ziyuzhou02 commited on
Commit
64af529
·
verified ·
1 Parent(s): 62677b6

Update leaderboard results from local eval

Browse files
results/chronos_2/all_results.csv CHANGED
@@ -1,15 +1,3 @@
1
- dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates,prediction_length
2
- binance_btcusdt_1h_close/1h/short,Chronos-2,2.2351909543412476,2.2351909543412476,nan,nan,0.006872015993651753,nan,nan,1.4950555020939014,nan,nan,0.7476989071223547,Finance,1,24
3
- coingecko_bitcoin_7d_price_usd/1h/short,Chronos-2,0.46766119047554405,0.46766119047554405,nan,nan,0.007905167973149461,nan,nan,0.6838575805498862,nan,nan,0.46522569178545187,Finance,1,24
4
- data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd/1mo/short,Chronos-2,25067.461899718543,25067.461899718543,121.96686029434204,1.2859549577545721,0.6608019070822674,0.9393767274480805,18.969076544647905,158.32707254199624,0.9747204171363386,0.7508734105557137,0.605299940786381,Finance,1,12
5
- data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,Chronos-2,5.8703416764697064e-05,5.8703416764697064e-05,nan,nan,nan,nan,nan,0.007661815500564932,nan,nan,0.30306435781150093,Climate,1,36
6
- data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,Chronos-2,1.7296862743653321e-18,1.7296862743653321e-18,nan,nan,nan,nan,nan,1.3151753777977035e-09,nan,nan,2.356162747109682e-09,Transportation,1,12
7
- nasa_power_shanghai_hourly_T2M/1h/short,Chronos-2,0.05755404396488803,0.05755404396488803,nan,nan,0.013492256137008982,nan,nan,0.23990423915572653,nan,nan,0.1779255586270698,Weather,1,24
8
- noaa_coops_sf_water_level_water_level/6min/short,Chronos-2,0.008435026025816129,0.008435026025816129,nan,nan,0.46985073955420986,nan,nan,0.0918423977573328,nan,nan,0.11780712482012697,Ocean,1,60
9
- noaa_ndbc_46013_realtime_wave_height/10min/short,Chronos-2,1.2590344320617552,1.2590344320617552,nan,nan,0.09515380096257456,nan,nan,1.1220670354581117,nan,nan,0.979254046679312,Ocean,1,72
10
- nws_ksfo_observations_temperature/1h/short,Chronos-2,0.22763978935275495,0.22763978935275495,0.4551292260487874,0.3293397414624391,0.02734639793034648,0.02740698654518156,1.2449814398684094,0.4771161172636646,0.02853423165374086,0.027219291695583462,0.02293888289302154,Weather,1,24
11
- open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,Chronos-2,0.004568087077043557,0.004568087077043557,nan,nan,0.1019209742528152,nan,nan,0.0675876251768292,nan,nan,0.07371692886298616,Air Quality,1,24
12
- open_meteo_shanghai_hourly_temperature_2m/1h/short,Chronos-2,0.03022152236565098,0.03022152236565098,nan,nan,0.01838861164214259,nan,nan,0.1738433845898399,nan,nan,0.17612253472655737,Weather,1,24
13
- usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Chronos-2,0.8102304159422345,0.8102304159422345,nan,nan,0.6696798883371339,nan,nan,0.9001279997546097,nan,nan,0.5943882512463644,Hazards,1,24
14
- usgs_potomac_iv_usgs_00060/15min/short,Chronos-2,32.755553990356304,32.755553990356304,nan,nan,0.04067665894107042,nan,nan,5.72324680494877,nan,nan,4.377331164808588,Hydrology,1,24
15
- wikimedia_time_series_hourly_pageviews/1D/short,Chronos-2,0.5379146607901764,0.5379146607901764,nan,nan,0.17100514688638668,nan,nan,0.7334266567218404,nan,nan,0.48842848142456025,Web,1,7
 
1
+ dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates
2
+ binance_btcusdt_1h_close/1h/short,Chronos-2,253427.98031171164,253427.98031171164,430.1599934895833,0.9318014749305178,0.007149086996462027,0.007183290602900378,3.2641156533937963,503.4163091435474,0.008389478022961463,0.007168654940634957,0.006453564120717358,Finance,1
3
+ coingecko_bitcoin_7d_price_usd/1h/short,Chronos-2,151474.27375920615,151474.27375920615,331.1985677083333,0.6128762551879093,0.00555338622541073,0.005536958612993723,3.7665332417731356,389.19696011043834,0.006507699932794779,0.005537918117874429,0.004363665891866698,Finance,1
 
 
 
 
 
 
 
 
 
 
 
 
results/chronos_2/config.json CHANGED
@@ -3,12 +3,9 @@
3
  "model_type": "zero-shot",
4
  "model_dtype": "float32",
5
  "model_link": "https://tsfm.ai/models/amazon/chronos-2",
6
- "code_link": "https://github.com/zhouziyu02/TS-Live/blob/main/scripts/run_online_eval.py",
7
  "org": "Amazon / TSFM.ai",
8
  "testdata_leakage": "No",
9
  "replication_code_available": "Yes",
10
- "api_model_id": "amazon/chronos-2",
11
- "admitted_at": "2026-06-01T00:00:00Z",
12
- "evaluation_protocol": "issue-now-score-later",
13
- "metric_version": "livehouse-canonical-v1"
14
  }
 
3
  "model_type": "zero-shot",
4
  "model_dtype": "float32",
5
  "model_link": "https://tsfm.ai/models/amazon/chronos-2",
6
+ "code_link": "https://github.com/zhouziyu02/TSFM_Bench/blob/main/scripts/run_online_eval.py",
7
  "org": "Amazon / TSFM.ai",
8
  "testdata_leakage": "No",
9
  "replication_code_available": "Yes",
10
+ "api_model_id": "amazon/chronos-2"
 
 
 
11
  }
results/chronos_2/online_meta.json CHANGED
@@ -1,19 +1,19 @@
1
  {
2
  "model": "Chronos-2",
3
  "api_model_id": "amazon/chronos-2",
4
- "admitted_at": "2026-06-01T00:00:00Z",
5
- "evaluation_protocol": "issue-now-score-later",
6
- "metric_version": "livehouse-canonical-v1",
7
- "evaluated_at": "2026-07-28T14:49:23.463160+00:00",
8
- "resolved_tasks": [
9
  {
10
- "dataset": "noaa_coops_sf_water_level_water_level/6min/short",
11
- "task_id": "future-8c0366116e16bb498905",
12
- "issued_at": "2026-07-28T07:51:37.750559+00:00",
13
- "resolved_at": "2026-07-28T14:46:46.166467+00:00",
14
- "target_end": "2026-07-28T13:42:00+00:00",
15
- "prediction_length": 60,
16
- "metric_version": "livehouse-canonical-v1"
 
 
 
17
  }
18
  ]
19
  }
 
1
  {
2
  "model": "Chronos-2",
3
  "api_model_id": "amazon/chronos-2",
4
+ "evaluated_at": "2026-06-30T10:59:48.162083+00:00",
5
+ "datasets": [
 
 
 
6
  {
7
+ "dataset": "task_binance_btcusdt_1h_crypto_btcusdt_close_20260628t230000z",
8
+ "data_fetched_at": "2026-06-30T10:58:37.207440Z",
9
+ "context_length": 48,
10
+ "prediction_length": 24
11
+ },
12
+ {
13
+ "dataset": "task_coingecko_bitcoin_7d_coin_bitcoin_price_usd_20260629t100204z",
14
+ "data_fetched_at": "2026-06-30T10:58:37.207440Z",
15
+ "context_length": 96,
16
+ "prediction_length": 24
17
  }
18
  ]
19
  }
results/dataset_properties.csv CHANGED
@@ -1,14 +1,8 @@
1
  dataset,domain,frequency,num_variates
2
  binance_btcusdt_1h_close,Finance,1h,1
3
- data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd,Finance,M,1
4
- data_gov_sg_singapore_rainfall_5min_rainfall_5min_total,Climate,5min,1
5
- data_gov_sg_singapore_taxi_availability_available_taxi_count,Transportation,5min,1
6
  nasa_power_shanghai_hourly_t2m,Weather,1h,1
7
- noaa_coops_sf_water_level_water_level,Ocean,6min,1
8
  noaa_ndbc_46013_realtime_wave_height,Ocean,10min,1
9
  nws_ksfo_observations_temperature,Weather,1h,1
10
  open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
11
- open_meteo_shanghai_hourly_temperature_2m,Weather,1h,1
12
- usgs_earthquake_all_week_hourly_earthquake_count,Hazards,1h,1
13
  usgs_potomac_iv_usgs_00060,Hydrology,15min,1
14
  wikimedia_time_series_hourly_pageviews,Web,1D,1
 
1
  dataset,domain,frequency,num_variates
2
  binance_btcusdt_1h_close,Finance,1h,1
 
 
 
3
  nasa_power_shanghai_hourly_t2m,Weather,1h,1
 
4
  noaa_ndbc_46013_realtime_wave_height,Ocean,10min,1
5
  nws_ksfo_observations_temperature,Weather,1h,1
6
  open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
 
 
7
  usgs_potomac_iv_usgs_00060,Hydrology,15min,1
8
  wikimedia_time_series_hourly_pageviews,Web,1D,1
results/online_status.json CHANGED
@@ -1,148 +1,19 @@
1
  {
2
- "status": "ok",
3
- "evaluation_protocol": "issue-now-score-later",
4
- "metric_version": "livehouse-canonical-v1",
5
- "started_at": "2026-07-28T16:03:49.711837+00:00",
6
- "finished_at": "2026-07-28T16:03:59.900104+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
- "task_count": 4,
10
- "issued_tasks": 0,
11
- "issued_forecasts": 0,
12
- "resolved_forecasts": 0,
13
- "pending_tasks": 13,
14
- "failed_forecasts": [],
15
- "models": {
16
- "Chronos-2": {
17
- "model": "Chronos-2",
18
- "api_model_id": "amazon/chronos-2",
19
- "admitted_at": "2026-06-01T00:00:00Z",
20
- "evaluation_protocol": "issue-now-score-later",
21
- "metric_version": "livehouse-canonical-v1",
22
- "evaluated_at": "2026-07-28T16:03:55.439048+00:00",
23
- "resolved_tasks": []
24
- },
25
- "TiRex": {
26
- "model": "TiRex",
27
- "api_model_id": "NX-AI/TiRex-1.1-gifteval",
28
- "admitted_at": "2026-06-01T00:00:00Z",
29
- "evaluation_protocol": "issue-now-score-later",
30
- "metric_version": "livehouse-canonical-v1",
31
- "evaluated_at": "2026-07-28T16:03:55.439067+00:00",
32
- "resolved_tasks": []
33
- },
34
- "TimesFM-2.5": {
35
- "model": "TimesFM-2.5",
36
- "api_model_id": "google/timesfm-2.5-200m-pytorch",
37
- "admitted_at": "2026-06-01T00:00:00Z",
38
- "evaluation_protocol": "issue-now-score-later",
39
- "metric_version": "livehouse-canonical-v1",
40
- "evaluated_at": "2026-07-28T16:03:55.439070+00:00",
41
- "resolved_tasks": []
42
- },
43
- "Toto-1.0": {
44
- "model": "Toto-1.0",
45
- "api_model_id": "Datadog/Toto-Open-Base-1.0",
46
- "admitted_at": "2026-06-01T00:00:00Z",
47
- "evaluation_protocol": "issue-now-score-later",
48
- "metric_version": "livehouse-canonical-v1",
49
- "evaluated_at": "2026-07-28T16:03:55.439073+00:00",
50
- "resolved_tasks": []
51
- },
52
- "Moirai-2.0": {
53
- "model": "Moirai-2.0",
54
- "api_model_id": "Salesforce/moirai-2.0-R-small",
55
- "admitted_at": "2026-06-01T00:00:00Z",
56
- "evaluation_protocol": "issue-now-score-later",
57
- "metric_version": "livehouse-canonical-v1",
58
- "evaluated_at": "2026-07-28T16:03:55.439075+00:00",
59
- "resolved_tasks": []
60
- },
61
- "Chronos-Bolt": {
62
- "model": "Chronos-Bolt",
63
- "api_model_id": "amazon/chronos-bolt-base",
64
- "admitted_at": "2026-06-01T00:00:00Z",
65
- "evaluation_protocol": "issue-now-score-later",
66
- "metric_version": "livehouse-canonical-v1",
67
- "evaluated_at": "2026-07-28T16:03:55.439077+00:00",
68
- "resolved_tasks": []
69
- },
70
- "TabPFN-TS": {
71
- "model": "TabPFN-TS",
72
- "api_model_id": "priorlabs/tabpfn-ts",
73
- "admitted_at": "2026-06-01T00:00:00Z",
74
- "evaluation_protocol": "issue-now-score-later",
75
- "metric_version": "livehouse-canonical-v1",
76
- "evaluated_at": "2026-07-28T16:03:55.439080+00:00",
77
- "resolved_tasks": []
78
- },
79
- "Sundial": {
80
- "model": "Sundial",
81
- "api_model_id": "thuml/sundial-base-128m",
82
- "admitted_at": "2026-06-01T00:00:00Z",
83
- "evaluation_protocol": "issue-now-score-later",
84
- "metric_version": "livehouse-canonical-v1",
85
- "evaluated_at": "2026-07-28T16:03:55.439082+00:00",
86
- "resolved_tasks": []
87
- },
88
- "Moving-Average": {
89
- "model": "Moving-Average",
90
- "api_model_id": "baseline/moving-average",
91
- "admitted_at": "2026-06-01T00:00:00Z",
92
- "evaluation_protocol": "issue-now-score-later",
93
- "metric_version": "livehouse-canonical-v1",
94
- "evaluated_at": "2026-07-28T16:03:55.439084+00:00",
95
- "resolved_tasks": []
96
- },
97
- "ETS": {
98
- "model": "ETS",
99
- "api_model_id": "baseline/ets",
100
- "admitted_at": "2026-06-01T00:00:00Z",
101
- "evaluation_protocol": "issue-now-score-later",
102
- "metric_version": "livehouse-canonical-v1",
103
- "evaluated_at": "2026-07-28T16:03:55.439087+00:00",
104
- "resolved_tasks": []
105
- },
106
- "ARIMA": {
107
- "model": "ARIMA",
108
- "api_model_id": "baseline/arima",
109
- "admitted_at": "2026-06-01T00:00:00Z",
110
- "evaluation_protocol": "issue-now-score-later",
111
- "metric_version": "livehouse-canonical-v1",
112
- "evaluated_at": "2026-07-28T16:03:55.439089+00:00",
113
- "resolved_tasks": []
114
- },
115
- "Seasonal-Naive": {
116
- "model": "Seasonal-Naive",
117
- "api_model_id": "baseline/seasonal-naive",
118
- "admitted_at": "2026-06-01T00:00:00Z",
119
- "evaluation_protocol": "issue-now-score-later",
120
- "metric_version": "livehouse-canonical-v1",
121
- "evaluated_at": "2026-07-28T16:03:55.439092+00:00",
122
- "resolved_tasks": []
123
- }
124
- },
125
- "skipped_models": [],
126
- "aggregate_status": "ok",
127
- "aggregate_files": {
128
- "gift_prediction_length": "aggregates/results_by_prediction_length.csv",
129
- "gift_domain": "aggregates/results_by_domain.csv",
130
- "gift_frequency": "aggregates/results_by_frequency.csv",
131
- "gift_overall": "aggregates/results_overall.csv",
132
- "gift_metadata": "aggregates/metadata.json",
133
- "live_releases": "aggregates/live_release_metrics.csv",
134
- "live_by_dataset": "aggregates/live_results_by_dataset.csv",
135
- "live_rank": "aggregates/live_rank_up_to_now.csv",
136
- "live_overall": "aggregates/live_overall_up_to_now.csv",
137
- "live_rank_1d": "aggregates/live_rank_1d.csv",
138
- "live_overall_1d": "aggregates/live_overall_1d.csv",
139
- "live_rank_7d": "aggregates/live_rank_7d.csv",
140
- "live_overall_7d": "aggregates/live_overall_7d.csv",
141
- "live_rank_30d": "aggregates/live_rank_30d.csv",
142
- "live_overall_30d": "aggregates/live_overall_30d.csv",
143
- "live_metadata": "aggregates/live_metadata.json"
144
- },
145
- "push_status": "ok",
146
- "pushed_at": "2026-07-28T16:05:17.777384+00:00",
147
- "push_detail": "HF Hub API"
148
  }
 
1
  {
2
+ "status": "partial",
3
+ "started_at": "2026-07-28T17:08:51.624239+00:00",
4
+ "finished_at": "2026-07-28T17:09:09.108507+00:00",
5
+ "task_count": 7,
 
6
  "data_source": "ts_bench",
7
  "data_config": "configs/datasets/ts_bench.yaml",
8
+ "ts_bench_root": "/Users/zhouziyu/Desktop/TS-Bench",
9
+ "models": {},
10
+ "failed_models": [
11
+ "Chronos-Bolt-Tiny",
12
+ "Chronos-Bolt-Mini",
13
+ "Chronos-Bolt-Base",
14
+ "Chronos-2",
15
+ "TimesFM-2.5",
16
+ "Moirai-1.1-Small"
17
+ ],
18
+ "push_status": "pending"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
results/timesfm_2_5/all_results.csv CHANGED
@@ -1,15 +1,11 @@
1
- dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates,prediction_length
2
- binance_btcusdt_1h_close/1h/short,TimesFM-2.5,2.544873715422005,2.1763895224570793,nan,nan,0.00733854194735763,nan,nan,1.5952660328051886,nan,nan,0.9400124419879271,Finance,1,24
3
- coingecko_bitcoin_7d_price_usd/1h/short,TimesFM-2.5,0.16431138716961843,0.2840452984238427,nan,nan,0.006365738815062364,nan,nan,0.40535341021091514,nan,nan,0.28603521259581766,Finance,1,24
4
- data_gov_sg_sgx_equities_turnover_monthly_turnover_value_million_sgd/1mo/short,TimesFM-2.5,28434.715767887308,30940.314541637516,136.81071631113687,1.4424608331286375,0.6894371389934627,1.1431172573156296,43.032391046456816,168.6259640977252,1.0381242287022936,0.8422577158188848,0.7508176845882389,Finance,1,12
5
- data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short,TimesFM-2.5,0.00016901519468899977,0.0001410442962292074,nan,nan,nan,nan,nan,0.013000584397979952,nan,nan,0.019137209007157194,Climate,1,36
6
- data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short,TimesFM-2.5,0.0,0.0,nan,nan,nan,nan,nan,0.0,nan,nan,0.0,Transportation,1,12
7
- nasa_power_shanghai_hourly_T2M/1h/short,TimesFM-2.5,0.07100583795216671,0.11015231373309131,nan,nan,0.017946478614699196,nan,nan,0.2664692063863416,nan,nan,0.19077303156426317,Weather,1,24
8
- noaa_coops_sf_water_level_water_level/6min/short,TimesFM-2.5,0.011001676967046684,0.004684032279350234,nan,nan,0.21161799885754823,nan,nan,0.10488887913905212,nan,nan,0.10275674813077912,Ocean,1,60
9
- noaa_ndbc_46013_realtime_wave_height/10min/short,TimesFM-2.5,1.1073154863140786,1.4107221533655678,nan,nan,0.0953658327893421,nan,nan,1.0522905902430557,nan,nan,0.786268762633924,Ocean,1,72
10
- nws_ksfo_observations_temperature/1h/short,TimesFM-2.5,0.21622905324208355,0.1617179170793861,0.26413559913635254,0.1911332978675114,0.01630353750267156,0.01601217538840988,10.994616695384883,0.4650043583043965,0.027809880236186378,0.015796796840529412,0.021259949519123158,Weather,1,24
11
- open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,TimesFM-2.5,0.006262990376178233,0.004554783835561518,nan,nan,0.09627439894456198,nan,nan,0.07913905721057228,nan,nan,0.10022450213355703,Air Quality,1,24
12
- open_meteo_shanghai_hourly_temperature_2m/1h/short,TimesFM-2.5,0.06269121952817955,0.10589695801141052,nan,nan,0.033732113336197196,nan,nan,0.25038214698372474,nan,nan,0.1887512228581642,Weather,1,24
13
- usgs_earthquake_all_week_hourly_earthquake_count/1h/short,TimesFM-2.5,0.7736671660082207,0.9192549938039831,nan,nan,0.6858045973238216,nan,nan,0.8795835184951004,nan,nan,0.6374611819871363,Hazards,1,24
14
- usgs_potomac_iv_usgs_00060/15min/short,TimesFM-2.5,32.86177357403732,31.531639228654843,nan,nan,0.03990939271216299,nan,nan,5.732518955401484,nan,nan,5.438520029653064,Hydrology,1,24
15
- wikimedia_time_series_hourly_pageviews/1D/short,TimesFM-2.5,0.38719216672060525,0.341005570724447,nan,nan,0.12667853599052806,nan,nan,0.6222476731339421,nan,nan,0.5343002043100503,Web,1,7
 
1
+ dataset,model,eval_metrics/MSE[mean],eval_metrics/MSE[0.5],eval_metrics/MAE[0.5],eval_metrics/MASE[0.5],eval_metrics/MAPE[0.5],eval_metrics/sMAPE[0.5],eval_metrics/MSIS,eval_metrics/RMSE[mean],eval_metrics/NRMSE[mean],eval_metrics/ND[0.5],eval_metrics/mean_weighted_sum_quantile_loss,domain,num_variates
2
+ binance_btcusdt_1h_close/1h/short,TimesFM-2.5,81742.42789522807,124744.15551821391,297.3611653645833,0.4486972705324055,0.004943552533723208,0.0049579917738521604,4.904699820126863,285.90632713395496,0.0047624096472577765,0.004953215610330298,0.003661364469335062,Finance,1
3
+ coingecko_bitcoin_7d_price_usd/1h/short,TimesFM-2.5,97952.0961373647,155042.49553426108,344.3505859375,0.494849513065497,0.005734942849078377,0.005753831848928334,4.4515950592935765,312.9729958596503,0.005223298429098694,0.005746968263655385,0.004048322861622117,Finance,1
4
+ nasa_power_shanghai_hourly_T2M/1h/short,TimesFM-2.5,11.641811304915336,13.423471256234128,2.7575780550638833,3.5293238475457582,0.10321913729068599,0.11204715871745875,101.69350427694228,3.4120098629569253,0.14059996314044312,0.11363254752226123,0.10196536560973148,Weather,1
5
+ noaa_coops_sf_water_level_water_level/6min/short,TimesFM-2.5,0.02908771671812005,0.034046774600905515,0.13568753997484842,0.17312143585760467,0.11185537202482503,0.12463965779787611,2.676967727907387,0.1705512143554541,0.1434961937098364,0.11416304242585044,0.08757558544176978,Ocean,1
6
+ noaa_ndbc_46013_realtime_wave_height/10min/short,TimesFM-2.5,0.05836318292564613,0.04761165148106272,0.16445205609003702,0.3447029766963658,0.07191232151835235,0.06762886788054125,17.47579260325252,0.24158473239351475,0.09877400134375952,0.06723764141999806,0.08169348159617512,Ocean,1
7
+ nws_ksfo_observations_temperature/1h/short,TimesFM-2.5,5.091922888105425,6.327109473932221,2.2220658461252847,1.3592926513955181,0.10384344306035338,0.11108617811955894,27.998005969855527,2.2565289468795706,0.10885767783941647,0.10719513629549113,0.08603730202253673,Weather,1
8
+ open_meteo_shanghai_air_quality_hourly_pm2_5/1h/short,TimesFM-2.5,49.47017191748849,82.91626740256955,7.3194271723429365,0.5005687624158839,0.2545421621602366,0.295325743742574,5.8418762834746945,7.033503530779557,0.27381035642937446,0.28494120378950605,0.21288132768520807,Air Quality,1
9
+ open_meteo_shanghai_hourly_temperature_2m/1h/short,TimesFM-2.5,1.6484289968751302,1.7882974488526695,1.16057284673055,0.9274277392234174,0.04635277574155072,0.04703534337119358,20.58434769273915,1.2839116001014752,0.04978813570351389,0.045005246764860715,0.03796367653364946,Weather,1
10
+ usgs_earthquake_all_week_hourly_earthquake_count/1h/short,TimesFM-2.5,12.541379031458973,13.808125303080638,3.0202603340148926,0.7396555920036473,0.33108155235761566,0.30808027947552724,19.43875757528811,3.5413809497791924,0.34691078691714533,0.29586223680145884,0.27081315021125635,Hazards,1
11
+ usgs_potomac_iv_usgs_00060/15min/short,TimesFM-2.5,430.1970050111413,571.0872243667642,16.349232991536457,0.15238120069781555,0.006005184220679013,0.0060436006179905065,2.234056811286407,20.741191022001153,0.007664181440000427,0.006041287017657814,0.004361342408824095,Hydrology,1
 
 
 
 
results/timesfm_2_5/config.json CHANGED
@@ -3,12 +3,9 @@
3
  "model_type": "zero-shot",
4
  "model_dtype": "float32",
5
  "model_link": "https://tsfm.ai/models/google/timesfm-2.5-200m-pytorch",
6
- "code_link": "https://github.com/zhouziyu02/TS-Live/blob/main/scripts/run_online_eval.py",
7
  "org": "Google / TSFM.ai",
8
  "testdata_leakage": "No",
9
  "replication_code_available": "Yes",
10
- "api_model_id": "google/timesfm-2.5-200m-pytorch",
11
- "admitted_at": "2026-06-01T00:00:00Z",
12
- "evaluation_protocol": "issue-now-score-later",
13
- "metric_version": "livehouse-canonical-v1"
14
  }
 
3
  "model_type": "zero-shot",
4
  "model_dtype": "float32",
5
  "model_link": "https://tsfm.ai/models/google/timesfm-2.5-200m-pytorch",
6
+ "code_link": "https://github.com/zhouziyu02/TSFM_Bench/blob/main/scripts/run_online_eval.py",
7
  "org": "Google / TSFM.ai",
8
  "testdata_leakage": "No",
9
  "replication_code_available": "Yes",
10
+ "api_model_id": "google/timesfm-2.5-200m-pytorch"
 
 
 
11
  }
results/timesfm_2_5/online_meta.json CHANGED
@@ -1,19 +1,67 @@
1
  {
2
  "model": "TimesFM-2.5",
3
  "api_model_id": "google/timesfm-2.5-200m-pytorch",
4
- "admitted_at": "2026-06-01T00:00:00Z",
5
- "evaluation_protocol": "issue-now-score-later",
6
- "metric_version": "livehouse-canonical-v1",
7
- "evaluated_at": "2026-07-28T14:49:23.506618+00:00",
8
- "resolved_tasks": [
9
- {
10
- "dataset": "noaa_coops_sf_water_level_water_level/6min/short",
11
- "task_id": "future-8c0366116e16bb498905",
12
- "issued_at": "2026-07-28T07:51:37.750559+00:00",
13
- "resolved_at": "2026-07-28T14:46:46.615747+00:00",
14
- "target_end": "2026-07-28T13:42:00+00:00",
15
- "prediction_length": 60,
16
- "metric_version": "livehouse-canonical-v1"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
18
  ]
19
  }
 
1
  {
2
  "model": "TimesFM-2.5",
3
  "api_model_id": "google/timesfm-2.5-200m-pytorch",
4
+ "evaluated_at": "2026-06-30T02:19:42.264357+00:00",
5
+ "datasets": [
6
+ {
7
+ "dataset": "task_binance_btcusdt_1h_crypto_btcusdt_close_20260629t020000z",
8
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
9
+ "context_length": 96,
10
+ "prediction_length": 24
11
+ },
12
+ {
13
+ "dataset": "task_coingecko_bitcoin_7d_coin_bitcoin_price_usd_20260629t010219z",
14
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
15
+ "context_length": 96,
16
+ "prediction_length": 24
17
+ },
18
+ {
19
+ "dataset": "task_nasa_power_shanghai_hourly_point_shanghai_31.2304_121.4737_t2m_20260625t230000z",
20
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
21
+ "context_length": 69,
22
+ "prediction_length": 24
23
+ },
24
+ {
25
+ "dataset": "task_noaa_coops_sf_water_level_coops_station_9414290_water_level_20260629t234200z",
26
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
27
+ "context_length": 96,
28
+ "prediction_length": 24
29
+ },
30
+ {
31
+ "dataset": "task_noaa_ndbc_46013_realtime_ndbc_station_46013_wave_height_20260629t171000z",
32
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
33
+ "context_length": 96,
34
+ "prediction_length": 24
35
+ },
36
+ {
37
+ "dataset": "task_nws_ksfo_observations_nws_station_ksfo_temperature_20260630t001000z",
38
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
39
+ "context_length": 96,
40
+ "prediction_length": 24
41
+ },
42
+ {
43
+ "dataset": "task_open_meteo_shanghai_air_quality_hourly_grid_shanghai_31.2304_121.4737_pm2_5_20260629t020000z",
44
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
45
+ "context_length": 96,
46
+ "prediction_length": 24
47
+ },
48
+ {
49
+ "dataset": "task_open_meteo_shanghai_hourly_grid_shanghai_31.2304_121.4737_temperature_2m_20260629t020000z",
50
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
51
+ "context_length": 96,
52
+ "prediction_length": 24
53
+ },
54
+ {
55
+ "dataset": "task_usgs_earthquake_all_week_hourly_earth_global_earthquake_count_20260629t010000z",
56
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
57
+ "context_length": 96,
58
+ "prediction_length": 24
59
+ },
60
+ {
61
+ "dataset": "task_usgs_potomac_iv_usgs_site_01646500_usgs_00060_20260629t235000z",
62
+ "data_fetched_at": "2026-06-30T02:16:24.198018Z",
63
+ "context_length": 96,
64
+ "prediction_length": 24
65
  }
66
  ]
67
  }