martimfasantos
/

tinyllama-1.1b-chat-dpo-qlora

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

tinyllama-1.1b-chat-dpo-qlora / train_results.json

martimfasantos's picture

Model save

44b1dd3 verified about 2 months ago

raw history blame contribute delete

No virus

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6288731582999011,
	"train_runtime": 37165.2285,
	"train_samples": 61134,
	"train_samples_per_second": 1.645,
	"train_steps_per_second": 0.103
	}