gpt_visual_memory / logs /imagenet_dalet_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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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_dalet', vocab_size=16384, block_size=255, batch_size=16, lr=0.0003, optimizer='Adam', epochs=1000, resume='/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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: 1528398400
Running on 16 GPUs total
=> loaded model weights and optimizer state at checkpoint '/scratch/eo41/visual-recognition-memory/gpt_pretrained_models/imagenet_dalet.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))
Epoch: 0 | Training loss: 5.36132043386911 | Elapsed time: 5611.475602149963
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_000_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 1 | Training loss: 5.353246255544992 | Elapsed time: 5609.176076889038
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_001_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 2 | Training loss: 5.352081888848609 | Elapsed time: 5609.765173435211
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_002_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 3 | Training loss: 5.348592715401511 | Elapsed time: 5609.775065898895
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_003_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 4 | Training loss: 5.345363831496263 | Elapsed time: 5608.818708658218
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_004_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 5 | Training loss: 5.339491759766113 | Elapsed time: 5609.52224946022
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_005_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 6 | Training loss: 5.33984013451682 | Elapsed time: 5609.668743610382
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_006_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 7 | Training loss: 5.330916097471407 | Elapsed time: 5609.77694439888
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_007_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 8 | Training loss: 5.328678440642761 | Elapsed time: 5609.147026062012
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_008_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 9 | Training loss: 5.322817993259335 | Elapsed time: 5610.099377155304
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_009_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 10 | Training loss: 5.322999638491696 | Elapsed time: 5609.647800445557
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_010_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 11 | Training loss: 5.3166510385709564 | Elapsed time: 5609.4286053180695
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_011_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 12 | Training loss: 5.314551228552789 | Elapsed time: 5609.531573057175
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_012_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 13 | Training loss: 5.310544481096449 | Elapsed time: 5609.943645954132
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_013_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 14 | Training loss: 5.307691298760139 | Elapsed time: 5610.385461807251
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_014_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 15 | Training loss: 5.304726327406419 | Elapsed time: 5609.1782310009
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_015_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 16 | Training loss: 5.3027097130393415 | Elapsed time: 5608.50914645195
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_016_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 17 | Training loss: 5.2987160214891915 | Elapsed time: 5609.189682483673
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_017_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 18 | Training loss: 5.295181529648178 | Elapsed time: 5609.2520797252655
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_018_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 19 | Training loss: 5.2975093622426765 | Elapsed time: 5609.4860327243805
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_019_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 20 | Training loss: 5.286686991120909 | Elapsed time: 5610.3333423137665
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_020_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 21 | Training loss: 5.290533660294174 | Elapsed time: 5609.560243368149
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_021_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 22 | Training loss: 5.285777743069918 | Elapsed time: 5609.129464626312
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_022_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 23 | Training loss: 5.282636421996278 | Elapsed time: 5609.90997338295
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_023_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 24 | Training loss: 5.279898757248611 | Elapsed time: 5609.894840478897
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_024_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 25 | Training loss: 5.275894250307645 | Elapsed time: 5609.922780275345
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_025_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 26 | Training loss: 5.273422160324874 | Elapsed time: 5608.922451257706
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_026_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 27 | Training loss: 5.273311212560633 | Elapsed time: 5609.505341529846
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_027_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 28 | Training loss: 5.267515561011407 | Elapsed time: 5609.848466873169
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_028_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
Epoch: 29 | Training loss: 5.2649664964590155 | Elapsed time: 5608.95155954361
Saving model to: /scratch/eo41/visual-recognition-memory/gpt_pretrained_models/model_029_imagenet_GPT_dalet_256b_0.0003lr_Adamo_0s.pt
srun: Job step aborted: Waiting up to 32 seconds for job step to finish.
slurmstepd: error: *** JOB 25928917 ON ga001 CANCELLED AT 2022-10-17T22:21:40 ***
slurmstepd: error: *** STEP 25928917.0 ON ga001 CANCELLED AT 2022-10-17T22:21:40 ***