JuanKO
/

rlhf_reward_model

Text Classification

Inference Endpoints

Model card Files Files and versions Community

rlhf_reward_model / notes.txt

JuanKO's picture

Upload 7 files

f7d66b0 about 1 year ago

history blame contribute delete

84 Bytes

	Dataset size from 10K to 40K samples
	from 5 to 8 epochs
	Lora.Dropout from 0.1 to 0.2