Files
qwen2.5-7b-instruct-bbq-age…/bbq_behavior_eval.jsonl
ModelHub XC 7629fb335f 初始化项目,由ModelHub XC社区提供模型
Model: NLP-Final-Project/qwen2.5-7b-instruct-bbq-age-sft
Source: Original Platform
2026-06-16 04:05:16 +08:00

7 lines
2.0 KiB
JSON

{"epoch": 0.0, "global_step": 0, "metrics": {"ambig": {"accuracy": 58.15, "bias_score": 21.2, "raw_bias_score": 50.65, "n": 368, "non_unknown": 154, "unknown_count": 214, "unknown_rate": 58.15}, "overall": {"accuracy": 58.15, "bias_score": 50.65, "raw_bias_score": 50.65, "n": 368, "non_unknown": 154, "unknown_count": 214, "unknown_rate": 58.15}}}
{"epoch": 1.0, "global_step": 92, "metrics": {"ambig": {"accuracy": 90.49, "bias_score": 4.08, "raw_bias_score": 42.86, "n": 368, "non_unknown": 35, "unknown_count": 333, "unknown_rate": 90.49}, "overall": {"accuracy": 90.49, "bias_score": 42.86, "raw_bias_score": 42.86, "n": 368, "non_unknown": 35, "unknown_count": 333, "unknown_rate": 90.49}}}
{"epoch": 2.0, "global_step": 184, "metrics": {"ambig": {"accuracy": 90.76, "bias_score": 3.8, "raw_bias_score": 41.18, "n": 368, "non_unknown": 34, "unknown_count": 334, "unknown_rate": 90.76}, "overall": {"accuracy": 90.76, "bias_score": 41.18, "raw_bias_score": 41.18, "n": 368, "non_unknown": 34, "unknown_count": 334, "unknown_rate": 90.76}}}
{"epoch": 3.0, "global_step": 276, "metrics": {"ambig": {"accuracy": 90.76, "bias_score": 3.8, "raw_bias_score": 41.18, "n": 368, "non_unknown": 34, "unknown_count": 334, "unknown_rate": 90.76}, "overall": {"accuracy": 90.76, "bias_score": 41.18, "raw_bias_score": 41.18, "n": 368, "non_unknown": 34, "unknown_count": 334, "unknown_rate": 90.76}}}
{"epoch": 4.0, "global_step": 368, "metrics": {"ambig": {"accuracy": 90.49, "bias_score": 4.08, "raw_bias_score": 42.86, "n": 368, "non_unknown": 35, "unknown_count": 333, "unknown_rate": 90.49}, "overall": {"accuracy": 90.49, "bias_score": 42.86, "raw_bias_score": 42.86, "n": 368, "non_unknown": 35, "unknown_count": 333, "unknown_rate": 90.49}}}
{"epoch": 5.0, "global_step": 460, "metrics": {"ambig": {"accuracy": 90.76, "bias_score": 3.8, "raw_bias_score": 41.18, "n": 368, "non_unknown": 34, "unknown_count": 334, "unknown_rate": 90.76}, "overall": {"accuracy": 90.76, "bias_score": 41.18, "raw_bias_score": 41.18, "n": 368, "non_unknown": 34, "unknown_count": 334, "unknown_rate": 90.76}}}