YYYYYYibo
/

two_agent_rdpo_iter_2

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

two_agent_rdpo_iter_2 / train_results.json

YYYYYYibo's picture

Model save

8097c02 verified 4 months ago

196 Bytes

	{
	"epoch": 0.99,
	"train_loss": 0.6840069897813734,
	"train_runtime": 41065.6381,
	"train_samples": 20000,
	"train_samples_per_second": 0.487,
	"train_steps_per_second": 0.004
	}