sengi
/

zephyr-7b-pl-qlora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-pl-qlora / all_results.json

sengi's picture

Model save

3073f9b verified 7 months ago

195 Bytes

	{
	"epoch": 0.01,
	"train_loss": 0.6498598456382751,
	"train_runtime": 1109.6734,
	"train_samples": 207865,
	"train_samples_per_second": 1.442,
	"train_steps_per_second": 0.09
	}