Files
Llama-3.1-8B-Instruct-GRPO-…/all_results.json
ModelHub XC 21a81a970c 初始化项目,由ModelHub XC社区提供模型
Model: luckeciano/Llama-3.1-8B-Instruct-GRPO-Base-v2_1346
Source: Original Platform
2026-06-24 19:30:32 +08:00

8 lines
202 B
JSON

{
"total_flos": 0.0,
"train_loss": 2.980232949312267e-11,
"train_runtime": 14681.8696,
"train_samples": 7500,
"train_samples_per_second": 0.545,
"train_steps_per_second": 0.007
}