-
ccdd43081d
test(real_bench): use 'swat' (guaranteed absent) for missing-data test
feature/20260629/ts-as-modality
张宗平
2026-07-03 11:53:02 +00:00
-
150e3bd9fd
docs(ts-as-modality): archive after cross-domain generalization failure
张宗平
2026-07-03 11:52:09 +00:00
-
8f644a7470
docs(ts-as-modality): update T5.6 with full-scale retrain results
张宗平
2026-07-01 13:45:14 +00:00
-
cd6209119a
eval(m5): full-scale retrain report — VUS-PR 0.14→0.22, model beats pure_llm
张宗平
2026-07-01 13:44:31 +00:00
-
17ed7947d3
fix(eval): parse_anomaly_segments must tolerate non-numeric junk entries
张宗平
2026-07-01 11:51:50 +00:00
-
77c2ada9b7
fix(train): _latest_step must consider final.pt (avoid re-running finished stage)
张宗平
2026-07-01 10:12:31 +00:00
-
5e3030a20e
feat(train): crash-resilient resume + EMA loss logging (stage1 & stage2)
张宗平
2026-07-01 01:06:15 +00:00
-
1a096ff989
feat(gen): streaming + crash-resilient resume for full-scale data gen
张宗平
2026-06-30 23:48:41 +00:00
-
9b9aa35f13
docs(ts-as-modality): mark M4 (T4.2/T4.3) + M5 (T5.6) done with results
张宗平
2026-06-30 10:03:35 +00:00
-
40ec960cf8
fix(m5): eval pipeline — anomaly_regions schema + nested JSON + pure-LLM baseline
张宗平
2026-06-30 10:02:59 +00:00
-
8aeddebce9
test(m4): instruct_check unit tests + unbuffered training scripts
张宗平
2026-06-30 07:27:03 +00:00
-
76fd636fae
feat(m4/m5): T4.2 instruct-check + QA judge table in eval report
张宗平
2026-06-30 07:24:55 +00:00
-
aecccfab1d
feat(m3): TS-token effectiveness check (T3.3) — change_rate=0.98/50 ≫ 0.5 target
张宗平
2026-06-30 07:14:22 +00:00
-
0723b257fd
fix(m1): _random_window fallback could return end < start
张宗平
2026-06-30 03:22:18 +00:00
-
4c4a8f6435
feat(m5): full eval pipeline — parse/metrics/judge/baselines/report (T5.1-T5.5)
张宗平
2026-06-30 03:18:14 +00:00
-
357e2e60bd
feat(m4): stage 2 SFT training script (LoRA r=16) + smoke (T4.1)
张宗平
2026-06-30 03:11:00 +00:00
-
8286b8276c
chore(ts-as-modality): build checkpoint — M2 done + M3 code done, training decision pending
张宗平
2026-06-30 02:23:27 +00:00
-
bf95ac18e4
feat(m3): stage 1 alignment training script + smoke (T3.2)
张宗平
2026-06-30 02:22:32 +00:00
-
204d5237ba
feat(m3): losses — masked LM CE + symmetric InfoNCE (T3.1)
张宗平
2026-06-30 02:19:02 +00:00
-
133bbac316
chore(ts-as-modality): M2-complete build checkpoint (T2.6 verified)
张宗平
2026-06-30 02:15:57 +00:00
-
7e1df76e3e
feat(m2): Collator — JSONL → wrapper raw batch (T2.5)
张宗平
2026-06-30 02:14:47 +00:00
-
aec8fd5ef1
feat(m2): MultimodalTSModel wrapper — end-to-end fwd/generate + LoRA (T2.4)
张宗平
2026-06-30 02:11:36 +00:00
-
f509d47878
feat(m2): multimodal splice [属性][时间戳][TS tok][事件][问题][回答] (T2.3)
张宗平
2026-06-30 02:05:15 +00:00
-
f20c2db803
feat(m2): Projector Linear(256→896)+LayerNorm (T2.2)
张宗平
2026-06-30 00:17:47 +00:00
-
545802d62c
feat(m2): TS Encoder — Patchify + 2-layer Transformer (T2.1)
张宗平
2026-06-30 00:16:54 +00:00
-
98fb1bfc53
chore(ts-as-modality): M1-complete build checkpoint + resume note
checkpoint/m1-complete
张宗平
2026-06-30 07:57:43 +08:00
-
bbc60f2cdd
test(m1): M1 exit verification (T1.7)
张宗平
2026-06-29 23:31:06 +08:00
-
722102b335
feat(m1): real benchmark loader (T1.6)
张宗平
2026-06-29 23:30:30 +08:00
-
9cfda37275
feat(m1): offline generation pipeline + CLI (T1.5)
张宗平
2026-06-29 23:29:04 +08:00
-
1b4c6ddf4c
feat(m1): instruction & answer generation, 6 categories (T1.4)
张宗平
2026-06-29 23:26:41 +08:00
-
e2c0756a78
feat(m1): synthesis — components + anomaly/event/missing (T1.3)
张宗平
2026-06-29 23:25:08 +08:00
-
6d10454484
feat(m1): attribute vocab + sampling (T1.2)
张宗平
2026-06-29 23:22:40 +08:00
-
748bf41c53
feat(m1): scaffold tsmm package (T1.1)
张宗平
2026-06-29 23:21:47 +08:00
-
c160718934
chore(ts-as-modality): scaffold OpenSpec change & adopt reviewed design
张宗平
2026-06-29 22:29:31 +08:00
-
7a5a1d033f
init version
main
张宗平
2026-06-29 21:16:52 +08:00