pbevan11
/

Mistral-Nemo-MCAI-SFT-DPO

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Mistral-Nemo-MCAI-SFT-DPO / all_results.json

pbevan11's picture

Model save

0736e78 verified 4 months ago

216 Bytes

	{
	"epoch": 1.0,
	"total_flos": 0.0,
	"train_loss": 0.5964088123964976,
	"train_runtime": 1125.1043,
	"train_samples": 3969,
	"train_samples_per_second": 3.528,
	"train_steps_per_second": 0.074
	}