<null> | fine_tune_timm Overview – Weights & Biases

Skip to main content

Capecape's group workspace

Group: <null>

3

2

1-2

of 2

Tags

Notes

Author

State

Crashed

Start time

October 2nd, 2024 11:28:49 AM

Sweep

Runtime

0s

Tracked hours

-

Run path

fastai/fine_tune_timm/ywlrrdn1

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 31 keys
- batch per epoch:
  98
- batch size:
  97
- batch_size:
  102
- dataset.tfms:
  "[Pipeline: PILBase.create"
- device:
  "cuda"
- dls.after_batch:
  "'div_mask': 1} -> Normalize -- {'mean': tensor([[[[0.4850]]"
- dls.after_item:
  "'method': 'crop'"
- dls.before_batch:
  "Pipeline: "
- epochs:
  9
- force_torchvision:
  "false"
- frozen:
  "true"
- img_size:
  180
- input 1 dim 1:
  51
- input 1 dim 2:
  3
- input 1 dim 3:
  115
- input 1 dim 4:
  444
- ▶
  Learner:{} 13 keys
- learning_rate:
  0.0017356526135480497
- MixedPrecision:
  "true"
- mixup:
  "false"
- model parameters:
  12,637,757
- model_name:
  "resnet18"
- n_inp:
  1
- num_experiments:
  6
- ParamScheduler:
  "true"
- ProgressCallback:
  "false"
- ▶
  Recorder:{} 3 keys
  - add_time:
    "true"
  - train_metrics:
    "false"
  - valid_metrics:
    "false"
- seed:
  61
- TrainEvalCallback:
  "true"
- wandb_project:
  "fine_tune_timm"
- ▶
  WandbCallback:{} 7 keys

Summary metrics are your model's outputs. Learn more

No summary metrics saved for this run.

Check the summary metrics documentation for more information.