Files
clarify-rl-grpo-qwen3-1-7b/training_summary.json
ModelHub XC c7810a6963 初始化项目,由ModelHub XC社区提供模型
Model: 2022uec1542/clarify-rl-grpo-qwen3-1-7b
Source: Original Platform
2026-06-16 05:23:17 +08:00

15 lines
615 B
JSON

{
"model": "Qwen/Qwen3-1.7B",
"max_steps": 300,
"num_generations": 8,
"vllm_gpu_memory_utilization": 0.55,
"max_completion_length": 1536,
"train_seconds": 3911.3378353118896,
"stats": "TrainOutput(global_step=300, training_loss=0.18028511427661822, metrics={'train_runtime': 3864.7546, 'train_samples_per_second': 0.621, 'train_steps_per_second': 0.078, 'total_flos': 0.0, 'train_loss': 0.18028511427661822})",
"failed": false,
"failure_reason": "",
"output_dir": "clarify-rl-grpo-qwen3-1-7b",
"trackio_space_id": "clarify-rl-grpo-qwen3-1-7b",
"num_log_entries": 301,
"smoke_test": false
}