mlxha
/

Qwen-2.5-3B-grpo-code

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Qwen-2.5-3B-grpo-code / train_results.json

mlxha's picture

Model save

d055e09 verified about 1 year ago

202 Bytes

	{
	"total_flos": 0.0,
	"train_loss": 0.001293145966497858,
	"train_runtime": 17459.8588,
	"train_samples": 35735,
	"train_samples_per_second": 0.512,
	"train_steps_per_second": 0.032
	}