MCPcopy Create free account
hub / github.com/Yang-Li-2000/Touch-Line-Transformer / adjust_learning_rate

Function adjust_learning_rate

util/optim.py:28–89  ·  view source on GitHub ↗

Adjust the lr according to the schedule. Args: Optimizer: torch optimizer to update. epoch(int): number of the current epoch. curr_step(int): number of optimization step taken so far. num_training_step(int): total number of optimization steps. args: addit

(
    optimizer,
    epoch: int,
    curr_step: int,
    num_training_steps: int,
    args,
)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

train_one_epochFunction · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected