ziyuzhou02 commited on
Commit
e4ab9b2
·
verified ·
1 Parent(s): b4dd918

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-2,0.17505582868640848,0.17505582868640848,nan,nan,0.003231618795337522,nan,nan,0.41839673598919064,nan,nan,0.2881331988179761,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-2,1.6284716271939715e-18,1.6284716271939715e-18,nan,nan,nan,nan,nan,1.2761158361191085e-09,nan,nan,1.8284365387902989e-09,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-2,0.06025211913342343,0.06025211913342343,nan,nan,0.014048149370033328,nan,nan,0.24546307081396873,nan,nan,0.16759977605525547,Weather,1,24
8
- noaa_coops_sf_water_level_water_level/6min/short,Chronos-2,0.39869489331544644,0.39869489331544644,nan,nan,0.23653810805327471,nan,nan,0.6314229116174408,nan,nan,0.3388036720406042,Ocean,1,60
9
- noaa_ndbc_46013_realtime_wave_height/10min/short,Chronos-2,1.6657052582798209,1.6657052582798209,nan,nan,0.11908254245050692,nan,nan,1.2906220431558655,nan,nan,0.8988337976886078,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-2,0.03526190188175566,0.03526190188175566,nan,nan,0.2142754133607554,nan,nan,0.1877815269981466,nan,nan,0.1128105078936095,Air Quality,1,24
12
- open_meteo_shanghai_hourly_temperature_2m/1h/short,Chronos-2,0.16410673128769995,0.16410673128769995,nan,nan,0.03774184875099514,nan,nan,0.4051008902578467,nan,nan,0.20244880321228498,Weather,1,24
13
- usgs_earthquake_all_week_hourly_earthquake_count/1h/short,Chronos-2,0.6326804740446184,0.6326804740446184,nan,nan,0.4433038595658039,nan,nan,0.7954121409964889,nan,nan,0.49632226407417623,Hazards,1,24
14
- usgs_potomac_iv_usgs_00060/15min/short,Chronos-2,5.076688428663051,5.076688428663051,nan,nan,0.07430929788919967,nan,nan,2.253150778057929,nan,nan,1.710286926999298,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
@@ -1,28 +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": "2026-07-28T01:39:02.132565+00:00",
8
- "resolved_tasks": [
9
  {
10
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
11
- "task_id": "future-1cf8a69c46ddfd207dc4",
12
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
13
- "resolved_at": "2026-07-28T01:34:12.894149+00:00",
14
- "target_end": "2026-07-27T17:35:00+00:00",
15
- "prediction_length": 36,
16
- "metric_version": "livehouse-canonical-v1"
17
  },
18
  {
19
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
20
- "task_id": "future-a378da744357008aedcd",
21
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
22
- "resolved_at": "2026-07-28T01:34:13.234112+00:00",
23
- "target_end": "2026-07-26T15:05:00+00:00",
24
- "prediction_length": 12,
25
- "metric_version": "livehouse-canonical-v1"
26
  }
27
  ]
28
  }
 
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
@@ -1,11 +1,7 @@
1
  dataset,domain,frequency,num_variates
2
  binance_btcusdt_1h_close,Finance,1h,1
3
  coingecko_bitcoin_7d_price_usd,Finance,1h,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
 
1
  dataset,domain,frequency,num_variates
2
  binance_btcusdt_1h_close,Finance,1h,1
3
  coingecko_bitcoin_7d_price_usd,Finance,1h,1
 
 
 
4
  noaa_coops_sf_water_level_water_level,Ocean,6min,1
 
5
  nws_ksfo_observations_temperature,Weather,1h,1
6
  open_meteo_shanghai_air_quality_hourly_pm2_5,Air Quality,1h,1
7
  open_meteo_shanghai_hourly_temperature_2m,Weather,1h,1
results/online_status.json CHANGED
@@ -1,376 +1,19 @@
1
  {
2
- "status": "ok",
3
- "evaluation_protocol": "issue-now-score-later",
4
- "metric_version": "livehouse-canonical-v1",
5
- "started_at": "2026-07-28T01:34:09.028402+00:00",
6
- "finished_at": "2026-07-28T01:39:06.500756+00:00",
7
  "data_source": "ts_bench",
8
  "data_config": "configs/datasets/ts_bench.yaml",
9
- "task_count": 4,
10
- "issued_tasks": 2,
11
- "issued_forecasts": 24,
12
- "resolved_forecasts": 24,
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": "2026-07-28T01:39:02.132565+00:00",
23
- "resolved_tasks": [
24
- {
25
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
26
- "task_id": "future-1cf8a69c46ddfd207dc4",
27
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
28
- "resolved_at": "2026-07-28T01:34:12.894149+00:00",
29
- "target_end": "2026-07-27T17:35:00+00:00",
30
- "prediction_length": 36,
31
- "metric_version": "livehouse-canonical-v1"
32
- },
33
- {
34
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
35
- "task_id": "future-a378da744357008aedcd",
36
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
37
- "resolved_at": "2026-07-28T01:34:13.234112+00:00",
38
- "target_end": "2026-07-26T15:05:00+00:00",
39
- "prediction_length": 12,
40
- "metric_version": "livehouse-canonical-v1"
41
- }
42
- ]
43
- },
44
- "TiRex": {
45
- "model": "TiRex",
46
- "api_model_id": "NX-AI/TiRex-1.1-gifteval",
47
- "admitted_at": "2026-06-01T00:00:00Z",
48
- "evaluation_protocol": "issue-now-score-later",
49
- "metric_version": "livehouse-canonical-v1",
50
- "evaluated_at": "2026-07-28T01:39:02.143578+00:00",
51
- "resolved_tasks": [
52
- {
53
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
54
- "task_id": "future-1cf8a69c46ddfd207dc4",
55
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
56
- "resolved_at": "2026-07-28T01:34:13.096194+00:00",
57
- "target_end": "2026-07-27T17:35:00+00:00",
58
- "prediction_length": 36,
59
- "metric_version": "livehouse-canonical-v1"
60
- },
61
- {
62
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
63
- "task_id": "future-a378da744357008aedcd",
64
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
65
- "resolved_at": "2026-07-28T01:34:13.471320+00:00",
66
- "target_end": "2026-07-26T15:05:00+00:00",
67
- "prediction_length": 12,
68
- "metric_version": "livehouse-canonical-v1"
69
- }
70
- ]
71
- },
72
- "TimesFM-2.5": {
73
- "model": "TimesFM-2.5",
74
- "api_model_id": "google/timesfm-2.5-200m-pytorch",
75
- "admitted_at": "2026-06-01T00:00:00Z",
76
- "evaluation_protocol": "issue-now-score-later",
77
- "metric_version": "livehouse-canonical-v1",
78
- "evaluated_at": "2026-07-28T01:39:02.149435+00:00",
79
- "resolved_tasks": [
80
- {
81
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
82
- "task_id": "future-1cf8a69c46ddfd207dc4",
83
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
84
- "resolved_at": "2026-07-28T01:34:13.078112+00:00",
85
- "target_end": "2026-07-27T17:35:00+00:00",
86
- "prediction_length": 36,
87
- "metric_version": "livehouse-canonical-v1"
88
- },
89
- {
90
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
91
- "task_id": "future-a378da744357008aedcd",
92
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
93
- "resolved_at": "2026-07-28T01:34:13.451024+00:00",
94
- "target_end": "2026-07-26T15:05:00+00:00",
95
- "prediction_length": 12,
96
- "metric_version": "livehouse-canonical-v1"
97
- }
98
- ]
99
- },
100
- "Toto-1.0": {
101
- "model": "Toto-1.0",
102
- "api_model_id": "Datadog/Toto-Open-Base-1.0",
103
- "admitted_at": "2026-06-01T00:00:00Z",
104
- "evaluation_protocol": "issue-now-score-later",
105
- "metric_version": "livehouse-canonical-v1",
106
- "evaluated_at": "2026-07-28T01:39:02.151603+00:00",
107
- "resolved_tasks": [
108
- {
109
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
110
- "task_id": "future-1cf8a69c46ddfd207dc4",
111
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
112
- "resolved_at": "2026-07-28T01:34:13.168150+00:00",
113
- "target_end": "2026-07-27T17:35:00+00:00",
114
- "prediction_length": 36,
115
- "metric_version": "livehouse-canonical-v1"
116
- },
117
- {
118
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
119
- "task_id": "future-a378da744357008aedcd",
120
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
121
- "resolved_at": "2026-07-28T01:34:13.535120+00:00",
122
- "target_end": "2026-07-26T15:05:00+00:00",
123
- "prediction_length": 12,
124
- "metric_version": "livehouse-canonical-v1"
125
- }
126
- ]
127
- },
128
- "Moirai-2.0": {
129
- "model": "Moirai-2.0",
130
- "api_model_id": "Salesforce/moirai-2.0-R-small",
131
- "admitted_at": "2026-06-01T00:00:00Z",
132
- "evaluation_protocol": "issue-now-score-later",
133
- "metric_version": "livehouse-canonical-v1",
134
- "evaluated_at": "2026-07-28T01:39:02.168888+00:00",
135
- "resolved_tasks": [
136
- {
137
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
138
- "task_id": "future-1cf8a69c46ddfd207dc4",
139
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
140
- "resolved_at": "2026-07-28T01:34:12.988273+00:00",
141
- "target_end": "2026-07-27T17:35:00+00:00",
142
- "prediction_length": 36,
143
- "metric_version": "livehouse-canonical-v1"
144
- },
145
- {
146
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
147
- "task_id": "future-a378da744357008aedcd",
148
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
149
- "resolved_at": "2026-07-28T01:34:13.327134+00:00",
150
- "target_end": "2026-07-26T15:05:00+00:00",
151
- "prediction_length": 12,
152
- "metric_version": "livehouse-canonical-v1"
153
- }
154
- ]
155
- },
156
- "Chronos-Bolt": {
157
- "model": "Chronos-Bolt",
158
- "api_model_id": "amazon/chronos-bolt-base",
159
- "admitted_at": "2026-06-01T00:00:00Z",
160
- "evaluation_protocol": "issue-now-score-later",
161
- "metric_version": "livehouse-canonical-v1",
162
- "evaluated_at": "2026-07-28T01:39:02.184014+00:00",
163
- "resolved_tasks": [
164
- {
165
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
166
- "task_id": "future-1cf8a69c46ddfd207dc4",
167
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
168
- "resolved_at": "2026-07-28T01:34:12.937188+00:00",
169
- "target_end": "2026-07-27T17:35:00+00:00",
170
- "prediction_length": 36,
171
- "metric_version": "livehouse-canonical-v1"
172
- },
173
- {
174
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
175
- "task_id": "future-a378da744357008aedcd",
176
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
177
- "resolved_at": "2026-07-28T01:34:13.245069+00:00",
178
- "target_end": "2026-07-26T15:05:00+00:00",
179
- "prediction_length": 12,
180
- "metric_version": "livehouse-canonical-v1"
181
- }
182
- ]
183
- },
184
- "TabPFN-TS": {
185
- "model": "TabPFN-TS",
186
- "api_model_id": "priorlabs/tabpfn-ts",
187
- "admitted_at": "2026-06-01T00:00:00Z",
188
- "evaluation_protocol": "issue-now-score-later",
189
- "metric_version": "livehouse-canonical-v1",
190
- "evaluated_at": "2026-07-28T01:39:02.199444+00:00",
191
- "resolved_tasks": [
192
- {
193
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
194
- "task_id": "future-1cf8a69c46ddfd207dc4",
195
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
196
- "resolved_at": "2026-07-28T01:34:13.062232+00:00",
197
- "target_end": "2026-07-27T17:35:00+00:00",
198
- "prediction_length": 36,
199
- "metric_version": "livehouse-canonical-v1"
200
- },
201
- {
202
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
203
- "task_id": "future-a378da744357008aedcd",
204
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
205
- "resolved_at": "2026-07-28T01:34:13.438085+00:00",
206
- "target_end": "2026-07-26T15:05:00+00:00",
207
- "prediction_length": 12,
208
- "metric_version": "livehouse-canonical-v1"
209
- }
210
- ]
211
- },
212
- "Sundial": {
213
- "model": "Sundial",
214
- "api_model_id": "thuml/sundial-base-128m",
215
- "admitted_at": "2026-06-01T00:00:00Z",
216
- "evaluation_protocol": "issue-now-score-later",
217
- "metric_version": "livehouse-canonical-v1",
218
- "evaluated_at": "2026-07-28T01:39:02.206382+00:00",
219
- "resolved_tasks": [
220
- {
221
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
222
- "task_id": "future-1cf8a69c46ddfd207dc4",
223
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
224
- "resolved_at": "2026-07-28T01:34:13.042165+00:00",
225
- "target_end": "2026-07-27T17:35:00+00:00",
226
- "prediction_length": 36,
227
- "metric_version": "livehouse-canonical-v1"
228
- },
229
- {
230
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
231
- "task_id": "future-a378da744357008aedcd",
232
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
233
- "resolved_at": "2026-07-28T01:34:13.402146+00:00",
234
- "target_end": "2026-07-26T15:05:00+00:00",
235
- "prediction_length": 12,
236
- "metric_version": "livehouse-canonical-v1"
237
- }
238
- ]
239
- },
240
- "Moving-Average": {
241
- "model": "Moving-Average",
242
- "api_model_id": "baseline/moving-average",
243
- "admitted_at": "2026-06-01T00:00:00Z",
244
- "evaluation_protocol": "issue-now-score-later",
245
- "metric_version": "livehouse-canonical-v1",
246
- "evaluated_at": "2026-07-28T01:39:02.209331+00:00",
247
- "resolved_tasks": [
248
- {
249
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
250
- "task_id": "future-1cf8a69c46ddfd207dc4",
251
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
252
- "resolved_at": "2026-07-28T01:34:13.007201+00:00",
253
- "target_end": "2026-07-27T17:35:00+00:00",
254
- "prediction_length": 36,
255
- "metric_version": "livehouse-canonical-v1"
256
- },
257
- {
258
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
259
- "task_id": "future-a378da744357008aedcd",
260
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
261
- "resolved_at": "2026-07-28T01:34:13.349113+00:00",
262
- "target_end": "2026-07-26T15:05:00+00:00",
263
- "prediction_length": 12,
264
- "metric_version": "livehouse-canonical-v1"
265
- }
266
- ]
267
- },
268
- "ETS": {
269
- "model": "ETS",
270
- "api_model_id": "baseline/ets",
271
- "admitted_at": "2026-06-01T00:00:00Z",
272
- "evaluation_protocol": "issue-now-score-later",
273
- "metric_version": "livehouse-canonical-v1",
274
- "evaluated_at": "2026-07-28T01:39:02.221180+00:00",
275
- "resolved_tasks": [
276
- {
277
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
278
- "task_id": "future-1cf8a69c46ddfd207dc4",
279
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
280
- "resolved_at": "2026-07-28T01:34:12.956211+00:00",
281
- "target_end": "2026-07-27T17:35:00+00:00",
282
- "prediction_length": 36,
283
- "metric_version": "livehouse-canonical-v1"
284
- },
285
- {
286
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
287
- "task_id": "future-a378da744357008aedcd",
288
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
289
- "resolved_at": "2026-07-28T01:34:13.280102+00:00",
290
- "target_end": "2026-07-26T15:05:00+00:00",
291
- "prediction_length": 12,
292
- "metric_version": "livehouse-canonical-v1"
293
- }
294
- ]
295
- },
296
- "ARIMA": {
297
- "model": "ARIMA",
298
- "api_model_id": "baseline/arima",
299
- "admitted_at": "2026-06-01T00:00:00Z",
300
- "evaluation_protocol": "issue-now-score-later",
301
- "metric_version": "livehouse-canonical-v1",
302
- "evaluated_at": "2026-07-28T01:39:02.233459+00:00",
303
- "resolved_tasks": [
304
- {
305
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
306
- "task_id": "future-1cf8a69c46ddfd207dc4",
307
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
308
- "resolved_at": "2026-07-28T01:34:12.840502+00:00",
309
- "target_end": "2026-07-27T17:35:00+00:00",
310
- "prediction_length": 36,
311
- "metric_version": "livehouse-canonical-v1"
312
- },
313
- {
314
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
315
- "task_id": "future-a378da744357008aedcd",
316
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
317
- "resolved_at": "2026-07-28T01:34:13.194114+00:00",
318
- "target_end": "2026-07-26T15:05:00+00:00",
319
- "prediction_length": 12,
320
- "metric_version": "livehouse-canonical-v1"
321
- }
322
- ]
323
- },
324
- "Seasonal-Naive": {
325
- "model": "Seasonal-Naive",
326
- "api_model_id": "baseline/seasonal-naive",
327
- "admitted_at": "2026-06-01T00:00:00Z",
328
- "evaluation_protocol": "issue-now-score-later",
329
- "metric_version": "livehouse-canonical-v1",
330
- "evaluated_at": "2026-07-28T01:39:02.252909+00:00",
331
- "resolved_tasks": [
332
- {
333
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
334
- "task_id": "future-1cf8a69c46ddfd207dc4",
335
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
336
- "resolved_at": "2026-07-28T01:34:13.022077+00:00",
337
- "target_end": "2026-07-27T17:35:00+00:00",
338
- "prediction_length": 36,
339
- "metric_version": "livehouse-canonical-v1"
340
- },
341
- {
342
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
343
- "task_id": "future-a378da744357008aedcd",
344
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
345
- "resolved_at": "2026-07-28T01:34:13.384132+00:00",
346
- "target_end": "2026-07-26T15:05:00+00:00",
347
- "prediction_length": 12,
348
- "metric_version": "livehouse-canonical-v1"
349
- }
350
- ]
351
- }
352
- },
353
- "skipped_models": [],
354
- "aggregate_status": "ok",
355
- "aggregate_files": {
356
- "gift_prediction_length": "aggregates/results_by_prediction_length.csv",
357
- "gift_domain": "aggregates/results_by_domain.csv",
358
- "gift_frequency": "aggregates/results_by_frequency.csv",
359
- "gift_overall": "aggregates/results_overall.csv",
360
- "gift_metadata": "aggregates/metadata.json",
361
- "live_releases": "aggregates/live_release_metrics.csv",
362
- "live_by_dataset": "aggregates/live_results_by_dataset.csv",
363
- "live_rank": "aggregates/live_rank_up_to_now.csv",
364
- "live_overall": "aggregates/live_overall_up_to_now.csv",
365
- "live_rank_1d": "aggregates/live_rank_1d.csv",
366
- "live_overall_1d": "aggregates/live_overall_1d.csv",
367
- "live_rank_7d": "aggregates/live_rank_7d.csv",
368
- "live_overall_7d": "aggregates/live_overall_7d.csv",
369
- "live_rank_30d": "aggregates/live_rank_30d.csv",
370
- "live_overall_30d": "aggregates/live_overall_30d.csv",
371
- "live_metadata": "aggregates/live_metadata.json"
372
- },
373
- "push_status": "ok",
374
- "pushed_at": "2026-07-28T01:40:06.607710+00:00",
375
- "push_detail": "HF Hub API"
376
  }
 
1
  {
2
+ "status": "partial",
3
+ "started_at": "2026-07-28T02:09:17.614699+00:00",
4
+ "finished_at": "2026-07-28T02:09:25.478616+00:00",
5
+ "task_count": 8,
 
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-2.5,0.18471364393609205,0.2511561167570871,nan,nan,0.003988779263392523,nan,nan,0.42978325227501835,nan,nan,0.26875152458008783,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-2.5,0.0,0.0,nan,nan,nan,nan,nan,0.0,nan,nan,0.0,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-2.5,0.07349968636756156,0.12715800629866036,nan,nan,0.017422859563450927,nan,nan,0.2711082558085636,nan,nan,0.19379553509865552,Weather,1,24
8
- noaa_coops_sf_water_level_water_level/6min/short,TimesFM-2.5,0.14262902462292637,0.10499166979015469,nan,nan,0.14590502381629022,nan,nan,0.3776625803848276,nan,nan,0.31992783287089027,Ocean,1,60
9
- noaa_ndbc_46013_realtime_wave_height/10min/short,TimesFM-2.5,1.2071519093124696,1.3019518027243746,nan,nan,0.10344735727774368,nan,nan,1.0987046506283977,nan,nan,0.8717528265991279,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-2.5,0.03785281024197016,0.017934866424511135,nan,nan,0.21483569476265685,nan,nan,0.19455798683675302,nan,nan,0.19205918049403484,Air Quality,1,24
12
- open_meteo_shanghai_hourly_temperature_2m/1h/short,TimesFM-2.5,0.06591225974664346,0.03575909793348882,nan,nan,0.01791180333102477,nan,nan,0.2567338305456518,nan,nan,0.19379445942016174,Weather,1,24
13
- usgs_earthquake_all_week_hourly_earthquake_count/1h/short,TimesFM-2.5,0.6086373270893934,0.641798892026256,nan,nan,0.34810479649554643,nan,nan,0.7801521179163673,nan,nan,0.5751539108404323,Hazards,1,24
14
- usgs_potomac_iv_usgs_00060/15min/short,TimesFM-2.5,5.54219699972541,6.215406233869209,nan,nan,0.08228977408365698,nan,nan,2.3541871207967753,nan,nan,2.1827408275623315,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
@@ -1,28 +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": "2026-07-28T01:39:02.149435+00:00",
8
- "resolved_tasks": [
9
- {
10
- "dataset": "data_gov_sg_singapore_rainfall_5min_rainfall_5min_total/5min/short",
11
- "task_id": "future-1cf8a69c46ddfd207dc4",
12
- "issued_at": "2026-07-27T15:13:09.871657+00:00",
13
- "resolved_at": "2026-07-28T01:34:13.078112+00:00",
14
- "target_end": "2026-07-27T17:35:00+00:00",
15
- "prediction_length": 36,
16
- "metric_version": "livehouse-canonical-v1"
17
- },
18
- {
19
- "dataset": "data_gov_sg_singapore_taxi_availability_available_taxi_count/5min/short",
20
- "task_id": "future-a378da744357008aedcd",
21
- "issued_at": "2026-07-27T22:37:47.857566+00:00",
22
- "resolved_at": "2026-07-28T01:34:13.451024+00:00",
23
- "target_end": "2026-07-26T15:05:00+00:00",
24
- "prediction_length": 12,
25
- "metric_version": "livehouse-canonical-v1"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
  ]
28
  }
 
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
  }