At final checkpoints with approximately matched theoretical cumulative training FLOPs, 67B SST has the lowest reported EMA-200 training LM loss: 1.5900 versus 1.6006 for 47B classic and 1.5921 for 63B classic, improvements of 0.0106 and 0.0021 respectively.

At final checkpoints with approximately matched theoretical cumulative training FLOPs, 67B SST has the lowest reported EMA-200 training LM loss: 1.5900 versus 1.6006 for 47B classic and 1.5921 for 63B classic, improvements of 0.0106 and 0.0021 respectively. · CiteArk

测量结果

已评估 0/12 项

获得支持 0有争议或冲突 0尚未评估 12

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
model: 67B SST · checkpoint: final · training_tokens_billion: 390.54	1.59 loss	—	尚未评估
model: 47B classic · checkpoint: final · training_tokens_billion: 443.16	1.6006 loss	—	尚未评估
model: 63B classic · checkpoint: final · training_tokens_billion: 334.62	1.5921 loss	—	尚未评估
model: 67B SST · comparison: 47B classic	-0.0106 loss	—	尚未评估
model: 67B SST · comparison: 63B classic	-0.0021 loss	—	尚未评估
model: 63B classic · comparison: 47B classic	-0.0085 loss	—	尚未评估
model: 47B classic	443.16 billion tokens	—	尚未评估
model: 63B classic	334.62 billion tokens	—	尚未评估
model: 47B classic	1 fraction of 47B reference	—	尚未评估
model: 63B classic · qualifier: approximately	1 fraction of 47B reference	—	尚未评估
model: 67B SST · qualifier: approximately · includes_source_stage: true	1 fraction of 47B reference	—	尚未评估
model: 47B classic · qualifier: approximately	5,168,360,000,000,000,000,000 FLOPs	—	尚未评估

At final checkpoints with approximately matched theoretical cumulative training FLOPs, 67B SST has the lowest reported EMA-200 training LM loss: 1.5900 versus 1.6006 for 47B classic and 1.5921 for 63B classic, improvements of 0.0106 and 0.0021 respectively.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果