KeyError: 'model_name'

[ningmeng-Mo]

Hello, whenever I run the programme, whether using your dataset or my own, I consistently encounter the following issue.
root@I2286be2f7200301457:/hy-tmp/TFB# python ./scripts/run_benchmark.py --config-path "rolling_forecast_config.json" --data-name-list "ILI.csv" --strategy-args '{"horizon": 24}' --model-name "duet.DUET" --model-hyper-params '{"CI": 1, "batch_size": 8, "d_ff": 512, "d_model": 256, "dropout": 0.1, "e_layers": 2, "factor": 3, "fc_dropout": 0, "horizon": 24, "k": 2, "loss": "MAE", "lr": 0.001, "lradj": "type1", "n_heads": 1, "norm": true, "num_epochs": 100, "num_experts": 2, "patch_len": 48, "patience": 5, "seq_len": 104}' --deterministic "full" --gpus 0 --num-workers 1 --timeout 60000 --save-path "ILI/DUET"
2025-09-19 16:34:08 [INFO] ts_benchmark.data.data_source(126): Start loading 1 series in parallel
2025-09-19 16:34:08 [INFO] ts_benchmark.data.data_source(135): Data loading finished.
2025-09-19 16:34:08 [INFO] ts_benchmark.data.suites.global_storage(40): Data server starting...
2025-09-19 16:34:08 [INFO] ts_benchmark.data.suites.global_storage(41): Start sending data to the global storage.
2025-09-19 16:34:08 [INFO] ts_benchmark.data.suites.global_storage(46): Notifying all workers to sync data from the global storage.
2025-09-19 16:34:08 [INFO] ts_benchmark.data.suites.global_storage(49): Data server started.
2025-09-19 16:34:08 [INFO] ts_benchmark.models.model_loader(102): Trying to load model ts_benchmark.baselines.duet.DUET
scheduling DUET: 0%| | 0/1 [00:00<?, ?it/s]2025-09-19 16:34:09 [WARNING] ts_benchmark.baselines.deep_forecasting_model_base(54): The model parameter horizon is deprecated. Please use pred_len.
---------------------------------------------------------- DUET
Total trainable parameters: 1225507
Validation loss decreased (inf --> 0.309561). Saving model ...
Updating learning rate to 0.001
EarlyStopping counter: 1 out of 5
Updating learning rate to 0.0005
Validation loss decreased (0.309561 --> 0.296071). Saving model ...
Updating learning rate to 0.00025
Validation loss decreased (0.296071 --> 0.283024). Saving model ...
Updating learning rate to 0.000125
EarlyStopping counter: 1 out of 5
Updating learning rate to 6.25e-05
Validation loss decreased (0.283024 --> 0.281689). Saving model ...
Updating learning rate to 3.125e-05
EarlyStopping counter: 1 out of 5
Updating learning rate to 1.5625e-05
Validation loss decreased (0.281689 --> 0.274102). Saving model ...
Updating learning rate to 7.8125e-06
EarlyStopping counter: 1 out of 5
Updating learning rate to 3.90625e-06
EarlyStopping counter: 2 out of 5
Updating learning rate to 1.953125e-06
EarlyStopping counter: 3 out of 5
Updating learning rate to 9.765625e-07
EarlyStopping counter: 4 out of 5
Updating learning rate to 4.8828125e-07
Validation loss decreased (0.274102 --> 0.271266). Saving model ...
Updating learning rate to 2.44140625e-07
EarlyStopping counter: 1 out of 5
Updating learning rate to 1.220703125e-07
EarlyStopping counter: 2 out of 5
Updating learning rate to 6.103515625e-08
EarlyStopping counter: 3 out of 5
Updating learning rate to 3.0517578125e-08
EarlyStopping counter: 4 out of 5
Updating learning rate to 1.52587890625e-08
EarlyStopping counter: 5 out of 5
scheduling DUET: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:42<00:00, 42.27s/it]
collecting DUET: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 4364.52it/s]
2025-09-19 16:34:52 [INFO] ts_benchmark.recording(103): loading log file /hy-tmp/TFB/result/ILI/DUET/DUET.1758270892.I2286be2f7200301457.1771.csv.tar.gz
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/pandas/core/indexes/base.py", line 3621, in get_loc
return self._engine.get_loc(casted_key)
File "pandas/_libs/index.pyx", line 136, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 163, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 5198, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 5206, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'model_name'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "./scripts/run_benchmark.py", line 357, in
report(report_config, report_method=args.report_method)
File "/hy-tmp/TFB/ts_benchmark/report/init.py", line 12, in report
report_csv.report(report_config)
File "/hy-tmp/TFB/ts_benchmark/report/report_csv.py", line 52, in report
leaderboard_df = get_leaderboard(
File "/hy-tmp/TFB/ts_benchmark/report/utils/leaderboard.py", line 154, in get_leaderboard
single_metric_result = _calculate_single_metric_result(
File "/hy-tmp/TFB/ts_benchmark/report/utils/leaderboard.py", line 53, in _calculate_single_metric_result
metric_df["model_name"] + ";" + metric_df["model_params"]
File "/usr/local/lib/python3.8/dist-packages/pandas/core/frame.py", line 3505, in getitem
indexer = self.columns.get_loc(key)
File "/usr/local/lib/python3.8/dist-packages/pandas/core/indexes/base.py", line 3623, in get_loc
raise KeyError(key) from err
KeyError: 'model_name'