lole25
/

phi-2-ipo-ultrafeedback-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-ipo-ultrafeedback-lora / train_results.json

lole25's picture

Model save

4bd8d55 verified 4 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 2.0,
	"train_loss": 2246.599348344143,
	"train_runtime": 18130.6033,
	"train_samples": 30567,
	"train_samples_per_second": 3.372,
	"train_steps_per_second": 0.053
	}