Files
clarify-rl-grpo-qwen3-0-6b/training_summary.json
ModelHub XC 7bf4b0f98e 初始化项目,由ModelHub XC社区提供模型
Model: agarwalanu3103/clarify-rl-grpo-qwen3-0-6b
Source: Original Platform
2026-07-19 02:19:25 +08:00

15 lines
614 B
JSON

{
"model": "Qwen/Qwen3-0.6B",
"max_steps": 300,
"num_generations": 8,
"vllm_gpu_memory_utilization": 0.55,
"max_completion_length": 1536,
"train_seconds": 2302.196548461914,
"stats": "TrainOutput(global_step=300, training_loss=0.20039798735951384, metrics={'train_runtime': 2281.1679, 'train_samples_per_second': 1.052, 'train_steps_per_second': 0.132, 'total_flos': 0.0, 'train_loss': 0.20039798735951384})",
"failed": false,
"failure_reason": "",
"output_dir": "clarify-rl-grpo-qwen3-0-6b",
"trackio_space_id": "clarify-rl-grpo-qwen3-0-6b",
"num_log_entries": 301,
"smoke_test": false
}