Upload folder using huggingface_hub

recipes/BirdCLEF2025/EfficientNetB0/exp/20250505-094415/log/20250505-094417/.hydra/config.yaml

@@ -0,0 +1,228 @@
+system:
+  seed: 0
+  distributed:
+    enable: null
+    nodes: null
+    nproc_per_node: null
+    backend: null
+    init_method: null
+    rdzv_id: null
+    rdzv_backend: null
+    rdzv_endpoint: null
+    max_restarts: null
+  cudnn:
+    benchmark: true
+    deterministic: false
+  amp:
+    enable: false
+    dtype: null
+  accelerator: cuda
+  compile:
+    enable: null
+    kwargs: null
+preprocess:
+  dump_format: birdclef2025
+  list_path: null
+  wav_dir: null
+  feature_dir: null
+  max_workers: null
+  max_shard_size: 1000000000
+  vad:
+    raw_root: null
+    trimmed_root: null
+    threshold: null
+    min_duration: 15
+  csv_path: ???
+  submission_path: ???
+  audio_root: ???
+  subset: ???
+  train_ratio: 0.8
+data:
+  audio:
+    sample_rate: 32000
+    duration: 15
+  melspectrogram:
+    _target_: birdclef2025.transforms.birdclef.BirdCLEF2025BaselineMelSpectrogram
+    sample_rate: ${..audio.sample_rate}
+    hop_length: 1253
+    f_min: 20
+    f_max: 16000
+    pad: 0
+    n_mels: 128
+    window_fn:
+      _target_: torch.hann_window
+      _partial_: true
+    power: 1.0
+    normalized: false
+    wkwargs: null
+    center: true
+    pad_mode: constant
+    onesided: null
+    norm: slaney
+    mel_scale: slaney
+    take_log: true
+    freq_mask_param:
+    - 0.06
+    - 0.1
+    time_mask_param:
+    - 0.06
+    - 0.12
+    eps: null
+train:
+  dataset:
+    train:
+      _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelDataset
+      list_path: dump/birdclef2025_15s/list/train.txt
+      feature_dir: /kaggle/input/birdclef-2025
+      audio_key: audio
+      sample_rate_key: sample_rate
+      label_name_key: primary_label
+      filename_key: filename
+    validation:
+      _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelDataset
+      list_path: dump/birdclef2025_15s/list/validation.txt
+      feature_dir: /kaggle/input/birdclef-2025
+      audio_key: ${..train.audio_key}
+      sample_rate_key: ${..train.sample_rate_key}
+      label_name_key: ${..train.label_name_key}
+      filename_key: ${..train.filename_key}
+  dataloader:
+    train:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 64
+      shuffle: true
+      collate_fn:
+        _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025BaselineValidationCollator
+        composer:
+          _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer
+          melspectrogram_transform: ${data.melspectrogram}
+          audio_key: audio
+          sample_rate_key: sample_rate
+          label_name_key: primary_label
+          filename_key: filename
+          waveform_key: waveform
+          melspectrogram_key: log_melspectrogram
+          label_index_key: label_index
+          sample_rate: ${data.audio.sample_rate}
+          duration: ${data.audio.duration}
+          decode_audio_as_waveform: true
+          decode_audio_as_monoral: true
+          training: false
+        melspectrogram_key: ${.composer.melspectrogram_key}
+        label_index_key: ${.composer.label_index_key}
+      num_workers: ${const:birdclef2025.utils.data.default_num_workers}
+    validation:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 64
+      shuffle: false
+      collate_fn:
+        _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025BaselineValidationCollator
+        composer:
+          _target_: ${....train.collate_fn.composer._target_}
+          melspectrogram_transform: ${....train.collate_fn.composer.melspectrogram_transform}
+          audio_key: ${....train.collate_fn.composer.audio_key}
+          sample_rate_key: ${....train.collate_fn.composer.sample_rate_key}
+          label_name_key: ${....train.collate_fn.composer.label_name_key}
+          filename_key: ${....train.collate_fn.composer.filename_key}
+          waveform_key: ${....train.collate_fn.composer.waveform_key}
+          melspectrogram_key: ${....train.collate_fn.composer.melspectrogram_key}
+          label_index_key: ${....train.collate_fn.composer.label_index_key}
+          sample_rate: ${....train.collate_fn.composer.sample_rate}
+          duration: ${....train.collate_fn.composer.duration}
+          decode_audio_as_waveform: ${....train.collate_fn.composer.decode_audio_as_waveform}
+          decode_audio_as_monoral: ${....train.collate_fn.composer.decode_audio_as_monoral}
+          training: false
+        melspectrogram_key: ${...train.collate_fn.composer.melspectrogram_key}
+        label_index_key: ${...train.collate_fn.composer.label_index_key}
+      num_workers: ${const:birdclef2025.utils.data.default_num_workers}
+  clip_gradient: {}
+  record: {}
+  trainer:
+    _target_: birdclef2025.utils.driver.BaseTrainer
+  key_mapping:
+    train:
+      input:
+        input: ${....dataloader.train.collate_fn.composer.melspectrogram_key}
+      output: logit
+    validation: ${.train}
+    inference: ${.validation}
+  ddp_kwargs: null
+  resume:
+    continue_from: ''
+  output:
+    exp_dir: ./exp/20250505-094415
+    tensorboard_dir: ./tensorboard/20250505-094415
+    save_checkpoint:
+      iteration:
+        every: 10000
+        path: ${...exp_dir}/model/iteration{iteration}.pth
+      epoch:
+        every: 10
+        path: ${...exp_dir}/model/epoch{epoch}.pth
+      last:
+        path: ${...exp_dir}/model/last.pth
+      best_epoch:
+        path: ${...exp_dir}/model/best_epoch.pth
+  steps:
+    epochs: 10
+    iterations: null
+    lr_scheduler: epoch
+test:
+  dataset:
+    test:
+      _target_: torch.utils.data.Dataset
+  dataloader:
+    test:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 1
+      shuffle: false
+  key_mapping:
+    inference:
+      input: null
+      output: null
+      identifier: null
+  checkpoint: null
+  remove_weight_norm: null
+  output:
+    exp_dir: ./exp
+    inference_dir: ${.exp_dir}/inference
+    audio:
+      sample_rate: ${data.audio.sample_rate}
+      key_mapping:
+        inference:
+          output: null
+          reference: null
+      transforms:
+        inference:
+          output: null
+          reference: null
+model:
+  _target_: birdclef2025.models.EfficientNetB0
+  weights: ${const:torchvision.models.EfficientNet_B0_Weights.IMAGENET1K_V1}
+  num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels}
+optimizer:
+  _target_: torch.optim.Adam
+lr_scheduler: {}
+criterion:
+  _target_: audyn.criterion.MultiCriteria
+  cross_entropy:
+    _target_: audyn.criterion.BaseCriterionWrapper
+    criterion:
+      _target_: torch.nn.CrossEntropyLoss
+      reduction: mean
+    weight: 1
+    key_mapping:
+      estimated:
+        input: logit
+      target:
+        target: ${train.dataloader.train.collate_fn.composer.label_index_key}
+metrics:
+  roc_auc:
+    metric:
+      _target_: birdclef2025.metrics.ROCAUC
+      take_softmax: true
+    key_mapping:
+      estimated:
+        input: logit
+      target:
+        target: ${train.dataloader.train.collate_fn.composer.label_index_key}

recipes/BirdCLEF2025/EfficientNetB0/exp/20250505-094415/log/20250505-094417/.hydra/hydra.yaml

@@ -0,0 +1,191 @@
+hydra:
+  run:
+    dir: ./exp/20250505-094415/log/20250505-094417
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.run.dir=./exp/20250505-094415/log/20250505-094417
+    - hydra.mode=RUN
+    task:
+    - system=cuda
+    - preprocess=birdclef2025
+    - data=birdclef2025_15s
+    - train=birdclef2025_noaug_efficientnet_b0
+    - model=birdclef2025_efficientnet_b0
+    - optimizer=adam
+    - lr_scheduler=none
+    - criterion=birdclef2025_categorical_cross_entropy
+    - +metrics=birdclef2025_categorical_cross_entropy
+    - preprocess.dump_format=birdclef2025
+    - train.dataset.train.list_path=dump/birdclef2025_15s/list/train.txt
+    - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025
+    - train.dataset.validation.list_path=dump/birdclef2025_15s/list/validation.txt
+    - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025
+    - train.resume.continue_from=
+    - train.output.exp_dir=./exp/20250505-094415
+    - train.output.tensorboard_dir=./tensorboard/20250505-094415
+  job:
+    name: train
+    chdir: false
+    override_dirname: +metrics=birdclef2025_categorical_cross_entropy,criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_15s,lr_scheduler=none,model=birdclef2025_efficientnet_b0,optimizer=adam,preprocess.dump_format=birdclef2025,preprocess=birdclef2025,system=cuda,train.dataset.train.feature_dir=/kaggle/input/birdclef-2025,train.dataset.train.list_path=dump/birdclef2025_15s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_15s/list/validation.txt,train.output.exp_dir=./exp/20250505-094415,train.output.tensorboard_dir=./tensorboard/20250505-094415,train.resume.continue_from=,train=birdclef2025_noaug_efficientnet_b0
+    id: ???
+    num: ???
+    config_name: config
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.2'
+    cwd: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/EfficientNetB0
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /usr/local/lib/python3.10/dist-packages/audyn/configs
+      schema: file
+      provider: main
+    - path: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/EfficientNetB0/conf
+      schema: file
+      provider: command-line
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/EfficientNetB0/exp/20250505-094415/log/20250505-094417
+    choices:
+      metrics: birdclef2025_categorical_cross_entropy
+      criterion: birdclef2025_categorical_cross_entropy
+      lr_scheduler: none
+      optimizer: adam
+      model: birdclef2025_efficientnet_b0
+      test: default
+      test/dataloader: default
+      test/dataset: default
+      train: birdclef2025_noaug_efficientnet_b0
+      train/record: default
+      train/clip_gradient: default
+      train/dataloader: default
+      train/dataset: birdclef2025_primary-label
+      data: birdclef2025_15s
+      preprocess: birdclef2025
+      system: cuda
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

recipes/BirdCLEF2025/EfficientNetB0/exp/20250505-094415/log/20250505-094417/.hydra/overrides.yaml

@@ -0,0 +1,17 @@
+- system=cuda
+- preprocess=birdclef2025
+- data=birdclef2025_15s
+- train=birdclef2025_noaug_efficientnet_b0
+- model=birdclef2025_efficientnet_b0
+- optimizer=adam
+- lr_scheduler=none
+- criterion=birdclef2025_categorical_cross_entropy
+- +metrics=birdclef2025_categorical_cross_entropy
+- preprocess.dump_format=birdclef2025
+- train.dataset.train.list_path=dump/birdclef2025_15s/list/train.txt
+- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025
+- train.dataset.validation.list_path=dump/birdclef2025_15s/list/validation.txt
+- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025
+- train.resume.continue_from=
+- train.output.exp_dir=./exp/20250505-094415
+- train.output.tensorboard_dir=./tensorboard/20250505-094415

recipes/BirdCLEF2025/EfficientNetB0/exp/20250505-094415/log/20250505-094417/.hydra/resolved_config.yaml

@@ -0,0 +1,287 @@
+system:
+  seed: 0
+  distributed:
+    enable: null
+    nodes: null
+    nproc_per_node: null
+    backend: null
+    init_method: null
+    rdzv_id: null
+    rdzv_backend: null
+    rdzv_endpoint: null
+    max_restarts: null
+  cudnn:
+    benchmark: true
+    deterministic: false
+  amp:
+    enable: false
+    dtype: null
+  accelerator: cuda
+  compile:
+    enable: false
+    kwargs: null
+preprocess:
+  dump_format: birdclef2025
+  list_path: null
+  wav_dir: null
+  feature_dir: null
+  max_workers: 2
+  max_shard_size: 1000000000
+  vad:
+    raw_root: null
+    trimmed_root: null
+    threshold: null
+    min_duration: 15
+  csv_path: ???
+  submission_path: ???
+  audio_root: ???
+  subset: ???
+  train_ratio: 0.8
+data:
+  audio:
+    sample_rate: 32000
+    duration: 15
+  melspectrogram:
+    _target_: birdclef2025.transforms.birdclef.BirdCLEF2025BaselineMelSpectrogram
+    sample_rate: 32000
+    hop_length: 1253
+    f_min: 20
+    f_max: 16000
+    pad: 0
+    n_mels: 128
+    window_fn:
+      _target_: torch.hann_window
+      _partial_: true
+    power: 1.0
+    normalized: false
+    wkwargs: null
+    center: true
+    pad_mode: constant
+    onesided: null
+    norm: slaney
+    mel_scale: slaney
+    take_log: true
+    freq_mask_param:
+    - 0.06
+    - 0.1
+    time_mask_param:
+    - 0.06
+    - 0.12
+    eps: null
+train:
+  dataset:
+    train:
+      _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelDataset
+      list_path: dump/birdclef2025_15s/list/train.txt
+      feature_dir: /kaggle/input/birdclef-2025
+      audio_key: audio
+      sample_rate_key: sample_rate
+      label_name_key: primary_label
+      filename_key: filename
+    validation:
+      _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelDataset
+      list_path: dump/birdclef2025_15s/list/validation.txt
+      feature_dir: /kaggle/input/birdclef-2025
+      audio_key: audio
+      sample_rate_key: sample_rate
+      label_name_key: primary_label
+      filename_key: filename
+  dataloader:
+    train:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 64
+      shuffle: true
+      collate_fn:
+        _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025BaselineValidationCollator
+        composer:
+          _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer
+          melspectrogram_transform:
+            _target_: birdclef2025.transforms.birdclef.BirdCLEF2025BaselineMelSpectrogram
+            sample_rate: 32000
+            hop_length: 1253
+            f_min: 20
+            f_max: 16000
+            pad: 0
+            n_mels: 128
+            window_fn:
+              _target_: torch.hann_window
+              _partial_: true
+            power: 1.0
+            normalized: false
+            wkwargs: null
+            center: true
+            pad_mode: constant
+            onesided: null
+            norm: slaney
+            mel_scale: slaney
+            take_log: true
+            freq_mask_param:
+            - 0.06
+            - 0.1
+            time_mask_param:
+            - 0.06
+            - 0.12
+            eps: null
+          audio_key: audio
+          sample_rate_key: sample_rate
+          label_name_key: primary_label
+          filename_key: filename
+          waveform_key: waveform
+          melspectrogram_key: log_melspectrogram
+          label_index_key: label_index
+          sample_rate: 32000
+          duration: 15
+          decode_audio_as_waveform: true
+          decode_audio_as_monoral: true
+          training: false
+        melspectrogram_key: log_melspectrogram
+        label_index_key: label_index
+      num_workers: 2
+    validation:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 64
+      shuffle: false
+      collate_fn:
+        _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025BaselineValidationCollator
+        composer:
+          _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer
+          melspectrogram_transform:
+            _target_: birdclef2025.transforms.birdclef.BirdCLEF2025BaselineMelSpectrogram
+            sample_rate: 32000
+            hop_length: 1253
+            f_min: 20
+            f_max: 16000
+            pad: 0
+            n_mels: 128
+            window_fn:
+              _target_: torch.hann_window
+              _partial_: true
+            power: 1.0
+            normalized: false
+            wkwargs: null
+            center: true
+            pad_mode: constant
+            onesided: null
+            norm: slaney
+            mel_scale: slaney
+            take_log: true
+            freq_mask_param:
+            - 0.06
+            - 0.1
+            time_mask_param:
+            - 0.06
+            - 0.12
+            eps: null
+          audio_key: audio
+          sample_rate_key: sample_rate
+          label_name_key: primary_label
+          filename_key: filename
+          waveform_key: waveform
+          melspectrogram_key: log_melspectrogram
+          label_index_key: label_index
+          sample_rate: 32000
+          duration: 15
+          decode_audio_as_waveform: true
+          decode_audio_as_monoral: true
+          training: false
+        melspectrogram_key: log_melspectrogram
+        label_index_key: label_index
+      num_workers: 2
+  clip_gradient: {}
+  record: {}
+  trainer:
+    _target_: birdclef2025.utils.driver.BaseTrainer
+  key_mapping:
+    train:
+      input:
+        input: log_melspectrogram
+      output: logit
+    validation:
+      input:
+        input: log_melspectrogram
+      output: logit
+    inference:
+      input:
+        input: log_melspectrogram
+      output: logit
+  ddp_kwargs: null
+  resume:
+    continue_from: ''
+  output:
+    exp_dir: ./exp/20250505-094415
+    tensorboard_dir: ./tensorboard/20250505-094415
+    save_checkpoint:
+      iteration:
+        every: 10000
+        path: ./exp/20250505-094415/model/iteration{iteration}.pth
+      epoch:
+        every: 10
+        path: ./exp/20250505-094415/model/epoch{epoch}.pth
+      last:
+        path: ./exp/20250505-094415/model/last.pth
+      best_epoch:
+        path: ./exp/20250505-094415/model/best_epoch.pth
+  steps:
+    epochs: 10
+    iterations: null
+    lr_scheduler: epoch
+test:
+  dataset:
+    test:
+      _target_: torch.utils.data.Dataset
+  dataloader:
+    test:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 1
+      shuffle: false
+  key_mapping:
+    inference:
+      input: null
+      output: null
+      identifier: null
+  checkpoint: null
+  remove_weight_norm: null
+  output:
+    exp_dir: ./exp
+    inference_dir: ./exp/inference
+    audio:
+      sample_rate: 32000
+      key_mapping:
+        inference:
+          output: null
+          reference: null
+      transforms:
+        inference:
+          output: null
+          reference: null
+  ddp_kwargs: null
+model:
+  _target_: birdclef2025.models.EfficientNetB0
+  weights: IMAGENET1K_V1
+  num_classes: 206
+optimizer:
+  _target_: torch.optim.Adam
+lr_scheduler: {}
+criterion:
+  _target_: audyn.criterion.MultiCriteria
+  cross_entropy:
+    _target_: audyn.criterion.BaseCriterionWrapper
+    criterion:
+      _target_: torch.nn.CrossEntropyLoss
+      reduction: mean
+    weight: 1
+    key_mapping:
+      estimated:
+        input: logit
+      target:
+        target: label_index
+metrics:
+  roc_auc:
+    metric:
+      _target_: birdclef2025.metrics.ROCAUC
+      take_softmax: true
+    key_mapping:
+      estimated:
+        input: logit
+      target:
+        target: label_index

recipes/BirdCLEF2025/EfficientNetB0/exp/20250505-094415/log/20250505-094417/train.log

@@ -0,0 +1,1045 @@
+[2025-05-05 09:44:45,181][BaseTrainer][INFO] - system:
+  seed: 0
+  distributed:
+    enable: null
+    nodes: null
+    nproc_per_node: null
+    backend: null
+    init_method: null
+    rdzv_id: null
+    rdzv_backend: null
+    rdzv_endpoint: null
+    max_restarts: null
+  cudnn:
+    benchmark: true
+    deterministic: false
+  amp:
+    enable: false
+    dtype: null
+  accelerator: cuda
+  compile:
+    enable: false
+    kwargs: null
+preprocess:
+  dump_format: birdclef2025
+  list_path: null
+  wav_dir: null
+  feature_dir: null
+  max_workers: 2
+  max_shard_size: 1000000000
+  vad:
+    raw_root: null
+    trimmed_root: null
+    threshold: null
+    min_duration: 15
+  csv_path: ???
+  submission_path: ???
+  audio_root: ???
+  subset: ???
+  train_ratio: 0.8
+data:
+  audio:
+    sample_rate: 32000
+    duration: 15
+  melspectrogram:
+    _target_: birdclef2025.transforms.birdclef.BirdCLEF2025BaselineMelSpectrogram
+    sample_rate: 32000
+    hop_length: 1253
+    f_min: 20
+    f_max: 16000
+    pad: 0
+    n_mels: 128
+    window_fn:
+      _target_: torch.hann_window
+      _partial_: true
+    power: 1.0
+    normalized: false
+    wkwargs: null
+    center: true
+    pad_mode: constant
+    onesided: null
+    norm: slaney
+    mel_scale: slaney
+    take_log: true
+    freq_mask_param:
+    - 0.06
+    - 0.1
+    time_mask_param:
+    - 0.06
+    - 0.12
+    eps: null
+train:
+  dataset:
+    train:
+      _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelDataset
+      list_path: dump/birdclef2025_15s/list/train.txt
+      feature_dir: /kaggle/input/birdclef-2025
+      audio_key: audio
+      sample_rate_key: sample_rate
+      label_name_key: primary_label
+      filename_key: filename
+    validation:
+      _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelDataset
+      list_path: dump/birdclef2025_15s/list/validation.txt
+      feature_dir: /kaggle/input/birdclef-2025
+      audio_key: ${..train.audio_key}
+      sample_rate_key: ${..train.sample_rate_key}
+      label_name_key: ${..train.label_name_key}
+      filename_key: ${..train.filename_key}
+  dataloader:
+    train:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 64
+      shuffle: true
+      collate_fn:
+        _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025BaselineValidationCollator
+        composer:
+          _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer
+          melspectrogram_transform: ${data.melspectrogram}
+          audio_key: audio
+          sample_rate_key: sample_rate
+          label_name_key: primary_label
+          filename_key: filename
+          waveform_key: waveform
+          melspectrogram_key: log_melspectrogram
+          label_index_key: label_index
+          sample_rate: ${data.audio.sample_rate}
+          duration: ${data.audio.duration}
+          decode_audio_as_waveform: true
+          decode_audio_as_monoral: true
+          training: false
+        melspectrogram_key: ${.composer.melspectrogram_key}
+        label_index_key: ${.composer.label_index_key}
+      num_workers: ${const:birdclef2025.utils.data.default_num_workers}
+    validation:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 64
+      shuffle: false
+      collate_fn:
+        _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025BaselineValidationCollator
+        composer:
+          _target_: ${....train.collate_fn.composer._target_}
+          melspectrogram_transform: ${....train.collate_fn.composer.melspectrogram_transform}
+          audio_key: ${....train.collate_fn.composer.audio_key}
+          sample_rate_key: ${....train.collate_fn.composer.sample_rate_key}
+          label_name_key: ${....train.collate_fn.composer.label_name_key}
+          filename_key: ${....train.collate_fn.composer.filename_key}
+          waveform_key: ${....train.collate_fn.composer.waveform_key}
+          melspectrogram_key: ${....train.collate_fn.composer.melspectrogram_key}
+          label_index_key: ${....train.collate_fn.composer.label_index_key}
+          sample_rate: ${....train.collate_fn.composer.sample_rate}
+          duration: ${....train.collate_fn.composer.duration}
+          decode_audio_as_waveform: ${....train.collate_fn.composer.decode_audio_as_waveform}
+          decode_audio_as_monoral: ${....train.collate_fn.composer.decode_audio_as_monoral}
+          training: false
+        melspectrogram_key: ${...train.collate_fn.composer.melspectrogram_key}
+        label_index_key: ${...train.collate_fn.composer.label_index_key}
+      num_workers: ${const:birdclef2025.utils.data.default_num_workers}
+  clip_gradient: {}
+  record: {}
+  trainer:
+    _target_: birdclef2025.utils.driver.BaseTrainer
+    _partial_: true
+  key_mapping:
+    train:
+      input:
+        input: ${....dataloader.train.collate_fn.composer.melspectrogram_key}
+      output: logit
+    validation: ${.train}
+    inference: ${.validation}
+  ddp_kwargs: null
+  resume:
+    continue_from: ''
+  output:
+    exp_dir: ./exp/20250505-094415
+    tensorboard_dir: ./tensorboard/20250505-094415
+    save_checkpoint:
+      iteration:
+        every: 10000
+        path: ${...exp_dir}/model/iteration{iteration}.pth
+      epoch:
+        every: 10
+        path: ${...exp_dir}/model/epoch{epoch}.pth
+      last:
+        path: ${...exp_dir}/model/last.pth
+      best_epoch:
+        path: ${...exp_dir}/model/best_epoch.pth
+  steps:
+    epochs: 10
+    iterations: null
+    lr_scheduler: epoch
+test:
+  dataset:
+    test:
+      _target_: torch.utils.data.Dataset
+  dataloader:
+    test:
+      _target_: torch.utils.data.DataLoader
+      batch_size: 1
+      shuffle: false
+  key_mapping:
+    inference:
+      input: null
+      output: null
+      identifier: null
+  checkpoint: null
+  remove_weight_norm: null
+  output:
+    exp_dir: ./exp
+    inference_dir: ${.exp_dir}/inference
+    audio:
+      sample_rate: ${data.audio.sample_rate}
+      key_mapping:
+        inference:
+          output: null
+          reference: null
+      transforms:
+        inference:
+          output: null
+          reference: null
+  ddp_kwargs: null
+model:
+  _target_: birdclef2025.models.EfficientNetB0
+  weights: ${const:torchvision.models.EfficientNet_B0_Weights.IMAGENET1K_V1}
+  num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels}
+optimizer:
+  _target_: torch.optim.Adam
+lr_scheduler: {}
+criterion:
+  _target_: audyn.criterion.MultiCriteria
+  cross_entropy:
+    _target_: audyn.criterion.BaseCriterionWrapper
+    criterion:
+      _target_: torch.nn.CrossEntropyLoss
+      reduction: mean
+    weight: 1
+    key_mapping:
+      estimated:
+        input: logit
+      target:
+        target: ${train.dataloader.train.collate_fn.composer.label_index_key}
+metrics:
+  roc_auc:
+    metric:
+      _target_: birdclef2025.metrics.ROCAUC
+      take_softmax: true
+    key_mapping:
+      estimated:
+        input: logit
+      target:
+        target: ${train.dataloader.train.collate_fn.composer.label_index_key}
+
+[2025-05-05 09:44:45,181][BaseTrainer][INFO] - EfficientNetB0(
+  (backbone): Sequential(
+    (0): Conv2dNormActivation(
+      (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+      (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+      (2): SiLU(inplace=True)
+    )
+    (1): Sequential(
+      (0): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
+            (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(32, 8, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(8, 32, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (2): Conv2dNormActivation(
+            (0): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.0, mode=row)
+      )
+    )
+    (2): Sequential(
+      (0): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)
+            (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(96, 4, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(4, 96, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.0125, mode=row)
+      )
+      (1): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)
+            (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.025, mode=row)
+      )
+    )
+    (3): Sequential(
+      (0): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(144, 144, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=144, bias=False)
+            (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(144, 6, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(6, 144, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(40, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.037500000000000006, mode=row)
+      )
+      (1): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=240, bias=False)
+            (1): BatchNorm2d(240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(40, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.05, mode=row)
+      )
+    )
+    (4): Sequential(
+      (0): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(240, 240, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=240, bias=False)
+            (1): BatchNorm2d(240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(240, 10, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(10, 240, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(240, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.0625, mode=row)
+      )
+      (1): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=480, bias=False)
+            (1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.07500000000000001, mode=row)
+      )
+      (2): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=480, bias=False)
+            (1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(80, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.08750000000000001, mode=row)
+      )
+    )
+    (5): Sequential(
+      (0): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(480, 480, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=480, bias=False)
+            (1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(480, 20, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(20, 480, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(480, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.1, mode=row)
+      )
+      (1): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=672, bias=False)
+            (1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.1125, mode=row)
+      )
+      (2): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(672, 672, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=672, bias=False)
+            (1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.125, mode=row)
+      )
+    )
+    (6): Sequential(
+      (0): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(672, 672, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=672, bias=False)
+            (1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(672, 28, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(28, 672, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.1375, mode=row)
+      )
+      (1): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.15000000000000002, mode=row)
+      )
+      (2): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.1625, mode=row)
+      )
+      (3): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.17500000000000002, mode=row)
+      )
+    )
+    (7): Sequential(
+      (0): MBConv(
+        (block): Sequential(
+          (0): Conv2dNormActivation(
+            (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (1): Conv2dNormActivation(
+            (0): Conv2d(1152, 1152, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=1152, bias=False)
+            (1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (2): SiLU(inplace=True)
+          )
+          (2): SqueezeExcitation(
+            (avgpool): AdaptiveAvgPool2d(output_size=1)
+            (fc1): Conv2d(1152, 48, kernel_size=(1, 1), stride=(1, 1))
+            (fc2): Conv2d(48, 1152, kernel_size=(1, 1), stride=(1, 1))
+            (activation): SiLU(inplace=True)
+            (scale_activation): Sigmoid()
+          )
+          (3): Conv2dNormActivation(
+            (0): Conv2d(1152, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (stochastic_depth): StochasticDepth(p=0.1875, mode=row)
+      )
+    )
+    (8): Conv2dNormActivation(
+      (0): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
+      (1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+      (2): SiLU(inplace=True)
+    )
+  )
+  (avgpool): AdaptiveAvgPool2d(output_size=1)
+  (classifier): Sequential(
+    (0): Dropout(p=0.2, inplace=False)
+    (1): Linear(in_features=1280, out_features=206, bias=True)
+  )
+)
+[2025-05-05 09:44:45,185][BaseTrainer][INFO] - # of parameters: 4271434.
+[2025-05-05 09:44:53,812][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.3044819831848145, cross_entropy: 5.3044819831848145
+[2025-05-05 09:44:54,104][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.359292030334473, cross_entropy: 5.359292030334473
+[2025-05-05 09:44:54,391][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.181077480316162, cross_entropy: 5.181077480316162
+[2025-05-05 09:44:54,709][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.193525314331055, cross_entropy: 5.193525314331055
+[2025-05-05 09:44:55,268][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.035099983215332, cross_entropy: 5.035099983215332
+[2025-05-05 09:44:57,704][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.028683662414551, cross_entropy: 5.028683662414551
+[2025-05-05 09:44:58,286][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 4.94443416595459, cross_entropy: 4.94443416595459
+[2025-05-05 09:45:00,754][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.00942850112915, cross_entropy: 5.00942850112915
+[2025-05-05 09:45:01,075][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 4.736028671264648, cross_entropy: 4.736028671264648
+[2025-05-05 09:45:03,926][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 4.761155128479004, cross_entropy: 4.761155128479004
+[2025-05-05 09:45:04,257][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 4.883791923522949, cross_entropy: 4.883791923522949
+[2025-05-05 09:45:06,691][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.7488603591918945, cross_entropy: 4.7488603591918945
+[2025-05-05 09:45:06,999][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.90508508682251, cross_entropy: 4.90508508682251
+[2025-05-05 09:45:10,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.743208885192871, cross_entropy: 4.743208885192871
+[2025-05-05 09:45:11,165][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.541562080383301, cross_entropy: 4.541562080383301
+[2025-05-05 09:45:13,644][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.653104305267334, cross_entropy: 4.653104305267334
+[2025-05-05 09:45:13,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 4.9948906898498535, cross_entropy: 4.9948906898498535
+[2025-05-05 09:45:16,796][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 4.959690093994141, cross_entropy: 4.959690093994141
+[2025-05-05 09:45:17,417][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.700274467468262, cross_entropy: 4.700274467468262
+[2025-05-05 09:45:19,582][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.301037788391113, cross_entropy: 4.301037788391113
+[2025-05-05 09:45:20,887][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.551095008850098, cross_entropy: 4.551095008850098
+[2025-05-05 09:45:22,143][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.5659990310668945, cross_entropy: 4.5659990310668945
+[2025-05-05 09:45:23,886][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.437910079956055, cross_entropy: 4.437910079956055
+[2025-05-05 09:45:25,221][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.478883743286133, cross_entropy: 4.478883743286133
+[2025-05-05 09:45:26,893][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.3158464431762695, cross_entropy: 4.3158464431762695
+[2025-05-05 09:45:29,233][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.4522504806518555, cross_entropy: 4.4522504806518555
+[2025-05-05 09:45:29,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.317988395690918, cross_entropy: 4.317988395690918
+[2025-05-05 09:45:32,527][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.0444722175598145, cross_entropy: 4.0444722175598145
+[2025-05-05 09:45:32,815][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.207454204559326, cross_entropy: 4.207454204559326
+[2025-05-05 09:45:35,800][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.256237983703613, cross_entropy: 4.256237983703613
+[2025-05-05 09:45:36,087][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.132406234741211, cross_entropy: 4.132406234741211
+[2025-05-05 09:45:38,886][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.214587211608887, cross_entropy: 4.214587211608887
+[2025-05-05 09:45:39,152][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.3889899253845215, cross_entropy: 4.3889899253845215
+[2025-05-05 09:45:42,643][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.112233638763428, cross_entropy: 4.112233638763428
+[2025-05-05 09:45:42,927][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.208951473236084, cross_entropy: 4.208951473236084
+[2025-05-05 09:45:45,674][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 3.9804739952087402, cross_entropy: 3.9804739952087402
+[2025-05-05 09:45:45,952][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.045773029327393, cross_entropy: 4.045773029327393
+[2025-05-05 09:45:48,380][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 3.831357479095459, cross_entropy: 3.831357479095459
+[2025-05-05 09:45:48,646][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.062015056610107, cross_entropy: 4.062015056610107
+[2025-05-05 09:45:52,395][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.1217498779296875, cross_entropy: 4.1217498779296875
+[2025-05-05 09:45:52,663][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 3.667060613632202, cross_entropy: 3.667060613632202
+[2025-05-05 09:45:55,796][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 3.9150490760803223, cross_entropy: 3.9150490760803223
+[2025-05-05 09:45:56,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 3.4254770278930664, cross_entropy: 3.4254770278930664
+[2025-05-05 09:45:58,235][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.047301769256592, cross_entropy: 4.047301769256592
+[2025-05-05 09:45:58,513][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 3.868840217590332, cross_entropy: 3.868840217590332
+[2025-05-05 09:46:01,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 3.602304458618164, cross_entropy: 3.602304458618164
+[2025-05-05 09:46:01,830][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.087170600891113, cross_entropy: 4.087170600891113
+[2025-05-05 09:46:04,620][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 3.497514247894287, cross_entropy: 3.497514247894287
+[2025-05-05 09:46:04,953][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 3.723015069961548, cross_entropy: 3.723015069961548
+[2025-05-05 09:46:07,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 3.4713640213012695, cross_entropy: 3.4713640213012695
+[2025-05-05 09:46:07,951][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 3.3803837299346924, cross_entropy: 3.3803837299346924
+[2025-05-05 09:46:10,538][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 3.4266440868377686, cross_entropy: 3.4266440868377686
+[2025-05-05 09:46:10,901][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 3.4024219512939453, cross_entropy: 3.4024219512939453
+[2025-05-05 09:46:14,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 3.674903392791748, cross_entropy: 3.674903392791748
+[2025-05-05 09:46:14,829][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 3.7284488677978516, cross_entropy: 3.7284488677978516
+[2025-05-05 09:46:17,464][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 3.896651268005371, cross_entropy: 3.896651268005371
+[2025-05-05 09:46:17,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 3.543196678161621, cross_entropy: 3.543196678161621
+[2025-05-05 09:46:20,605][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 3.4224328994750977, cross_entropy: 3.4224328994750977
+[2025-05-05 09:46:20,885][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 3.528635025024414, cross_entropy: 3.528635025024414
+[2025-05-05 09:46:24,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 3.2219009399414062, cross_entropy: 3.2219009399414062
+[2025-05-05 09:46:24,355][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 3.474341869354248, cross_entropy: 3.474341869354248
+[2025-05-05 09:46:27,570][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 3.117574453353882, cross_entropy: 3.117574453353882
+[2025-05-05 09:46:27,837][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 3.488274097442627, cross_entropy: 3.488274097442627
+[2025-05-05 09:46:30,446][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 2.8341617584228516, cross_entropy: 2.8341617584228516
+[2025-05-05 09:46:30,727][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 3.3542423248291016, cross_entropy: 3.3542423248291016
+[2025-05-05 09:46:33,560][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 3.385037899017334, cross_entropy: 3.385037899017334
+[2025-05-05 09:46:33,845][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 3.3171205520629883, cross_entropy: 3.3171205520629883
+[2025-05-05 09:46:36,949][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 3.467435121536255, cross_entropy: 3.467435121536255
+[2025-05-05 09:46:37,226][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 3.5573220252990723, cross_entropy: 3.5573220252990723
+[2025-05-05 09:46:39,503][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 3.022134304046631, cross_entropy: 3.022134304046631
+[2025-05-05 09:46:39,782][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 3.5358519554138184, cross_entropy: 3.5358519554138184
+[2025-05-05 09:46:42,825][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 3.5402398109436035, cross_entropy: 3.5402398109436035
+[2025-05-05 09:46:43,117][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 2.891481399536133, cross_entropy: 2.891481399536133
+[2025-05-05 09:46:46,312][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 2.97945499420166, cross_entropy: 2.97945499420166
+[2025-05-05 09:46:46,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 3.1224918365478516, cross_entropy: 3.1224918365478516
+[2025-05-05 09:46:49,781][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 2.911125898361206, cross_entropy: 2.911125898361206
+[2025-05-05 09:46:50,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 2.999051094055176, cross_entropy: 2.999051094055176
+[2025-05-05 09:46:52,794][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 3.449187755584717, cross_entropy: 3.449187755584717
+[2025-05-05 09:46:53,067][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 2.743861675262451, cross_entropy: 2.743861675262451
+[2025-05-05 09:46:55,680][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 2.905088424682617, cross_entropy: 2.905088424682617
+[2025-05-05 09:46:55,953][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 3.1474924087524414, cross_entropy: 3.1474924087524414
+[2025-05-05 09:46:58,936][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 3.0723185539245605, cross_entropy: 3.0723185539245605
+[2025-05-05 09:46:59,290][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 3.306333541870117, cross_entropy: 3.306333541870117
+[2025-05-05 09:47:01,869][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 3.0679280757904053, cross_entropy: 3.0679280757904053
+[2025-05-05 09:47:02,577][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 3.4102044105529785, cross_entropy: 3.4102044105529785
+[2025-05-05 09:47:05,249][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 3.0075879096984863, cross_entropy: 3.0075879096984863
+[2025-05-05 09:47:06,137][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 2.9128518104553223, cross_entropy: 2.9128518104553223
+[2025-05-05 09:47:08,479][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 3.0350518226623535, cross_entropy: 3.0350518226623535
+[2025-05-05 09:47:08,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 2.9499733448028564, cross_entropy: 2.9499733448028564
+[2025-05-05 09:47:12,073][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 3.022963047027588, cross_entropy: 3.022963047027588
+[2025-05-05 09:47:12,340][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 2.994563579559326, cross_entropy: 2.994563579559326
+[2025-05-05 09:47:14,549][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 2.632516622543335, cross_entropy: 2.632516622543335
+[2025-05-05 09:47:15,470][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 3.2041497230529785, cross_entropy: 3.2041497230529785
+[2025-05-05 09:47:18,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 2.9007208347320557, cross_entropy: 2.9007208347320557
+[2025-05-05 09:47:19,009][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 3.005298137664795, cross_entropy: 3.005298137664795
+[2025-05-05 09:47:21,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 2.8202903270721436, cross_entropy: 2.8202903270721436
+[2025-05-05 09:47:21,843][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 3.1353464126586914, cross_entropy: 3.1353464126586914
+[2025-05-05 09:47:24,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 2.6882143020629883, cross_entropy: 2.6882143020629883
+[2025-05-05 09:47:25,255][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 2.542910099029541, cross_entropy: 2.542910099029541
+[2025-05-05 09:47:28,739][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 2.6153109073638916, cross_entropy: 2.6153109073638916
+[2025-05-05 09:47:29,029][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 3.251145362854004, cross_entropy: 3.251145362854004
+[2025-05-05 09:47:31,835][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 2.772571563720703, cross_entropy: 2.772571563720703
+[2025-05-05 09:47:32,102][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 3.0203089714050293, cross_entropy: 3.0203089714050293
+[2025-05-05 09:47:35,187][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 2.638249397277832, cross_entropy: 2.638249397277832
+[2025-05-05 09:47:35,476][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 2.763543128967285, cross_entropy: 2.763543128967285
+[2025-05-05 09:47:38,050][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 3.3073742389678955, cross_entropy: 3.3073742389678955
+[2025-05-05 09:47:38,321][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 2.858224868774414, cross_entropy: 2.858224868774414
+[2025-05-05 09:47:41,506][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 2.8307814598083496, cross_entropy: 2.8307814598083496
+[2025-05-05 09:47:41,799][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 2.6661691665649414, cross_entropy: 2.6661691665649414
+[2025-05-05 09:47:44,763][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 2.993783712387085, cross_entropy: 2.993783712387085
+[2025-05-05 09:47:45,055][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 2.4647257328033447, cross_entropy: 2.4647257328033447
+[2025-05-05 09:47:48,092][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 3.0236153602600098, cross_entropy: 3.0236153602600098
+[2025-05-05 09:47:48,383][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 2.8135550022125244, cross_entropy: 2.8135550022125244
+[2025-05-05 09:47:50,874][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 3.0279812812805176, cross_entropy: 3.0279812812805176
+[2025-05-05 09:47:51,142][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 2.353130340576172, cross_entropy: 2.353130340576172
+[2025-05-05 09:47:53,991][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 2.427293300628662, cross_entropy: 2.427293300628662
+[2025-05-05 09:47:54,287][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 2.7655386924743652, cross_entropy: 2.7655386924743652
+[2025-05-05 09:47:57,082][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 2.973236560821533, cross_entropy: 2.973236560821533
+[2025-05-05 09:47:57,375][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 3.0423779487609863, cross_entropy: 3.0423779487609863
+[2025-05-05 09:48:00,019][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 2.8837733268737793, cross_entropy: 2.8837733268737793
+[2025-05-05 09:48:00,292][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 3.0309014320373535, cross_entropy: 3.0309014320373535
+[2025-05-05 09:48:03,200][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 2.4118125438690186, cross_entropy: 2.4118125438690186
+[2025-05-05 09:48:03,485][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 2.163151741027832, cross_entropy: 2.163151741027832
+[2025-05-05 09:48:05,812][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 2.070911169052124, cross_entropy: 2.070911169052124
+[2025-05-05 09:48:06,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 2.8572659492492676, cross_entropy: 2.8572659492492676
+[2025-05-05 09:48:08,406][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 2.412656307220459, cross_entropy: 2.412656307220459
+[2025-05-05 09:48:08,830][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 2.7920114994049072, cross_entropy: 2.7920114994049072
+[2025-05-05 09:48:10,967][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 2.2450432777404785, cross_entropy: 2.2450432777404785
+[2025-05-05 09:48:12,887][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 2.7679288387298584, cross_entropy: 2.7679288387298584
+[2025-05-05 09:48:13,773][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 2.589447021484375, cross_entropy: 2.589447021484375
+[2025-05-05 09:48:15,599][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 2.4124765396118164, cross_entropy: 2.4124765396118164
+[2025-05-05 09:48:16,777][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 2.4687347412109375, cross_entropy: 2.4687347412109375
+[2025-05-05 09:48:18,770][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 2.8234610557556152, cross_entropy: 2.8234610557556152
+[2025-05-05 09:48:19,147][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 2.389613151550293, cross_entropy: 2.389613151550293
+[2025-05-05 09:48:22,089][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 2.3148984909057617, cross_entropy: 2.3148984909057617
+[2025-05-05 09:48:22,385][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 2.8420419692993164, cross_entropy: 2.8420419692993164
+[2025-05-05 09:48:24,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 2.29653263092041, cross_entropy: 2.29653263092041
+[2025-05-05 09:48:25,130][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 2.443634510040283, cross_entropy: 2.443634510040283
+[2025-05-05 09:48:27,786][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 2.458268642425537, cross_entropy: 2.458268642425537
+[2025-05-05 09:48:28,237][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 2.3709287643432617, cross_entropy: 2.3709287643432617
+[2025-05-05 09:48:30,507][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 2.7334578037261963, cross_entropy: 2.7334578037261963
+[2025-05-05 09:48:30,817][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 2.576626777648926, cross_entropy: 2.576626777648926
+[2025-05-05 09:48:33,333][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 2.551196336746216, cross_entropy: 2.551196336746216
+[2025-05-05 09:48:33,746][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 2.6161606311798096, cross_entropy: 2.6161606311798096
+[2025-05-05 09:48:36,572][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 2.496171712875366, cross_entropy: 2.496171712875366
+[2025-05-05 09:48:36,882][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 2.6214725971221924, cross_entropy: 2.6214725971221924
+[2025-05-05 09:48:39,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 2.706058979034424, cross_entropy: 2.706058979034424
+[2025-05-05 09:48:39,895][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 2.4072933197021484, cross_entropy: 2.4072933197021484
+[2025-05-05 09:48:43,163][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 2.228184700012207, cross_entropy: 2.228184700012207
+[2025-05-05 09:48:43,439][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 2.6638638973236084, cross_entropy: 2.6638638973236084
+[2025-05-05 09:48:45,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 2.2962441444396973, cross_entropy: 2.2962441444396973
+[2025-05-05 09:48:46,172][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 2.375032901763916, cross_entropy: 2.375032901763916
+[2025-05-05 09:48:49,025][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 2.8031396865844727, cross_entropy: 2.8031396865844727
+[2025-05-05 09:48:49,292][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 2.2409143447875977, cross_entropy: 2.2409143447875977
+[2025-05-05 09:48:52,033][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 2.580317497253418, cross_entropy: 2.580317497253418
+[2025-05-05 09:48:52,323][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 2.499070882797241, cross_entropy: 2.499070882797241
+[2025-05-05 09:48:55,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 2.282062530517578, cross_entropy: 2.282062530517578
+[2025-05-05 09:48:55,607][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 2.359468936920166, cross_entropy: 2.359468936920166
+[2025-05-05 09:48:59,018][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 2.647857427597046, cross_entropy: 2.647857427597046
+[2025-05-05 09:48:59,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 2.8444228172302246, cross_entropy: 2.8444228172302246
+[2025-05-05 09:49:01,927][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 2.19181489944458, cross_entropy: 2.19181489944458
+[2025-05-05 09:49:02,210][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 2.5929222106933594, cross_entropy: 2.5929222106933594
+[2025-05-05 09:49:04,993][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 2.351461410522461, cross_entropy: 2.351461410522461
+[2025-05-05 09:49:05,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 2.3750619888305664, cross_entropy: 2.3750619888305664
+[2025-05-05 09:49:08,198][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 2.4669322967529297, cross_entropy: 2.4669322967529297
+[2025-05-05 09:49:08,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 2.9245047569274902, cross_entropy: 2.9245047569274902
+[2025-05-05 09:49:11,194][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 2.381864309310913, cross_entropy: 2.381864309310913
+[2025-05-05 09:49:11,483][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 2.5745413303375244, cross_entropy: 2.5745413303375244
+[2025-05-05 09:49:14,174][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 2.686976671218872, cross_entropy: 2.686976671218872
+[2025-05-05 09:49:14,458][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 2.435781955718994, cross_entropy: 2.435781955718994
+[2025-05-05 09:49:17,471][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 2.5392961502075195, cross_entropy: 2.5392961502075195
+[2025-05-05 09:49:17,756][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 2.492906332015991, cross_entropy: 2.492906332015991
+[2025-05-05 09:49:21,164][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 2.358499765396118, cross_entropy: 2.358499765396118
+[2025-05-05 09:49:21,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 2.6670870780944824, cross_entropy: 2.6670870780944824
+[2025-05-05 09:49:23,993][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 2.619516372680664, cross_entropy: 2.619516372680664
+[2025-05-05 09:49:24,287][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 2.337444305419922, cross_entropy: 2.337444305419922
+[2025-05-05 09:49:27,098][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 2.225595712661743, cross_entropy: 2.225595712661743
+[2025-05-05 09:49:27,364][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 2.194519519805908, cross_entropy: 2.194519519805908
+[2025-05-05 09:49:30,533][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 2.2509477138519287, cross_entropy: 2.2509477138519287
+[2025-05-05 09:49:30,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 2.0769686698913574, cross_entropy: 2.0769686698913574
+[2025-05-05 09:49:33,517][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 2.1994895935058594, cross_entropy: 2.1994895935058594
+[2025-05-05 09:49:33,809][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 1.9446724653244019, cross_entropy: 1.9446724653244019
+[2025-05-05 09:49:37,015][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 2.339994192123413, cross_entropy: 2.339994192123413
+[2025-05-05 09:49:37,282][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 2.393031597137451, cross_entropy: 2.393031597137451
+[2025-05-05 09:49:40,335][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 2.134624719619751, cross_entropy: 2.134624719619751
+[2025-05-05 09:49:40,623][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 2.350126266479492, cross_entropy: 2.350126266479492
+[2025-05-05 09:49:43,184][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 2.6669764518737793, cross_entropy: 2.6669764518737793
+[2025-05-05 09:49:43,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 2.644606113433838, cross_entropy: 2.644606113433838
+[2025-05-05 09:49:46,203][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 1.9613032341003418, cross_entropy: 1.9613032341003418
+[2025-05-05 09:49:46,469][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 2.8871889114379883, cross_entropy: 2.8871889114379883
+[2025-05-05 09:49:49,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 1.9578357934951782, cross_entropy: 1.9578357934951782
+[2025-05-05 09:49:49,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 2.2871298789978027, cross_entropy: 2.2871298789978027
+[2025-05-05 09:49:52,294][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 2.071976900100708, cross_entropy: 2.071976900100708
+[2025-05-05 09:49:52,582][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 2.0094850063323975, cross_entropy: 2.0094850063323975
+[2025-05-05 09:49:56,010][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 2.0015220642089844, cross_entropy: 2.0015220642089844
+[2025-05-05 09:49:56,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 2.7452821731567383, cross_entropy: 2.7452821731567383
+[2025-05-05 09:49:59,103][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 2.210491180419922, cross_entropy: 2.210491180419922
+[2025-05-05 09:49:59,379][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 2.0572052001953125, cross_entropy: 2.0572052001953125
+[2025-05-05 09:50:01,917][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 1.8931865692138672, cross_entropy: 1.8931865692138672
+[2025-05-05 09:50:02,205][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 2.6257567405700684, cross_entropy: 2.6257567405700684
+[2025-05-05 09:50:04,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 2.301325798034668, cross_entropy: 2.301325798034668
+[2025-05-05 09:50:04,831][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 2.1421902179718018, cross_entropy: 2.1421902179718018
+[2025-05-05 09:50:07,622][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 2.3199124336242676, cross_entropy: 2.3199124336242676
+[2025-05-05 09:50:07,891][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 1.9478565454483032, cross_entropy: 1.9478565454483032
+[2025-05-05 09:50:10,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 2.031534194946289, cross_entropy: 2.031534194946289
+[2025-05-05 09:50:10,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 1.5908913612365723, cross_entropy: 1.5908913612365723
+[2025-05-05 09:50:13,516][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 1.9361119270324707, cross_entropy: 1.9361119270324707
+[2025-05-05 09:50:13,801][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 1.8822338581085205, cross_entropy: 1.8822338581085205
+[2025-05-05 09:50:17,060][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 1.9554469585418701, cross_entropy: 1.9554469585418701
+[2025-05-05 09:50:17,342][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 2.131263017654419, cross_entropy: 2.131263017654419
+[2025-05-05 09:50:19,577][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 2.7405385971069336, cross_entropy: 2.7405385971069336
+[2025-05-05 09:50:19,866][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 2.1455931663513184, cross_entropy: 2.1455931663513184
+[2025-05-05 09:50:22,243][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 2.1557955741882324, cross_entropy: 2.1557955741882324
+[2025-05-05 09:50:22,509][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 1.8553715944290161, cross_entropy: 1.8553715944290161
+[2025-05-05 09:50:25,417][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 2.2070069313049316, cross_entropy: 2.2070069313049316
+[2025-05-05 09:50:25,709][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 1.602014183998108, cross_entropy: 1.602014183998108
+[2025-05-05 09:50:28,697][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 1.8780882358551025, cross_entropy: 1.8780882358551025
+[2025-05-05 09:50:28,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 1.7485675811767578, cross_entropy: 1.7485675811767578
+[2025-05-05 09:50:31,529][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 2.1740505695343018, cross_entropy: 2.1740505695343018
+[2025-05-05 09:50:31,797][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 2.364553689956665, cross_entropy: 2.364553689956665
+[2025-05-05 09:50:34,637][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 2.018742084503174, cross_entropy: 2.018742084503174
+[2025-05-05 09:50:34,930][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 2.467301845550537, cross_entropy: 2.467301845550537
+[2025-05-05 09:50:37,663][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 2.0563735961914062, cross_entropy: 2.0563735961914062
+[2025-05-05 09:50:37,948][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 2.325286865234375, cross_entropy: 2.325286865234375
+[2025-05-05 09:50:40,408][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 1.734659194946289, cross_entropy: 1.734659194946289
+[2025-05-05 09:50:40,682][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 2.2344789505004883, cross_entropy: 2.2344789505004883
+[2025-05-05 09:50:43,195][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 2.372894287109375, cross_entropy: 2.372894287109375
+[2025-05-05 09:50:43,481][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 1.9628961086273193, cross_entropy: 1.9628961086273193
+[2025-05-05 09:50:46,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 1.878267526626587, cross_entropy: 1.878267526626587
+[2025-05-05 09:50:46,726][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 1.7528660297393799, cross_entropy: 1.7528660297393799
+[2025-05-05 09:50:49,875][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 1.9477362632751465, cross_entropy: 1.9477362632751465
+[2025-05-05 09:50:50,144][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 2.0673203468322754, cross_entropy: 2.0673203468322754
+[2025-05-05 09:50:53,003][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 2.2647716999053955, cross_entropy: 2.2647716999053955
+[2025-05-05 09:50:53,270][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 1.9522674083709717, cross_entropy: 1.9522674083709717
+[2025-05-05 09:50:55,882][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 2.08988356590271, cross_entropy: 2.08988356590271
+[2025-05-05 09:50:56,148][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 2.33000111579895, cross_entropy: 2.33000111579895
+[2025-05-05 09:50:59,089][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 1.4400973320007324, cross_entropy: 1.4400973320007324
+[2025-05-05 09:50:59,378][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 2.1513843536376953, cross_entropy: 2.1513843536376953
+[2025-05-05 09:51:02,963][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 1.8079352378845215, cross_entropy: 1.8079352378845215
+[2025-05-05 09:51:03,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 2.222867965698242, cross_entropy: 2.222867965698242
+[2025-05-05 09:51:06,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 2.185883045196533, cross_entropy: 2.185883045196533
+[2025-05-05 09:51:06,534][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 2.454998731613159, cross_entropy: 2.454998731613159
+[2025-05-05 09:51:09,033][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 1.819913387298584, cross_entropy: 1.819913387298584
+[2025-05-05 09:51:09,318][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 1.996874213218689, cross_entropy: 1.996874213218689
+[2025-05-05 09:51:12,034][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 2.1636722087860107, cross_entropy: 2.1636722087860107
+[2025-05-05 09:51:12,323][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 2.109215497970581, cross_entropy: 2.109215497970581
+[2025-05-05 09:51:15,644][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 2.327542781829834, cross_entropy: 2.327542781829834
+[2025-05-05 09:51:15,910][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 2.3415567874908447, cross_entropy: 2.3415567874908447
+[2025-05-05 09:51:17,860][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 1.991217017173767, cross_entropy: 1.991217017173767
+[2025-05-05 09:51:18,131][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 1.9958906173706055, cross_entropy: 1.9958906173706055
+[2025-05-05 09:51:20,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 1.9864914417266846, cross_entropy: 1.9864914417266846
+[2025-05-05 09:51:20,914][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 2.311190128326416, cross_entropy: 2.311190128326416
+[2025-05-05 09:51:23,474][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 2.269057273864746, cross_entropy: 2.269057273864746
+[2025-05-05 09:51:23,762][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 1.3703190088272095, cross_entropy: 1.3703190088272095
+[2025-05-05 09:51:27,148][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 2.0604770183563232, cross_entropy: 2.0604770183563232
+[2025-05-05 09:51:27,414][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 2.0235233306884766, cross_entropy: 2.0235233306884766
+[2025-05-05 09:51:30,871][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 2.533194065093994, cross_entropy: 2.533194065093994
+[2025-05-05 09:51:31,159][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 1.829576015472412, cross_entropy: 1.829576015472412
+[2025-05-05 09:51:34,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 2.383409261703491, cross_entropy: 2.383409261703491
+[2025-05-05 09:51:34,871][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 1.7044014930725098, cross_entropy: 1.7044014930725098
+[2025-05-05 09:51:37,419][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 1.7177097797393799, cross_entropy: 1.7177097797393799
+[2025-05-05 09:51:37,709][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 2.376150131225586, cross_entropy: 2.376150131225586
+[2025-05-05 09:51:40,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 2.3659605979919434, cross_entropy: 2.3659605979919434
+[2025-05-05 09:51:41,120][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 2.284888505935669, cross_entropy: 2.284888505935669
+[2025-05-05 09:51:44,668][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 1.8810943365097046, cross_entropy: 1.8810943365097046
+[2025-05-05 09:51:44,935][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 1.9273468255996704, cross_entropy: 1.9273468255996704
+[2025-05-05 09:51:47,541][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 2.427088975906372, cross_entropy: 2.427088975906372
+[2025-05-05 09:51:47,807][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 2.3629322052001953, cross_entropy: 2.3629322052001953
+[2025-05-05 09:51:50,532][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 2.0712502002716064, cross_entropy: 2.0712502002716064
+[2025-05-05 09:51:50,820][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 1.8640518188476562, cross_entropy: 1.8640518188476562
+[2025-05-05 09:51:53,070][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 2.3092873096466064, cross_entropy: 2.3092873096466064
+[2025-05-05 09:51:53,352][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 2.160331964492798, cross_entropy: 2.160331964492798
+[2025-05-05 09:51:56,767][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 2.1224117279052734, cross_entropy: 2.1224117279052734
+[2025-05-05 09:51:57,033][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 2.066070079803467, cross_entropy: 2.066070079803467
+[2025-05-05 09:51:59,740][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 1.9042013883590698, cross_entropy: 1.9042013883590698
+[2025-05-05 09:52:00,024][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 1.7828054428100586, cross_entropy: 1.7828054428100586
+[2025-05-05 09:52:03,327][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 2.3629775047302246, cross_entropy: 2.3629775047302246
+[2025-05-05 09:52:03,622][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 1.797624111175537, cross_entropy: 1.797624111175537
+[2025-05-05 09:52:06,251][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 2.3308746814727783, cross_entropy: 2.3308746814727783
+[2025-05-05 09:52:06,557][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 2.8353261947631836, cross_entropy: 2.8353261947631836
+[2025-05-05 09:52:09,145][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 2.230394124984741, cross_entropy: 2.230394124984741
+[2025-05-05 09:52:09,428][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 1.965634822845459, cross_entropy: 1.965634822845459
+[2025-05-05 09:52:12,157][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 2.075137138366699, cross_entropy: 2.075137138366699
+[2025-05-05 09:52:12,437][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 1.6591405868530273, cross_entropy: 1.6591405868530273
+[2025-05-05 09:52:14,673][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 1.6709420680999756, cross_entropy: 1.6709420680999756
+[2025-05-05 09:52:14,940][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 2.1470398902893066, cross_entropy: 2.1470398902893066
+[2025-05-05 09:52:17,686][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 1.849224328994751, cross_entropy: 1.849224328994751
+[2025-05-05 09:52:17,965][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 2.1824347972869873, cross_entropy: 2.1824347972869873
+[2025-05-05 09:52:20,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 1.8390185832977295, cross_entropy: 1.8390185832977295
+[2025-05-05 09:52:20,888][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 1.895951747894287, cross_entropy: 1.895951747894287
+[2025-05-05 09:52:23,391][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 2.008394479751587, cross_entropy: 2.008394479751587
+[2025-05-05 09:52:23,677][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 1.8846654891967773, cross_entropy: 1.8846654891967773
+[2025-05-05 09:52:26,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 1.9871348142623901, cross_entropy: 1.9871348142623901
+[2025-05-05 09:52:26,596][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 1.9298832416534424, cross_entropy: 1.9298832416534424
+[2025-05-05 09:52:29,507][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 2.6350250244140625, cross_entropy: 2.6350250244140625
+[2025-05-05 09:52:29,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 2.036161422729492, cross_entropy: 2.036161422729492
+[2025-05-05 09:52:32,496][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 1.7561547756195068, cross_entropy: 1.7561547756195068
+[2025-05-05 09:52:32,782][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 1.9822800159454346, cross_entropy: 1.9822800159454346
+[2025-05-05 09:52:35,971][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 2.130452871322632, cross_entropy: 2.130452871322632
+[2025-05-05 09:52:36,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 1.7963216304779053, cross_entropy: 1.7963216304779053
+[2025-05-05 09:52:39,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 2.1473166942596436, cross_entropy: 2.1473166942596436
+[2025-05-05 09:52:39,903][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 2.4878604412078857, cross_entropy: 2.4878604412078857
+[2025-05-05 09:52:42,247][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 2.1226227283477783, cross_entropy: 2.1226227283477783
+[2025-05-05 09:52:42,514][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 1.913116216659546, cross_entropy: 1.913116216659546
+[2025-05-05 09:52:45,665][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 1.6049457788467407, cross_entropy: 1.6049457788467407
+[2025-05-05 09:52:45,932][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 2.292205810546875, cross_entropy: 2.292205810546875
+[2025-05-05 09:52:48,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 1.8730549812316895, cross_entropy: 1.8730549812316895
+[2025-05-05 09:52:48,547][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 1.8482187986373901, cross_entropy: 1.8482187986373901
+[2025-05-05 09:52:51,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 2.1439313888549805, cross_entropy: 2.1439313888549805
+[2025-05-05 09:52:51,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 1.626539945602417, cross_entropy: 1.626539945602417
+[2025-05-05 09:52:53,846][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 1.5768496990203857, cross_entropy: 1.5768496990203857
+[2025-05-05 09:52:54,122][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 1.9663681983947754, cross_entropy: 1.9663681983947754
+[2025-05-05 09:52:56,966][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 2.328012466430664, cross_entropy: 2.328012466430664
+[2025-05-05 09:52:57,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 1.5617284774780273, cross_entropy: 1.5617284774780273
+[2025-05-05 09:53:00,630][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.2280170917510986, cross_entropy: 2.2280170917510986
+[2025-05-05 09:53:00,909][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 1.9406999349594116, cross_entropy: 1.9406999349594116
+[2025-05-05 09:53:03,922][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.3057799339294434, cross_entropy: 2.3057799339294434
+[2025-05-05 09:53:04,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 1.965660572052002, cross_entropy: 1.965660572052002
+[2025-05-05 09:53:07,605][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 1.5760626792907715, cross_entropy: 1.5760626792907715
+[2025-05-05 09:53:07,890][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 1.740902066230774, cross_entropy: 1.740902066230774
+[2025-05-05 09:53:10,790][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 1.7732293605804443, cross_entropy: 1.7732293605804443
+[2025-05-05 09:53:11,065][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 1.9820091724395752, cross_entropy: 1.9820091724395752
+[2025-05-05 09:53:13,669][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 1.4971777200698853, cross_entropy: 1.4971777200698853
+[2025-05-05 09:53:13,935][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 1.635733962059021, cross_entropy: 1.635733962059021
+[2025-05-05 09:53:16,925][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 1.9015440940856934, cross_entropy: 1.9015440940856934
+[2025-05-05 09:53:17,192][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 1.7800923585891724, cross_entropy: 1.7800923585891724
+[2025-05-05 09:53:19,942][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 2.3088884353637695, cross_entropy: 2.3088884353637695
+[2025-05-05 09:53:20,213][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 1.5234527587890625, cross_entropy: 1.5234527587890625
+[2025-05-05 09:53:22,489][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 1.6320879459381104, cross_entropy: 1.6320879459381104
+[2025-05-05 09:53:22,776][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 1.793968915939331, cross_entropy: 1.793968915939331
+[2025-05-05 09:53:25,352][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 1.8218343257904053, cross_entropy: 1.8218343257904053
+[2025-05-05 09:53:25,619][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 1.9146698713302612, cross_entropy: 1.9146698713302612
+[2025-05-05 09:53:28,632][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 1.609933853149414, cross_entropy: 1.609933853149414
+[2025-05-05 09:53:28,898][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 2.052873373031616, cross_entropy: 2.052873373031616
+[2025-05-05 09:53:32,037][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 1.7238523960113525, cross_entropy: 1.7238523960113525
+[2025-05-05 09:53:32,330][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 1.653236985206604, cross_entropy: 1.653236985206604
+[2025-05-05 09:53:34,866][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 1.7774677276611328, cross_entropy: 1.7774677276611328
+[2025-05-05 09:53:35,143][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 1.9091377258300781, cross_entropy: 1.9091377258300781
+[2025-05-05 09:53:37,667][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 1.8947666883468628, cross_entropy: 1.8947666883468628
+[2025-05-05 09:53:37,971][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 1.9489954710006714, cross_entropy: 1.9489954710006714
+[2025-05-05 09:53:40,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 2.2012619972229004, cross_entropy: 2.2012619972229004
+[2025-05-05 09:53:41,232][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 1.7727586030960083, cross_entropy: 1.7727586030960083
+[2025-05-05 09:53:44,226][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 1.9406934976577759, cross_entropy: 1.9406934976577759
+[2025-05-05 09:53:44,513][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 2.1256887912750244, cross_entropy: 2.1256887912750244
+[2025-05-05 09:53:46,615][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 2.093701124191284, cross_entropy: 2.093701124191284
+[2025-05-05 09:53:46,882][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 1.8950786590576172, cross_entropy: 1.8950786590576172
+[2025-05-05 09:53:49,438][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.1647377014160156, cross_entropy: 2.1647377014160156
+[2025-05-05 09:53:49,724][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 2.382690906524658, cross_entropy: 2.382690906524658
+[2025-05-05 09:53:52,776][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 1.4423621892929077, cross_entropy: 1.4423621892929077
+[2025-05-05 09:53:53,045][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 1.4608666896820068, cross_entropy: 1.4608666896820068
+[2025-05-05 09:53:55,572][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 2.0346779823303223, cross_entropy: 2.0346779823303223
+[2025-05-05 09:53:55,861][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 1.9468430280685425, cross_entropy: 1.9468430280685425
+[2025-05-05 09:53:58,407][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 2.13270902633667, cross_entropy: 2.13270902633667
+[2025-05-05 09:53:58,677][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 1.85300874710083, cross_entropy: 1.85300874710083
+[2025-05-05 09:54:00,859][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 1.6413021087646484, cross_entropy: 1.6413021087646484
+[2025-05-05 09:54:04,112][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 1.5595623254776, cross_entropy: 1.5595623254776
+[2025-05-05 09:56:34,736][BaseTrainer][INFO] - [Epoch 1/10] (train) 2.649425745010376, cross_entropy: 2.649425745010376
+[2025-05-05 09:56:34,736][BaseTrainer][INFO] - [Epoch 1/10] (validation) 1.8284838199615479, cross_entropy: 1.8284838199615479
+[2025-05-05 09:56:34,737][BaseTrainer][INFO] - [Epoch 1/10] (metrics) roc_auc: 0.9597710371017456
+[2025-05-05 09:56:34,925][BaseTrainer][INFO] - Save model: ./exp/20250505-094415/model/best_epoch.pth.
+[2025-05-05 09:56:35,081][BaseTrainer][INFO] - Save model: ./exp/20250505-094415/model/last.pth.
+[2025-05-05 09:56:38,555][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 1.1553785800933838, cross_entropy: 1.1553785800933838
+[2025-05-05 09:56:38,877][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 1.7672476768493652, cross_entropy: 1.7672476768493652
+[2025-05-05 09:56:41,165][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 1.25618314743042, cross_entropy: 1.25618314743042
+[2025-05-05 09:56:41,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 1.3965697288513184, cross_entropy: 1.3965697288513184
+[2025-05-05 09:56:43,503][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 1.5174055099487305, cross_entropy: 1.5174055099487305
+[2025-05-05 09:56:43,791][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 1.6941776275634766, cross_entropy: 1.6941776275634766
+[2025-05-05 09:56:46,159][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 1.7774323225021362, cross_entropy: 1.7774323225021362
+[2025-05-05 09:56:46,434][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 1.4445414543151855, cross_entropy: 1.4445414543151855