lole25
/

phi-2-gpo-ultrachat-lora-2

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

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

lole25's picture

Model save

ec33c3e verified 8 months ago

197 Bytes

	{
	"epoch": 2.0,
	"train_loss": 0.008370190804172112,
	"train_runtime": 12459.0229,
	"train_samples": 30567,
	"train_samples_per_second": 4.907,
	"train_steps_per_second": 0.077
	}