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 / eval_results.json

kanishka's picture

End of training

fbe8702 verified 4 months ago

raw history blame contribute delete

No virus

269 Bytes

	{
	"epoch": 20.0,
	"eval_accuracy": 0.40612524722144594,
	"eval_loss": 3.434004545211792,
	"eval_runtime": 154.4279,
	"eval_samples": 57920,
	"eval_samples_per_second": 375.062,
	"eval_steps_per_second": 5.86,
	"perplexity": 31.000537567186907
	}