onmt.EpochState

Class for managing the training process by logging and storing the state of the current epoch.

[src]

onmt.EpochState(epoch, startIterations, numIterations, learningRate)

Initialize for epoch epoch

[src]

onmt.EpochState:update(model, batch, loss)

Update training status. Takes batch (described in data.lua) and last loss.

[src]

onmt.EpochState:log(iteration)

Log to status stdout.

Undocumented methods

* onmt.EpochState:reset() * onmt.EpochState:getTime()