Files
SmolLM2-360M-Instruct/eval_results.json
ModelHub XC 10c26b49d2 初始化项目,由ModelHub XC社区提供模型
Model: HuggingFaceTB/SmolLM2-360M-Instruct
Source: Original Platform
2026-05-16 18:29:42 +08:00

16 lines
589 B
JSON

{
"epoch": 1.9973828840617638,
"eval_logits/chosen": -1.6407532691955566,
"eval_logits/rejected": -1.6968854665756226,
"eval_logps/chosen": -375.6463623046875,
"eval_logps/rejected": -323.7197570800781,
"eval_loss": 0.6348475217819214,
"eval_rewards/accuracies": 0.6190476417541504,
"eval_rewards/chosen": -0.034213583916425705,
"eval_rewards/margins": 0.3567626178264618,
"eval_rewards/rejected": -0.3909761905670166,
"eval_runtime": 22.3598,
"eval_samples": 2000,
"eval_samples_per_second": 89.446,
"eval_steps_per_second": 2.818
}