Minbyul
/

llama2-7b-dpo-full-wo-live_qa-ep3

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

llama2-7b-dpo-full-wo-live_qa-ep3 / train_results.json

Minbyul's picture

Model save

b820d93 verified 2 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6189163742643414,
	"train_runtime": 2381.9724,
	"train_samples": 10591,
	"train_samples_per_second": 4.446,
	"train_steps_per_second": 0.069
	}