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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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=5000, lr=0.0003, optimizer='Adam', resume='/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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. Number of parameters: 730671360 Running on 16 GPUs total => loaded model weights and optimizer state at checkpoint '/scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_190000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.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: 5.30007791519165 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_0_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 5000 | Training loss: 5.138480274868011 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_5000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 10000 | Training loss: 5.107799020719528 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_10000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 15000 | Training loss: 5.088881051254273 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_15000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 20000 | Training loss: 5.085070754432678 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_20000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 25000 | Training loss: 5.080795408391952 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_25000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 30000 | Training loss: 5.380685155773163 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_30000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 35000 | Training loss: 5.718056494235992 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_35000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 40000 | Training loss: 5.23170142364502 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_40000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 45000 | Training loss: 5.106258099412918 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_45000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 50000 | Training loss: 5.080553993320465 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_50000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 55000 | Training loss: 5.211881767654419 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_55000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 60000 | Training loss: 5.073302331018448 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_60000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 65000 | Training loss: 5.081954577064514 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_65000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 70000 | Training loss: 5.065998318481445 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_70000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 75000 | Training loss: 5.060894852352142 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_75000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 80000 | Training loss: 5.057493374586105 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_80000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 85000 | Training loss: 5.0525652509212495 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_85000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 90000 | Training loss: 5.048048374509811 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_90000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 95000 | Training loss: 5.045162040233612 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_95000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 100000 | Training loss: 5.047997813224793 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_100000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 105000 | Training loss: 5.035569662857056 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_105000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 110000 | Training loss: 5.030170858097076 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_110000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 115000 | Training loss: 5.020523439121247 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_115000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 120000 | Training loss: 5.033615832281113 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_120000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 125000 | Training loss: 5.024354502677918 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_125000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 130000 | Training loss: 5.030594699859619 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_130000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 135000 | Training loss: 5.01051748251915 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_135000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 140000 | Training loss: 5.021781470680237 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_140000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 145000 | Training loss: 5.01388137922287 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_145000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 150000 | Training loss: 5.007130924606323 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_150000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 155000 | Training loss: 5.010347195625306 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_155000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 160000 | Training loss: 5.009956067085266 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_160000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 165000 | Training loss: 5.00600462846756 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_165000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 170000 | Training loss: 5.006761898326873 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_170000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 175000 | Training loss: 4.996211072683335 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_175000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 180000 | Training loss: 4.990817209720611 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_180000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt Iteration: 185000 | Training loss: 4.992834660196304 Saving model to: /scratch/eo41/vqgan-gpt/gpt_pretrained_models/model_185000_36l_20h_1280e_96b_0.0003lr_Adamo_0s.pt slurmstepd: error: *** JOB 24809016 ON ga002 CANCELLED AT 2022-09-15T08:32:40 *** srun: Job step aborted: Waiting up to 32 seconds for job step to finish. slurmstepd: error: *** STEP 24809016.0 ON ga002 CANCELLED AT 2022-09-15T08:32:40 ***