kanishka
/

smolm-autoreg-bpe-counterfactual-babylm-random_removal-1e-4

Text Generation

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

smolm-autoreg-bpe-counterfactual-babylm-random_removal-1e-4 / train_results.json

kanishka's picture

End of training

fbe8702 verified 5 months ago

raw history blame contribute delete

No virus

198 Bytes

	{
	"epoch": 20.0,
	"train_loss": 3.159074606280223,
	"train_runtime": 81093.9235,
	"train_samples": 594739,
	"train_samples_per_second": 146.679,
	"train_steps_per_second": 4.584
	}