gpt_visual_memory / logs /imagenet_gimel_1.out
eminorhan's picture
Upload 26 files
fea8e2a
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
Namespace(data_path='/scratch/work/public/imagenet/train', vqconfig_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.yaml', vqmodel_path='/scratch/eo41/visual-recognition-memory/vqgan_pretrained_models/imagenet_16x16_16384.ckpt', num_workers=8, seed=0, save_dir='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models', gpt_config='GPT_gimel', vocab_size=16384, block_size=255, batch_size=32, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt', save_prefix='imagenet', gpu=None, world_size=-1, rank=-1, dist_url='env://', dist_backend='nccl', local_rank=-1)
model:
base_learning_rate: 4.5e-06
params:
ddconfig:
attn_resolutions:
- 16
ch: 128
ch_mult:
- 1
- 1
- 2
- 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_num_layers: 2
disc_start: 0
disc_weight: 0.75
target: vqloss.VQLPIPSWithDiscriminator
monitor: val/rec_loss
n_embed: 16384
target: vqmodel.VQModel
Working with z of shape (1, 256, 16, 16) = 65536 dimensions.
loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth
VQLPIPSWithDiscriminator running with hinge loss.
Loaded VQ encoder.
Data loaded: dataset contains 1281167 images, and takes 5005 training iterations per epoch.
Number of parameters: 750659840
Running on 8 GPUs total
=> loaded model weights and optimizer state at checkpoint '/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_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))
Epoch: 0 | Training loss: 5.4122182536434815 | Elapsed time: 4451.620691537857
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_000_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 1 | Training loss: 5.407565878297423 | Elapsed time: 4448.908405780792
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_001_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 2 | Training loss: 5.4076390378839605 | Elapsed time: 4449.1268055438995
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_002_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 3 | Training loss: 5.405201209960999 | Elapsed time: 4448.375809907913
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_003_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 4 | Training loss: 5.402879751931418 | Elapsed time: 4448.051635503769
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_004_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 5 | Training loss: 5.398940936382953 | Elapsed time: 4447.108489990234
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_005_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 6 | Training loss: 5.3984892385942 | Elapsed time: 4448.6805555820465
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_006_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 7 | Training loss: 5.394524213484117 | Elapsed time: 4447.839882135391
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_007_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 8 | Training loss: 5.393681722349458 | Elapsed time: 4447.997987985611
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_008_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 9 | Training loss: 5.389481829834747 | Elapsed time: 4446.9174818992615
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_009_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 10 | Training loss: 5.3900642942834445 | Elapsed time: 4450.051897764206
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_010_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 11 | Training loss: 5.38399512570102 | Elapsed time: 4446.795197725296
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_011_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 12 | Training loss: 5.382598996805502 | Elapsed time: 4447.133504629135
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_012_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 13 | Training loss: 5.380970008556659 | Elapsed time: 4447.336958885193
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_013_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 14 | Training loss: 5.380182438296871 | Elapsed time: 4448.077193975449
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_014_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 15 | Training loss: 5.37776358468192 | Elapsed time: 4447.623661279678
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_015_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 16 | Training loss: 5.3761095024131755 | Elapsed time: 4446.6331260204315
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_016_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 17 | Training loss: 5.373553631331895 | Elapsed time: 4448.016380786896
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_017_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 18 | Training loss: 5.372018059626683 | Elapsed time: 4447.691753149033
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_018_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 19 | Training loss: 5.373565301409253 | Elapsed time: 4449.665137767792
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_019_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 20 | Training loss: 5.368000029945946 | Elapsed time: 4447.717018127441
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_020_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 21 | Training loss: 5.368069200487166 | Elapsed time: 4448.9792404174805
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_021_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 22 | Training loss: 5.365969175439734 | Elapsed time: 4448.452637910843
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_022_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 23 | Training loss: 5.36370946005746 | Elapsed time: 4449.199255228043
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_023_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 24 | Training loss: 5.361778489740698 | Elapsed time: 4448.894506216049
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_024_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 25 | Training loss: 5.36139729773248 | Elapsed time: 4449.400998592377
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_025_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 26 | Training loss: 5.357821354308686 | Elapsed time: 4448.22802734375
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_026_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 27 | Training loss: 5.3575045292194075 | Elapsed time: 4448.227440834045
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_027_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 28 | Training loss: 5.356028392002894 | Elapsed time: 4449.236404657364
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_028_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 29 | Training loss: 5.3537167115644975 | Elapsed time: 4448.098119497299
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_029_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 30 | Training loss: 5.354773959580001 | Elapsed time: 4448.19157743454
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_030_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 31 | Training loss: 5.349621527726119 | Elapsed time: 4448.848588943481
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_031_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 32 | Training loss: 5.347856791226657 | Elapsed time: 4449.08669257164
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_032_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 33 | Training loss: 5.349459922420872 | Elapsed time: 4449.880000591278
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_033_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 34 | Training loss: 5.3449111444966775 | Elapsed time: 4448.975071430206
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_034_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 35 | Training loss: 5.345478597578111 | Elapsed time: 4449.066173315048
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_035_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 36 | Training loss: 5.345441694097681 | Elapsed time: 4449.324020385742
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_036_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
Epoch: 37 | Training loss: 5.34429892197951 | Elapsed time: 4449.110852479935
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_037_imagenet_GPT_gimel_256b_0.0003lr_Adamo_0s.pt
slurmstepd: error: *** JOB 25481932 ON ga007 CANCELLED AT 2022-09-29T05:17:09 DUE TO TIME LIMIT ***
srun: Job step aborted: Waiting up to 32 seconds for job step to finish.
slurmstepd: error: *** STEP 25481932.0 ON ga007 CANCELLED AT 2022-09-29T05:17:09 DUE TO TIME LIMIT ***