torchvision | fastai Workspace – Weights & Biases

Skip to main content

Capecape's group workspace

Group: torchvision

16

1-1

of 1

Tags

Notes

Author

State

Finished

Start time

May 6th, 2022 6:12:33 PM

Runtime

1m 50s

Tracked hours

1m 46s

Run path

fastai/fine_tune_timm/2hmuqi0x

OS

Linux-5.4.0-109-generic-x86_64-with-glibc2.31

Python version

3.9.9

Command

/home/paperspace/wandb/fastai_2022/fine_tune.py --num_experiments=5 --force_torchvision

System Hardware

CPU count	8
GPU count	1
GPU type	NVIDIA RTX A6000

W&B CLI Version

0.12.15

Group

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 32 keys
- batch per epoch:
  92
- batch size:
  64
- batch_size:
  64
- dataset.tfms:
  "[Pipeline: PILBase.create, Pipeline: partial -> Categorize -- {'vocab': None, 'sort': True, 'add_na': False}]"
- device:
  "cuda"
- dls.after_batch:
  "Pipeline: IntToFloatTensor -- {'div': 255.0, 'div_mask': 1}"
- dls.after_item:
  "Pipeline: Resize -- {'size': (224, 224), 'method': 'crop', 'pad_mode': 'reflection', 'resamples': (<Resampling.BILINEAR: 2>, 0), 'p': 1.0} -> ToTensor"
- dls.before_batch:
  "Pipeline: "
- epochs:
  5
- force_torchvision:
  true
- frozen:
  false
- frozen idx:
  0
- img_size:
  224
- input 1 dim 1:
  64
- input 1 dim 2:
  3
- input 1 dim 3:
  224
- input 1 dim 4:
  224
- ▶
  Learner:{} 16 keys
- learning_rate:
  0.002
- MixedPrecision:
  true
- mixup:
  false
- model parameters:
  25,633,344
- model_name:
  "resnet50"
- n_inp:
  1
- num_experiments:
  5
- ParamScheduler:
  true
- ProgressCallback:
  true
- ▶
  Recorder:{} 3 keys
  - add_time:
    true
  - train_metrics:
    false
  - valid_metrics:
    true
- seed:
  42
- TrainEvalCallback:
  true
- wandb_project:
  "fine_tune_timm"
- ▶
  WandbCallback:{} 9 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 20 keys
- accuracy:
  0.9154262542724608
- epoch:
  6
- eps_0:
  0.00001
- eps_1:
  0.00001
- eps_2:
  0.00001
- lr_0:
  0.00000000033796749234
- lr_1:
  0.00000000337967492338
- lr_2:
  0.00000003379674923384
- mom_0:
  0.9499976203012797
- mom_1:
  0.9499976203012797
- mom_2:
  0.9499976203012797
- raw_loss:
  0.05997484177350998
- sqr_mom_0:
  0.99
- sqr_mom_1:
  0.99
- sqr_mom_2:
  0.99
- train_loss:
  0.13102661073207855
- valid_loss:
  0.26477867364883423
- wd_0:
  0.01
- wd_1:
  0.01
- wd_2:
  0.01

This run produced these artifacts as outputs. Learn more

run-2hmuqi0x-history:v0

Loading...