From b7856ece4d695704d05861732f5b94a5f099486e Mon Sep 17 00:00:00 2001 From: Xin Wang Date: Mon, 24 Aug 2026 12:02:49 +0800 Subject: [PATCH] Archive EasyCom sparse supervision results --- README.md | 10 ++ .../README.md | 80 ++++++++++++++++ .../metrics.csv | 41 ++++++++ .../raw_8s_console.txt | 45 +++++++++ .../summary.json | 76 +++++++++++++++ .../README.md | 94 +++++++++++++++++++ .../metrics.csv | 41 ++++++++ .../summary.json | 43 +++++++++ 8 files changed, 430 insertions(+) create mode 100644 results/easycom_open_stream_8s_vs_20s_2026-08-23/README.md create mode 100644 results/easycom_open_stream_8s_vs_20s_2026-08-23/metrics.csv create mode 100644 results/easycom_open_stream_8s_vs_20s_2026-08-23/raw_8s_console.txt create mode 100644 results/easycom_open_stream_8s_vs_20s_2026-08-23/summary.json create mode 100644 results/easycom_sparse_supervision_vs_lora_2026-08-24/README.md create mode 100644 results/easycom_sparse_supervision_vs_lora_2026-08-24/metrics.csv create mode 100644 results/easycom_sparse_supervision_vs_lora_2026-08-24/summary.json diff --git a/README.md b/README.md index a6f4d27..6fe665c 100644 --- a/README.md +++ b/README.md @@ -1241,7 +1241,9 @@ sparse LoRA recipe: | Checkpoint | Full-timeline mean mAP | Strict causal mean mAP | |---|---:|---:| | Frozen Thinker dense-cache control | 58.16091 | 58.17146 | +| Frozen states + sparse supervision, 50 epochs | 57.20379 | 57.21367 | | Sparse LoRA epoch1 | 56.52480 | 56.53450 | +| Frozen-head initialized LoRA, 3 epochs | 56.19608 | 56.20535 | | Sparse LoRA weights-only epoch2 | 54.19850 | 54.20711 | Epoch2 is a weights-only continuation: adapter/head weights resume, but AdamW @@ -1251,6 +1253,14 @@ regression is camera-wearer speaking. Do not continue the same recipe to a third run. The complete snapshot and per-class metrics are archived in [`results/easycom_omni_lora_sparse_epoch2_2026-08-24/`](results/easycom_omni_lora_sparse_epoch2_2026-08-24/). +The frozen-state sparse-supervision and frozen-head initialized three-epoch +LoRA tables are archived in +[`results/easycom_sparse_supervision_vs_lora_2026-08-24/`](results/easycom_sparse_supervision_vs_lora_2026-08-24/README.md). +At 0.2 seconds, sparse supervision alone changes mAP from `71.69695` to +`71.69194` (effectively unchanged), while the three-epoch LoRA result is +`71.08589`. This isolates the short-horizon regression primarily to Thinker +updating rather than sparse target selection. + For a speed-only alternative, `train_omni_turn_lora.py` supports a two-GPU producer-consumer benchmark. The producer GPU runs the frozen AV towers and places current-tail embeddings in a bounded CPU queue while the consumer GPU diff --git a/results/easycom_open_stream_8s_vs_20s_2026-08-23/README.md b/results/easycom_open_stream_8s_vs_20s_2026-08-23/README.md new file mode 100644 index 0000000..9046fe5 --- /dev/null +++ b/results/easycom_open_stream_8s_vs_20s_2026-08-23/README.md @@ -0,0 +1,80 @@ +# EasyCom open-stream context: 8 seconds versus 20 seconds + +Recorded on **2026-08-23**. This is a single-run experiment snapshot, not a +final multi-seed paper result. + +## Experiment contract + +- Dataset: EasyCom with EgoSpeak's official split. +- Train sessions: 7, 11, 10, 6, 9, 4, 8, 5, and 12. +- Test sessions: 3, 2, and 1. +- Representation: frozen Qwen2.5-Omni-3B Thinker, open-stream replay. +- Head: MLP `2048 -> 1024 -> 30`, reshaped to `10 x 3`. +- Video sampling: 2 FPS. +- Prediction rate: 5 Hz. +- Context budgets: 8 seconds and 20 seconds. +- Targets: ten future horizons from 0.2 through 2.0 seconds. +- Loss/evaluation: EgoSpeak LSTR MCE and Table 2 frame AP/mAP protocol. + +The heads were trained separately for their corresponding representations. A +head trained on the 20-second states was not reused on the 8-second states. + +## Summary + +All values are percentages. + +| Protocol | 8 seconds | 20 seconds | 8s minus 20s | +|---|---:|---:|---:| +| EgoSpeak full timeline | **58.51937** | 58.316 | **+0.20337** | +| Strict causal valid only | **58.53015** | 58.326 | **+0.20415** | + +The full-timeline per-horizon comparison is: + +| Horizon | Time | 8s mAP | 20s mAP | 8s minus 20s | +|---:|---:|---:|---:|---:| +| 1 | 0.2s | **71.99768** | 69.756 | **+2.24168** | +| 2 | 0.4s | **66.74289** | 65.163 | **+1.57989** | +| 3 | 0.6s | **62.38972** | 61.578 | **+0.81172** | +| 4 | 0.8s | **59.12229** | 58.783 | **+0.33929** | +| 5 | 1.0s | 56.71380 | **56.913** | -0.19920 | +| 6 | 1.2s | 55.36300 | **55.727** | -0.36400 | +| 7 | 1.4s | 54.21297 | **54.819** | -0.60603 | +| 8 | 1.6s | 53.43221 | **53.957** | -0.52479 | +| 9 | 1.8s | 52.84703 | **53.459** | -0.61197 | +| 10 | 2.0s | 52.37207 | **53.002** | -0.62993 | +| Mean | — | **58.51937** | 58.316 | **+0.20337** | + +For the full-timeline protocol, averaging AP over the ten horizons gives: + +| Class | 8s mean AP | 20s mean AP | 8s minus 20s | +|---|---:|---:|---:| +| Background | 39.63094 | **40.49350** | -0.86256 | +| Camera wearer speaking | **58.91206** | 58.59400 | +0.31806 | +| Other people speaking | **77.01510** | 75.85970 | +1.15540 | + +## Interpretation + +The aggregate 8-second advantage is only 0.20 mAP, but it is not distributed +uniformly. The 8-second representation is substantially stronger at 0.2--0.6 +seconds, while the 20-second representation becomes stronger from 1.0 seconds +onward. This looks like a short/long-horizon tradeoff rather than evidence that +one context budget is uniformly better. + +The class pattern is also mixed: 8 seconds improves the two speaking classes, +especially other-person speech, but reduces background AP. Because the heads +were trained once and the aggregate difference is small, training variance +could plausibly reverse the mean comparison. Identical multi-seed runs are +required before selecting the context budget for the paper. + +## Files and provenance + +- `raw_8s_console.txt` preserves the reported 8-second console output. +- `metrics.csv` contains both contexts, protocols, horizons, and classes. +- `summary.json` contains the machine-readable aggregate comparison. +- The 20-second values come from the previously archived + `easycom_open_stream_vs_causal_prefix_2026-08-19` snapshot and therefore + have only three-decimal precision. +- Aggregate differences use the separately reported aggregate means. Averaging + differences reconstructed from the rounded 20-second horizon rows can vary + slightly from those aggregate differences. +- The original remote `metrics.json` files have not yet been copied here. diff --git a/results/easycom_open_stream_8s_vs_20s_2026-08-23/metrics.csv b/results/easycom_open_stream_8s_vs_20s_2026-08-23/metrics.csv new file mode 100644 index 0000000..b16a28d --- /dev/null +++ b/results/easycom_open_stream_8s_vs_20s_2026-08-23/metrics.csv @@ -0,0 +1,41 @@ +context_seconds,protocol,horizon,seconds,background_ap_percent,camera_wearer_ap_percent,other_people_ap_percent,map_percent,num_steps +8,egospeak_full_timeline,1,0.2,54.84736,76.45639,84.68928,71.99768,23048 +8,egospeak_full_timeline,2,0.4,47.46373,71.02340,81.74154,66.74289,23048 +8,egospeak_full_timeline,3,0.6,42.19659,65.57303,79.39953,62.38972,23048 +8,egospeak_full_timeline,4,0.8,38.81557,60.96834,77.58298,59.12229,23048 +8,egospeak_full_timeline,5,1.0,36.79821,57.21128,76.13193,56.71380,23048 +8,egospeak_full_timeline,6,1.2,36.09944,54.87811,75.11144,55.36300,23048 +8,egospeak_full_timeline,7,1.4,35.41214,52.71169,74.51507,54.21297,23048 +8,egospeak_full_timeline,8,1.6,35.15599,51.16932,73.97133,53.43221,23048 +8,egospeak_full_timeline,9,1.8,34.85984,50.01901,73.66226,52.84703,23048 +8,egospeak_full_timeline,10,2.0,34.66053,49.11007,73.34560,52.37207,23048 +8,causal_valid_only,1,0.2,54.84736,76.45639,84.69504,71.99960,23045 +8,causal_valid_only,2,0.4,47.46373,71.02340,81.75175,66.74630,23042 +8,causal_valid_only,3,0.6,42.19659,65.57933,79.41330,62.39641,23039 +8,causal_valid_only,4,0.8,38.81557,60.97945,77.59974,59.13158,23036 +8,causal_valid_only,5,1.0,36.79821,57.22612,76.15127,56.72520,23033 +8,causal_valid_only,6,1.2,36.09944,54.89639,75.13207,55.37597,23030 +8,causal_valid_only,7,1.4,35.41214,52.73278,74.53730,54.22741,23027 +8,causal_valid_only,8,1.6,35.15831,51.18915,73.99506,53.44751,23024 +8,causal_valid_only,9,1.8,34.86210,50.03791,73.68883,52.86295,23021 +8,causal_valid_only,10,2.0,34.66276,49.12823,73.37487,52.38862,23018 +20,egospeak_full_timeline,1,0.2,53.605,74.331,81.331,69.756,23048 +20,egospeak_full_timeline,2,0.4,47.066,69.402,79.020,65.163,23048 +20,egospeak_full_timeline,3,0.6,42.615,64.600,77.520,61.578,23048 +20,egospeak_full_timeline,4,0.8,39.463,60.641,76.244,58.783,23048 +20,egospeak_full_timeline,5,1.0,38.002,57.371,75.367,56.913,23048 +20,egospeak_full_timeline,6,1.2,37.398,55.258,74.523,55.727,23048 +20,egospeak_full_timeline,7,1.4,36.933,53.400,74.126,54.819,23048 +20,egospeak_full_timeline,8,1.6,36.653,51.502,73.716,53.957,23048 +20,egospeak_full_timeline,9,1.8,36.527,50.346,73.504,53.459,23048 +20,egospeak_full_timeline,10,2.0,36.673,49.089,73.246,53.002,23048 +20,causal_valid_only,1,0.2,53.605,74.331,81.336,69.757,23045 +20,causal_valid_only,2,0.4,47.066,69.402,79.029,65.166,23042 +20,causal_valid_only,3,0.6,42.615,64.607,77.532,61.585,23039 +20,causal_valid_only,4,0.8,39.463,60.652,76.259,58.792,23036 +20,causal_valid_only,5,1.0,38.002,57.386,75.385,56.924,23033 +20,causal_valid_only,6,1.2,37.398,55.277,74.543,55.739,23030 +20,causal_valid_only,7,1.4,36.933,53.421,74.148,54.834,23027 +20,causal_valid_only,8,1.6,36.656,51.522,73.740,53.973,23024 +20,causal_valid_only,9,1.8,36.529,50.365,73.530,53.475,23021 +20,causal_valid_only,10,2.0,36.676,49.107,73.275,53.019,23018 diff --git a/results/easycom_open_stream_8s_vs_20s_2026-08-23/raw_8s_console.txt b/results/easycom_open_stream_8s_vs_20s_2026-08-23/raw_8s_console.txt new file mode 100644 index 0000000..c8e930e --- /dev/null +++ b/results/easycom_open_stream_8s_vs_20s_2026-08-23/raw_8s_console.txt @@ -0,0 +1,45 @@ +egospeak_full_timeline: +Action anticipation (0.20s) perframe mAP: 71.99768 + AP: background=54.84736, camera_wearer_speaking=76.45639, other_people_speaking=84.68928; n=23048 +Action anticipation (0.40s) perframe mAP: 66.74289 + AP: background=47.46373, camera_wearer_speaking=71.02340, other_people_speaking=81.74154; n=23048 +Action anticipation (0.60s) perframe mAP: 62.38972 + AP: background=42.19659, camera_wearer_speaking=65.57303, other_people_speaking=79.39953; n=23048 +Action anticipation (0.80s) perframe mAP: 59.12229 + AP: background=38.81557, camera_wearer_speaking=60.96834, other_people_speaking=77.58298; n=23048 +Action anticipation (1.00s) perframe mAP: 56.71380 + AP: background=36.79821, camera_wearer_speaking=57.21128, other_people_speaking=76.13193; n=23048 +Action anticipation (1.20s) perframe mAP: 55.36300 + AP: background=36.09944, camera_wearer_speaking=54.87811, other_people_speaking=75.11144; n=23048 +Action anticipation (1.40s) perframe mAP: 54.21297 + AP: background=35.41214, camera_wearer_speaking=52.71169, other_people_speaking=74.51507; n=23048 +Action anticipation (1.60s) perframe mAP: 53.43221 + AP: background=35.15599, camera_wearer_speaking=51.16932, other_people_speaking=73.97133; n=23048 +Action anticipation (1.80s) perframe mAP: 52.84703 + AP: background=34.85984, camera_wearer_speaking=50.01901, other_people_speaking=73.66226; n=23048 +Action anticipation (2.00s) perframe mAP: 52.37207 + AP: background=34.66053, camera_wearer_speaking=49.11007, other_people_speaking=73.34560; n=23048 +Action anticipation (mean) perframe mAP: 58.51937 + +causal_valid_only: +Action anticipation (0.20s) perframe mAP: 71.99960 + AP: background=54.84736, camera_wearer_speaking=76.45639, other_people_speaking=84.69504; n=23045 +Action anticipation (0.40s) perframe mAP: 66.74630 + AP: background=47.46373, camera_wearer_speaking=71.02340, other_people_speaking=81.75175; n=23042 +Action anticipation (0.60s) perframe mAP: 62.39641 + AP: background=42.19659, camera_wearer_speaking=65.57933, other_people_speaking=79.41330; n=23039 +Action anticipation (0.80s) perframe mAP: 59.13158 + AP: background=38.81557, camera_wearer_speaking=60.97945, other_people_speaking=77.59974; n=23036 +Action anticipation (1.00s) perframe mAP: 56.72520 + AP: background=36.79821, camera_wearer_speaking=57.22612, other_people_speaking=76.15127; n=23033 +Action anticipation (1.20s) perframe mAP: 55.37597 + AP: background=36.09944, camera_wearer_speaking=54.89639, other_people_speaking=75.13207; n=23030 +Action anticipation (1.40s) perframe mAP: 54.22741 + AP: background=35.41214, camera_wearer_speaking=52.73278, other_people_speaking=74.53730; n=23027 +Action anticipation (1.60s) perframe mAP: 53.44751 + AP: background=35.15831, camera_wearer_speaking=51.18915, other_people_speaking=73.99506; n=23024 +Action anticipation (1.80s) perframe mAP: 52.86295 + AP: background=34.86210, camera_wearer_speaking=50.03791, other_people_speaking=73.68883; n=23021 +Action anticipation (2.00s) perframe mAP: 52.38862 + AP: background=34.66276, camera_wearer_speaking=49.12823, other_people_speaking=73.37487; n=23018 +Action anticipation (mean) perframe mAP: 58.53015 diff --git a/results/easycom_open_stream_8s_vs_20s_2026-08-23/summary.json b/results/easycom_open_stream_8s_vs_20s_2026-08-23/summary.json new file mode 100644 index 0000000..5094d81 --- /dev/null +++ b/results/easycom_open_stream_8s_vs_20s_2026-08-23/summary.json @@ -0,0 +1,76 @@ +{ + "schema_version": 1, + "recorded_date": "2026-08-23", + "status": "single_run_snapshot", + "dataset": "EasyCom", + "representation": "Qwen2.5-Omni-3B open-stream replay", + "video_fps": 2, + "prediction_step_seconds": 0.2, + "split": { + "train_sessions": [7, 11, 10, 6, 9, 4, 8, 5, 12], + "test_sessions": [3, 2, 1] + }, + "metrics_percent": { + "8_seconds": { + "egospeak_full_timeline_mean_map": 58.51937, + "causal_valid_only_mean_map": 58.53015, + "egospeak_full_timeline_horizon_map": [ + 71.99768, + 66.74289, + 62.38972, + 59.12229, + 56.71380, + 55.36300, + 54.21297, + 53.43221, + 52.84703, + 52.37207 + ] + }, + "20_seconds": { + "egospeak_full_timeline_mean_map": 58.316, + "causal_valid_only_mean_map": 58.326, + "egospeak_full_timeline_horizon_map": [ + 69.756, + 65.163, + 61.578, + 58.783, + 56.913, + 55.727, + 54.819, + 53.957, + 53.459, + 53.002 + ] + }, + "8_seconds_minus_20_seconds": { + "egospeak_full_timeline_mean_map": 0.20337, + "causal_valid_only_mean_map": 0.20415, + "egospeak_full_timeline_horizon_map": [ + 2.24168, + 1.57989, + 0.81172, + 0.33929, + -0.19920, + -0.36400, + -0.60603, + -0.52479, + -0.61197, + -0.62993 + ], + "egospeak_full_timeline_mean_class_ap": { + "background": -0.86256, + "camera_wearer_speaking": 0.31806, + "other_people_speaking": 1.15540 + } + } + }, + "provenance": { + "8_seconds": "User-reported infer_turn_head.py console output; preserved in raw_8s_console.txt", + "20_seconds": "Previously archived 2026-08-19 open-stream snapshot; values available to three decimals", + "precision_note": "Aggregate differences use the separately reported aggregate means. Per-horizon and per-class differences use the available row values and can differ slightly when averaged because the archived 20-second rows were rounded to three decimals.", + "raw_8_seconds_metrics_json_archived_here": false, + "raw_20_seconds_metrics_json_archived_here": false, + "multi_seed": false + } +} diff --git a/results/easycom_sparse_supervision_vs_lora_2026-08-24/README.md b/results/easycom_sparse_supervision_vs_lora_2026-08-24/README.md new file mode 100644 index 0000000..33e23a1 --- /dev/null +++ b/results/easycom_sparse_supervision_vs_lora_2026-08-24/README.md @@ -0,0 +1,94 @@ +# EasyCom: sparse supervision versus Thinker LoRA + +Recorded on **2026-08-24** from user-reported remote evaluation tables. These +are single-run diagnostic results, not final multi-seed paper numbers. + +## Experiment contract + +- Dataset and split: EasyCom with EgoSpeak's official nine training sessions + and test Sessions 3, 2, and 1. +- Prediction rate: 5 Hz; ten future horizons from 0.2 to 2.0 seconds. +- Video sampling: 2 FPS. +- Evaluator: EgoSpeak full-timeline AP/mAP plus strict causal-valid AP/mAP. +- Sparse policy: ordinary anchors at 1 Hz plus 5 Hz anchors around annotated + target transitions. +- Evaluation is dense at every 5 Hz test timestamp. +- Frozen sparse run: previously extracted frozen Thinker states; only the head + is trained for 50 epochs on sparse target indices. +- LoRA three-epoch run: initialized with the trained frozen head, then updated + the Thinker LoRA and head for three epochs. + +The remote `metrics.json`, exact checkpoint configuration, git revision, and +feature-root path were not copied into this repository. The context/feature +identity with the frozen 8-second control must therefore be verified before +publication. + +## Summary + +All values are percentages. + +| Experiment | 0.2s full mAP | Full mean mAP | Strict mean mAP | +|---|---:|---:|---:| +| Frozen Thinker dense-cache control | 71.69695 | 58.16091 | 58.17146 | +| Frozen states + sparse supervision, 50 epochs | **71.69194** | **57.20379** | **57.21367** | +| Sparse LoRA epoch 1 | 67.40167 | 56.52480 | 56.53450 | +| Frozen-head initialized LoRA, 3 epochs | **71.08589** | **56.19608** | **56.20535** | +| Sparse LoRA weights-only epoch 2 | 65.55214 | 54.19850 | 54.20711 | + +The epoch-2 continuation is archived separately in +[`../easycom_omni_lora_sparse_epoch2_2026-08-24/`](../easycom_omni_lora_sparse_epoch2_2026-08-24/README.md). + +## Frozen states with sparse supervision + +| Horizon | Full mAP | Strict mAP | Full background AP | Full wearer AP | Full others AP | +|---:|---:|---:|---:|---:|---:| +| 0.2s | 71.69194 | 71.69383 | 54.64681 | 76.09602 | 84.33299 | +| 0.4s | 65.98617 | 65.98941 | 46.86427 | 70.48309 | 80.61116 | +| 0.6s | 61.14072 | 61.14698 | 41.30997 | 64.40092 | 77.71127 | +| 0.8s | 57.39854 | 57.40704 | 37.50173 | 59.07507 | 75.61882 | +| 1.0s | 54.57513 | 54.58522 | 35.47209 | 54.41110 | 73.84220 | +| 1.2s | 53.70320 | 53.71497 | 35.16647 | 52.41903 | 73.52409 | +| 1.4s | 52.74547 | 52.75864 | 34.64200 | 50.53203 | 73.06238 | +| 1.6s | 52.04826 | 52.06226 | 34.36442 | 49.18784 | 72.59253 | +| 1.8s | 51.55154 | 51.56613 | 34.13135 | 48.17972 | 72.34356 | +| 2.0s | 51.19693 | 51.21218 | 33.99937 | 47.47712 | 72.11430 | +| Mean | **57.20379** | **57.21367** | — | — | — | + +## Frozen-head initialized LoRA after three epochs + +| Horizon | Full mAP | Strict mAP | Full background AP | Full wearer AP | Full others AP | +|---:|---:|---:|---:|---:|---:| +| 0.2s | 71.08589 | 71.08773 | 53.71399 | 75.95995 | 83.58373 | +| 0.4s | 65.20613 | 65.20927 | 46.04420 | 69.65188 | 79.92232 | +| 0.6s | 60.10484 | 60.11088 | 40.44134 | 62.71065 | 77.16253 | +| 0.8s | 56.35250 | 56.36069 | 36.98112 | 56.61255 | 75.46383 | +| 1.0s | 53.48271 | 53.49230 | 35.10974 | 51.63824 | 73.70016 | +| 1.2s | 52.50271 | 52.51364 | 34.83634 | 49.81663 | 72.85516 | +| 1.4s | 51.46987 | 51.48201 | 34.06639 | 48.01675 | 72.32646 | +| 1.6s | 50.91134 | 50.92429 | 34.04663 | 46.85967 | 71.82772 | +| 1.8s | 50.54008 | 50.55369 | 33.82003 | 46.15156 | 71.64864 | +| 2.0s | 50.30475 | 50.31903 | 33.74069 | 45.80527 | 71.36829 | +| Mean | **56.19608** | **56.20535** | — | — | — | + +## 0.2-second diagnosis + +Sparse supervision alone changes 0.2-second full-timeline mAP by only +`-0.00501` relative to the frozen dense-cache control. The three-epoch LoRA +run changes it by `-0.61106`. The much larger epoch-1 and weights-only epoch-2 +regressions show that short-horizon degradation is primarily associated with +updating the Thinker representation, not with dropping ordinary supervision +anchors. + +The next required control is a 2-by-2 checkpoint evaluation: frozen Thinker +with frozen head, frozen Thinker with LoRA-trained head, LoRA Thinker with +frozen head, and LoRA Thinker with LoRA-trained head. Select LoRA checkpoints +on a training-session development split using 0.2-second mAP rather than the +official test sessions. + +## Provenance + +- Source: user-reported remote `infer_turn_head.py` and + `eval_omni_turn_lora.py` console tables. +- Raw remote metrics archived: no. +- Multi-seed: no. +- Publication status: diagnostic only. diff --git a/results/easycom_sparse_supervision_vs_lora_2026-08-24/metrics.csv b/results/easycom_sparse_supervision_vs_lora_2026-08-24/metrics.csv new file mode 100644 index 0000000..7307fbe --- /dev/null +++ b/results/easycom_sparse_supervision_vs_lora_2026-08-24/metrics.csv @@ -0,0 +1,41 @@ +experiment,protocol,horizon_seconds,map,background_ap,camera_wearer_speaking_ap,other_people_speaking_ap,num_steps +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,0.2,71.69194,54.64681,76.09602,84.33299,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,0.4,65.98617,46.86427,70.48309,80.61116,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,0.6,61.14072,41.30997,64.40092,77.71127,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,0.8,57.39854,37.50173,59.07507,75.61882,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,1.0,54.57513,35.47209,54.41110,73.84220,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,1.2,53.70320,35.16647,52.41903,73.52409,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,1.4,52.74547,34.64200,50.53203,73.06238,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,1.6,52.04826,34.36442,49.18784,72.59253,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,1.8,51.55154,34.13135,48.17972,72.34356,23048 +frozen_states_sparse_supervision_50_epochs,egospeak_full_timeline,2.0,51.19693,33.99937,47.47712,72.11430,23048 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,0.2,71.69383,54.64681,76.09602,84.33868,23045 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,0.4,65.98941,46.86427,70.48309,80.62088,23042 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,0.6,61.14698,41.30997,64.40704,77.72392,23039 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,0.8,57.40704,37.50173,59.08557,75.63383,23036 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,1.0,54.58522,35.47209,54.42458,73.85900,23033 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,1.2,53.71497,35.16647,52.43571,73.54273,23030 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,1.4,52.75864,34.64200,50.55135,73.08256,23027 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,1.6,52.06226,34.36659,49.20607,72.61411,23024 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,1.8,51.56613,34.13348,48.19712,72.36779,23021 +frozen_states_sparse_supervision_50_epochs,causal_valid_only,2.0,51.21218,34.00148,47.49396,72.14111,23018 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,0.2,71.08589,53.71399,75.95995,83.58373,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,0.4,65.20613,46.04420,69.65188,79.92232,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,0.6,60.10484,40.44134,62.71065,77.16253,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,0.8,56.35250,36.98112,56.61255,75.46383,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,1.0,53.48271,35.10974,51.63824,73.70016,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,1.2,52.50271,34.83634,49.81663,72.85516,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,1.4,51.46987,34.06639,48.01675,72.32646,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,1.6,50.91134,34.04663,46.85967,71.82772,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,1.8,50.54008,33.82003,46.15156,71.64864,23048 +frozen_head_initialized_lora_3_epochs,egospeak_full_timeline,2.0,50.30475,33.74069,45.80527,71.36829,23048 +frozen_head_initialized_lora_3_epochs,causal_valid_only,0.2,71.08773,53.71399,75.95995,83.58924,23045 +frozen_head_initialized_lora_3_epochs,causal_valid_only,0.4,65.20927,46.04420,69.65188,79.93173,23042 +frozen_head_initialized_lora_3_epochs,causal_valid_only,0.6,60.11088,40.44134,62.71649,77.17481,23039 +frozen_head_initialized_lora_3_epochs,causal_valid_only,0.8,56.36069,36.98112,56.62225,75.47870,23036 +frozen_head_initialized_lora_3_epochs,causal_valid_only,1.0,53.49230,35.10974,51.65037,73.71680,23033 +frozen_head_initialized_lora_3_epochs,causal_valid_only,1.2,52.51364,34.83634,49.83161,72.87296,23030 +frozen_head_initialized_lora_3_epochs,causal_valid_only,1.4,51.48201,34.06639,48.03402,72.34561,23027 +frozen_head_initialized_lora_3_epochs,causal_valid_only,1.6,50.92429,34.04874,46.87600,71.84812,23024 +frozen_head_initialized_lora_3_epochs,causal_valid_only,1.8,50.55369,33.82210,46.16732,71.67164,23021 +frozen_head_initialized_lora_3_epochs,causal_valid_only,2.0,50.31903,33.74274,45.82075,71.39361,23018 diff --git a/results/easycom_sparse_supervision_vs_lora_2026-08-24/summary.json b/results/easycom_sparse_supervision_vs_lora_2026-08-24/summary.json new file mode 100644 index 0000000..9970fbe --- /dev/null +++ b/results/easycom_sparse_supervision_vs_lora_2026-08-24/summary.json @@ -0,0 +1,43 @@ +{ + "schema_version": 1, + "recorded_date": "2026-08-24", + "status": "single_run_diagnostic_snapshot", + "dataset": "EasyCom", + "prediction_step_seconds": 0.2, + "video_fps": 2, + "metrics_percent": { + "frozen_dense_cache_control": { + "full_timeline_horizon_0.2_map": 71.69695, + "full_timeline_mean_map": 58.16091, + "causal_valid_mean_map": 58.17146 + }, + "frozen_states_sparse_supervision_50_epochs": { + "full_timeline_mean_map": 57.20379, + "causal_valid_mean_map": 57.21367, + "full_timeline_horizon_map": [71.69194, 65.98617, 61.14072, 57.39854, 54.57513, 53.70320, 52.74547, 52.04826, 51.55154, 51.19693], + "causal_valid_horizon_map": [71.69383, 65.98941, 61.14698, 57.40704, 54.58522, 53.71497, 52.75864, 52.06226, 51.56613, 51.21218] + }, + "sparse_lora_epoch1": { + "full_timeline_horizon_0.2_map": 67.40167, + "full_timeline_mean_map": 56.52480, + "causal_valid_mean_map": 56.53450 + }, + "frozen_head_initialized_lora_3_epochs": { + "full_timeline_mean_map": 56.19608, + "causal_valid_mean_map": 56.20535, + "full_timeline_horizon_map": [71.08589, 65.20613, 60.10484, 56.35250, 53.48271, 52.50271, 51.46987, 50.91134, 50.54008, 50.30475], + "causal_valid_horizon_map": [71.08773, 65.20927, 60.11088, 56.36069, 53.49230, 52.51364, 51.48201, 50.92429, 50.55369, 50.31903] + }, + "sparse_lora_weights_only_epoch2": { + "full_timeline_horizon_0.2_map": 65.55214, + "full_timeline_mean_map": 54.19850, + "causal_valid_mean_map": 54.20711 + } + }, + "provenance": { + "source": "User-reported remote console tables", + "raw_metrics_json_archived": false, + "exact_remote_feature_root_archived": false, + "multi_seed": false + } +}