btherien
/

410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_dpo-full

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_dpo-full / train_results.json

btherien's picture

Model save

22385c4 verified 3 months ago

raw history blame contribute delete

No virus

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6625334221861897,
	"train_runtime": 3684.7873,
	"train_samples": 61135,
	"train_samples_per_second": 16.591,
	"train_steps_per_second": 0.129
	}