Minbyul
/

llama2-7b-dpo-full-sft-wo-live_qa

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

llama2-7b-dpo-full-sft-wo-live_qa / train_results.json

Minbyul's picture

Model save

d5d7ad8 verified about 2 months ago

raw history blame contribute delete

No virus

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.4338115497871681,
	"train_runtime": 2557.4167,
	"train_samples": 8634,
	"train_samples_per_second": 3.376,
	"train_steps_per_second": 0.053
	}