/scratch/eo41/vqgan-gpt/vqgan_pretrained_models/say_32x32_8192.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/vqgan-gpt/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=8192, block_size=1023, batch_size=6, print_freq=10000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt', 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. loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth VQLPIPSWithDiscriminator running with hinge loss. /scratch/eo41/miniconda3/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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/lib/python3.9/site-packages/torch/utils/data/dataloader.py:478: 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 => loaded model weights and optimizer state at checkpoint '/scratch/eo41/vqgan-gpt/gpt_pretrained_models/say_gimel.pt' /scratch/eo41/miniconda3/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/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/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/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/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/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/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/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/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/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/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/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/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/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/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/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: 5.033977508544922 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_0_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 10000 | Training loss: 5.000367347049713 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_10000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 20000 | Training loss: 4.979147749662399 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_20000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 30000 | Training loss: 4.972516257357597 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_30000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 40000 | Training loss: 4.970100594377517 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_40000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 50000 | Training loss: 5.405501440525055 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_50000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 60000 | Training loss: 5.353503350329399 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_60000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 70000 | Training loss: 5.220138521456718 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_70000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 80000 | Training loss: 5.138026001763344 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_80000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 90000 | Training loss: 4.997180798411369 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_90000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 100000 | Training loss: 4.972350775599479 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_100000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 110000 | Training loss: 4.9657788955450055 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_110000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 120000 | Training loss: 4.953705482721329 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_120000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 130000 | Training loss: 4.9448775294542315 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_130000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 140000 | Training loss: 4.944383617019653 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_140000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 150000 | Training loss: 4.944210085701942 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_150000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 160000 | Training loss: 4.938878140282631 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_160000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 170000 | Training loss: 4.931895919656753 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_170000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 180000 | Training loss: 4.933802534270287 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_180000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt slurmstepd: error: *** JOB 27300133 ON ga001 CANCELLED AT 2022-11-26T10:02:03 DUE TO TIME LIMIT *** slurmstepd: error: *** STEP 27300133.0 ON ga001 CANCELLED AT 2022-11-26T10:02:03 DUE TO TIME LIMIT *** srun: Job step aborted: Waiting up to 32 seconds for job step to finish.