第五轮:锁/续跑/超时/自动分支/R4 探针与 encode-once/控制台加固;阶段内断点续跑(gen 按条、prep 按 shard、训练与 APG 定时原子存档+体面停止);分歧以实现方意见为准
This commit is contained in:
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"model": {"d": 128, "heads": 8, "ff": 512, "enc": 4, "dec": 4},
|
||||
"train": {
|
||||
"batch": 1024, "lr": 1e-3, "warmup": 1000, "steps": 60000, "wd": 0.01, "betas": [0.9, 0.95],
|
||||
"amp": "bf16", "grad_clip": 1.0,
|
||||
"w_mf": 1.0, "w_fk": 0.5, "w_smooth": 0.05, "w_value": 0.1, "w_sub": 0.1,
|
||||
"p_neq": 0.25, "fk_caps": 96,
|
||||
"ckpt_min": 10, "eval_every": 2000, "eval_tasks": 512, "log_every": 50, "patience_evals": 5
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user