lole25
/

phi-2-gpo-ultrachat-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-gpo-ultrachat-lora / train_results.json

lole25's picture

Model save

7912528 verified 4 months ago

raw history blame contribute delete

No virus

195 Bytes

	{
	"epoch": 0.99,
	"train_loss": 0.0001254068662283795,
	"train_runtime": 1151.127,
	"train_samples": 6113,
	"train_samples_per_second": 5.31,
	"train_steps_per_second": 0.083
	}