rsamf
/

g1-walk

Reinforcement Learning

Model card Files Files and versions

g1-walk / metadata.json

rsamf's picture

Update checkpoint (iter 9900)

f3dac84 verified 14 days ago

history blame contribute delete

93 Bytes

	{
	"training_iterations": 9900,
	"total_samples": 5190975488,
	"num_parameters": 3712535
	}