klcsp
/

mistral-7b-0.3-gpt4o_100k_summarize-lora

alignment-handbook

Generated from Trainer

8-bit precision

Model card Files Files and versions Metrics Training metrics Community

mistral-7b-0.3-gpt4o_100k_summarize-lora / eval_results.json

chansung's picture

End of training

815f9b0 verified about 2 months ago

183 Bytes

	{
	"epoch": 1.0,
	"eval_loss": 1.8227200508117676,
	"eval_runtime": 1.5837,
	"eval_samples": 25,
	"eval_samples_per_second": 7.577,
	"eval_steps_per_second": 0.631
	}