RFTHyperParameters.Builder |
RFTHyperParameters.Builder.batchSize(Integer batchSize) |
Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training.
|
static RFTHyperParameters.Builder |
RFTHyperParameters.builder() |
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.epochCount(Integer epochCount) |
Number of training epochs to run during reinforcement fine-tuning.
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.evalInterval(Integer evalInterval) |
Interval between evaluation runs during RFT training, measured in training steps.
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.inferenceMaxTokens(Integer inferenceMaxTokens) |
Maximum number of tokens the model can generate in response to each prompt during RFT training.
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.learningRate(Float learningRate) |
Learning rate for the reinforcement fine-tuning.
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.maxPromptLength(Integer maxPromptLength) |
Maximum length of input prompts during RFT training, measured in tokens.
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.reasoningEffort(String reasoningEffort) |
Level of reasoning effort applied during RFT training.
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.reasoningEffort(ReasoningEffort reasoningEffort) |
Level of reasoning effort applied during RFT training.
|
RFTHyperParameters.Builder |
RFTHyperParameters.toBuilder() |
|
RFTHyperParameters.Builder |
RFTHyperParameters.Builder.trainingSamplePerPrompt(Integer trainingSamplePerPrompt) |
Number of response samples generated per prompt during RFT training.
|