lole25
/

phi-2-dpo-ultrafeedback-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

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

lole25's picture

Model save

37f2f6b verified 9 months ago

195 Bytes

	{
	"epoch": 2.0,
	"train_loss": 0.6680307045922589,
	"train_runtime": 18174.3674,
	"train_samples": 30567,
	"train_samples_per_second": 3.364,
	"train_steps_per_second": 0.052
	}