rsamf
/

g1-fight

Reinforcement Learning

Model card Files Files and versions

g1-fight / metadata.json

rsamf's picture

Update checkpoint (iter 8900)

fbef418 verified 5 days ago

history blame contribute delete

93 Bytes

	{
	"training_iterations": 8900,
	"total_samples": 4666687488,
	"num_parameters": 1983104
	}