ZhangShenao
/

SELM-Llama-3-8B-Instruct-iter-1

Text Generation

alignment-handbook

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

SELM-Llama-3-8B-Instruct-iter-1 / train_results.json

ZhangShenao's picture

Model save

f44f70b verified 29 days ago

raw history blame contribute delete

No virus

232 Bytes

	{
	"epoch": 0.9984301412872841,
	"total_flos": 0.0,
	"train_loss": 0.5789602717513558,
	"train_runtime": 4365.2801,
	"train_samples": 20378,
	"train_samples_per_second": 4.668,
	"train_steps_per_second": 0.036
	}