added keep_best and keep_after to test configs.

This commit is contained in:
gerazov 2021-02-12 11:03:52 +01:00
parent 310d18325e
commit 702dff3edc
6 changed files with 187 additions and 175 deletions

View File

@ -106,6 +106,8 @@
"print_eval": false, // If True, it prints intermediate loss values in evalulation.
"save_step": 5000, // Number of training steps expected to save traninpg stats and checkpoints.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"keep_best": true, // If true, keeps all best_models after keep_after steps
"keep_after": 10000, // Global step after which to keep best models if keep_best is true
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
"apex_amp_level": null,

View File

@ -111,6 +111,8 @@
"print_eval": false, // If True, it prints intermediate loss values in evalulation.
"save_step": 5000, // Number of training steps expected to save traninpg stats and checkpoints.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"keep_best": true, // If true, keeps all best_models after keep_after steps
"keep_after": 10000, // Global step after which to keep best models if keep_best is true
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.:set n
"mixed_precision": false,

View File

@ -122,6 +122,8 @@
"print_eval": false, // If True, it prints intermediate loss values in evalulation.
"save_step": 10000, // Number of training steps expected to save traninpg stats and checkpoints.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"keep_best": true, // If true, keeps all best_models after keep_after steps
"keep_after": 10000, // Global step after which to keep best models if keep_best is true
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
// DATA LOADING

View File

@ -131,6 +131,8 @@
"print_eval": false, // If True, it prints loss values for each step in eval run.
"save_step": 25000, // Number of training steps expected to plot training stats on TB and save model checkpoints.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"keep_best": true, // If true, keeps all best_models after keep_after steps
"keep_after": 10000, // Global step after which to keep best models if keep_best is true
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
// DATA LOADING

View File

@ -101,6 +101,8 @@
"print_eval": false, // If True, it prints loss values for each step in eval run.
"save_step": 10000, // Number of training steps expected to plot training stats on TB and save model checkpoints.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"keep_best": true, // If true, keeps all best_models after keep_after steps
"keep_after": 10000, // Global step after which to keep best models if keep_best is true
"tb_model_param_stats": true, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
// DATA LOADING

View File

@ -97,6 +97,8 @@
"print_eval": false, // If True, it prints loss values for each step in eval run.
"save_step": 25000, // Number of training steps expected to plot training stats on TB and save model checkpoints.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"keep_best": true, // If true, keeps all best_models after keep_after steps
"keep_after": 10000, // Global step after which to keep best models if keep_best is true
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
// DATA LOADING