nnheui
/

pythia-1.4b-dpo-full

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

pythia-1.4b-dpo-full / train_results.json

nnheui's picture

Model save

91aef91 verified 11 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6502101503246783,
	"train_runtime": 8979.6364,
	"train_samples": 61135,
	"train_samples_per_second": 6.808,
	"train_steps_per_second": 0.227
	}