Minbyul
/

llama2-7b-dpo-full-wo-medication_qa-ep3

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

llama2-7b-dpo-full-wo-medication_qa-ep3 / all_results.json

Minbyul's picture

Model save

ddc112f verified 7 months ago

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6277184326883772,
	"train_runtime": 2301.3874,
	"train_samples": 9071,
	"train_samples_per_second": 3.942,
	"train_steps_per_second": 0.062
	}