lole25
/

phi-2-gpo-ultrachat-lora-0.1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-gpo-ultrachat-lora-0.1 / train_results.json

lole25's picture

Model save

e412c7e verified 4 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 0.99,
	"train_loss": 0.009997876410029437,
	"train_runtime": 1153.3315,
	"train_samples": 6113,
	"train_samples_per_second": 5.3,
	"train_steps_per_second": 0.082
	}