lole25
/

phi-2-sft-ultrachat-qlora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-sft-ultrachat-qlora / train_results.json

lole25's picture

Model save

f5c22ba verified 9 months ago

196 Bytes

	{
	"epoch": 0.06,
	"train_loss": 1.3271520497798919,
	"train_runtime": 4460.9425,
	"train_samples": 207865,
	"train_samples_per_second": 3.587,
	"train_steps_per_second": 0.112
	}